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.
Fetal heart rate (fHR) is used to evaluate the fetal well-being during the delivery. It provides information of fe tal status and allows doctors to detect ongoing hypoxia. Routine clinical evaluation of intrapartal fHR is based on... more
Fetal heart rate (fHR) is used to evaluate the fetal well-being during
the delivery. It provides information of fe
tal status and allows doctors to detect
ongoing hypoxia. Routine clinical evaluation of intrapartal fHR is based on de-
scription of macroscopic morphological features of its baseline. In this paper we
show, that by using additional features for description of the fHR recordings,
we can improve the classification accuracy. Additionally since results of
automatic signal evaluation are easily reproducible we can objectify the whole
process, thus enabling us to focus on the underlying reasons for high expert
inter-observer and intra-observer variability.
the delivery. It provides information of fe
tal status and allows doctors to detect
ongoing hypoxia. Routine clinical evaluation of intrapartal fHR is based on de-
scription of macroscopic morphological features of its baseline. In this paper we
show, that by using additional features for description of the fHR recordings,
we can improve the classification accuracy. Additionally since results of
automatic signal evaluation are easily reproducible we can objectify the whole
process, thus enabling us to focus on the underlying reasons for high expert
inter-observer and intra-observer variability.
"The main objective of this paper is to investigate and pro- pose a new approach to distinguish between two classes of beats from the ECG holter recordings - the premature ventricular beats (V) and the nor- mal ones (N). The integrated... more
"The main objective of this paper is to investigate and pro-
pose a new approach to distinguish between two classes of beats from the
ECG holter recordings - the premature ventricular beats (V) and the nor-
mal ones (N). The integrated methodology consists of a specific sequence:
R-peak detection, feature extraction, Principal Component Analysis di-
mensionality reduction and classification with a neural classifier. ECG
beats of holter recordings are described using means as simple as pos-
sible resulting in a description of the QRS complex by features derived
mathematically from the signal using only R-peak detection. For this re-
search work, normal (N) and ventricular (V) beats from the well known
MIT-BIH database were used to test the proposed methodology. The
results are promising paving the way for the more demanding multiclass
classification problem."
pose a new approach to distinguish between two classes of beats from the
ECG holter recordings - the premature ventricular beats (V) and the nor-
mal ones (N). The integrated methodology consists of a specific sequence:
R-peak detection, feature extraction, Principal Component Analysis di-
mensionality reduction and classification with a neural classifier. ECG
beats of holter recordings are described using means as simple as pos-
sible resulting in a description of the QRS complex by features derived
mathematically from the signal using only R-peak detection. For this re-
search work, normal (N) and ventricular (V) beats from the well known
MIT-BIH database were used to test the proposed methodology. The
results are promising paving the way for the more demanding multiclass
classification problem."
n this research work we investigate the analysis o f Acoustic Emission (AE) signals using wavelet decomp osition to locate a single event (crack), which usually takes place in three typical areas in a ship hull. The problem is a... more
n this research work we investigate the analysis o
f
Acoustic Emission (AE) signals using wavelet decomp
osition to
locate a single event (crack), which usually takes
place in three
typical areas in a ship hull. The problem is a typi
cal
classification problem relying on the use of novel
features
extracted from the AE time series. As in most class
ification
problems the extraction and selection of the most a
ppropriate
set of features plays a major role in the overall p
erformance of
the method and it is by no means a trivial task. On
ce a suitable
set of features is extracted even “simple” classifi
cation models
can perform adequately whereas a non-informative se
t of
features even combined with sophisticated classifie
rs can lead
to disappointing results. Here, we exploit the mult
i-resolution
capabilities of wavelet decomposition, so that a se
t of features
is extracted which it is then combined with a simpl
e classifier.
The proposed method gives superior classification r
ates for
noisy environments compared to our previous work wh
ere
conventional methods for feature extraction were de
ployed.
f
Acoustic Emission (AE) signals using wavelet decomp
osition to
locate a single event (crack), which usually takes
place in three
typical areas in a ship hull. The problem is a typi
cal
classification problem relying on the use of novel
features
extracted from the AE time series. As in most class
ification
problems the extraction and selection of the most a
ppropriate
set of features plays a major role in the overall p
erformance of
the method and it is by no means a trivial task. On
ce a suitable
set of features is extracted even “simple” classifi
cation models
can perform adequately whereas a non-informative se
t of
features even combined with sophisticated classifie
rs can lead
to disappointing results. Here, we exploit the mult
i-resolution
capabilities of wavelet decomposition, so that a se
t of features
is extracted which it is then combined with a simpl
e classifier.
The proposed method gives superior classification r
ates for
noisy environments compared to our previous work wh
ere
conventional methods for feature extraction were de
ployed.
This paper introduces a novel approach based on signal processing methods to extract features from speech signals and based on them to detect a specific type of articulation disorders. Articulation, in effect, is the specific and... more
This paper introduces a novel approach based on
signal processing methods to extract features from speech
signals and based on them to detect a specific type of
articulation disorders. Articulation, in effect, is the specific and
characteristic way that an individual produces the speech
sounds. Empirical Mode Decomposition and the Hilbert Huang
transform are applied to the speech signal in order to calculate
the marginal spectrum of the signal. The marginal spectrum is
subsequently subject to a mel-cepstrum like processing to
extract features which are fed to a neural network classifier
responsible for the identification of the articulation disorder.
Our preliminary results suggest that this approach is very
promising for the detection of the disorder under study.
signal processing methods to extract features from speech
signals and based on them to detect a specific type of
articulation disorders. Articulation, in effect, is the specific and
characteristic way that an individual produces the speech
sounds. Empirical Mode Decomposition and the Hilbert Huang
transform are applied to the speech signal in order to calculate
the marginal spectrum of the signal. The marginal spectrum is
subsequently subject to a mel-cepstrum like processing to
extract features which are fed to a neural network classifier
responsible for the identification of the articulation disorder.
Our preliminary results suggest that this approach is very
promising for the detection of the disorder under study.
Acoustic Emission (AE) is one of the most important Non-Destructive Testing (NDT) methods for materials and constructions. Using AE testing, the location of a single event (crack) can be classified efficiently into three typical areas... more
Acoustic Emission (AE) is one of the most
important Non-Destructive Testing (NDT) methods for
materials and constructions. Using AE testing, the location of a
single event (crack) can be classified efficiently into three
typical areas in a ship hull. The problem is a typical
classification problem based on the use of features extracted
from piezo-sensors’ signal. As in most classification problems,
the extraction and selection of the most appropriate set of
features plays a major role in the overall performance of the
system. In this research work we investigate the use of an
evolutionary algorithm to extract new features from a set of
primitive features in a lower dimensional space through a linear
transformation. These features are subsequently fed into a
Probabilistic Neural Network (PNN) that performs the
classification. In simulation experiments, where a Stiffened
Plate Model (SPM) is partially sank into water, the localization
rate in noisy environments outperforms a recent work, where a
feature selection phase alone was used before the classification
phase. The proposed hybrid computational intelligent approach
shows the potential merit of using it in real life situations where
the signal is distorted by noise.
important Non-Destructive Testing (NDT) methods for
materials and constructions. Using AE testing, the location of a
single event (crack) can be classified efficiently into three
typical areas in a ship hull. The problem is a typical
classification problem based on the use of features extracted
from piezo-sensors’ signal. As in most classification problems,
the extraction and selection of the most appropriate set of
features plays a major role in the overall performance of the
system. In this research work we investigate the use of an
evolutionary algorithm to extract new features from a set of
primitive features in a lower dimensional space through a linear
transformation. These features are subsequently fed into a
Probabilistic Neural Network (PNN) that performs the
classification. In simulation experiments, where a Stiffened
Plate Model (SPM) is partially sank into water, the localization
rate in noisy environments outperforms a recent work, where a
feature selection phase alone was used before the classification
phase. The proposed hybrid computational intelligent approach
shows the potential merit of using it in real life situations where
the signal is distorted by noise.
Flexible Manufacturing Systems (FMSs) cope with multi-product, usually small sized production. In this research work we investigate the use of evolutionary methods to solve the linear or single-row layout problem, which is the most... more
Flexible Manufacturing Systems (FMSs) cope with multi-product, usually small sized
production. In this research work we investigate the use of evolutionary methods to solve the linear or
single-row layout problem, which is the most commonly implemented layout in FMSs. Three different
approaches, based on Ant Colony Optimization, Genetic Algorithms and Particle Swarm Optimization
are tested. The experimental results show that a near optimal solution can be found for all three methods,
exploiting only a small portion of the feasible solution space, pinpointing once more the merit of using
evolutionary algorithms to tackle difficult combinatorial problems.
production. In this research work we investigate the use of evolutionary methods to solve the linear or
single-row layout problem, which is the most commonly implemented layout in FMSs. Three different
approaches, based on Ant Colony Optimization, Genetic Algorithms and Particle Swarm Optimization
are tested. The experimental results show that a near optimal solution can be found for all three methods,
exploiting only a small portion of the feasible solution space, pinpointing once more the merit of using
evolutionary algorithms to tackle difficult combinatorial problems.
Electronic fetal monitoring - continuous recording of the cardiotocogram (CTG) - consisting of fetal heart rate (fHR) and tocographic signals, is a method used for intrapartal evaluation of the well being of the fetus. In this paper... more
Electronic fetal monitoring - continuous recording of
the cardiotocogram (CTG) - consisting of fetal heart rate
(fHR) and tocographic signals, is a method used for
intrapartal evaluation of the well being of the fetus. In
this paper we evaluate several subsets of features for
outcome classification of the pregnancy based on the
CTG recording of the last 20 minutes preceding actual
delivery. The features subsets are created based on PCA,
information gain and Group of Adaptive Models
Evolution (GAME) neural network feature selection
algorithm. Our data set consisted of 104 intrapartum
recordings including 18 pregnancies with acidemia
reflected in umbilical artery pH<7.20. The results show
that the best subset consisting of mix of time-domain and
non-linear features performs consistently over the whole
data set with sensitivity and specificity over 70%, which
is well comparable to interobserver variations.
the cardiotocogram (CTG) - consisting of fetal heart rate
(fHR) and tocographic signals, is a method used for
intrapartal evaluation of the well being of the fetus. In
this paper we evaluate several subsets of features for
outcome classification of the pregnancy based on the
CTG recording of the last 20 minutes preceding actual
delivery. The features subsets are created based on PCA,
information gain and Group of Adaptive Models
Evolution (GAME) neural network feature selection
algorithm. Our data set consisted of 104 intrapartum
recordings including 18 pregnancies with acidemia
reflected in umbilical artery pH<7.20. The results show
that the best subset consisting of mix of time-domain and
non-linear features performs consistently over the whole
data set with sensitivity and specificity over 70%, which
is well comparable to interobserver variations.
This paper presents a new hybrid modeling methodology for the Complex Decis ion Making processes. It extends previous work on Competitive Fuzzy Cognitive Maps for Medical Decision Support Sy stems by complementing them with Genetic... more
This paper presents a new hybrid modeling
methodology for the Complex Decis
ion Making processes. It
extends previous work on
Competitive Fuzzy Cognitive Maps
for Medical Decision Support Sy
stems by complementing them
with Genetic Algorithms
Methods. The synergy of these
methodologies is accomplished by a new proposed algorithm
that leads to more dependabl
e Advanced Medical Decision
Support Systems that are suitable to handle situations where
the decisions are not clearly distinct. The methodology
developed here is applied su
ccessfully to model and test a
differential diagnosis prob
lem from the speech pathology area
for the diagnosis of language impairments.
methodology for the Complex Decis
ion Making processes. It
extends previous work on
Competitive Fuzzy Cognitive Maps
for Medical Decision Support Sy
stems by complementing them
with Genetic Algorithms
Methods. The synergy of these
methodologies is accomplished by a new proposed algorithm
that leads to more dependabl
e Advanced Medical Decision
Support Systems that are suitable to handle situations where
the decisions are not clearly distinct. The methodology
developed here is applied su
ccessfully to model and test a
differential diagnosis prob
lem from the speech pathology area
for the diagnosis of language impairments.
A Fuzzy Cognitive Maps (FCMs) is a modelling methodology based on exploiting knowledge and experience. It comprises the main advantages of fuzzy logic and neural networks, representing a graphical model that consists of nodes-concepts... more
A Fuzzy Cognitive Maps (FCMs) is a modelling methodology based on exploiting knowledge and
experience. It comprises the main advantages of fuzzy logic and neural networks, representing
a graphical model that consists of nodes-concepts (describing elements of the system) which
are connected with weighted edges (representing the cause and effect relationships among the
concepts). FCMs have proved to be a promising modeling methodology with many successful
applications in different areas especially for simulating system design, modeling and control. In
this work, FCMs are introduced to model a decision support system for precision agriculture (PA).
The FCM model developed consists of nodes which describe soil properties and cotton yield and
of the weighted relationships between these nodes. The nodes of the FCM model represent the
main factors influencing cotton crop production i.e. essential soil properties such as texture, pH,
OM, K, and P. The proposed FCM model addresses the problem of crop development and spatial
variability of cotton yield, taking into consideration the spatial distribution of all the important
factors affecting yield. The first results of the study are very promising; our model achieves a 70%
average success rate on yield class prediction between two possible categories (low and high) for
three different years. This model will be further investigated to achieve better results by introducing
learning algorithms into FCMs.
experience. It comprises the main advantages of fuzzy logic and neural networks, representing
a graphical model that consists of nodes-concepts (describing elements of the system) which
are connected with weighted edges (representing the cause and effect relationships among the
concepts). FCMs have proved to be a promising modeling methodology with many successful
applications in different areas especially for simulating system design, modeling and control. In
this work, FCMs are introduced to model a decision support system for precision agriculture (PA).
The FCM model developed consists of nodes which describe soil properties and cotton yield and
of the weighted relationships between these nodes. The nodes of the FCM model represent the
main factors influencing cotton crop production i.e. essential soil properties such as texture, pH,
OM, K, and P. The proposed FCM model addresses the problem of crop development and spatial
variability of cotton yield, taking into consideration the spatial distribution of all the important
factors affecting yield. The first results of the study are very promising; our model achieves a 70%
average success rate on yield class prediction between two possible categories (low and high) for
three different years. This model will be further investigated to achieve better results by introducing
learning algorithms into FCMs.
Fuzzy Cognitive Map (FCM) is an advanced modeling methodology that provides flexibility on the system’s design, modeling, simulation and control. This research work combines the Fuzzy Cognitive Map model for tumor grading with Support... more
Fuzzy Cognitive Map (FCM) is an advanced modeling methodology
that provides flexibility on the system’s design, modeling, simulation and
control. This research work combines the Fuzzy Cognitive Map model for
tumor grading with Support Vector Machines (SVMs) to achieve better tumor
malignancy classification. The classification is based on the histopathological
characteristics, which are the concepts of the Fuzzy Cognitive Map model that
was trained using an unsupervised learning algorithm, the Nonlinear Hebbian
Algorithm. The classification accuracy of the proposed approach is 89.13% for
High Grade tumor cases and 85.54%, for tumors of Low Grade. The results of
the proposed hybrid approach were also compared with other conventional
classifiers and are very promising.
that provides flexibility on the system’s design, modeling, simulation and
control. This research work combines the Fuzzy Cognitive Map model for
tumor grading with Support Vector Machines (SVMs) to achieve better tumor
malignancy classification. The classification is based on the histopathological
characteristics, which are the concepts of the Fuzzy Cognitive Map model that
was trained using an unsupervised learning algorithm, the Nonlinear Hebbian
Algorithm. The classification accuracy of the proposed approach is 89.13% for
High Grade tumor cases and 85.54%, for tumors of Low Grade. The results of
the proposed hybrid approach were also compared with other conventional
classifiers and are very promising.
"Electronic fetal monitoring is an essential tool for fetal surveillance during labor. It is mainly based on the monitoring and evaluation of the Fetal Heart Rate (FHR) signal, which has to be interpreted... more
"Electronic
fetal
monitoring
is
an
essential
tool
for
fetal
surveillance
during
labor.
It
is
mainly
based
on
the
monitoring
and
evaluation
of
the
Fetal
Heart
Rate
(FHR)
signal,
which
has
to
be
interpreted
online.
Evaluation
and
interpretation of FHR gives an indication of the fetal condition. A lot of research efforts have been done towards the development of automatic and reliable methods for processing and evaluating FHR. This research work introduces an integrated methodology for processing and classifying FHR based on the novel approach of grammatical evolution for feature construction and selection. The proposed methodology is presented, and it is applied to a data set. Experimental results are promising paving the way for further research in that direction."
fetal
monitoring
is
an
essential
tool
for
fetal
surveillance
during
labor.
It
is
mainly
based
on
the
monitoring
and
evaluation
of
the
Fetal
Heart
Rate
(FHR)
signal,
which
has
to
be
interpreted
online.
Evaluation
and
interpretation of FHR gives an indication of the fetal condition. A lot of research efforts have been done towards the development of automatic and reliable methods for processing and evaluating FHR. This research work introduces an integrated methodology for processing and classifying FHR based on the novel approach of grammatical evolution for feature construction and selection. The proposed methodology is presented, and it is applied to a data set. Experimental results are promising paving the way for further research in that direction."
This paper proposes a novel integrated methodology to extract features and classify speech sounds with intent to detect the possible existence of a speech articulation disorder in a speaker. Articulation, in effec t, is the specific... more
This paper proposes a novel integrated methodology
to extract features and classify speech sounds with intent to detect
the possible existence of a speech
articulation disorder in a
speaker. Articulation, in effec
t, is the specific a
nd characteristic
way that an individual produces the speech sounds. A
methodology to process the speech
signal, extract features and
finally classify the signal and detect articulation problems in a
speaker is presented. The use
of Support Vector Machines
(SVMs), for the classification of speech sounds and detection of
articulation disorders is intro
duced. The propos
ed method is
implemented on a data set where different sets of features and
different schemes of SVMs are te
sted leading to satisfactory
performance
to extract features and classify speech sounds with intent to detect
the possible existence of a speech
articulation disorder in a
speaker. Articulation, in effec
t, is the specific a
nd characteristic
way that an individual produces the speech sounds. A
methodology to process the speech
signal, extract features and
finally classify the signal and detect articulation problems in a
speaker is presented. The use
of Support Vector Machines
(SVMs), for the classification of speech sounds and detection of
articulation disorders is intro
duced. The propos
ed method is
implemented on a data set where different sets of features and
different schemes of SVMs are te
sted leading to satisfactory
performance
Ant Colony System (ACS) is a meta-heuristic methodology, inspired by the behaviour of natural ants, which has already been applied to a numerous combinatorial problems. Flexible Manufacturing Systems cope with multi-product, usually... more
Ant Colony System (ACS) is a meta-heuristic methodology, inspired by the
behaviour of natural ants, which has already been applied to a numerous combinatorial
problems. Flexible Manufacturing Systems cope with multi-product, usually small sized
production. In this research work we investigate and apply an Ant Colony Optimization
algorithm, which arranges the machines of a production line so that to minimize the total
amount of backward flows. The experimental results show that a near optimal solution
can be found exploiting only a small portion of the feasible solution space. Thus, the
proposed algorithm indicates that it is a promising method, which can be applied to
complex shop floor configuration for a generalised layout.
behaviour of natural ants, which has already been applied to a numerous combinatorial
problems. Flexible Manufacturing Systems cope with multi-product, usually small sized
production. In this research work we investigate and apply an Ant Colony Optimization
algorithm, which arranges the machines of a production line so that to minimize the total
amount of backward flows. The experimental results show that a near optimal solution
can be found exploiting only a small portion of the feasible solution space. Thus, the
proposed algorithm indicates that it is a promising method, which can be applied to
complex shop floor configuration for a generalised layout.
This research work compares the cla ssification results of Fetal Heart Rate signal using three different feature sets. The Discrete Wavelet Transform is employed to extract three different sets consisted of scale and time-scale... more
This research work compares the cla
ssification results of Fetal Heart Rate signal
using three different feature sets. The Discrete
Wavelet Transform is employed to extract
three different sets consisted of scale and
time-scale dependent features from the Fetal
Heart Rate signal. The three sets of features are classified using the method of Support
Vector Machines (SVM) with RBF kernels. Th
e experimental data set are 40 intrapartum
recordings and the extracted thre
e different sets of features are entered to SVM to classify
the FHR. The classification results for the three
data sets are compared with respect to their
ability to characterize fetal condition. The best classification performance achieved was 90%
ssification results of Fetal Heart Rate signal
using three different feature sets. The Discrete
Wavelet Transform is employed to extract
three different sets consisted of scale and
time-scale dependent features from the Fetal
Heart Rate signal. The three sets of features are classified using the method of Support
Vector Machines (SVM) with RBF kernels. Th
e experimental data set are 40 intrapartum
recordings and the extracted thre
e different sets of features are entered to SVM to classify
the FHR. The classification results for the three
data sets are compared with respect to their
ability to characterize fetal condition. The best classification performance achieved was 90%
: One new approach for the problem of feature extraction and cl assification of Fetal Heart Rate signal is introduced in this paper. It considers the use of the Discrete Wavelet Transformation to extract scale-dependent feat ures of... more
: One new approach for the problem of
feature extraction and cl
assification of Fetal
Heart Rate signal is introduced in this paper.
It considers the use of the Discrete Wavelet
Transformation to extract scale-dependent feat
ures of Fetal Heart Rate (FHR) signal and
the use of Support Vector Machines for classification of FHR. The proposed methodology
is tested on real data acquired just before
delivery. The results proved the viability of the
approach and its potential for further application by achieving an overall classification
performance of 90%.
feature extraction and cl
assification of Fetal
Heart Rate signal is introduced in this paper.
It considers the use of the Discrete Wavelet
Transformation to extract scale-dependent feat
ures of Fetal Heart Rate (FHR) signal and
the use of Support Vector Machines for classification of FHR. The proposed methodology
is tested on real data acquired just before
delivery. The results proved the viability of the
approach and its potential for further application by achieving an overall classification
performance of 90%.
"There is an ongoing effort to develop advanced methods and computer based systems to assist the obstetricians in the difficult task of feature extraction and the classification of the Cardiotocogram (CTG), which is the most widely... more
"There is an ongoing effort to develop advanced methods and computer based
systems to assist the obstetricians in the difficult task of feature extraction and the
classification of the Cardiotocogram (CTG),
which is the most widely used electronic
fetal monitoring method all over the world. In this research work we propose an
integrated methodology for CTG analysis an
d classification. A novel set of features,
derived from the time and frequency domains, is used to feed the new powerful tool for
pattern classification, named Support Vector
Machines (SVMs). Here a new integrated
methodology is proposed for signal processing, feature extraction and finally
classification of CTG, This methodology is applied to a data set and the achieved overall
classification performance is 86.11%. "
systems to assist the obstetricians in the difficult task of feature extraction and the
classification of the Cardiotocogram (CTG),
which is the most widely used electronic
fetal monitoring method all over the world. In this research work we propose an
integrated methodology for CTG analysis an
d classification. A novel set of features,
derived from the time and frequency domains, is used to feed the new powerful tool for
pattern classification, named Support Vector
Machines (SVMs). Here a new integrated
methodology is proposed for signal processing, feature extraction and finally
classification of CTG, This methodology is applied to a data set and the achieved overall
classification performance is 86.11%. "
"Computational diagnosis tools are becoming indispensable to support modern medical diagnosis. This research work introduces an hybrid soft computing scheme consisting of Fuzzy Cognitive Maps and the effective Active Hebbian Learning... more
"Computational diagnosis tools are becoming indispensable
to support modern medical diagnosis. This research work introduces an
hybrid soft computing scheme consisting of Fuzzy Cognitive Maps and
the effective Active Hebbian Learning (AHL) algorithm for tumor cha-
racterization. The proposed method exploits human experts’ knowledge
on histopathology expressed in descriptive terms and concepts and it is
enhanced with Hebbian learning and then it classifies tumors based on
the morphology of tissues. This method was validated in clinical data
and the results enforce the effectiveness of the proposed approach."
to support modern medical diagnosis. This research work introduces an
hybrid soft computing scheme consisting of Fuzzy Cognitive Maps and
the effective Active Hebbian Learning (AHL) algorithm for tumor cha-
racterization. The proposed method exploits human experts’ knowledge
on histopathology expressed in descriptive terms and concepts and it is
enhanced with Hebbian learning and then it classifies tumors based on
the morphology of tissues. This method was validated in clinical data
and the results enforce the effectiveness of the proposed approach."
In this paper an integrated hierarchical soft computing methodology for modeling of industrial plants by aggregating models of different types is presented. The problem of designing adequate and reliable models for non-linear plants with... more
In this paper an integrated hierarchical soft computing methodology for modeling of industrial plants by aggregating models of different types is presented. The problem of designing adequate and reliable models for non-linear plants with large uncertainties is under consideration here. The proposed approach has the ability to model system behaviour under, different circumstances and it is especially efficient for complex industrial systems with immeasurable process variables and large uncertainties. A Fuzzy Cognitive Map (FCh4) is used to aggregate multiple models and to create a hybrid model, which makes a selection between the different models, according to the current operational conditions of the industrial process. The proposed methodology is considered as a promising way to cope with the modeling of a real industrial plant.
"Fuzzy Cognitive Map (FCM) is a soft computing technique for modeling systems. It combines synergistically the theories of neural networks and fuzzy logic. The methodology of developing FCMs is easily adaptable but relies on human... more
"Fuzzy Cognitive Map (FCM) is a soft computing technique
for modeling systems. It combines synergistically the theories of neural
networks and fuzzy logic. The methodology of developing FCMs is
easily adaptable but relies on human experience and knowledge, and
thus FCMs exhibit weaknesses and dependence on human experts. The
critical dependence on the expert’s opinion and knowledge, and the
potential convergence to undesired steady states are deficiencies of
FCMs. In order to overcome these deficiencies and improve the
efficiency and robustness of FCM a possible solution is the utilization
of learning methods. This research work proposes the utilization of the
unsupervised Hebbian algorithm to nonlinear units for training FCMs.
Using the proposed learning procedure, the FCM modifies its fuzzy
causal web as causal patterns change and as experts update their causal
knowledge."
for modeling systems. It combines synergistically the theories of neural
networks and fuzzy logic. The methodology of developing FCMs is
easily adaptable but relies on human experience and knowledge, and
thus FCMs exhibit weaknesses and dependence on human experts. The
critical dependence on the expert’s opinion and knowledge, and the
potential convergence to undesired steady states are deficiencies of
FCMs. In order to overcome these deficiencies and improve the
efficiency and robustness of FCM a possible solution is the utilization
of learning methods. This research work proposes the utilization of the
unsupervised Hebbian algorithm to nonlinear units for training FCMs.
Using the proposed learning procedure, the FCM modifies its fuzzy
causal web as causal patterns change and as experts update their causal
knowledge."
"The present paper is devoted to Fuzzy Cognitive Maps stability analysis. There are investigated the Fuzzy Bidirectional Associative Memories (FBAMs) and some common features for FCMs and FBAMs have been revealed, which may lend to... more
"The present paper is devoted to Fuzzy Cognitive
Maps stability analysis. There are investigated the Fuzzy
Bidirectional Associative Memories (FBAMs) and some
common features for FCMs and FBAMs have been revealed,
which may lend to use the theoretical background of FBAMS
for the case of FCMs. Basing on the existing mathematical
apparatus for FBAMs stability analysis the FCMs stability
criterion was form and described in this research work. The
proposed approach is an initiative attempt to the
mathematical formulation of FCMs stability and it require
further future research."
Maps stability analysis. There are investigated the Fuzzy
Bidirectional Associative Memories (FBAMs) and some
common features for FCMs and FBAMs have been revealed,
which may lend to use the theoretical background of FBAMS
for the case of FCMs. Basing on the existing mathematical
apparatus for FBAMs stability analysis the FCMs stability
criterion was form and described in this research work. The
proposed approach is an initiative attempt to the
mathematical formulation of FCMs stability and it require
further future research."
Nowadays fetal monitoring is based on the acquisition and interpretation of the Cardiotocogram (CTG). There is an ongoing effort to develop advanced methods and computer based systems to assist the obstetricians in the difficult task of... more
Nowadays fetal monitoring is based on the acquisition and interpretation of the Cardiotocogram (CTG). There is an ongoing effort to develop advanced methods and computer based systems to assist the obstetricians in the difficult task of feature extraction and the classification of the CTG. This paper describes an integrated methodology for CTG classification, introducing the reduction of the dimensionality of the input data space, using Independent Component Analysis (ICA). The milestone of the method is the utilization of the rows of the estimated mixing matrix after the implementation of ICA method as feature vectors, which are subsequently fed to a feed-forward Neural Network (NN) classifier, which categorizes the CTG.
"This work emphasizes on the implementation of soft computing techniques for the production planning of complex manufacturing plants. A hierarchical control structure has been assumed to control and to optimize the chemical process of a... more
"This work emphasizes on the implementation of soft computing techniques for
the production planning of complex manufacturing plants. A hierarchical control
structure has been assumed to control and to optimize the chemical process of a complex
plant with successful results and at the highest hierarchical level the production planning
should meet the fluctuating demands in optimal way. This level integrates the
operational and business management requirements where the soft computing technique
of Fuzzy Cognitive Maps is proposed to model these tasks. The strategic planning for
the hierarchical integrated system realizes the optimal total management at the corporate
level. The obtained simulation results prove the applicability of the proposed
methodology and the advantages of using soft computing modeling techniques for the
sophisticated high level of hierarchical systems."
the production planning of complex manufacturing plants. A hierarchical control
structure has been assumed to control and to optimize the chemical process of a complex
plant with successful results and at the highest hierarchical level the production planning
should meet the fluctuating demands in optimal way. This level integrates the
operational and business management requirements where the soft computing technique
of Fuzzy Cognitive Maps is proposed to model these tasks. The strategic planning for
the hierarchical integrated system realizes the optimal total management at the corporate
level. The obtained simulation results prove the applicability of the proposed
methodology and the advantages of using soft computing modeling techniques for the
sophisticated high level of hierarchical systems."
"This work introduces the use of the snft computing technique of F W L ~ Cognitive Maps to model the decision-making process of radiation therapy and develop an advanced system to estimate the delivered dnse to the target volumc.... more
"This work introduces the use of the snft
computing technique of F W L ~ Cognitive Maps to model the
decision-making process of radiation therapy and develop an
advanced system to estimate the delivered dnse to the target
volumc. During radiotherapy planning numerous factors are
taking into consideration that increase the complexity of the
decisiun-making problem. The modeling methodology of FCM
ha6 the ability to integrate and consider different, discipline and
conflicting factors to determine the dose. A Fuzzy Cognitive
Map Model is developed, that can handle imprecise and
uncertain information and is used as the decision-making model
determining the radiation dose and the complex radiation
therapy system. The proposed FCM model is implemented for a
practical radiotherapy treatment planning case of gynecological
cancer."
computing technique of F W L ~ Cognitive Maps to model the
decision-making process of radiation therapy and develop an
advanced system to estimate the delivered dnse to the target
volumc. During radiotherapy planning numerous factors are
taking into consideration that increase the complexity of the
decisiun-making problem. The modeling methodology of FCM
ha6 the ability to integrate and consider different, discipline and
conflicting factors to determine the dose. A Fuzzy Cognitive
Map Model is developed, that can handle imprecise and
uncertain information and is used as the decision-making model
determining the radiation dose and the complex radiation
therapy system. The proposed FCM model is implemented for a
practical radiotherapy treatment planning case of gynecological
cancer."
"This study investigates the problem of design adequate models for non-linear large and complex plants with high uncertainties. A new hierarchical structure is considered that utilize soft computing methodologies to model the... more
"This study investigates the problem of design
adequate models for non-linear large and complex
plants with high uncertainties. A new hierarchical
structure is considered that utilize soft computing
methodologies to model the supervisor. The
proposed approach is based on the combination of
different modelling techniques within a hierarchical
supervised structure that has the ability to model
system behaviour under different operational
circumstances. A Fuzzy Cognitive Map (FCM) is
used to aggregate multiple models and to create a
hybrid model based on the current operational
conditions of the industrial process. The proposed
methodology is applied to model and simulate the
operation of an industrial plant."
adequate models for non-linear large and complex
plants with high uncertainties. A new hierarchical
structure is considered that utilize soft computing
methodologies to model the supervisor. The
proposed approach is based on the combination of
different modelling techniques within a hierarchical
supervised structure that has the ability to model
system behaviour under different operational
circumstances. A Fuzzy Cognitive Map (FCM) is
used to aggregate multiple models and to create a
hybrid model based on the current operational
conditions of the industrial process. The proposed
methodology is applied to model and simulate the
operation of an industrial plant."
"This paper presents a soft computing model for differential diagnosis of Specific Language Impairment (SLI). SLI is a language disorder that, in many cases, cannot be easily diagnosed by the specialists. This difficulty necessitates... more
"This paper presents a soft computing model for
differential diagnosis of Specific Language Impairment (SLI).
SLI is a language disorder that, in many cases, cannot be easily
diagnosed by the specialists. This difficulty necessitates the
development of a methodology, which will contribute to the
differential diagnosis of SLI and will help and support the
speech therapist in the diagnostic process. The methodologytool
used is based on Fuzzy Cognitive Maps. The development
of the model was based on proven and published knowledge
from the literature and then it was successfully tested on four
different clinical cases. The results obtained point to its final
integration in the future and to its valid contribution as a
model of differential diagnosis of SLI."
differential diagnosis of Specific Language Impairment (SLI).
SLI is a language disorder that, in many cases, cannot be easily
diagnosed by the specialists. This difficulty necessitates the
development of a methodology, which will contribute to the
differential diagnosis of SLI and will help and support the
speech therapist in the diagnostic process. The methodologytool
used is based on Fuzzy Cognitive Maps. The development
of the model was based on proven and published knowledge
from the literature and then it was successfully tested on four
different clinical cases. The results obtained point to its final
integration in the future and to its valid contribution as a
model of differential diagnosis of SLI."
"This paper describes a soft computing technique for modelling and controlling systems, Fuzzy Cognitive Maps. The description, representation and models of FCM are examined thoroughly, a FCM model is proposed and their characteristics... more
"This paper describes a soft computing technique for modelling and controlling
systems, Fuzzy Cognitive Maps. The description, representation and models of FCM are
examined thoroughly, a FCM model is proposed and their characteristics and advantages
are presented, and a development algorithm is described. Fuzzy Cognitive Maps and similar
soft computing techniques may contribute to develop more sophisticated systems"
systems, Fuzzy Cognitive Maps. The description, representation and models of FCM are
examined thoroughly, a FCM model is proposed and their characteristics and advantages
are presented, and a development algorithm is described. Fuzzy Cognitive Maps and similar
soft computing techniques may contribute to develop more sophisticated systems"
This paper presents an overview in existing representations of Fuzzy Cognitive Maps (FCM) and a new approach in the formulation of Fuzzy Cognitive Maps is examined. The description and construction of Fuzzy Cognitive Maps (FCM) is... more
This paper presents an overview in existing representations of Fuzzy Cognitive Maps (FCM) and a new
approach in the formulation of Fuzzy Cognitive Maps is examined. The description and construction of Fuzzy
Cognitive Maps (FCM) is briefly represented and some new ideas for the modeling of Fuzzy Cognitive Maps are
presented. Research in this area was mainly focalized on the representation, construction and application of
FCM, and now in this paper different types and mathematical description of Fuzzy Cognitive Maps are examined
and FCMs are mathematically transformed in forms that are analogous to Recurrent Neural Networks. This
similarity stimulates the investigation of Forward Accessibility for discrete-time FCM models. Finally, an
example of a process is presented and it is formulated in form that controllability aspects can be examined.
approach in the formulation of Fuzzy Cognitive Maps is examined. The description and construction of Fuzzy
Cognitive Maps (FCM) is briefly represented and some new ideas for the modeling of Fuzzy Cognitive Maps are
presented. Research in this area was mainly focalized on the representation, construction and application of
FCM, and now in this paper different types and mathematical description of Fuzzy Cognitive Maps are examined
and FCMs are mathematically transformed in forms that are analogous to Recurrent Neural Networks. This
similarity stimulates the investigation of Forward Accessibility for discrete-time FCM models. Finally, an
example of a process is presented and it is formulated in form that controllability aspects can be examined.
This paper investigates the implementation of a hybrid methodology, which combines fuzzy logic and neural networks, Fuzzy Cognitive Map (FCM), for the modeling of the supervisor of Large Scale Systems. The description and the... more
This paper investigates the implementation of a hybrid methodology, which
combines fuzzy logic and neural networks, Fuzzy Cognitive Map (FCM), for the
modeling of the supervisor of Large Scale Systems. The description and the
construction of Fuzzy Cognitive Map will be extensively examined and it will be
proposed a model for the supervisor. There is an oncoming need for more autonomous
and intelligent systems, especially in Large Scale Systems and the application of Fuzzy
Cognitive Map for the modeling of the Supervisor may contribute in the development of
more autonomous systems.
combines fuzzy logic and neural networks, Fuzzy Cognitive Map (FCM), for the
modeling of the supervisor of Large Scale Systems. The description and the
construction of Fuzzy Cognitive Map will be extensively examined and it will be
proposed a model for the supervisor. There is an oncoming need for more autonomous
and intelligent systems, especially in Large Scale Systems and the application of Fuzzy
Cognitive Map for the modeling of the Supervisor may contribute in the development of
more autonomous systems.