The most common approach to assess fetal well-being during delivery is monitoring of fetal heart rate and uterine contractions-the cardiotocogram (CTG). Nevertheless, 40 years since the introduction of CTG to clinical practice, its... more
The most common approach to assess fetal well-being during delivery is monitoring of fetal heart rate and uterine contractions-the cardiotocogram (CTG). Nevertheless, 40 years since the introduction of CTG to clinical practice, its evaluation is still challenging with high inter- and intra-observer variability. Therefore the development of more objective methods has become an issue of major importance in the field. Unlike the usually proposed approaches to assign classes for classification methods that rely either on biochemical parameters (e.g. pH value) or a simple aggregation of expert judgment, this work investigates the use of an alternative labeling system using latent class analysis (LCA) along with an ordinal classification scheme. The study is performed on a well-documented open-access database, where nine expert obstetricians provided CTG annotations. The LCA is proposed here to produce more objective class labels while the ordinal classification aims to explore the natura...
Research Interests:
The scope of this work is to describe the design and development of a web-based Geographic Information System (GIS) application and highlight its usefulness regarding monitoring and evaluating environmental conditions in several ports and... more
The scope of this work is to describe the design and development of a web-based Geographic Information System (GIS) application and highlight its usefulness regarding monitoring and evaluating environmental conditions in several ports and their surroundings in the greater South East Europe (SEE). The system receives inputs and handles two kinds of data that are processed and illustrated through maps and graphs at various temporal and spatial scales in this informational platform. The aforementioned data consists of point measurements from stations operating in the area of SEE ports as well as satellite date sets derived monthly for a period of 10 to 12 years, in terms of sea surface temperature, chlorophyll a, and colored dissolved organic matter (CDOM). The WebGIS platform is based on the client–server model and uses Google Maps API services for data plotting. Advanced designing and development tools and methodologies are used. The available valuable data render the application into a trustful and accurate provider of visual environmental interest information regarding the main ports of southeastern Europe and their surroundings that would operate as a guide for an environmentally sustainable future of ports and sea corridors in SEE.
Research Interests:
This article presents a novel computational method for the diagnosis of broken rotor bars in three phase asynchronous machines. The proposed method is based on Principal Component Analysis (PCA) and is applied to the stator’s three... more
This article presents a novel computational method for the diagnosis of broken rotor bars in three phase
asynchronous machines. The proposed method is based on Principal Component Analysis (PCA) and is
applied to the stator’s three phase start-up current. The fault detection is easier in the start-up transient
because of the increased current in the rotor circuit, which amplifies the effects of the fault in the stator’s
current independently of the motor’s load. In the proposed fault detection methodology, PCA is initially
utilized to extract a characteristic component, which reflects the rotor asymmetry caused by the broken
bars. This component can be subsequently processed using Hidden Markov Models (HMMs). Two
schemes, a multiclass and a one-class approach are proposed. The efficiency of the novel proposed
schemes is evaluated by multiple experimental test cases. The results obtained indicate that the sug-
gested approaches based on the combination of PCA and HMMs, can be successfully utilized not only
for identifying the presence of a broken bar but also for estimating the severity (number of broken bars)
of the fault.
asynchronous machines. The proposed method is based on Principal Component Analysis (PCA) and is
applied to the stator’s three phase start-up current. The fault detection is easier in the start-up transient
because of the increased current in the rotor circuit, which amplifies the effects of the fault in the stator’s
current independently of the motor’s load. In the proposed fault detection methodology, PCA is initially
utilized to extract a characteristic component, which reflects the rotor asymmetry caused by the broken
bars. This component can be subsequently processed using Hidden Markov Models (HMMs). Two
schemes, a multiclass and a one-class approach are proposed. The efficiency of the novel proposed
schemes is evaluated by multiple experimental test cases. The results obtained indicate that the sug-
gested approaches based on the combination of PCA and HMMs, can be successfully utilized not only
for identifying the presence of a broken bar but also for estimating the severity (number of broken bars)
of the fault.
In this research work a new hybrid approach to spatio-temporal seismic clustering is proposed. The method builds upon a novel density based clustering scheme that explicitly takes into account earthquake’s magnitude during the density... more
In this research work a new hybrid approach to spatio-temporal seismic clustering is proposed. The
method builds upon a novel density based clustering scheme that explicitly takes into account earthquake’s
magnitude during the density estimation. The new density based clustering algorithm considers
both time and spatial information during cluster formation. Therefore clusters lie in a spatio-temporal
space. A hierarchical agglomerative clustering algorithm acts upon the identified clusters after dropping
the time information in order to come up only with the spatial description of seismic events. The
approach is demonstrated using data from the vicinity of the Hellenic seismic arc in order to enable its
comparison with some of the state-of-the-art distinct seismic region identification methodologies. The
presented results indicate that the combination of the two clustering stages could be potentially used
for an automatic definition of major seismic sources.
method builds upon a novel density based clustering scheme that explicitly takes into account earthquake’s
magnitude during the density estimation. The new density based clustering algorithm considers
both time and spatial information during cluster formation. Therefore clusters lie in a spatio-temporal
space. A hierarchical agglomerative clustering algorithm acts upon the identified clusters after dropping
the time information in order to come up only with the spatial description of seismic events. The
approach is demonstrated using data from the vicinity of the Hellenic seismic arc in order to enable its
comparison with some of the state-of-the-art distinct seismic region identification methodologies. The
presented results indicate that the combination of the two clustering stages could be potentially used
for an automatic definition of major seismic sources.
Aiming at more efficient fault diagnosis, this research work presents an integrated anomaly detection approach for seeded bearing faults.Vibration signals from normal bearings and bearings with three different faultl ocations, as well as... more
Aiming at more efficient fault diagnosis, this research work presents an integrated
anomaly detection approach for seeded bearing faults.Vibration signals from normal
bearings and bearings with three different faultl ocations, as well as different fault sizes and loading conditions are examined.The Empirical Mode Decomposition and the Hilbert Huang transform are employed for the extraction of a compact feature set.Then, a hybrid ensemble detector is trained using data coming only from the normal bearings and it is successfully applied for the detection of any deviation from the normal condition.The results prove the potential use of the proposed scheme as a first stage of an alarm signalling system for the detection of bearing faults irrespective of their loading condition.
anomaly detection approach for seeded bearing faults.Vibration signals from normal
bearings and bearings with three different faultl ocations, as well as different fault sizes and loading conditions are examined.The Empirical Mode Decomposition and the Hilbert Huang transform are employed for the extraction of a compact feature set.Then, a hybrid ensemble detector is trained using data coming only from the normal bearings and it is successfully applied for the detection of any deviation from the normal condition.The results prove the potential use of the proposed scheme as a first stage of an alarm signalling system for the detection of bearing faults irrespective of their loading condition.
This study investigates the Land Use & Land Cover (LULC) changes in a coastal area of the southwest part of Epirus region, called Preveza, situated in North-western Greece. Remote sensing imagery coming from the Enhanced Thematic Mapper... more
This study investigates the Land Use & Land Cover (LULC) changes in a coastal area of the southwest part
of Epirus region, called Preveza, situated in North-western Greece. Remote sensing imagery coming from
the Enhanced Thematic Mapper (ETMþ) sensor on board at the Landsat 7 satellite platform is used for
this purpose. More specifically, we identified LULC changes in this environmentally sensitive coastal area,
using Landsat image scenes for the dates of June 19th, 2000 and July 22nd, 2009. During this period,
there was an increasing tourist activity and a high growth in the construction sector of the study area.
The land-use changes were identified, examining several vegetation indices and band combinations,
along with the implementation of different well-known classification techniques. The Normalized Difference
Vegetation Index (NDVI) and the Brightness Index (BI) have proved to be the most suitable
indices to successfully identify discrete land surface classes for this study area. Regarding the classifiers, a
series of traditional and modern algorithms were tested. The Artificial Neural Networks (ANNs) and the
Support Vector Machines (SVMs) gave improved results in comparison to other more traditional classification
techniques. The best overall accuracy for the study area was achieved with the SVM classifier
and reached 96.25% and 97.15% on the dates of June 19th, 2000 and July 22nd, 2009 respectively. The
classification results depicted notable urbanization, small deforestation and important LULC changes in
the agriculture sector, indicating a rapid coastal environment change in the region of interest
of Epirus region, called Preveza, situated in North-western Greece. Remote sensing imagery coming from
the Enhanced Thematic Mapper (ETMþ) sensor on board at the Landsat 7 satellite platform is used for
this purpose. More specifically, we identified LULC changes in this environmentally sensitive coastal area,
using Landsat image scenes for the dates of June 19th, 2000 and July 22nd, 2009. During this period,
there was an increasing tourist activity and a high growth in the construction sector of the study area.
The land-use changes were identified, examining several vegetation indices and band combinations,
along with the implementation of different well-known classification techniques. The Normalized Difference
Vegetation Index (NDVI) and the Brightness Index (BI) have proved to be the most suitable
indices to successfully identify discrete land surface classes for this study area. Regarding the classifiers, a
series of traditional and modern algorithms were tested. The Artificial Neural Networks (ANNs) and the
Support Vector Machines (SVMs) gave improved results in comparison to other more traditional classification
techniques. The best overall accuracy for the study area was achieved with the SVM classifier
and reached 96.25% and 97.15% on the dates of June 19th, 2000 and July 22nd, 2009 respectively. The
classification results depicted notable urbanization, small deforestation and important LULC changes in
the agriculture sector, indicating a rapid coastal environment change in the region of interest
• We analyzed fetal heart rate of normal and acidemic fetuses. • We used conventional and nonlinear features for the signal analysis. • Addition of nonlinear features improves accuracy of classification. • The best nonlinear... more
•
We analyzed fetal heart rate of normal and acidemic fetuses.
•
We used conventional and nonlinear
features for the signal analysis.
•
Addition of nonlinear features improves accuracy of classification.
•
The
best nonlinear features are: Lempel Ziv complexity and Sample entropy.
•
Combination of conventional
and nonlinear features provides the best accuracy.
Abstract: Fetal heart rate (FHR) is used to evaluate fetal well-being and enables clinicians to detect ongoing
hypoxia during delivery. Routine clinical evaluation of intrapartum FHR is based on macroscopic
morphological features visible to the naked eye. In this paper we evaluated conventional features and
compared them to the nonlinear ones in the task of intrapartum FHR classification. The experiments were
performed using a database of 217 FHR records with objective annotations, i.e. pH measurement. We have
proven that the addition of nonlinear features improves accuracy of classification. The best classification
results were achieved using a combination of conventional and nonlinear features with sensitivity of
73.4%, specificity of 76.3%, and F-measure of 71.9%. The best selected nonlinear features were: Lempel
Ziv complexity, Sample entropy, and fractal dimension estimated by Higuchi method. Since the results
of automatic signal evaluation are easily reproducible, the process of FHR evaluation can become more
objective and may enable clinicians to focus on additional non-cardiotocography parameters influencing
the fetus during delivery.
We analyzed fetal heart rate of normal and acidemic fetuses.
•
We used conventional and nonlinear
features for the signal analysis.
•
Addition of nonlinear features improves accuracy of classification.
•
The
best nonlinear features are: Lempel Ziv complexity and Sample entropy.
•
Combination of conventional
and nonlinear features provides the best accuracy.
Abstract: Fetal heart rate (FHR) is used to evaluate fetal well-being and enables clinicians to detect ongoing
hypoxia during delivery. Routine clinical evaluation of intrapartum FHR is based on macroscopic
morphological features visible to the naked eye. In this paper we evaluated conventional features and
compared them to the nonlinear ones in the task of intrapartum FHR classification. The experiments were
performed using a database of 217 FHR records with objective annotations, i.e. pH measurement. We have
proven that the addition of nonlinear features improves accuracy of classification. The best classification
results were achieved using a combination of conventional and nonlinear features with sensitivity of
73.4%, specificity of 76.3%, and F-measure of 71.9%. The best selected nonlinear features were: Lempel
Ziv complexity, Sample entropy, and fractal dimension estimated by Higuchi method. Since the results
of automatic signal evaluation are easily reproducible, the process of FHR evaluation can become more
objective and may enable clinicians to focus on additional non-cardiotocography parameters influencing
the fetus during delivery.
This work presents the experience gained by Patras Science Park through interregional growth projects. This experience is very useful to regional and central authorities that determine growth policies and to any actor who works towards... more
This work presents the experience gained by Patras Science Park
through interregional growth projects. This experience is very useful to
regional and central authorities that determine growth policies and to any actor
who works towards regional growth especially through innovation and
technology, such as science and technology parks (STPs). HuReDePIS
interregional project examined growth potential of the areas around Ionian Sea
for six strategic sectors: SMEs, services, environment, CAP, culture and
tourism and there were initiated growth and an immigration network. The
current situation for the six sectors is highlighted and the problems and
difficulties for regional and spatial development are identified and diagnosed.
Special emphasis is given to the important role of innovation for growth of a
region. The key role of STPs for growth is validated by their ability to serve as
mediators between knowledge producer organisations and local economic
factors.
through interregional growth projects. This experience is very useful to
regional and central authorities that determine growth policies and to any actor
who works towards regional growth especially through innovation and
technology, such as science and technology parks (STPs). HuReDePIS
interregional project examined growth potential of the areas around Ionian Sea
for six strategic sectors: SMEs, services, environment, CAP, culture and
tourism and there were initiated growth and an immigration network. The
current situation for the six sectors is highlighted and the problems and
difficulties for regional and spatial development are identified and diagnosed.
Special emphasis is given to the important role of innovation for growth of a
region. The key role of STPs for growth is validated by their ability to serve as
mediators between knowledge producer organisations and local economic
factors.
The detection of ventricular beats in the holter recording is a task of great importance since it can direct clinicians toward the parts of the electrocardiogram record that might be crucial for determining the final diagnosis.... more
The detection of ventricular beats in the holter recording is a task of
great importance since it can direct clinicians toward the parts of the
electrocardiogram record that might be crucial for determining the final
diagnosis. Although there already exists a fair amount of research work
dealing with ventricular beat detection in holter recordings, the vast majority
uses a local training approach, which is highly disputable from the point of
view of any practical—real-life—application. In this paper, we compare five
well-known methods: a classical decision tree approach and its variant with
fuzzy rules, a self-organizing map clustering method with template matching
for classification, a back-propagation neural network and a support vector
machine classifier, all examined using the same global cross-database approach
for training and testing. For this task two databases were used—the MIT–BIH
database and the AHA database. Both databases are required for testing any
newly developed algorithms for holter beat classification that is going to be
deployed in the EU market. According to cross-database global training, when
the classifier is trained with the beats from the records of one database then the
records from the other database are used for testing. The results of all the
methods are compared and evaluated using the measures of sensitivity and
specificity. The support vector machine classifier is the best classifier from
the five we tested, achieving an average sensitivity of 87.20% and an average
specificity of 91.57%, which outperforms nearly all the published algorithms
when applied in the context of a similar global training approach.
great importance since it can direct clinicians toward the parts of the
electrocardiogram record that might be crucial for determining the final
diagnosis. Although there already exists a fair amount of research work
dealing with ventricular beat detection in holter recordings, the vast majority
uses a local training approach, which is highly disputable from the point of
view of any practical—real-life—application. In this paper, we compare five
well-known methods: a classical decision tree approach and its variant with
fuzzy rules, a self-organizing map clustering method with template matching
for classification, a back-propagation neural network and a support vector
machine classifier, all examined using the same global cross-database approach
for training and testing. For this task two databases were used—the MIT–BIH
database and the AHA database. Both databases are required for testing any
newly developed algorithms for holter beat classification that is going to be
deployed in the EU market. According to cross-database global training, when
the classifier is trained with the beats from the records of one database then the
records from the other database are used for testing. The results of all the
methods are compared and evaluated using the measures of sensitivity and
specificity. The support vector machine classifier is the best classifier from
the five we tested, achieving an average sensitivity of 87.20% and an average
specificity of 91.57%, which outperforms nearly all the published algorithms
when applied in the context of a similar global training approach.
Medical decision support systems can provide assistance in crucial clinical judgments, particularly for inexperienced medical professionals. Fuzzy cognitive maps (FCMs) is a soft computing technique for modeling complex systems, which... more
Medical decision support systems can provide assistance in crucial clinical judgments, particularly for inexperienced medical professionals.
Fuzzy cognitive maps (FCMs) is a soft computing technique for modeling complex systems, which follows an approach similar to human reasoning
and the human decision-making process. FCMs can successfully represent knowledge and human experience, introducing concepts to represent the
essential elements and the cause and effect relationships among the concepts to model the behavior of any system. Medical decision systems are
complex systems that can be decomposed to non-related and related subsystems and elements, where many factors have to be taken into
consideration that may be complementary, contradictory, and competitive; these factors influence each other and determine the overall clinical
decision with a different degree. Thus, FCMs are suitable for medical decision support systems and appropriate FCM architectures are proposed
and developed as well as the corresponding examples from two medical disciplines, i.e. speech and language pathology and obstetrics, are
described.
Fuzzy cognitive maps (FCMs) is a soft computing technique for modeling complex systems, which follows an approach similar to human reasoning
and the human decision-making process. FCMs can successfully represent knowledge and human experience, introducing concepts to represent the
essential elements and the cause and effect relationships among the concepts to model the behavior of any system. Medical decision systems are
complex systems that can be decomposed to non-related and related subsystems and elements, where many factors have to be taken into
consideration that may be complementary, contradictory, and competitive; these factors influence each other and determine the overall clinical
decision with a different degree. Thus, FCMs are suitable for medical decision support systems and appropriate FCM architectures are proposed
and developed as well as the corresponding examples from two medical disciplines, i.e. speech and language pathology and obstetrics, are
described.
The characterization and accurate determination of brain tumor grade is very important because it influences and specifies patient’s treatment planning and eventually his life. A new method for characterizing brain tumors is presented in... more
The characterization and accurate determination of brain tumor grade is very important because it influences and specifies patient’s treatment
planning and eventually his life. A new method for characterizing brain tumors is presented in this research work, which models the human
thinking approach and the classification results are compared with other computational intelligent techniques proving the efficiency of the
proposed methodology. The novelty of the method is based on the use of the soft computing method of fuzzy cognitive maps (FCMs) to represent
and model experts’ knowledge (experience, expertise, heuristic). The FCM grading model classification ability was enhanced introducing a
computational intelligent training technique, the Activation Hebbian Algorithm. The proposed method was validated for clinical material,
comprising of 100 cases. FCM grading model achieved a diagnostic output of accuracy of 90.26% (37/41) and 93.22% (55/59) for brain tumors of
low-grade and high-grade, respectively. The results of the proposed grading model present reasonably high accuracy, and are comparable with
existing algorithms, such as decision trees and fuzzy decision trees which were tested at the same type of initial data. The main advantage of the
proposed FCM grading model is the sufficient interpretability and transparency in decision process, which make it a convenient consulting tool in
characterizing tumor aggressiveness for every day clinical practice.
planning and eventually his life. A new method for characterizing brain tumors is presented in this research work, which models the human
thinking approach and the classification results are compared with other computational intelligent techniques proving the efficiency of the
proposed methodology. The novelty of the method is based on the use of the soft computing method of fuzzy cognitive maps (FCMs) to represent
and model experts’ knowledge (experience, expertise, heuristic). The FCM grading model classification ability was enhanced introducing a
computational intelligent training technique, the Activation Hebbian Algorithm. The proposed method was validated for clinical material,
comprising of 100 cases. FCM grading model achieved a diagnostic output of accuracy of 90.26% (37/41) and 93.22% (55/59) for brain tumors of
low-grade and high-grade, respectively. The results of the proposed grading model present reasonably high accuracy, and are comparable with
existing algorithms, such as decision trees and fuzzy decision trees which were tested at the same type of initial data. The main advantage of the
proposed FCM grading model is the sufficient interpretability and transparency in decision process, which make it a convenient consulting tool in
characterizing tumor aggressiveness for every day clinical practice.
Fetal heart rate (FHR) variations reflect the level of oxygenation and blood pressure of the fetus. Electronic Fetal Monitoring (EFM), the continuous monitoring of the FHR, was introduced into clinical practice in the late 1960s and... more
Fetal heart rate (FHR) variations reflect the level of oxygenation and blood pressure of the fetus. Electronic Fetal Monitoring (EFM), the
continuous monitoring of the FHR, was introduced into clinical practice in the late 1960s and since then it has been considered as an indispensable
tool for fetal surveillance. However, EFM evaluation and its merit is still an open field of controversy, mainly because it is not consistently
reproducible and effective. In this work, we present a novel method based on grammatical evolution to discriminate acidemic from normal fetuses,
utilizing features extracted from the FHR signal during the minutes immediately preceding delivery. The proposed method identifies linear and
nonlinear correlations among the originally extracted features and creates/constructs a set of new ones, which, in turn, feed a nonlinear classifier.
The classifier, which also uses a hybrid method for training, along with the constructed features was tested using a set of real data achieving an
overall performance of 90% (specificity = sensitivity = 90%).
continuous monitoring of the FHR, was introduced into clinical practice in the late 1960s and since then it has been considered as an indispensable
tool for fetal surveillance. However, EFM evaluation and its merit is still an open field of controversy, mainly because it is not consistently
reproducible and effective. In this work, we present a novel method based on grammatical evolution to discriminate acidemic from normal fetuses,
utilizing features extracted from the FHR signal during the minutes immediately preceding delivery. The proposed method identifies linear and
nonlinear correlations among the originally extracted features and creates/constructs a set of new ones, which, in turn, feed a nonlinear classifier.
The classifier, which also uses a hybrid method for training, along with the constructed features was tested using a set of real data achieving an
overall performance of 90% (specificity = sensitivity = 90%).
Fuzzy Cognitive Maps (FCMs) constitute an attractive knowledge-based methodology, combining the robust properties of fuzzy logic and neural networks. FCMs represent causal knowledge as a signed directed graph with feedback and provide an... more
Fuzzy Cognitive Maps (FCMs) constitute an attractive knowledge-based methodology, combining the robust properties of fuzzy logic
and neural networks. FCMs represent causal knowledge as a signed directed graph with feedback and provide an intuitive framework
which incorporates the experts’ knowledge. FCMs handle available information and knowledge from an abstract point of view. They
develop behavioural model of the system exploiting the experience and knowledge of experts. The construction of FCMs is based mainly
on experts who determine the structure of FCM, i.e. concepts and weighted interconnections among concepts. But this methodology may
not be a sufficient model of the system because the human factor is not always reliable. Thus the FCM model of the system may requires
restructuring which is achieved through adjustment the weights of FCM interconnections using specific learning algorithms for FCMs. In
this article, two unsupervised learning algorithms are presented and compared for training FCMs; how they define, select or fine-tuning
weights of the causal interconnections among concepts. The implementation and results of these unsupervised learning techniques for an
industrial process control problem are discussed. The simulations results of training the process system verify the effectiveness, validity
and advantageous characteristics of those learning techniques for FCMs.
and neural networks. FCMs represent causal knowledge as a signed directed graph with feedback and provide an intuitive framework
which incorporates the experts’ knowledge. FCMs handle available information and knowledge from an abstract point of view. They
develop behavioural model of the system exploiting the experience and knowledge of experts. The construction of FCMs is based mainly
on experts who determine the structure of FCM, i.e. concepts and weighted interconnections among concepts. But this methodology may
not be a sufficient model of the system because the human factor is not always reliable. Thus the FCM model of the system may requires
restructuring which is achieved through adjustment the weights of FCM interconnections using specific learning algorithms for FCMs. In
this article, two unsupervised learning algorithms are presented and compared for training FCMs; how they define, select or fine-tuning
weights of the causal interconnections among concepts. The implementation and results of these unsupervised learning techniques for an
industrial process control problem are discussed. The simulations results of training the process system verify the effectiveness, validity
and advantageous characteristics of those learning techniques for FCMs.
Cardiotocography is the main method used for fetal assessment in every day clinical practice for the last 30 years. Many attempts have been made to increase the effectiveness of the evaluation of cardiotocographic recordings and... more
Cardiotocography is the main method used for fetal
assessment in every day clinical practice for the last 30 years.
Many attempts have been made to increase the effectiveness of
the evaluation of cardiotocographic recordings and minimize the
variations of their interpretation utilizing technological advances.
This research work proposes and focuses on an advanced method
able to identify fetuses compromised and suspicious of developing
metabolic acidosis. The core of the proposed method is the introduction
of a support vector machine to “foresee” undesirable and
risky situations for the fetus, based on features extracted from the
fetal heart rate signal at the time and frequency domains along
with some morphological features. This method has been tested
successfully on a data set of intrapartum recordings, achieving
better and balanced overall performance compared to other
classification methods, constituting, therefore, a promising new
automatic methodology for the prediction of metabolic acidosis.
assessment in every day clinical practice for the last 30 years.
Many attempts have been made to increase the effectiveness of
the evaluation of cardiotocographic recordings and minimize the
variations of their interpretation utilizing technological advances.
This research work proposes and focuses on an advanced method
able to identify fetuses compromised and suspicious of developing
metabolic acidosis. The core of the proposed method is the introduction
of a support vector machine to “foresee” undesirable and
risky situations for the fetus, based on features extracted from the
fetal heart rate signal at the time and frequency domains along
with some morphological features. This method has been tested
successfully on a data set of intrapartum recordings, achieving
better and balanced overall performance compared to other
classification methods, constituting, therefore, a promising new
automatic methodology for the prediction of metabolic acidosis.
This paper introduces a new learning algorithm for Fuzzy Cognitive Maps, which is based on the application of a swarm intelligence algorithm, namely Particle Swarm Optimization. The proposed approach is applied to detect weight matrices... more
This paper introduces a new learning algorithm for Fuzzy Cognitive Maps, which is based on the
application of a swarm intelligence algorithm, namely Particle Swarm Optimization. The proposed approach is
applied to detect weight matrices that lead the Fuzzy Cognitive Map to desired steady states, thereby refining the
initial weight approximation provided by the experts. This is performed through the minimization of a properly
defined objective function. This novel method overcomes some deficiencies of other learning algorithms and, thus,
improves the efficiency and robustness of Fuzzy Cognitive Maps. The operation of the new method is illustrated
on an industrial process control problem, and the obtained simulation results support the claim that it is robust and
efficient.
application of a swarm intelligence algorithm, namely Particle Swarm Optimization. The proposed approach is
applied to detect weight matrices that lead the Fuzzy Cognitive Map to desired steady states, thereby refining the
initial weight approximation provided by the experts. This is performed through the minimization of a properly
defined objective function. This novel method overcomes some deficiencies of other learning algorithms and, thus,
improves the efficiency and robustness of Fuzzy Cognitive Maps. The operation of the new method is illustrated
on an industrial process control problem, and the obtained simulation results support the claim that it is robust and
efficient.
Fuzzy cognitive map is a soft computing technique for modeling systems, which combines synergistically the theories of neural networks and fuzzy logic. Developing of fuzzy cognitive map (FCM) relies on human experience and knowledge,... more
Fuzzy cognitive map is a soft computing technique for modeling systems, which
combines synergistically the theories of neural networks and fuzzy logic. Developing of
fuzzy cognitive map (FCM) relies on human experience and knowledge, but still exhibits
weaknesses in utilization of learning methods. The critical dependence on experts and the
potential uncontrollable convergence to undesired steady-states are important deficiencies
to manage FCMs. Overcoming these deficiencies will improve the efficiency and
robustness of the FCM methodology. Learning and convergence algorithms constitute
the mean to improve these characteristics of FCMs, by modifying the values of cause–
effect weights among concepts. In this paper a new learning algorithm that alleviates the
problem of the potential convergence to a steady-state, named Active Hebbian Learning
(AHL) is presented, validated and implemented. This proposed learning procedure is a
promising approach for exploiting experts’ involvement with their subjective reasoning
and at the same time improving the effectiveness of the FCM operation mode and thus
it broadens the applicability of FCMs modeling for complex systems.
combines synergistically the theories of neural networks and fuzzy logic. Developing of
fuzzy cognitive map (FCM) relies on human experience and knowledge, but still exhibits
weaknesses in utilization of learning methods. The critical dependence on experts and the
potential uncontrollable convergence to undesired steady-states are important deficiencies
to manage FCMs. Overcoming these deficiencies will improve the efficiency and
robustness of the FCM methodology. Learning and convergence algorithms constitute
the mean to improve these characteristics of FCMs, by modifying the values of cause–
effect weights among concepts. In this paper a new learning algorithm that alleviates the
problem of the potential convergence to a steady-state, named Active Hebbian Learning
(AHL) is presented, validated and implemented. This proposed learning procedure is a
promising approach for exploiting experts’ involvement with their subjective reasoning
and at the same time improving the effectiveness of the FCM operation mode and thus
it broadens the applicability of FCMs modeling for complex systems.
This research deals with the soft computing methodology of fuzzy cognitive map (FCM). Here a mathematical description of FCM is presented and a new methodology based on fuzzy logic techniques for developing the FCM is examined. The... more
This research deals with the soft computing methodology of
fuzzy cognitive map (FCM). Here a mathematical description of FCM is
presented and a new methodology based on fuzzy logic techniques for developing
the FCM is examined. The capability and usefulness of FCM in
modeling complex systems and the application of FCM to modeling and
describing the behavior of a heat exchanger system is presented. The applicability
of FCM to model the supervisor of complex systems is discussed
and the FCM-supervisor for evaluating the performance of a system is constructed;
simulation results are presented and discussed.
fuzzy cognitive map (FCM). Here a mathematical description of FCM is
presented and a new methodology based on fuzzy logic techniques for developing
the FCM is examined. The capability and usefulness of FCM in
modeling complex systems and the application of FCM to modeling and
describing the behavior of a heat exchanger system is presented. The applicability
of FCM to model the supervisor of complex systems is discussed
and the FCM-supervisor for evaluating the performance of a system is constructed;
simulation results are presented and discussed.
The radiation therapy decision-making is a complex process that has to take into consideration a variety of interrelated functions. Many fuzzy factors that must be considered in the calculation of the appropriate dose increase the... more
The radiation therapy decision-making is a complex
process that has to take into consideration a variety of interrelated
functions. Many fuzzy factors that must be considered in the calculation
of the appropriate dose increase the complexity of the decision-
making problem. A novel approach introduces fuzzy cognitive
maps (FCMs) as the computational modeling method, which
tackles the complexity and allows the analysis and simulation of the
clinical radiation procedure. Specifically this approach is used to
determine the success of radiation therapy process estimating the
final dose delivered to the target volume, based on the soft computing
technique of FCMs. Furthermore a two-level integrated hierarchical
structure is proposed to supervise and evaluate the radiotherapy
process prior to treatment execution. The supervisor
determines the treatment variables of cancer therapy and the acceptance
level of final radiation dose to the target volume. Two
clinical case studies are used to test the proposed methodology and
evaluate the simulation results. The usefulness of this two-level hierarchical
structure discussed and future research directions are
suggested for the clinical use of this methodology.
process that has to take into consideration a variety of interrelated
functions. Many fuzzy factors that must be considered in the calculation
of the appropriate dose increase the complexity of the decision-
making problem. A novel approach introduces fuzzy cognitive
maps (FCMs) as the computational modeling method, which
tackles the complexity and allows the analysis and simulation of the
clinical radiation procedure. Specifically this approach is used to
determine the success of radiation therapy process estimating the
final dose delivered to the target volume, based on the soft computing
technique of FCMs. Furthermore a two-level integrated hierarchical
structure is proposed to supervise and evaluate the radiotherapy
process prior to treatment execution. The supervisor
determines the treatment variables of cancer therapy and the acceptance
level of final radiation dose to the target volume. Two
clinical case studies are used to test the proposed methodology and
evaluate the simulation results. The usefulness of this two-level hierarchical
structure discussed and future research directions are
suggested for the clinical use of this methodology.
This paper presents a computer-based model for differential diagnosis of specific language impairment (SLI), a language disorder that, in many cases, cannot be easily diagnosed. This difficulty necessitates the development of a... more
This paper presents a computer-based model for differential diagnosis of specific language
impairment (SLI), a language disorder that, in many cases, cannot be easily diagnosed. This
difficulty necessitates the development of a methodology to assist the speech therapist in the
diagnostic process. The methodology tool is based on fuzzy cognitive maps and constitutes a
qualitative and quantitative computer model comprised of the experience and knowledge of
specialists. The development of the model was based on knowledge from the literature and then
it was successfully tested on four clinical cases. The results obtained point to its final integration in
the future and to its valid contribution as a differential diagnosis model of SLI.
impairment (SLI), a language disorder that, in many cases, cannot be easily diagnosed. This
difficulty necessitates the development of a methodology to assist the speech therapist in the
diagnostic process. The methodology tool is based on fuzzy cognitive maps and constitutes a
qualitative and quantitative computer model comprised of the experience and knowledge of
specialists. The development of the model was based on knowledge from the literature and then
it was successfully tested on four clinical cases. The results obtained point to its final integration in
the future and to its valid contribution as a differential diagnosis model of SLI.
Modelling complex systems and their supervisior has attracted the high interest of many scientists and engineers. There has been a need for highly sophisticated Autonomous Intelligent Systems. A very promising methodology to model the... more
Modelling complex systems and their supervisior has attracted the high interest of many scientists and engineers. There has been a
need for highly sophisticated Autonomous Intelligent Systems. A very promising methodology to model the Supervisor of a plant is the
use of Fuzzy Cognitive Maps (FCM). FCM are a combination of Fuzzy Logic and Neural Networks. A new mathematical model for
FCMs is proposed and its representation is examined in this paper. FCM construction is presented through the development of the
model for a simple control process problem. Then, issues for the application of FCM as the model of the supervisor of a complex
system are addressed and a hierarchical two-level structure is proposed. Ó 1999 Elsevier Science Ltd. All rights reserved.
need for highly sophisticated Autonomous Intelligent Systems. A very promising methodology to model the Supervisor of a plant is the
use of Fuzzy Cognitive Maps (FCM). FCM are a combination of Fuzzy Logic and Neural Networks. A new mathematical model for
FCMs is proposed and its representation is examined in this paper. FCM construction is presented through the development of the
model for a simple control process problem. Then, issues for the application of FCM as the model of the supervisor of a complex
system are addressed and a hierarchical two-level structure is proposed. Ó 1999 Elsevier Science Ltd. All rights reserved.
Fuzzy Cognitive Maps FCMs. is a new approach in modelling the behaviour and operation of complex systems. FCMs are proposed to be used in the modelling of control systems and particularly in the modelling of the upper part or... more
Fuzzy Cognitive Maps FCMs. is a new approach in modelling the behaviour and operation of complex systems. FCMs
are proposed to be used in the modelling of control systems and particularly in the modelling of the upper part or supervisor
of a hierarchical control system. The description and the formulation of FCM are examined, moreover a process control
problem is presented and its model and control is investigated using FCMs. Then the implementation of FCM in the
modelling of the supervisor of a control system is discussed and it becomes apparent how efficient FCMs are in expressing
qualitative information and knowledge about the process structure. Finally, some interesting points for further research are
presented and discussed. q1999 Elsevier Science B.V. All rights reserved.
are proposed to be used in the modelling of control systems and particularly in the modelling of the upper part or supervisor
of a hierarchical control system. The description and the formulation of FCM are examined, moreover a process control
problem is presented and its model and control is investigated using FCMs. Then the implementation of FCM in the
modelling of the supervisor of a control system is discussed and it becomes apparent how efficient FCMs are in expressing
qualitative information and knowledge about the process structure. Finally, some interesting points for further research are
presented and discussed. q1999 Elsevier Science B.V. All rights reserved.
The development of a novel soft computing approach to model the supervisor of manufacturing systems is described, it is named Fuzzy Cognitive Maps (FCMs) and it is used to model the behaviour of complex systems. Fuzzy cognitive maps... more
The development of a novel soft computing approach to model the supervisor of manufacturing
systems is described, it is named Fuzzy Cognitive Maps (FCMs) and it is used to model
the behaviour of complex systems. Fuzzy cognitive maps combine characteristics of both fuzzy logic
and neural networks. The description and the construction of fuzzy cognitive maps are examined, a
new methodology for developing fuzzy cognitive maps is proposed here and as an example the fuzzy
cognitive map for a simple plant is developed. A hierarchical two-level structure for supervision of
manufacturing systems is presented, where the supervisor is modelled as a fuzzy cognitive map. The
fuzzy cognitive map model for the failure diagnosis part of the supervisor for a simple chemical
process is constructed.
systems is described, it is named Fuzzy Cognitive Maps (FCMs) and it is used to model
the behaviour of complex systems. Fuzzy cognitive maps combine characteristics of both fuzzy logic
and neural networks. The description and the construction of fuzzy cognitive maps are examined, a
new methodology for developing fuzzy cognitive maps is proposed here and as an example the fuzzy
cognitive map for a simple plant is developed. A hierarchical two-level structure for supervision of
manufacturing systems is presented, where the supervisor is modelled as a fuzzy cognitive map. The
fuzzy cognitive map model for the failure diagnosis part of the supervisor for a simple chemical
process is constructed.
Research Interests:
This paper examines fuzzy cognitive map (FCM) theory and its use in supervisory control systems. An FCM is a graph used to depict cause and eect between concepts that stand for the states and variables of the system. An FCM represents... more
This paper examines fuzzy cognitive map (FCM) theory and its use in supervisory control
systems. An FCM is a graph used to depict cause and eect between concepts that stand for
the states and variables of the system. An FCM represents the whole system in a symbolic
manner, just as humans have stored the operation of the system in their brains, thus it is
possible to help man's intention for more intelligent and autonomous systems. FCM repre-
sentation, construction and a mathematical model are examined; a generic system is proposed
and the implementation of FCM in a process control problem is illustrated and a model for
supervisors of manufacturing systems is discussed. Although an FCM seems to be a simple
model of system behaviour, it appears to be a powerful and eective tool describing the
behaviour of a system and representing the accumulated knowledge of a system.
systems. An FCM is a graph used to depict cause and eect between concepts that stand for
the states and variables of the system. An FCM represents the whole system in a symbolic
manner, just as humans have stored the operation of the system in their brains, thus it is
possible to help man's intention for more intelligent and autonomous systems. FCM repre-
sentation, construction and a mathematical model are examined; a generic system is proposed
and the implementation of FCM in a process control problem is illustrated and a model for
supervisors of manufacturing systems is discussed. Although an FCM seems to be a simple
model of system behaviour, it appears to be a powerful and eective tool describing the
behaviour of a system and representing the accumulated knowledge of a system.
ABSTRACT The quality of marine environment has a vital importance for the sustainable future of Earth’s planet. On the other hand, the human activities, the sea commerce and transportation affect significantly the marine environment... more
ABSTRACT The quality of marine environment has a vital importance for the sustainable future of Earth’s planet. On the other hand, the human activities, the sea commerce and transportation affect significantly the marine environment especially in coastal areas, port areas and the sea-corridors. These induced activities impose contiguous and accurate methods for marine environment monitoring. Nowadays, modern satellite instruments gather data and the derived from them relative products can be used as an alternative, robust and accurate way to monitor many and basic marine parameters such as Chlorophyll, Sea Surface Temperature, Euphotic Depth, Dissolved Organic matter and examine their long-term (climatic) tendencies. This study comprises an effort to assess the accuracy of satellite products, comparing them with relative ground based measurements and it also focuses on provision of satellite-based mean variations in monthly basis regarding two important marine parameters (Chlorophyll-a and Sea Surface Temperature). In this study, available measurements of two different ports are used, i.e. port of Bar in Montenegro and port of Burgas in Bulgaria, which are partners of TEN ECOPORT (Transnational ENhancement of ECOPORT8 network) project.
ABSTRACT Eventual failures in induction machines may lead to catastrophic consequences in terms of economic costs for the companies. The development of reliable systems for fault detection that enable to diagnose a wide range of faults is... more
ABSTRACT Eventual failures in induction machines may lead to catastrophic consequences in terms of economic costs for the companies. The development of reliable systems for fault detection that enable to diagnose a wide range of faults is a motivation of many researchers worldwide. In this context, non-invasive condition monitoring strategies have drawn special attention since they do not require interfering with the operation process of the machine. Though the analysis of the motor currents has proven to be a reliable, non-invasive methodology to detect some of the faults (especially when assessing the rotor condition), it lacks reliability for the diagnosis of other faults (e.g. bearing faults). The infrared thermography has proven to be an excellent, non-invasive tool that can complement the diagnosis reached with the motor current analysis, especially for some specific faults. However, there are still some pending issues regarding its application to induction motor faults diagnosis, such as the lack of automation or the extraction of reliable fault indicators based on the infrared data. This paper proposes a methodology that intends to provide a solution to the first issue: a method based on image segmentation is employed to detect several failures in an automated way. Four specific faults are analyzed: bearing faults, fan failures, rotor bar breakages and stator unbalance. The results show the potential of the technique to automatically identify the fault present in the machine.
Research Interests:
In this study we investigate the feasibility of applying Symbolic Aggregate approximation (SAX) to automatically classify phasic eletromyographic (EMG) activity in human polysomnograms (PSGs). SAX offers potential benefits for time series... more
In this study we investigate the feasibility of applying Symbolic Aggregate approximation (SAX) to automatically classify phasic eletromyographic (EMG) activity in human polysomnograms (PSGs). SAX offers potential benefits for time series analysis of PSGs that include: 1) dimensionality and storage space reduction and 2) access to robust symbolic based data mining algorithms, such as intelligent icons. To evaluate the proposed symbolic classification scheme we compare, expert visual scoring of phasic EMG activity, a reliable quantitative metric to assist in discriminating neurodegenerative disorder populations and age-matched controls, to a k-Nearest Neighbor intelligent icon based SAX scheme. Detection of non-phasic EMG activity exceeded 90% and detection of phasic EMG activity ranged between 53 to 90 %, for six subjects.
Research Interests:
Abstract. Time dependence in medical diagnosis is important since, frequently, symptoms evolve over time, thus, changing with the progression of an illness. Taking into consideration that medical information may be vague, missing and/or... more
Abstract.
Time dependence in medical diagnosis is important since, frequently, symptoms evolve over time, thus, changing with the progression of an illness. Taking into consideration that medical information may be vague, missing and/or conflicting during the diagnostic procedure, a new type of Fuzzy Cognitive Maps (FCMs), the soft computing technique that can handle uncertainty to infer a result, have been developed for Medical Diagnosis. Here, a method to enhance the FCM behaviour is proposed introducing time units that can follow disease progression. An example from the pulmonary field is described.
Keywords: Fuzzy Cognitive Map, time evolution, medical diagnosis.
Time dependence in medical diagnosis is important since, frequently, symptoms evolve over time, thus, changing with the progression of an illness. Taking into consideration that medical information may be vague, missing and/or conflicting during the diagnostic procedure, a new type of Fuzzy Cognitive Maps (FCMs), the soft computing technique that can handle uncertainty to infer a result, have been developed for Medical Diagnosis. Here, a method to enhance the FCM behaviour is proposed introducing time units that can follow disease progression. An example from the pulmonary field is described.
Keywords: Fuzzy Cognitive Map, time evolution, medical diagnosis.
Abstract. Recent research on manual/visual identification of phasic muscle activity utilizing the phasic electromyographic metric (PEM) in human polysomnograms (PSGs) cites evidence that PEM is a potentially reliable quantitative metric... more
Abstract.
Recent research on manual/visual identification of phasic muscle activity utilizing the phasic electromyographic metric (PEM) in human polysomnograms (PSGs) cites evidence that PEM is a potentially reliable quantitative metric to assist in distinguishing between neurodegenerative disorder populations and age-matched controls. However, visual scoring of PEM activity is time consuming-preventing feasible implementation within a clinical setting. Therefore, here we propose an assistive/semi-supervised software platform designed and tested to automatically identify and characterize PEM events in a clinical setting that will be extremely useful for sleep physicians and technicians. The proposed semi-automated approach consists of four levels: A) Signal Parsing, B) Calculation of quantitative features on candidate PEM events, C) Classification of PEM and non-PEM events using a linear classifier, and D) Post-processing/Expert feedback to correct/remove automated misclassifications of PEM and Non-PEM events. Performance evaluation of the designed software compared to manual labeling is provided for electromyographic (EMG) activity from the PSG of a control subject. Results indicate that the semi-automated approach provides an excellent benchmark that could be embedded into a clinical decision support system to detect PEM events that would be used in neurological disorder identification and treatment.
Recent research on manual/visual identification of phasic muscle activity utilizing the phasic electromyographic metric (PEM) in human polysomnograms (PSGs) cites evidence that PEM is a potentially reliable quantitative metric to assist in distinguishing between neurodegenerative disorder populations and age-matched controls. However, visual scoring of PEM activity is time consuming-preventing feasible implementation within a clinical setting. Therefore, here we propose an assistive/semi-supervised software platform designed and tested to automatically identify and characterize PEM events in a clinical setting that will be extremely useful for sleep physicians and technicians. The proposed semi-automated approach consists of four levels: A) Signal Parsing, B) Calculation of quantitative features on candidate PEM events, C) Classification of PEM and non-PEM events using a linear classifier, and D) Post-processing/Expert feedback to correct/remove automated misclassifications of PEM and Non-PEM events. Performance evaluation of the designed software compared to manual labeling is provided for electromyographic (EMG) activity from the PSG of a control subject. Results indicate that the semi-automated approach provides an excellent benchmark that could be embedded into a clinical decision support system to detect PEM events that would be used in neurological disorder identification and treatment.
Abstract. Electronic fetal monitoring has become the gold standard for fetal assessment both during pregnancy as well as during delivery. Even though electronic fetal monitoring has been introduced to clinical practice more than forty... more
Abstract. Electronic fetal monitoring has become the gold standard for fetal assessment both during pregnancy as well as during delivery. Even though electronic fetal monitoring has been introduced to clinical practice more than forty years ago, there is still controversy in its usefulness especially due to the high inter- and intra-observer variability. Therefore the need for a more reliable and consistent interpretation has prompted the research community to investigate and propose various automated methodologies. In this work we propose the use of an automated method for the evaluation of fetal heart rate, the main monitored signal, which is based on a data set, whose labels/annotations are determined using a mixture model of clinical annotations. The successful results of the method suggest that it could be integrated into an assistive technology during delivery.
Keywords: Electronic fetal monitoring, Fetal Heart Rate, Random Forests, Classification.
Keywords: Electronic fetal monitoring, Fetal Heart Rate, Random Forests, Classification.
Medical Decision Support Systems can provide assistance in crucial clinical judgm ents, particularly for inexperienced medical professionals. Fuzzy Cognitive Maps (FCMs) is a soft computing technique for mo d eling complex systems... more
Medical Decision Support Systems can provide
assistance in crucial clinical judgm
ents, particularly for
inexperienced medical professionals. Fuzzy Cognitive Maps
(FCMs) is a soft computing technique for mo
d
eling complex
systems follow
ing
an approach similar to human reasoning and
decision
-
making. FCMs successfully represent knowledge a
nd
human experience, introducing co
n
cepts to represent the
essential elements and the cause and effect relationships among
the concepts to model the behavior of any system. Medical
Decision Systems are complex syst
ems that can be decomposed
to
su
b
systems a
nd elements, where many factors have to be
taken into consideration that may be complementary,
contr
a
dictory, and competitive; these factors influence each
other and determine the overall clinical decision with
varying
degree
s
.
Here a
Medical Decision Sup
port System
based on an
appropriate FCM arch
i
tecture
is
proposed and developed
,
as
well as
a
corresponding
paradigm
from obstetrics is d
e
scribed.
assistance in crucial clinical judgm
ents, particularly for
inexperienced medical professionals. Fuzzy Cognitive Maps
(FCMs) is a soft computing technique for mo
d
eling complex
systems follow
ing
an approach similar to human reasoning and
decision
-
making. FCMs successfully represent knowledge a
nd
human experience, introducing co
n
cepts to represent the
essential elements and the cause and effect relationships among
the concepts to model the behavior of any system. Medical
Decision Systems are complex syst
ems that can be decomposed
to
su
b
systems a
nd elements, where many factors have to be
taken into consideration that may be complementary,
contr
a
dictory, and competitive; these factors influence each
other and determine the overall clinical decision with
varying
degree
s
.
Here a
Medical Decision Sup
port System
based on an
appropriate FCM arch
i
tecture
is
proposed and developed
,
as
well as
a
corresponding
paradigm
from obstetrics is d
e
scribed.
The main focus of this paper is to investigate the possibility to distinguish among different classes of beats, as provided by ANSI/AAMI EC57:1998 standard, from the ECG holter recordings. We compare the perform- ance of an ensemble... more
The main focus of this paper is to investigate
the possibility to distinguish among different classes of
beats, as provided by ANSI/AAMI EC57:1998 standard,
from the ECG holter recordings.
We compare the perform-
ance of an ensemble classifier
based on three classifiers on
distinguishing ECG beats from holter
recordings character-
ized by two distinct
sets of features.
The first feature set is one relying upon the "classical"
time interval measurements of QRS complex and T-wave.
The second one tries to de
scribe the beat using means as
simple as possible resulting in a description of the QRS
complex in terms of "easy-to-compute" statistical moments;
hermite coefficients and Karhunen
Loeve coefficients.
The results of the ensemble classifier consisting of three
different classifiers – namely a k-NN classifier, a Back
propagation Neural Network and a Support Vector classi-
fier- are as general as possible by using global train-
ing/testing approach that uses one half of the recordings
from the MIT-BIH database for training and the other half
for testing. Results of the cl
assifier are computed using
sensitivity (Se) and specificity (Sp) for both feature sets. The
best results achieved during
the experiments
were those
using the "classical" feature set and the ensemble classifier.
The specificity for detection of normal beats was 74.26%
and sensitivities were 68.19%, 45.73%, 35.19%, 48.70% for
ventricular, bundle branch
blocks, supraventricular, and
fusion beats respectively. The
results achieved
on the "easy-
to-compute" approach are comparable to those from "clas-
sical" approach when dealing
with the detection of ventricu-
lar beats with specificity 74.73% and sensitivity 59.97% –
but they have performed much
worse when trying to detect
the other classes such as supr
aventricular, fusion or bundle
branch block beats.
the possibility to distinguish among different classes of
beats, as provided by ANSI/AAMI EC57:1998 standard,
from the ECG holter recordings.
We compare the perform-
ance of an ensemble classifier
based on three classifiers on
distinguishing ECG beats from holter
recordings character-
ized by two distinct
sets of features.
The first feature set is one relying upon the "classical"
time interval measurements of QRS complex and T-wave.
The second one tries to de
scribe the beat using means as
simple as possible resulting in a description of the QRS
complex in terms of "easy-to-compute" statistical moments;
hermite coefficients and Karhunen
Loeve coefficients.
The results of the ensemble classifier consisting of three
different classifiers – namely a k-NN classifier, a Back
propagation Neural Network and a Support Vector classi-
fier- are as general as possible by using global train-
ing/testing approach that uses one half of the recordings
from the MIT-BIH database for training and the other half
for testing. Results of the cl
assifier are computed using
sensitivity (Se) and specificity (Sp) for both feature sets. The
best results achieved during
the experiments
were those
using the "classical" feature set and the ensemble classifier.
The specificity for detection of normal beats was 74.26%
and sensitivities were 68.19%, 45.73%, 35.19%, 48.70% for
ventricular, bundle branch
blocks, supraventricular, and
fusion beats respectively. The
results achieved
on the "easy-
to-compute" approach are comparable to those from "clas-
sical" approach when dealing
with the detection of ventricu-
lar beats with specificity 74.73% and sensitivity 59.97% –
but they have performed much
worse when trying to detect
the other classes such as supr
aventricular, fusion or bundle
branch block beats.
A new hybrid modeling methodology to support medical diagnosis decisions is developed here. It extends previous work on Competitive Fuzzy Cognitive Maps for Medical Diagnosis Support Systems by complementing them with Genetic... more
A new hybrid modeling methodology to support
medical diagnosis decisions is developed here. It extends
previous work on Competitive Fuzzy Cognitive Maps for
Medical Diagnosis Support Systems by complementing them
with Genetic Algorithms Methods for concept interaction. The
synergy of these methodologies is accomplished by a new
proposed algorithm that leads to more dependable Advanced
Medical Diagnosis Support Systems that are suitable to handle
situations where the decisions are not clearly distinct. The
technique developed here is applied successfully to model and
test a differential diagnosis problem from the speech pathology
area for the diagnosis of language impairments.
medical diagnosis decisions is developed here. It extends
previous work on Competitive Fuzzy Cognitive Maps for
Medical Diagnosis Support Systems by complementing them
with Genetic Algorithms Methods for concept interaction. The
synergy of these methodologies is accomplished by a new
proposed algorithm that leads to more dependable Advanced
Medical Diagnosis Support Systems that are suitable to handle
situations where the decisions are not clearly distinct. The
technique developed here is applied successfully to model and
test a differential diagnosis problem from the speech pathology
area for the diagnosis of language impairments.
This paper presents a preliminary study of the applicability of a novel signal processing technique as a means to exact valuable information so that to diagnose the possible existence of a speech articulation disorder in a speaker.... more
This paper presents a preliminary study of
the applicability of a novel signal processing
technique as a means to exact valuable information
so that to diagnose the possible existence of a speech
articulation disorder in a speaker. Articulation, in
effect, is the specific and characteristic way that an
individual produces the speech sounds. Emprirical
Mode Decomposition and the Hilbert Huang
transform is applied in an attempt to identify
potential features to be used in an articulator
disorder detector.
the applicability of a novel signal processing
technique as a means to exact valuable information
so that to diagnose the possible existence of a speech
articulation disorder in a speaker. Articulation, in
effect, is the specific and characteristic way that an
individual produces the speech sounds. Emprirical
Mode Decomposition and the Hilbert Huang
transform is applied in an attempt to identify
potential features to be used in an articulator
disorder detector.
In this work we present a comparative study, testing selected methods for clustering and classification of holter electrocardiogram (ECG). More specifically we focus on the task of discriminating between normal ‘N’ beats and premature... more
In this work we present a comparative study,
testing selected methods for clustering and classification of
holter electrocardiogram (ECG). More specifically we focus on
the task of discriminating between normal ‘N’ beats and
premature ventricular ‘V’ beats
Some of the tested methods represent the state of the art in
pattern analysis, while others are novel algorithms developed
by us. All the algorithms were tested on the same datasets,
namely the MIT-BIH and the AHA databases.
The results for all the employed methods are compared and
evaluated using the measures of sensitivity and specificity
testing selected methods for clustering and classification of
holter electrocardiogram (ECG). More specifically we focus on
the task of discriminating between normal ‘N’ beats and
premature ventricular ‘V’ beats
Some of the tested methods represent the state of the art in
pattern analysis, while others are novel algorithms developed
by us. All the algorithms were tested on the same datasets,
namely the MIT-BIH and the AHA databases.
The results for all the employed methods are compared and
evaluated using the measures of sensitivity and specificity
Medical problems involve different types of variables and data, which have to be processed, analyzed and synthesized in order to reach a decision and/or conclude to a diagnosis. Usually, information and data set are both symbolic and... more
Medical problems involve different types of
variables and data, which have to be processed, analyzed and
synthesized in order to reach a decision and/or conclude to a
diagnosis. Usually, information and data set are both symbolic
and numeric but most of the well-known data analysis methods
deal with only one kind of data. Even when fuzzy approaches
are considered, which are not depended on the scales of
variables, usually only numeric data is considered. The medical
decision support methods usually are accessed in only one type
of available data. Thus, sophisticated methods have been
proposed such as integrated hybrid learning approaches to
process symbolic and numeric data for the decision support
tasks. Fuzzy Cognitive Maps (FCM) is an efficient modelling
method, which is based on human knowledge and experience
and it can handle with uncertainty and it is constructed by
extracted knowledge in the form of fuzzy rules. The FCM
model can be enhanced if a fuzzy rule base (IF-THEN rules) is
available. This rule base could be derived by a number of
machine learning and knowledge extraction methods. Here it is
introduced a hybrid attempt to handle situations with different
types of available medical and /or clinical data and with
difficulty to handle them for decision support tasks using soft
computing techniques.
variables and data, which have to be processed, analyzed and
synthesized in order to reach a decision and/or conclude to a
diagnosis. Usually, information and data set are both symbolic
and numeric but most of the well-known data analysis methods
deal with only one kind of data. Even when fuzzy approaches
are considered, which are not depended on the scales of
variables, usually only numeric data is considered. The medical
decision support methods usually are accessed in only one type
of available data. Thus, sophisticated methods have been
proposed such as integrated hybrid learning approaches to
process symbolic and numeric data for the decision support
tasks. Fuzzy Cognitive Maps (FCM) is an efficient modelling
method, which is based on human knowledge and experience
and it can handle with uncertainty and it is constructed by
extracted knowledge in the form of fuzzy rules. The FCM
model can be enhanced if a fuzzy rule base (IF-THEN rules) is
available. This rule base could be derived by a number of
machine learning and knowledge extraction methods. Here it is
introduced a hybrid attempt to handle situations with different
types of available medical and /or clinical data and with
difficulty to handle them for decision support tasks using soft
computing techniques.
Holter ECG mon i torin g is u s ed for lon g -term monitoring of patients w i th heart problems for diagnosis reas o n s . A lot of res earch w o rk h a s b een d o n in th is field an d many me... more
Holter ECG mon
i
torin
g
is
u
s
ed
for lon
g
-term
monitoring of patients w
i
th
heart problems for diagnosis
reas
o
n
s
. A lot of res
earch
w
o
rk
h
a
s
b
een
d
o
n
in
th
is
field
an
d
many
me
thods and pr
oc
e
dur
e
s
h
ave been investigated. This
p
a
p
er d
i
s
c
u
s
s
e
s
an
d
comp
ares
a n
u
m
b
er of d
i
fferen
t ap
p
r
oach
e
s
of c
l
uste
r
i
ng algor
ithms foc
u
sing
on distinguishing pr
e
m
atur
e
ventricular complexes (V) from the normal (N)
beats.
Algorith
m
s
w
ere tes
t
ed
on
MI
T-BI
H
d
a
tab
a
s
e
an
d
res
u
l
ts
are
comp
u
t
ed
for local an
d
glob
al
tr
aining sets. Template matching
tech
n
i
q
u
e
u
s
in
g ru
le-b
as
ed
d
ecis
i
on
tree clu
s
terin
g
algorith
m
for
data r
e
duc
tion pe
r
f
or
me
d
be
st w
i
th specificity
of 96.63 %
and sensitivity
of 92.64 %.
i
torin
g
is
u
s
ed
for lon
g
-term
monitoring of patients w
i
th
heart problems for diagnosis
reas
o
n
s
. A lot of res
earch
w
o
rk
h
a
s
b
een
d
o
n
in
th
is
field
an
d
many
me
thods and pr
oc
e
dur
e
s
h
ave been investigated. This
p
a
p
er d
i
s
c
u
s
s
e
s
an
d
comp
ares
a n
u
m
b
er of d
i
fferen
t ap
p
r
oach
e
s
of c
l
uste
r
i
ng algor
ithms foc
u
sing
on distinguishing pr
e
m
atur
e
ventricular complexes (V) from the normal (N)
beats.
Algorith
m
s
w
ere tes
t
ed
on
MI
T-BI
H
d
a
tab
a
s
e
an
d
res
u
l
ts
are
comp
u
t
ed
for local an
d
glob
al
tr
aining sets. Template matching
tech
n
i
q
u
e
u
s
in
g ru
le-b
as
ed
d
ecis
i
on
tree clu
s
terin
g
algorith
m
for
data r
e
duc
tion pe
r
f
or
me
d
be
st w
i
th specificity
of 96.63 %
and sensitivity
of 92.64 %.
For medical decision making processes (diag- nosing, classification, etc.) all decisions must be made effec- tively and reliably. Conceptual decision making models with the potential of learning capabilities are more appropriate and... more
For medical decision
making processes (diag-
nosing, classification, etc.) all decisions must be made effec-
tively and reliably. Conceptual decision making models with
the potential of learning capabilities are more appropriate and
suitable for performing such hard
tasks. Decision trees are a
well known technique, which has been applied in many medi-
cal systems to support decisions based on a set of instances. On
the other hand, the soft computing technique of Fuzzy Cogni-
tive Maps (FCMs) is an effective decision making technique,
which provides high performance with a conceptual represen-
tation of gathered knowledge a
nd existing experience. FCMs
have been used for medical decision making with emphasis in
radiotherapy and classification
tasks for bladder tumour grad-
ing. This paper proposes and
presents an hybrid model de-
rived from the combination and
the synergistic application of
the above mentioned techniques.
The proposed Decision Tree-
Fuzzy Cognitive Map model has
enhanced operation and effec-
tiveness based on both methods
giving better accuracy results
in medical decision tasks.
making processes (diag-
nosing, classification, etc.) all decisions must be made effec-
tively and reliably. Conceptual decision making models with
the potential of learning capabilities are more appropriate and
suitable for performing such hard
tasks. Decision trees are a
well known technique, which has been applied in many medi-
cal systems to support decisions based on a set of instances. On
the other hand, the soft computing technique of Fuzzy Cogni-
tive Maps (FCMs) is an effective decision making technique,
which provides high performance with a conceptual represen-
tation of gathered knowledge a
nd existing experience. FCMs
have been used for medical decision making with emphasis in
radiotherapy and classification
tasks for bladder tumour grad-
ing. This paper proposes and
presents an hybrid model de-
rived from the combination and
the synergistic application of
the above mentioned techniques.
The proposed Decision Tree-
Fuzzy Cognitive Map model has
enhanced operation and effec-
tiveness based on both methods
giving better accuracy results
in medical decision tasks.
For most tumor types in histopathology, includ- ing bladder tumors, the morphology of tissues-as viewed through a light microscope-exp ress the tumor characterization as malignant or not. Due to the subjective nature of this classi-... more
For most tumor types in histopathology, includ-
ing bladder tumors, the morphology of tissues-as viewed
through a light microscope-exp
ress the tumor characterization
as malignant or not. Due to the subjective nature of this classi-
fication, a large number of computer assisted methodologies
have been used to increase th
e diagnostic and/or prognostic
value of tumors’ characterization. In this research work, com-
putational intelligence methods such as Fuzzy Cognitive Maps
(FCMs) and Support Vector Machines (SVMs) are explored
for assisting tumour characterization. The classification results
are presented and are compared
with other conventional clas-
sifiers proving their efficiency.
ing bladder tumors, the morphology of tissues-as viewed
through a light microscope-exp
ress the tumor characterization
as malignant or not. Due to the subjective nature of this classi-
fication, a large number of computer assisted methodologies
have been used to increase th
e diagnostic and/or prognostic
value of tumors’ characterization. In this research work, com-
putational intelligence methods such as Fuzzy Cognitive Maps
(FCMs) and Support Vector Machines (SVMs) are explored
for assisting tumour characterization. The classification results
are presented and are compared
with other conventional clas-
sifiers proving their efficiency.
The objective of this study is the investigation of a novel feature selection method based on the implementation of the binary Particle Swarm Algorithm and its application to the demanding problem of the classification of Fetal Heart... more
The objective of this study is the investigation of
a novel feature selection method based on the implementation
of the binary Particle Swarm Algorithm and its application to
the demanding problem of the classification of Fetal Heart
Rate signals during the intrap
artum period. The results are
promising paving the way for more research towards the im-
provement of the proposed algorithm.
a novel feature selection method based on the implementation
of the binary Particle Swarm Algorithm and its application to
the demanding problem of the classification of Fetal Heart
Rate signals during the intrap
artum period. The results are
promising paving the way for more research towards the im-
provement of the proposed algorithm.
In this paper we pres ent a novel method for the classi fication of Fetal H e art Rate signals using a very powerful tool from the fi eld of pattern recogni tion, the Support Vector Machines ( S VMs) , combined with Partic le... more
In this paper we pres
ent a novel method for the classi
fication of Fetal H
e
art Rate
signals using a very powerful tool from the fi
eld of pattern recogni
tion, the Support Vector
Machines
(
S
VMs)
, combined with Partic
le Sw
arm Optimization (PSO)
for tuning the free
parameters of the SVM. The proposed method wa
s tested on a data set of intrapartum FHR
recordings with promising results.
ent a novel method for the classi
fication of Fetal H
e
art Rate
signals using a very powerful tool from the fi
eld of pattern recogni
tion, the Support Vector
Machines
(
S
VMs)
, combined with Partic
le Sw
arm Optimization (PSO)
for tuning the free
parameters of the SVM. The proposed method wa
s tested on a data set of intrapartum FHR
recordings with promising results.
This paper examines the use of disciplines signal processing approaches for data pre-processing and feature extraction from biologi cal signals. Then, it follows a discussion on AI methods for Classification such as Support Vector... more
This paper examines the use of disciplines
signal processing
approaches for data pre-processing and
feature extraction from biologi
cal signals. Then, it follows
a discussion on AI methods
for Classification such as
Support Vector Machines, Decision Trees, K-Neural
Networks. The application framework includes detecting
ECG, EEG, and FHR events as case studies.
signal processing
approaches for data pre-processing and
feature extraction from biologi
cal signals. Then, it follows
a discussion on AI methods
for Classification such as
Support Vector Machines, Decision Trees, K-Neural
Networks. The application framework includes detecting
ECG, EEG, and FHR events as case studies.
In this paper we present a novel method for the discrimination of fetuses suspicious of developing acidemia from healthy ones. The proposed methodology employs wavelet analysis, neural networks and a newly developed paradigm from the... more
In this paper we present a novel method
for the discrimination of fetuses suspicious of
developing acidemia from healthy ones. The
proposed methodology employs wavelet analysis,
neural networks and a newly developed paradigm
from the field of evolutionary computation in a
unified framework, to achieve better feature
extraction and classification results for Fetal Heart
Rate. The methodology is te
sted in experimental data
set and the discrimination
results are promising
paving the way for further investigation and
experimentation
for the discrimination of fetuses suspicious of
developing acidemia from healthy ones. The
proposed methodology employs wavelet analysis,
neural networks and a newly developed paradigm
from the field of evolutionary computation in a
unified framework, to achieve better feature
extraction and classification results for Fetal Heart
Rate. The methodology is te
sted in experimental data
set and the discrimination
results are promising
paving the way for further investigation and
experimentation
"This research work presents a novel modeling me thod for gr ading brain tumors . The accur a te de te rminati on of brain tum o r malign a nc y (gr a de ) is c r u c ial bec a use it deter m ines and... more
"This research work presents
a
novel
modeling
me
thod for gr
ading brain
tumors
.
The
accur
a
te
de
te
rminati
on of brain tum
o
r
malign
a
nc
y
(gr
a
de
) is c
r
u
c
ial bec
a
use
it deter
m
ines
and s
p
ecifies
patie
n
t’s tre
a
tment planni
ng
and m
a
nagement. The
novelty of the
method is based on the use
of the S
o
ft
C
o
mp
ut
in
g
of
F
u
zzy
C
o
gn
itiv
e Ma
ps (FCMs) to
represent
and model experts’
knowledge
(experience,
exper
t
ise, h
e
uristic),
an
d on
the
use of
a
co
mputa
t
i
o
nal intellig
ent metho
d the efficient AHL
algorithm for
enhancing th
e FCM’s classific
a
tion
a
b
ility.
The pr
opose
d
method w
a
s teste
d
and
validated for
clinical mate
rial, compri
sing
100 cases. F
C
M
gra
d
i
n
g m
o
d
e
l
achi
eved
a di
a
g
n
o
sti
c
out
put
of
accur
a
cy
o
f
9
2
.
68%
(38/
41
)
and
93
.2
2
%
(5
5/
5
9
)
for
brai
n t
u
m
o
u
r
s of l
o
w
g
r
ade
and
hi
gh
gra
d
e,
respectivel
y.
The results
of the pr
oposed gr
ading
model prese
n
t reasonably high
ac
curac
y
in
comparison
to
other m
e
thods. The
propose
d
a
pproa
ch present suffici
ent interpretability
a
n
d
transparenc
y
in
decision
pro
ces
s
,
wh
ich ma
k
e
it
a
convenient consulting tool
in char
acteri
z
i
ng tumor
ag
gressi
venes
s
i
n
clinical practice"
a
novel
modeling
me
thod for gr
ading brain
tumors
.
The
accur
a
te
de
te
rminati
on of brain tum
o
r
malign
a
nc
y
(gr
a
de
) is c
r
u
c
ial bec
a
use
it deter
m
ines
and s
p
ecifies
patie
n
t’s tre
a
tment planni
ng
and m
a
nagement. The
novelty of the
method is based on the use
of the S
o
ft
C
o
mp
ut
in
g
of
F
u
zzy
C
o
gn
itiv
e Ma
ps (FCMs) to
represent
and model experts’
knowledge
(experience,
exper
t
ise, h
e
uristic),
an
d on
the
use of
a
co
mputa
t
i
o
nal intellig
ent metho
d the efficient AHL
algorithm for
enhancing th
e FCM’s classific
a
tion
a
b
ility.
The pr
opose
d
method w
a
s teste
d
and
validated for
clinical mate
rial, compri
sing
100 cases. F
C
M
gra
d
i
n
g m
o
d
e
l
achi
eved
a di
a
g
n
o
sti
c
out
put
of
accur
a
cy
o
f
9
2
.
68%
(38/
41
)
and
93
.2
2
%
(5
5/
5
9
)
for
brai
n t
u
m
o
u
r
s of l
o
w
g
r
ade
and
hi
gh
gra
d
e,
respectivel
y.
The results
of the pr
oposed gr
ading
model prese
n
t reasonably high
ac
curac
y
in
comparison
to
other m
e
thods. The
propose
d
a
pproa
ch present suffici
ent interpretability
a
n
d
transparenc
y
in
decision
pro
ces
s
,
wh
ich ma
k
e
it
a
convenient consulting tool
in char
acteri
z
i
ng tumor
ag
gressi
venes
s
i
n
clinical practice"
his paper discusses an under development Intelligent Multimedia Environment for the Speech and Language Impaired to support people with special needs to improve their performance and intervene in their Speech and Language... more
his paper discusses an under development
Intelligent Multimedia Environment for the Speech and
Language Impaired to support people with special needs to
improve their performance and intervene in their Speech and
Language disabilities. This environment supports speech and
language therapy professionals to perform speech and language
tests, validate the results, use differential diagnosis methods to
provide therapists with a diagnosis of the disorder, and suggest
an appropriate intervention plan. It is an integrated
environment supporting even people with severe speech and
language disorders by providing them a suitable, easy-to-use,
and health-safe communication environment to alert hospital
and other medical centers for life at risk.
Intelligent Multimedia Environment for the Speech and
Language Impaired to support people with special needs to
improve their performance and intervene in their Speech and
Language disabilities. This environment supports speech and
language therapy professionals to perform speech and language
tests, validate the results, use differential diagnosis methods to
provide therapists with a diagnosis of the disorder, and suggest
an appropriate intervention plan. It is an integrated
environment supporting even people with severe speech and
language disorders by providing them a suitable, easy-to-use,
and health-safe communication environment to alert hospital
and other medical centers for life at risk.
"Fuzzy Cognitive Map (FCM) is a soft computing modelling methodology for complex systems. Beyond the mathematical formulation of the FCM theory, there was a need of developing a software tool to facilitate the implementation of FCMs.... more
"Fuzzy Cognitive Map (FCM) is a soft computing
modelling methodology for complex systems. Beyond the
mathematical formulation of the FCM theory, there was a need
of developing a software tool to facilitate the implementation of
FCMs. This paper describes the use of a software tool that was
developed to construct FCM models. Some theoretical elements
of Fuzzy Cognitive Maps are presented. Then, it is discussed
how the software tool is used to develop a model and simulate
the use of Fuzzy Cognitive Maps. The user interface of the
software tool is described and how the FCM-Analyst is used to
facilitate the implementation and simulation of Fuzzy Cognitive
Maps. "
modelling methodology for complex systems. Beyond the
mathematical formulation of the FCM theory, there was a need
of developing a software tool to facilitate the implementation of
FCMs. This paper describes the use of a software tool that was
developed to construct FCM models. Some theoretical elements
of Fuzzy Cognitive Maps are presented. Then, it is discussed
how the software tool is used to develop a model and simulate
the use of Fuzzy Cognitive Maps. The user interface of the
software tool is described and how the FCM-Analyst is used to
facilitate the implementation and simulation of Fuzzy Cognitive
Maps. "
he catalytic reforming of naphta is one of the major refinery processes, designed to increase the octane number of naphta or to produce aromatics. This paper presents a soft computing method for catalytic reforming units performance... more
he catalytic reforming of naphta is one of the major refinery processes, designed to increase the octane
number of naphta or to produce aromatics. This paper presents a soft computing method for catalytic reforming units
performance monitoring. The method is based on Fuzzy Cognitive Maps, which are fuzzy digraph of fuzzy sets,
connected by edges. Edge values represent the causal relationship among the concept nodes. As for the problem of how
to determine the degree of causal relationship, a differential Hebbian learning developed by improving self-organizated
learning of neural networks is proposed. A naphta reforming kinetic model is developed for abnormal operation
conditions simulation.
number of naphta or to produce aromatics. This paper presents a soft computing method for catalytic reforming units
performance monitoring. The method is based on Fuzzy Cognitive Maps, which are fuzzy digraph of fuzzy sets,
connected by edges. Edge values represent the causal relationship among the concept nodes. As for the problem of how
to determine the degree of causal relationship, a differential Hebbian learning developed by improving self-organizated
learning of neural networks is proposed. A naphta reforming kinetic model is developed for abnormal operation
conditions simulation.
During radiotherapy many decisions have to be made and the development of an advanced decision support system that take into consideration different and discipline factors in determining the dose calculation for radiotherapy... more
During radiotherapy many decisions have
to be
made and the development
of
an
advanced decision support system
that
take
into consideration different
and
discipline
factors
in
determining the dose calculation
for radiotherapy treatment
would
be very
useful.
The
implementation
of
Fuzzy
Cognitive
Maps
(FCM)
for
decision-
making issues
in
radiotherapy is proposed.
FCMs
can handle with imprecise, uncertain
information and can be used
as
a decision
making model determining radiation dose
and other related quantities.
to be
made and the development
of
an
advanced decision support system
that
take
into consideration different
and
discipline
factors
in
determining the dose calculation
for radiotherapy treatment
would
be very
useful.
The
implementation
of
Fuzzy
Cognitive
Maps
(FCM)
for
decision-
making issues
in
radiotherapy is proposed.
FCMs
can handle with imprecise, uncertain
information and can be used
as
a decision
making model determining radiation dose
and other related quantities.
Fuzzy Cognitive Maps have been introduced as a combination of Fuzzy logic and Neural Networks. In this paper a new learning rule based on unsupervised Hebbian learning and a new training algorithm based on Hopfield... more
Fuzzy Cognitive Maps have
been
introduced as
a
combination of Fuzzy logic
and Neural Networks.
In
this paper
a
new
learning rule
based on
unsupervised
Hebbian
learning
and
a
new training
algorithm based
on
Hopfield
nets are
introduced
and
are compared for
the
training
of Fuzzy Cognitive Maps.
been
introduced as
a
combination of Fuzzy logic
and Neural Networks.
In
this paper
a
new
learning rule
based on
unsupervised
Hebbian
learning
and
a
new training
algorithm based
on
Hopfield
nets are
introduced
and
are compared for
the
training
of Fuzzy Cognitive Maps.
Labour is a stressed procedure for both the fetus and the mother and a key issue for fetus surveillance is the detection of fetal distress. This paper describes a software tool that has been developed in order to monitoring fetus status... more
Labour is a stressed procedure for both the fetus and the mother and a key issue for fetus surveillance is the detection
of fetal distress. This paper describes a software tool that has been developed in order to monitoring fetus status by acquiring and
processing the Cardiotocogram (CTG). This software tool establishes a communication between PC and the cardiotocograph, the
medical device that records and prints out the Fetal Heard Rate and the Uterine Activity. Then, the software tool pre-processes the
signal from the cardiotocographic device, artifacts are removed and non-signal parts (gaps) are filled utilizing an interpolation
method. The more advanced part of the software tool includes the processing of CTG signal, extracting the characteristics of the
signal such as baseline, variability, accelerations and decelerations. According to these characteristics, CTG can be evaluated and
comments on the physiological or not status of the fetus can be done and giving an objective estimation on the health of fetus to the
doctor.
of fetal distress. This paper describes a software tool that has been developed in order to monitoring fetus status by acquiring and
processing the Cardiotocogram (CTG). This software tool establishes a communication between PC and the cardiotocograph, the
medical device that records and prints out the Fetal Heard Rate and the Uterine Activity. Then, the software tool pre-processes the
signal from the cardiotocographic device, artifacts are removed and non-signal parts (gaps) are filled utilizing an interpolation
method. The more advanced part of the software tool includes the processing of CTG signal, extracting the characteristics of the
signal such as baseline, variability, accelerations and decelerations. According to these characteristics, CTG can be evaluated and
comments on the physiological or not status of the fetus can be done and giving an objective estimation on the health of fetus to the
doctor.
Fuzzy Cognitive Maps (FCM) are presented in this paper. A short reference on their implementation in a wide field of science is provided in the introduction; then it is examined their representation and the methodology which is used to... more
Fuzzy Cognitive Maps (FCM) are presented in this paper. A short reference on their implementation in
a wide field of science is provided in the introduction; then it is examined their representation and the methodology
which is used to construct a FCM. In the last part of this paper a generic system is proposed to be used for the
modeling and control of a plant-process, the supervisor of this system is modeled as a Fuzzy Cognitive Map.
a wide field of science is provided in the introduction; then it is examined their representation and the methodology
which is used to construct a FCM. In the last part of this paper a generic system is proposed to be used for the
modeling and control of a plant-process, the supervisor of this system is modeled as a Fuzzy Cognitive Map.
This paper specifies a Decision Support System (DSS) devoted to manage Intermodal Transportation Networks (ITN). With the aim to support decision makers in the management of the complex processes in the ITN, we describe the... more
This paper specifies a Decision Support System
(DSS) devoted to manage Intermodal Transportation
Networks (ITN). With the aim to support decision
makers in the management of the complex processes in
the ITN, we describe the architecture of a DSS and its
main components. In order to obtain a generic DSS, we
employ the Unified Modeling Language (UML) to
describe the components and the architecture of the
DSS and we apply the solutions based on Service
Oriented Architecture, the simulation drivers and
window services.
(DSS) devoted to manage Intermodal Transportation
Networks (ITN). With the aim to support decision
makers in the management of the complex processes in
the ITN, we describe the architecture of a DSS and its
main components. In order to obtain a generic DSS, we
employ the Unified Modeling Language (UML) to
describe the components and the architecture of the
DSS and we apply the solutions based on Service
Oriented Architecture, the simulation drivers and
window services.
Modeling and development approaches for Decision Support Systems (DSSs) attract much attention as technological systems are becoming more complex in order to respond to the constantly growing requirements of nowadays organizational... more
Modeling and development approaches for Decision
Support Systems (DSSs) attract much attention as technological
systems are becoming more complex in order to respond to the
constantly growing requirements of nowadays organizational
needs, and to support Decision Makers (DM) and managers. In
this paper we describe the use of the Unified Modeling Language
(UML) to mo
del DSSs. We present a general framework for
describing and developing DSSs in a coherent and structured
way to all the phases of the development procedure, from the
problem definition to the final implementation. Finally, we apply
this methodology to a pa
rticular case study, the Bay Allocation
Problem (BAP).
Support Systems (DSSs) attract much attention as technological
systems are becoming more complex in order to respond to the
constantly growing requirements of nowadays organizational
needs, and to support Decision Makers (DM) and managers. In
this paper we describe the use of the Unified Modeling Language
(UML) to mo
del DSSs. We present a general framework for
describing and developing DSSs in a coherent and structured
way to all the phases of the development procedure, from the
problem definition to the final implementation. Finally, we apply
this methodology to a pa
rticular case study, the Bay Allocation
Problem (BAP).
Noisy optimization problems arise very often in real–life ap- plications. A common practice to tackle problems charac- terized by uncertainties, is the re–evaluation of the objective function at every point of interest for a fixed... more
Noisy optimization problems arise very often in real–life ap-
plications. A common practice to tackle problems charac-
terized by uncertainties, is the re–evaluation of the objective
function at every point of interest for a fixed number of repli-
cations. The obtained objective values are then averaged
and their mean is considered as the approximation of the
actual objective value. However, this approach can prove
inefficient, allocating replications to unpromising candidate
solutions. We propose a hybrid approach that integrates the
established Particle Swarm Optimization algorithm with the
Reinforcement Learning approach to efficiently tackle noisy
problems by intelligently allocating the available computa-
tional budget. Two variants of the proposed approach, based
on different selection schemes, are assessed and compared
against the typical alternative of equal sampling. The re-
sults are reported and analyzed, offering significant evidence
regarding the potential of the proposed approach.
plications. A common practice to tackle problems charac-
terized by uncertainties, is the re–evaluation of the objective
function at every point of interest for a fixed number of repli-
cations. The obtained objective values are then averaged
and their mean is considered as the approximation of the
actual objective value. However, this approach can prove
inefficient, allocating replications to unpromising candidate
solutions. We propose a hybrid approach that integrates the
established Particle Swarm Optimization algorithm with the
Reinforcement Learning approach to efficiently tackle noisy
problems by intelligently allocating the available computa-
tional budget. Two variants of the proposed approach, based
on different selection schemes, are assessed and compared
against the typical alternative of equal sampling. The re-
sults are reported and analyzed, offering significant evidence
regarding the potential of the proposed approach.
This paper presents the implementation and the results of downscaling thermal infrared satellite ima gery produced by Meteosat Second Generation. A new methodology is examined based on com putational intelligence techniques for... more
This paper presents the implementation and the results of downscaling
thermal infrared satellite ima
gery produced by Meteosat Second Generation. A new
methodology is examined based on com
putational intelligence techniques for
downscaling of a series of consequent infrar
ed images. Our intention is to develop an
automated methodology that will be
able to operate either as
a stand-alone procedure or
in conjunction with existing software app
lications that detect and monitor cloud
systems, rainfall and other essential parameters for the observation of atmosphere and
Earth that all are based on contiguous, accu
rate and high spatia
l resolution datasets.
thermal infrared satellite ima
gery produced by Meteosat Second Generation. A new
methodology is examined based on com
putational intelligence techniques for
downscaling of a series of consequent infrar
ed images. Our intention is to develop an
automated methodology that will be
able to operate either as
a stand-alone procedure or
in conjunction with existing software app
lications that detect and monitor cloud
systems, rainfall and other essential parameters for the observation of atmosphere and
Earth that all are based on contiguous, accu
rate and high spatia
l resolution datasets.
Medical Decision Support Systems (MDSS) are very important constructions that are incorporated into Intelligent Information E - Health Systems aiming to produce warning s or to consult and suggest clinical ju dgments either... more
Medical Decision Support Systems (MDSS) are very important
constructions
that are
incorporated into Intelligent Information E
-
Health Systems aiming to
produce
warning
s
or to
consult and
suggest clinical ju
dgments either
to
inexperienced medical professionals or in their light
er
versions to the
general public through
medical advisors websites
. Soft Computing
(SC)
techniques
,
especially th
ose
that
are based on exploit
ing
human knowledge and experience
,
are extr
emely useful to model complex
decision making procedures and thus
,
they
have a key role in development such MDSS. Such a modeling
methodology i
s Fuzzy Cognitive Maps
which is
suitable to represent human reasoning and
to
infer
conclusions and decisions in a
human
-
like
way. In
order to develop
an integrated
stand alone
MDSS,
Fuzzy Cognitive Maps could be complemented by other Soft Computing techniques such as Genetic
Algorithms
and/
or Case Based Reasoning and so to construct more efficient advanced Medical De
cision
Support Systems. The synergism and complementary of these methodologies may pave
the way
to new
sophisticated systems.
constructions
that are
incorporated into Intelligent Information E
-
Health Systems aiming to
produce
warning
s
or to
consult and
suggest clinical ju
dgments either
to
inexperienced medical professionals or in their light
er
versions to the
general public through
medical advisors websites
. Soft Computing
(SC)
techniques
,
especially th
ose
that
are based on exploit
ing
human knowledge and experience
,
are extr
emely useful to model complex
decision making procedures and thus
,
they
have a key role in development such MDSS. Such a modeling
methodology i
s Fuzzy Cognitive Maps
which is
suitable to represent human reasoning and
to
infer
conclusions and decisions in a
human
-
like
way. In
order to develop
an integrated
stand alone
MDSS,
Fuzzy Cognitive Maps could be complemented by other Soft Computing techniques such as Genetic
Algorithms
and/
or Case Based Reasoning and so to construct more efficient advanced Medical De
cision
Support Systems. The synergism and complementary of these methodologies may pave
the way
to new
sophisticated systems.
Fuzzy Cognitive Maps (FCMs) is an abstract soft computing modeling methodology that has been applied in many areas quite successfully. In this paper we discuss its modeling applicability to complex logistics systems involved in an... more
Fuzzy Cognitive Maps (FCMs) is an abstract soft
computing modeling methodology
that has been applied in
many areas quite successfully. In this paper we discuss its
modeling applicability to complex
logistics systems involved in
an intermodal container terminal and the way it could
represent and handle the vast amount of information by an
abstract point of view based on a decentralized approach,
where the supervisor of the system is modeled as an FCM. We
also investigate its applicab
ility as a metamodel of the
intermodal terminal in a simu
lation-optimization framework.
Experts have a key role in developing the FCM as they describe
a general operational and behavior
al model of the system using
concepts for the main aspects of the system, and weighted
directed edges to represent causality. On the other hand, when
data is available, data driven approaches have also been
proposed for the development of FCM models. The FCM
representation and implementation is discussed to develop a
behavioral model of any complex system mainly based on a
hierarchical structure, as well as its use as a metamodel of the
system.
computing modeling methodology
that has been applied in
many areas quite successfully. In this paper we discuss its
modeling applicability to complex
logistics systems involved in
an intermodal container terminal and the way it could
represent and handle the vast amount of information by an
abstract point of view based on a decentralized approach,
where the supervisor of the system is modeled as an FCM. We
also investigate its applicab
ility as a metamodel of the
intermodal terminal in a simu
lation-optimization framework.
Experts have a key role in developing the FCM as they describe
a general operational and behavior
al model of the system using
concepts for the main aspects of the system, and weighted
directed edges to represent causality. On the other hand, when
data is available, data driven approaches have also been
proposed for the development of FCM models. The FCM
representation and implementation is discussed to develop a
behavioral model of any complex system mainly based on a
hierarchical structure, as well as its use as a metamodel of the
system.
The Phasic Electromyographic Metric (PEM) has been recently introduced as a sensitive indicator to differentiate Parkinson’s Disease (PD) patients from controls, non-PD patients with a history of Rapid Eye Movement Disorder (RBD) from... more
The Phasic Electromyographic Metric (PEM) has
been recently introduced as a sensitive indicator to differentiate
Parkinson’s Disease (PD) patients from controls, non-PD
patients with a history of Rapid Eye Movement Disorder
(RBD) from controls
,
and PD patients with early and late stage
disease. However, PEM assessment through visual inspection is
a cumbersome and time consuming process. Therefore, a
reliable automated approach is required so as to increase the
utilization of PEM as a reliable and efficient clinical tool to
track PD progression. In this
study an automated method for
the detection of PEM is presented, based on the use of signal
analysis and pattern recognition techniques. The results are
promising indicating that an
automatic PEM identification
procedure is feasible.
been recently introduced as a sensitive indicator to differentiate
Parkinson’s Disease (PD) patients from controls, non-PD
patients with a history of Rapid Eye Movement Disorder
(RBD) from controls
,
and PD patients with early and late stage
disease. However, PEM assessment through visual inspection is
a cumbersome and time consuming process. Therefore, a
reliable automated approach is required so as to increase the
utilization of PEM as a reliable and efficient clinical tool to
track PD progression. In this
study an automated method for
the detection of PEM is presented, based on the use of signal
analysis and pattern recognition techniques. The results are
promising indicating that an
automatic PEM identification
procedure is feasible.
This paper presents a hybrid approach for extreme artifact detection in electroencephalogram (EEG) data, recorded as part of the polysomnogram (psg). The approach is based on the selection of an “optimal” set of features guided by an... more
This paper presents a hybrid approach for extreme artifact detection
in electroencephalogram (EEG) data, recorded as part of the polysomnogram
(psg). The approach is based on the selection of an “optimal” set of features
guided by an evolutionary algorithm and a novelty detector based on Parzen
window estimation, whose kernel parameter
h
is also selected by the evolution-
ary algorithm. The results here suggest that this approach could be very helpful
in cases of absence of artifacts during the training process.
in electroencephalogram (EEG) data, recorded as part of the polysomnogram
(psg). The approach is based on the selection of an “optimal” set of features
guided by an evolutionary algorithm and a novelty detector based on Parzen
window estimation, whose kernel parameter
h
is also selected by the evolution-
ary algorithm. The results here suggest that this approach could be very helpful
in cases of absence of artifacts during the training process.