- Selcuk University Technology Faculty Electrical Electronics Engineering Department Campus 42031 Selcuklu KONYA
- +903322233335
- Cryptography, Fuzzy Logic Control, Fuzzy Logic, Image Steganography, Machine Learning, Image Processing, and 10 moreImage Processing and steganography, Natural Language Processing, Fuzzy Logic and Its Application, Fuzzy Logic Controller, Electronics, Engineering, Computer Science, Artificial Intelligence, Data Mining, and Electrical Engineeringedit
- He has been working in Electrical and Electronics Department in Technology Faculty since 2000. He got two master degr... moreHe has been working in Electrical and Electronics Department in Technology Faculty since 2000. He got two master degrees; one in Free University of Brussels (Master of Applied of Computer Sciences) and one in Selcuk University (Master in Electronics and Computer Education ). He got his PhD degree in Electronics Engineering. He has been involved in National and international R&D and social development projects since 2005. He was the coordinator of two ETN projects and two Turkish National Agency-supported projects in favor of Selcuk University. His main research areas are Cryptography, Image Steganography, Fuzzy Logic, Fuzzy Logic Control, Machine Learning and Image Processing.edit
We’re at beginning of a golden age of AI. Recent advancements have already led to invention that previously lived in the realm of science fiction – and we have only scratched the surface of what’s possible. Today, artificial intelligence... more
We’re at beginning of a golden age of AI. Recent advancements have already led to invention that previously lived in the realm of science fiction – and we have only scratched the surface of what’s possible. Today, artificial intelligence techniques are used in almost all areas of our lives, from agriculture to financial technologies. It is not possible to cover all artificial intelligence applications that can learn and reason with high accuracy using available examples in this workshop. In the workshop, we wanted to discuss successful applications of artificial intelligence in 4 different fields. These areas; they were determined as agriculture, health, financial technologies and international trade and logistics. For more information please visit http://staffmobility.eu/staffweek/international-staff-week-building-blocks
Research Interests:
Background. Analysis of the nutritional values and chemical composition of grain products plays an essential role in determining the quality of the products. Near-infrared spectroscopy has attracted the attention of researchers in recent... more
Background. Analysis of the nutritional values and chemical composition of grain products plays an essential role in determining the quality of the products. Near-infrared spectroscopy has attracted the attention of researchers in recent years due to its advantages in the analysis process. However, preprocessing and regression models in near-infrared spectroscopy are usually determined by trial and error. Combining newly popular deep learning algorithms with near-infrared spectroscopy has brought a new perspective to this area. Methods. This article presents a new method that combines a one-dimensional convolutional autoencoder with near-infrared spectroscopy to analyze the protein, moisture, oil, and starch content of corn kernels. First, a one-dimensional convolutional autoencoder model was created for three different spectra in the corn dataset. Thirtytwo latent variables were obtained for each spectrum, which is a low-dimensional spectrum representation. Multiple linear regression models were built for each target using the latent variables of obtained autoencoder models. Results. R 2 , RMSE, and RMSPE were used to show the performance of the proposed model. The created one-dimensional convolutional autoencoder model achieved a high reconstruction rate with a mean RMSPE value of 1.90% and 2.27% for calibration and prediction sets, respectively. This way, a spectrum with 700 features was converted to only 32 features. The created MLR models which use these features as input were compared to partial least squares regression and principal component regression combined with various preprocessing methods. Experimental results indicate that the proposed method has superior performance, especially in MP5 and MP6 datasets.
Research Interests:
Research Interests:
This study proposes a new hybrid n-LSB (Least Significant Bit) substitution-based image steganography method in the spatial plane. The previously proposed n-LSB substitution method by authors of this paper is combined with the... more
This study proposes a new hybrid n-LSB (Least Significant Bit) substitution-based image steganography method in the spatial plane. The previously proposed n-LSB substitution method by authors of this paper is combined with the Rivest-Shamir-Adleman (RSA), RC5, and Data Encryption Standard (DES) encryption algorithms to improve the security of the steganography, which is one of the requirements of steganography, and the Lempel-Ziv-Welch (LZW), Arithmetic and Deflate lossless compression algorithms to increase the secret message capacity. Also, embedding was done randomly using a logistic map-based chaos generator to increase the security more. The classical n-LSB substitution method and the proposed hybrid approaches based on the previously proposed n-LSB were implemented using different secret messages and cover images. When the results were examined, it has been seen that the proposed hybrid n-LSB approach showed improvement in all three criteria of steganography. The proposed hybrid approach that consists of previously proposed n-LSB, RSA, Deflate, and the logistic map had the best results regarding capacity, security, and imperceptibility.
Research Interests:
Research Interests:
It's our great honor to announce that International Congress of Climate Change Effects on Health, Life, Engineering and Social Sciences (ICLIC 2022) with the themes 'Collaboration in Health, Natural, Engineering and Social Sciences for... more
It's our great honor to announce that International Congress of Climate Change Effects on Health, Life, Engineering and Social Sciences (ICLIC 2022) with the themes 'Collaboration in Health, Natural, Engineering and Social Sciences for Climate Changes', 'Zero Waste Supported Climate Change' and 'Carbon management' will take place during September 27-30, 2022 in Konya, Turkey. You may find all the details about the congress on the web address: www.icliccongress.org.
Research Interests:
Image steganography is a technique to hide secret information in an image without leaving any apparent evidence of image alteration. Hiding capacity, perceptual transparency, robustnes ...
Research Interests:
Research Interests:
Özet-Teknoloji insan gücüne olan ihtiyacı azaltmasından ve zamandan tasarruf sağlamasından dolayı günümüzde çok tercih edilir hale gelmiştir. Artık teknolojik cihazlara hayatımızın her köşesinde rastlamak mümkündür. Günümüzde bilgi... more
Özet-Teknoloji insan gücüne olan ihtiyacı azaltmasından ve zamandan tasarruf sağlamasından dolayı günümüzde çok tercih edilir hale gelmiştir. Artık teknolojik cihazlara hayatımızın her köşesinde rastlamak mümkündür. Günümüzde bilgi teknolojileri tıp ve sağlık bakımında gittikçe yaygınlaşmakta, sağlık bakımı giderek teknolojiye bağımlı hale gelmektedir. Tıpta kullanılan bu teknolojilerden biri de kapilleroskopi kullanımıdır. Kapilleroskopi, gelişmiş bir mikroskop yardımıyla tırnak yatağında yer alan kapiller adı verilen küçük damarların görüntülenmesi işlemidir. Tırnak yatağındaki küçük damarlarda görülen bazı değişiklikler başta skleroderma olmak üzere bazı romatizmal hastalıkların erken dönemde tanınmasına yardımcı olabilir. Günümüzde romatolojik hastalıkların mikrovasküler tutulumlarını belirlemek amacıyla sıkça kullanılmaktadır. Tırnak kıvrımı kapiller sistemini değerlendirmede hızlı ve etkili bir tanısal araç olan dermatoskopi cihazlarının ucuz, kolay uygulanabiliyor olması ve z...
Having done in this study, air-conditioning<br> automation for patisserie shopwindow was designed. In the cooling<br> sector it is quite important to cooling up the air temperature in the<br> shopwindow within short time... more
Having done in this study, air-conditioning<br> automation for patisserie shopwindow was designed. In the cooling<br> sector it is quite important to cooling up the air temperature in the<br> shopwindow within short time interval. Otherwise the patisseries<br> inside of the shopwindow will be spoilt in a few days. Additionally<br> the humidity is other important parameter for the patisseries kept in<br> shopwindow. It must be raised up to desired level in a quite short<br> time. Traditional patisserie shopwindows only allow controlling<br> temperature manually. There is no humidity control and humidity is<br> supplied by fans that are directed to the water at the bottom of the<br> shopwindows. In this study, humidity and temperature sensors<br> (SHT11), PIC, AC motor controller, DC motor controller, ultrasonic<br> nebulizer and other electronic circuit members were used to simulate<br> air conditioning aut...
Research Interests:
modeling of a diesel engine performance by FCM and ANFIS
Background In terms of data-hiding areas, video steganography is more advantageous compared to other steganography techniques since it uses video as its cover medium. For any video steganography, the good trade-off among robustness,... more
Background In terms of data-hiding areas, video steganography is more advantageous compared to other steganography techniques since it uses video as its cover medium. For any video steganography, the good trade-off among robustness, imperceptibility, and payload must be created and maintained. Even though it has the advantage of capacity, video steganography has the robustness problem especially regarding spatial domain is used to implement it. Transformation operations and statistical attacks can harm secret data. Thus, the ideal video steganography technique must provide high imperceptibility, high payload, and resistance towards visual, statistical and transformation-based steganalysis attacks. Methods One of the most common spatial methods for hiding data within the cover medium is the Least Significant Bit (LSB) method. In this study, an LSB-based video steganography application that uses a poly-pattern key block matrix (KBM) as the key was proposed. The key is a 64 × 64 pixel ...
Research Interests:
Research Interests:
Although the analysis of the structure of objects and the components that makeup them has been done for decades, it is one of today's research topics to do this analysis quickly and without damaging the sample. Near-infrared... more
Although the analysis of the structure of objects and the components that makeup them has been done for decades, it is one of today's research topics to do this analysis quickly and without damaging the sample. Near-infrared spectroscopy is used in many areas due to its non-contact measurement, fast analysis, and high accuracy features. Near-infrared spectroscopy is used in the classification or quality analysis of products, especially in the agriculture and food sector, due to the chemical bonds interacting in this region. The most critical part of achieving a successful result in near-infrared spectroscopy is pre-processing and analyzing the spectral data using the correct method. In this review, we perform a survey of recent studies that use near-infrared spectroscopy in food production and agriculture. Since there are many studies in this field in the literature, the survey is limited to cover works in the last five years. The review's main question is the pre-processing...
Research Interests:
Previous studies showed that knowing occupancy certainly can save energy in the control system of building. In this regard, occupancy detection has a significant role in many smart building applications such as heating, cooling,... more
Previous studies showed that knowing occupancy certainly can save energy in the control system of building. In this regard, occupancy detection has a significant role in many smart building applications such as heating, cooling, ventilation (HVAC) and lighting system. In this paper, various Artificial Neural Network algorithms were applied to the dataset composed by samples obtained from light, temperature, humidity and CO2 sensors. When the results were compared, it was seen that Limited Memory Quasi-Newton algorithm has the highest accuracy rate with 99.061%. The lowest accuracy rate was obtained from Batch Back algorithm with 80.324%. KeywordsOccupancy Detection, Classification, Artificial Neural Network
Mesothelioma, which is a disease of the pleura and peritoneum, is an asbestos-related environmental disease in undeveloped countries. Although the incidence of this disease is lower than that of lung cancer, the reaction it creates in... more
Mesothelioma, which is a disease of the pleura and peritoneum, is an asbestos-related environmental disease in undeveloped countries. Although the incidence of this disease is lower than that of lung cancer, the reaction it creates in society is very high. In this study, 9 different classification algorithms of data mining were applied to the Mesethelioma data set obtained from real patients in Dicle University, Faculty of Medicine and loaded into UCI Machine Learning Repository, and the results were compared. When the obtained results were examined, it has been seen that Artificial Neural Network (ANN) had %99.0740 correct classification ratio.
The incredible progress of technology has made the use of communication and information technologies indispensable because of the possibilities it offers. These possibilities increased the security issues on personal information and... more
The incredible progress of technology has made the use of communication and information technologies indispensable because of the possibilities it offers. These possibilities increased the security issues on personal information and communication security problems such as phone calls, retrieving e-mail contents, copying private information on computers. Encryption algorithms used in classical security approaches, while ensuring the confidentiality of information, cannot provide the principle of “imprecision” that has become increasingly important in recent times. A coded or encrypted text can be solved by advanced machines when focused on it. So the key point is “do not raise suspicion”. For this reason, steganography and watermarking methods that put the invisibility of the existence of a secret message into the primary goal are especially the focus of interest after 2000's years. In this study, Least Significant Bit (LSB) technique, which is the most basic and commonly used te...
Research Interests:
Research Interests:
The young people are not only in the most efficient position at the countries but also the assurance of the future of the countries. It is very important to grow up young people whose personalities are balanced in today's world where... more
The young people are not only in the most efficient position at the countries but also the assurance of the future of the countries. It is very important to grow up young people whose personalities are balanced in today's world where everything is changing quickly. Young people are facing with a lot of problems due to be in puberty stage or development properties. They can also have tendency to the extremism at this stage. In this research, it's been aimed to investigate the extremism behaviors of young people in Turkey and member countries of European Union (EU). The sample of the research consists of the young people from Turkey and 9 EU member countries. According to the results of this study; the young people think that people from different nations are as good as people in their own country, they check the source and the credibility of the videos they watch on the Internet and social networks and, they break their relationships with their friends who are in a violent te...
Research Interests:
Bu tez calismasinda 2B bir icerikten 3B bir icerik olusturma teknikleri olacaktir. Bu tekniklerde tek bir goruntu mevcuttur ve amac bu goruntu bilgisini kullanarak ikinci goruntuyu olusturmaktir. En sik kullanilan 2B’den 3B’ye cevrim... more
Bu tez calismasinda 2B bir icerikten 3B bir icerik olusturma teknikleri olacaktir. Bu tekniklerde tek bir goruntu mevcuttur ve amac bu goruntu bilgisini kullanarak ikinci goruntuyu olusturmaktir. En sik kullanilan 2B’den 3B’ye cevrim yontemi derinlik haritasinin olusturulmasi ve bu sekilde DIBR (Depth image based rendering) kullanilarak ikinci goruntunun olusturulmasidir. Bu tez calismasin da veri setleri olusturmak amaciyla materyal olarak Matlab yazilimi kullanilacaktir. Kullanilan bu sistemin girdileri 3 boyutlandirilmasi istenen resim, Fark Degiskeni,,Lineer Derinlik Haritasi Perpesktif Yonu, LDH baslangic ve son degerleri ve isteniyorsa obje bulunmasidir. Cikti olarak elde edebilecegimiz Bolutlenmis Goruntu, Derinlik Haritasi, Sol goruntu, Sag goruntu, 3 Boyutlu goruntudur. Dolayisiyla sistem minumum girdi kullanarak 3 boyutlandirma islemi yapabilmektedir. Ayrica , bu yontem es zamanli olmamakla beraber videolar icinde uygulanabilir. Yapilan arastirmalar ve incelemeler sonucund...
The academic mobility is one of key factors that enable the globalization of research and education. In this paper we study the network of ERASMUS staff and student exchange agreements between academic institutions involved in FETCH - a... more
The academic mobility is one of key factors that enable the globalization of research and education. In this paper we study the network of ERASMUS staff and student exchange agreements between academic institutions involved in FETCH - a big European project oriented towards future education and training in computer science. The structure of the network was investigated relying on standard metrics and techniques of social network analysis. Obtained results indicate that the network is in a mature phase of the development in which none of the institutions has a critical role to the overall connectedness of the network. Additionally, the network has a clear core-periphery structure with an active core and mostly inactive periphery.
Research Interests:
One of the most important functions of guidance services within the training process is to direct the students to the appropriate professions in line with their interests, tendencies and needs. One of the main objectives of primary... more
One of the most important functions of guidance services within the training process is to direct the students to the appropriate professions in line with their interests, tendencies and needs. One of the main objectives of primary education is to direct students to schools that are suitable for the profession they will choose by recognizing their professions. The main aim of the vocational guidance activities to be carried out in high school is to determine in which areas the students have abilities, not exactly which profession they will choose. The main aim of the guidance services to be done should be to make the student know himself and make realistic preferences. Most people are unaware of what areas they are interested in before they start to a work or an occupation. As long as people live and specialize, they learn about their own interests. Various methods are used to measure students' interests. One of them is to use inventories and the other one is to ask the area whe...
Research Interests:
Extremism is defined as the state of adoption to the most extreme form of opinion or attitude. Young people can have excessive behavior. One of the biggest problems of the world in recent times is extremism. In Europe, especially... more
Extremism is defined as the state of adoption to the most extreme form of opinion or attitude. Young people can have excessive behavior. One of the biggest problems of the world in recent times is extremism. In Europe, especially religious motivated extremism and politically motivated extremism are increasing. Today, struggle with all kinds of extremism is important and efforts should be spent for this struggle. It is a requirement that teachers who train young people who are assurance of future must have enough knowledge about extremism behaviors. In this research, it's been aimed to investigate the opinions of teachers in Turkey and 5 member countries of European Union (Sweden, Italy, Hungary, Poland and Slovenia). 332 teachers (214 female, 118 male) participated to the research. As data collecting tool, the scale titled “opinions of teachers about extremism” was used. The results showed us that the teachers should have in-service training that may have title of "How to o...
Research Interests:
Research Interests:
Research Interests:
Latest smart buildings are not only be intelligent to allow occupant to control the light, heating, cooling, gas and other systems but also focuses on occupancy detection since accurate occupancy detection can result in saving energy up... more
Latest smart buildings are not only be intelligent to allow occupant to control the light, heating, cooling, gas and other systems but also focuses on occupancy detection since accurate occupancy detection can result in saving energy up to 42% as can be seen in literature. For this aim, different autonomous systems including sensors, actuators, microcontroller and etc. are at the development phase for smart buildings. At this point, determination of classification methods to detect the occupancy together with hardware plays crucial role. Having done in this study 3 different classification methods that is based on Machine Learning Methods were applied on benchmark dataset named Occupancy by UCI Machine Learning Repository, 2016. The classifiers are Random Forest, Decision Tree and Bagging. They were chosen by following two principals. First one is to have classifier methods that were not use in literature for benchmark dataset and the second one almost never usage of tree based clas...
Research Interests:
The definition of the data mining can be told as to extract information or knowledge from large volumes of data. One of the main challenging area of data mining is classification. There are so many different classification algorithm in... more
The definition of the data mining can be told as to extract information or knowledge from large volumes of data. One of the main challenging area of data mining is classification. There are so many different classification algorithm in literature ranging from statistical based to artificial intelligence based. This study make use of Waikato Environment for Knowledge Analysis or in short, WEKA to compare the different classification techniques on different medical datasets. 23 different classification techniques were applied to three different medical datasets namely EEG Eye State, Fertility and Thoracic Surgery Medical Datasets that were taken from UCI Machine Learning Repository. The results showed that Multilayer Perceptron (MLP) had highest accuracy for Fertility Dataset (90%), three different techniques namely Bagging, Dagging and Grading had highest and same accuracies for Thoracic Surgery Data Set (85.1064%) and finally Kstar had highest accuracy for EEG Eye State Dataset (96.7757%).
Research Interests:
Internet is a network protocol that consists o f m illions o f sub-network where the people com m unicate each other interactively by text, visual and auditory way. There is no doubt that internet is one o f the m ost com m on and w idely... more
Internet is a network protocol that consists o f m illions o f sub-network where the people com m unicate each other interactively by text, visual and auditory way. There is no doubt that internet is one o f the m ost com m on and w idely used com m unication tool. D ue to these properties Internet has a w ide range o f use in education field. The sources and materials for almost all education fields are provided on the Internet especially in personnel or social share WEB sites. Even homeworks or exercises are presented to the students over Internet to reinforce what they learn in class environment. The difficulty arises when the quality and quantity o f the questions and exercises and also solutions o f them are considered. The questions and exercises must cover all the topics in the related field such a way that the one that apply for this source can find any answer that he/she seeks for. Additionally the qualities o f the questions-exercises must respect the tips, tricks and quite specific know ledge for the related domain. Considering all these aspects, a W EB site in electronic field that contains questions, exercises and practical information in a hierarchical way for this field is designed and im plem ented in this study. All the questions and exercises include solutions and som e additional information if it is necessary such as alternative solution ways, hints and etc. The WEB site requires membership activities and also includes a form for the user to ask questions and/or information that doesn't exist in the W EB site. The users can add new questions and exercises with solutions to the site. After being exam ined by the site administration w ho also studies in electronic new ly added questions and exercises are either approved and published or declined. The users o f the WEB site can be lecturer, students or even the one w ho is quite interested in electronic science.
Research Interests:
Privacy is one of the most important issues in today's communication systems. In applications where the importance of your privacy is indispensable, the main aim is to send the information to desired target without being captured by the... more
Privacy is one of the most important issues in today's communication systems. In applications where the importance of your privacy is indispensable, the main aim is to send the information to desired target without being captured by the third persons or by bringing them in such a way that they cannot understand. Today, researchers have developed data hiding methods using a wide variety of digital media. At this point, it is important not only to hide data, but also to develop mechanisms to prevent third parties from identifying hidden data. In this study, a new method that combine chaos-based logistic map encryption with improved Least Significant Bit (LSB) insertion method of image steganography was proposed. The message to hidden is encrypted by one dimensional logistic map and then improved LSB method was used to form stego-image. Proposed method has been tested on 3 different images. Likewise, the classical LSB methods have also been tested on the same images. It has been seen that proposed method increased the resistance of stego-images against attacks due to encryption. Additionally, Peak Signal to Noise Ratio (PSNR) in the stego-images were increased up to 6.6% that means to decrease sense by the human observation. Thus, proposed method increased the resistance and visibility of the stego-images.
Research Interests:
Nowadays, many methods and algorithms have been developed that may influence the decision-making process and are used to extract meaningful information. One of the well know methods or approaches in information extraction is data mining.... more
Nowadays, many methods and algorithms have been developed that may influence the decision-making process and are used to extract meaningful information. One of the well know methods or approaches in information extraction is data mining. Data mining tries to establish the best model to support decision system, to extract information and to categorize, to summarize and etc. according to given data set. The Parkinson's disease-related data obtained from UCI Machine Learning Database is used to try several data mining techniques and methods to see the successes of techniques regarding to diagnosis accuracy ratio to support the expert. So far, Parkinson's disease can actually be diagnosed after medical examinations. However, diagnosis with computer has been the subject of many researches due to demand to help physician. In this study, a research is conducted using 16 different data mining techniques and methods to support the doctors in the decision-making process. The results of the applied methods for the study regarding to diagnosis accuracy ratesare as follows; IB1 (96.4103%), RotationForest (92.3077%) RandomForest (91.7949%), MultilayerPerceptron (90.7692%),
Research Interests:
The definition of the data mining can be told as to extract information or knowledge from large volumes of data. One of the main challenging area of data mining is classification. There are so many different classification algorithm in... more
The definition of the data mining can be told as to extract information or knowledge from large volumes of data. One of the main challenging area of data mining is classification. There are so many different classification algorithm in literature ranging from statistical based to artificial intelligence based. This study make use of Waikato Environment for Knowledge Analysis or in short, WEKA to compare the different classification techniques on different medical datasets. 23 different classification techniques were applied to three different medical datasets namely EEG Eye State, Fertility and Thoracic Surgery Medical Datasets that were taken from UCI Machine Learning Repository. The results showed that Multilayer Perceptron (MLP) had highest accuracy for Fertility Dataset (90%), three different techniques namely Bagging, Dagging and Grading had highest and same accuracies for Thoracic Surgery Data Set (85.1064%) and finally Kstar had highest accuracy for EEG Eye State Dataset (96.7757%).
Research Interests:
Data mining, a step of knowledge discovery process, has gathered together statistical, database, machine learning and artificial intelligence studies in recent researches. When investigating large amounts of data, it is important to use... more
Data mining, a step of knowledge discovery process, has gathered together statistical, database, machine learning and artificial intelligence studies in recent researches. When investigating large amounts of data, it is important to use an effective search method for the occurrence of patterns. Statistical and machine learning techniques are used for the determination of the models to be used for data mining predictions. Today, Data mining is used in many different areas such as science and engineering, health, commerce, shopping, banking and finance, education and internet.The objective of this study is Chronic kidney disease dataset using 4 different Data Mining methods namely; Naive Bayes, C4.5 Algorithm, Support Vector Machine (SVM) and Multilayer Perceptron. Correctly classified instances were found as 95,00%, 97,75%, 99,00% and 99,75% for Naive Bayes, C4.5 Algorithm, SVM and Multilayer Perceptron respectively.
Research Interests:
Previous studies showed that knowing occupancy certainly can save energy in the control system of building. In this regard, occupancy detection has a significant role in many smart building applications such as heating, cooling,... more
Previous studies showed that knowing occupancy certainly can save energy in the control system of building. In this regard, occupancy detection has a significant role in many smart building applications such as heating, cooling, ventilation (HVAC) and lighting system. In this paper, various Artificial Neural Network algorithms were applied to the dataset composed by samples obtained from light, temperature, humidity and CO2 sensors. When the results were compared, it was seen that Limited Memory Quasi-Newton algorithm has the highest accuracy rate with 99.061%. The lowest accuracy rate was obtained from Batch Back algorithm with 80.324%.
Research Interests:
Research Interests:
Micro-calcification in the breast is a symptom of breast cancer. Therefore, detection of micro-calcification in mammogram image plays an important role in the early diagnosis of breast cancer. Because the mammogram images are... more
Micro-calcification in the breast is a symptom of breast cancer. Therefore, detection of micro-calcification in mammogram image plays an important role in the early diagnosis of breast cancer. Because the mammogram images are 2-dimensional, different tissues in the breast are seen on top of each other. Therefore, it is a compelling task for radiologists to identify the masses found in mammogram images. There are different methods for detecting micro-calcification in mammogram images. In this study, different image processing techniques were applied on mammogram images and a region of 80x80 pixel was taken from breast tissue. Texture features of this region were extracted using co-occurrence matrix and classified by logistic regression analysis. Classification success of 88% was achieved with the proposed model.
Research Interests:
Although the analysis of the structure of objects and the components that makeup them has been done for decades, it is one of today's research topics to do this analysis quickly and without damaging the sample. Near-infrared spectroscopy... more
Although the analysis of the structure of objects and the components that makeup them has been done for decades, it is one of today's research topics to do this analysis quickly and without damaging the sample. Near-infrared spectroscopy is used in many areas due to its non-contact measurement, fast analysis, and high accuracy features. Near-infrared spectroscopy is used in the classification or quality analysis of products, especially in the agriculture and food sector, due to the chemical bonds interacting in this region. The most critical part of achieving a successful result in near-infrared spectroscopy is pre-processing and analyzing the spectral data using the correct method. In this review, we perform a survey of recent studies that use near-infrared spectroscopy in food production and agriculture. Since there are many studies in this field in the literature, the survey is limited to cover works in the last five years. The review's main question is the pre-processing and data analysis methods used in these studies and the main features of these methods. Among the examined studies, the most frequently used pre-processing method was standard normal variate, and the most frequently used analysis method was partial least squares regression. In addition, the software tools and the spectrum range were also examined within the scope of the study.
Research Interests:
Modeling and optimization from natural phenomena and observations of the physical earth is an extremely important issue. In the light of the developments in computer and artificial intelligence technologies, the applications of... more
Modeling and optimization from natural phenomena and observations of the physical earth is an extremely important issue. In the light of the developments in computer and artificial intelligence technologies, the applications of learning-based modeling and optimization techniques in all kinds of study fields are increasing. In this research, the applicability of four different state-of-the-art metaheuristic algorithms which are Particle swarm optimization (PSO), Tree-Seed Algorithm (TSA), Artificial Bee Colony (ABC) algorithm, and Grey Wolf Optimizer (GWO), in local GNSS/leveling geoid studies have been examined. The most suitable geoid model has been tried to be obtained by using different reference points via the well-known machine learning algorithms, Artificial Neural Network (ANN) and Extreme Learning Machine (ELM), at the existing GNSS/leveling points in Burdur city of Turkey. In this study, eight different hybrid approaches are proposed by using each metaheuristic algorithm together with machine learning methods. By using these hybrid approaches, the model closest to the minimum number of reference points has been tried to be obtained. Furthermore, the performance of the hybrid approaches has been compared. According to the comparisons, the hybrid approach performed with GWO and ELM has achieved better results than other proposed hybrid approaches. As a result of the research, it has been seen that the most suitable local GNSS/Leveling geoid can be determined with a lower number of reference points in an appropriate distribution.
Research Interests:
This study proposes a new hybrid n-LSB (Least Significant Bit) substitution-based image steganography method in the spatial plane. The previously proposed n-LSB substitution method by authors of this paper is combined with the... more
This study proposes a new hybrid n-LSB (Least Significant Bit) substitution-based image steganography method in the spatial plane. The previously proposed n-LSB substitution method by authors of this paper is combined with the Rivest-Shamir-Adleman (RSA), RC5, and Data Encryption Standard (DES) encryption algorithms to improve the security of the steganography, which is one of the requirements of steganography, and the Lempel-Ziv-Welch (LZW), Arithmetic and Deflate lossless compression algorithms to increase the secret message capacity. Also, embedding was done randomly using a logistic map-based chaos generator to increase the security more. The classical n-LSB substitution method and the proposed hybrid approaches based on the previously proposed n-LSB were implemented using different secret messages and cover images. When the results were examined, it has been seen that the proposed hybrid n-LSB approach showed improvement in all three criteria of steganography. The proposed hybrid approach that consists of previously proposed n-LSB, RSA, Deflate, and the logistic map had the best results regarding capacity, security, and imperceptibility.
Research Interests:
Background. In terms of data-hiding areas, video steganography is more advantageous compared to other steganography techniques since it uses video as its cover medium. For any video steganography, the good trade-off among robustness,... more
Background. In terms of data-hiding areas, video steganography is more advantageous compared to other steganography techniques since it uses video as its cover medium. For any video steganography, the good trade-off among robustness, imperceptibility, and payload must be created and maintained. Even though it has the advantage of capacity, video steganography has the robustness problem especially regarding spatial domain is used to implement it. Transformation operations and statistical attacks can harm secret data. Thus, the ideal video steganography technique must provide high imperceptibility, high payload, and resistance towards visual, statistical and transformation-based steganalysis attacks. Methods. One of the most common spatial methods for hiding data within the cover medium is the Least Significant Bit (LSB) method. In this study, an LSB-based video steganography application that uses a poly-pattern key block matrix (KBM) as the key was proposed. The key is a 64 × 64 pixel block matrix that consists of 16 subpattern blocks with a pixel size of 16 × 16. To increase the security of the proposed approach, sub-patterns in the KBM are allowed to shift in four directions and rotate up to 270 • depending on the user preference and logical operations. For additional security XOR and AND logical operations were used to determine whether to choose the next predetermined 64 × 64 pixel block or jump to another pixel block in the cover video frame to place a KBM to embed the secret data. The fact that the combination of variable KBM structure and logical operator for the secret data embedding distinguishes the proposed algorithm from previous video steganography studies conducted with LSB-based approaches. Results. Mean Squared Error (MSE), Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR) parameters were calculated for the detection of the imperceptibility (or the resistance against visual attacks) of the proposed algorithm. The proposed algorithm obtained the best MSE, SSIM and PSNR parameter values based on the secret message length as 0.00066, 0.99999, 80.01458 dB for 42.8 Kb of secret message and 0.00173, 0.99999, 75.72723 dB for 109 Kb of secret message, respectively. These results are better than the results of classic LSB and the studies conducted with LSB-based video steganography approaches in the literature. Since the proposed system allows an equal amount of data embedding in each video frame the data loss will be less in transformation operations. The lost data can be easily obtained from the entire text with natural language processing. The variable structure of the KBM, logical operators and extra security preventions makes the proposed system be more secure and complex. This increases the unpredictability and resistance against statistical attacks. How to cite this article Hacimurtazaoglu M, Tutuncu K. 2022. LSB-based pre-embedding video steganography with rotating & shifting poly-pattern block matrix. PeerJ Comput. Sci. 8:e843 http://doi.org/10.7717/peerj-cs.843 visual, statistical and transformation-based attacks while acceptable even high payload.
Research Interests:
Image steganography is a technique to hide secret information in an image without leaving any apparent evidence of image alteration. Hiding capacity, perceptual transparency, robustness, and resistance against attack must be considered as... more
Image steganography is a technique to hide secret information in an image without leaving any apparent evidence of image alteration. Hiding capacity, perceptual transparency, robustness, and resistance against attack must be considered as characteristics of the image steganography algorithms. In this study, Improved Chaos Based Bit Embedding has been proposed as a new steganography algorithm. It is based on two basic principles. One of them is determining the bits in which the secret data will be embedded by logistic map and the other one is embedding the secret data into only one of the three color channels that is chosen randomly. It distorts the other remaining channels so that it is harder to obtain the text within the image by an unwanted person. The proposed algorithm has been tested on 10 sample images along with the four basic steganography algorithms: Least Significant Bit Embedding, Pseudo Random Least Significant Bit Embedding, EzStego, and F5. It has been seen that generating unpredictable indexes by the chaotic random number generators, and embedding the secret data into only one of the three channels (distorting remaining channels) increased resistance against attacks. Perceptual transparencies and capacity ratio of the proposed algorithm are compatible with the other four algorithms.
Research Interests:
Having done in this study, embedded fuzzy logic control system (EFLCS) was designed and implemented for closed refrigerated display cabinets (CRDC) to meet the required storage conditions for the pastry productions stored in CRDCs. The... more
Having done in this study, embedded fuzzy logic control system (EFLCS) was designed and implemented for closed refrigerated display cabinets (CRDC) to meet the required storage conditions for the pastry productions stored in CRDCs. The system keeps the temperature and relative humidity (RH) of CRDC at approximately + 4 ◦C and 80% RH, respectively. It has two fuzzy logic controllers. One of them controls the speed levels of the fans, and the other controls the steam level of ultrasonic atomizer. Temperature and RH values are read by sensor SHT11 and transferred to PIC18F4620 microcontroller that is programmed with fuzzy Logic approach. On the other hand, the compressor was controlled with on–off control in the range of 3–5 ◦C. On the condition of starting from + 7 ◦C temperature, the time to approach to the set values (4 ◦C and 80% RH) for traditional system and EFLCS is 191.8 and 109.6 s, respectively. Additionally, the ranges of temperature and RH obtained by EFLCS are between 4.44 and 3.69 ◦C and between 81.33% RH and 78.57% RH, respectively. The temperature and RH values obtained by traditional system are between 5.56 and 3.2 ◦C and between 61.81% RH and 57.45% RH, respectively. Traditional system never reached to desired humidity value (80% RH). It has been seen that developed EFLCS becomes stable in shorter time than traditional system and kept the desired values as almost constants.
Research Interests:
Mesothelioma, which is a disease of the pleura and peritoneum, is an asbestos-related environmental disease in undeveloped countries. Although the incidence of this disease is lower than that of lung cancer, the reaction it creates in... more
Mesothelioma, which is a disease of the pleura and peritoneum, is an asbestos-related environmental disease in undeveloped countries. Although the incidence of this disease is lower than that of lung cancer, the reaction it creates in society is very high. In this study, 9 different classification algorithms of data mining were applied to the Mesethelioma data set obtained from real patients in Dicle University, Faculty of Medicine and loaded into UCI Machine Learning Repository, and the results were compared. When the obtained results were examined, it has been seen that Artificial Neural Network (ANN) had %99.0740 correct classification ratio.
Research Interests:
Research Interests:
ABSTRACT Searching for similar document has an important role in text mining and document management. In whether similar document search or in other text mining applications generally document classification is focused and class or... more
ABSTRACT Searching for similar document has an important role in text mining and document management. In whether similar document search or in other text mining applications generally document classification is focused and class or category that the documents belong to is tried to be determined. The aim of the present study is the investigation of the case which includes the documents that belong to more than one category. The system used in the present study is a similar document search system that uses fuzzy clustering. The situation of belonging to more than one category for the documents is included by this system. The proposed approach consists of two stages to solve multicategories problem. The first stage is to find out the documents belonging to more than one category. The second stage is the determination of the categories to which these found documents belong to. For these two aims α-threshold Fuzzy Similarity Classification Method (α-FSCM) and Multiple Categories Vector Method (MCVM) are proposed as written order. Experimental results showed that proposed system can distinguish the documents that belong to more than one category efficiently. Regarding to the finding which documents belong to which classes, proposed system has better performance and success than the traditional approach.
Research Interests:
Industrial production and packaging face significant challenges, such as product damage, color changes, and the presence of foreign bodies. These issues greatly impact product quality, profitability, and marketability, leading to... more
Industrial production and packaging face significant challenges, such as product damage, color changes, and the presence of foreign bodies. These issues greatly impact product quality, profitability, and marketability, leading to increased consumer complaints. To address these concerns, this study presents a novel method for classifying Taralli biscuits using image processing techniques. The research encompasses a dataset of 4,900 images, featuring four types of defects: no defect, defectshape, defect-object, and defect-color. Leveraging advanced deep learning architectures, including MobileNet-v2 and DenseNet-201, the classification process achieves impressive accuracy rates of 98.71% and 99.39% respectively. By automating the detection of biscuit damage, the proposed method enhances quality control and inspection processes within the food industry. The combination of state-of-the-art image processing and deep learning techniques in this research provides an effective solution for automatically detecting and categorizing biscuit defects.
Research Interests:
Elektronik ve bilgisayar teknolojilerinin gelişimine paralel olarak yapay zekâ uygulamaları birçok alanda gelişme imkânı bulmuştur. Bu alanlardan birisi de hassas tarımda yapay zekanın kullanımıdır. Yapay zekanın alt dalı olan derin... more
Elektronik ve bilgisayar teknolojilerinin gelişimine paralel olarak yapay zekâ uygulamaları birçok alanda gelişme imkânı bulmuştur. Bu alanlardan birisi de hassas tarımda yapay zekanın kullanımıdır. Yapay zekanın alt dalı olan derin öğrenme teknikleriyle güçlü donanıma sahip bilgisayarlar kullanılarak hassas tarım için birçok başarılı bilgisayarlı görü uygulamaları geliştirilmiştir. Ancak bu uygulamaların gerçek zamanlı çalışabilen bir robotik sisteme entegre edilmesi yüksek maliyet gerektirmektedir. Bu sebeple hassas tarıma yönelik gerçek zamanlı uygulamalar tasarlayabilmek ve robotik makinelerin alt sistemlerinde yapay zekayı kullanabilmek için düşük maliyetli çözümlere ihtiyaç duyulmaktadır. Bu çalışmada hassas tarımda robotik makinelerin bilgisayarlı görü sistemlerinde kullanmak için Raspberry Pi 4 ile gerçek zamanlı bir bitki algılama sistemi gerçekleştirilmiştir. Ayrıca sistemin algılama hızını artırmak için Coral USB hızlandırıcı kullanılarak sonuçlar algılama hızı bakımından değerlendirilmiştir. Coral USB hızlandırıcı ile Raspberry Pi 4’ün birlikte kullanımıyla 30 FPS’lere varan algılama hızı elde edilmiştir. Bu sonuçlar bir mikrobilgisayar üzerinde gerçek zamanlı bitki algılamanın yapılabileceğinin mümkün olduğunu göstermektedir.
Research Interests:
Steganography refers to techniques that hide information into the cover object. In this study, a new technique for the F5 method was performed with the Discrete Cosine Transform (DCT) method, Key Block Matrix (KBM) consisting of different... more
Steganography refers to techniques that hide information into the cover object. In this study, a new technique for the F5 method was performed with the Discrete Cosine Transform (DCT) method, Key Block Matrix (KBM) consisting of different sub-pattern blocks, and additional security algorithms. This paper evaluates the applications of different algorithms and their results which can be chosen by users for video steganography using F5 methods. To evaluate the results Mean Square Error (MSE), Structure Similarity Index Measurement (SSIM), Peak Signal Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM) quality metrics were used. The fact that the KBM structures are variable increases data security in the proposed algorithms and fills the gap of security issues in the video steganography. The quality metric values obtained showed that the proposed approach can compete with the results obtained in the literature regarding PSNR, MSE, and SSIM values.
Research Interests:
Of the millions of mushroom species growing all around the world, one type is edible, while the other is poisonous. It is not easy to distinguish edible and poisonous mushrooms from each other and it is a condition that requires... more
Of the millions of mushroom species growing all around the world, one type is edible, while the other is poisonous. It is not easy to distinguish edible and poisonous mushrooms from each other and it is a condition that requires expertise. The classification of poisonous and edible mushrooms is therefore important. Machine learning algorithms are an alternative method for classifying poisonous and edible mushrooms using morphological or physical features of fungi. The dataset used in this study is the Mushroom dataset available in the UC Irvine Machine Learning Repository. Based on 22 features in the Mushroom dataset and four different machine learning algorithms, models have been created for the classification of edible and poisonous fungi. The classification success rates of these models were obtained from Naive Bayes, Decision Tree, Support Vector Machine and AdaBoost algorithms with 90.99%, 98.82%, 99.98% and 100%, respectively. When these results were examined, taking into account the physical appearance features of the mushrooms, it was determined whether the mushrooms were edible and poisonous by 100% with the AdaBoost model.
Research Interests:
I am pleased to announce that the International Congress on Engineering and Agricultural Sciences (ENAG 2022, www.enagcongress.org) will be held from September 26 to 29, 2022 in Konya, Turkey. Selected papers will be published in; -... more
I am pleased to announce that the International Congress on Engineering and Agricultural Sciences (ENAG 2022, www.enagcongress.org) will be held from September 26 to 29, 2022 in Konya, Turkey.
Selected papers will be published in;
- Turkish Journal of Entomology (Science Citation Index Expanded)
- Selcuk Journal of Agriculture and Food Sciences (TR Dizin Indexed)
- Turkish Journal of Agriculture - Food Science and Technology (TR Dizin Indexed)
- International Journal of Engineering and Geosciences (ESCI and TR Dizin Indexed)
- Turkish Journal of Engineering (TR Dizin Indexed)
- Science International (Scopus)
- International Journal of Phytopathology (Scopus)
- Eurasian Journal of Family Medicine (TR Dizin Indexed)
* Negotiations and deals with the journals indexed in SCI, SCI-E or TR index still continue.
For more information please visit http://enagcongress.org/index.html
Selected papers will be published in;
- Turkish Journal of Entomology (Science Citation Index Expanded)
- Selcuk Journal of Agriculture and Food Sciences (TR Dizin Indexed)
- Turkish Journal of Agriculture - Food Science and Technology (TR Dizin Indexed)
- International Journal of Engineering and Geosciences (ESCI and TR Dizin Indexed)
- Turkish Journal of Engineering (TR Dizin Indexed)
- Science International (Scopus)
- International Journal of Phytopathology (Scopus)
- Eurasian Journal of Family Medicine (TR Dizin Indexed)
* Negotiations and deals with the journals indexed in SCI, SCI-E or TR index still continue.
For more information please visit http://enagcongress.org/index.html
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Because of the technological advances in communication between people, information security is so important that it is not at any stage in history. Steganography is a science that is used in the field of information security and aims to... more
Because of the technological advances in communication between people, information security is so important that it is not at any stage in history. Steganography is a science that is used in the field of information security and aims to conceal the existence of a confidential message. In this study, the effect of text compression algorithms on image steganography is examined. Three different text files on different sizes are compressed using 4 different compression algorithms namely LZW, MTF, Arithmetic and Deflate and embedded with LSB substitution method on 3 different images. When the results are examined, it is seen that the Deflate algorithm has a higher compression ratio than the other algorithms. In this way, a significant increase in image capacities has been achieved and the distortion in the image has been reduced.
Research Interests:
Today, it is possible to find many types of compressors according to the manufacturing capacity and size. However, the diversity for mini-size compressors is drastically reduced. It causes serious problems for small systems where... more
Today, it is possible to find many types of compressors according to the manufacturing capacity and size. However, the diversity for mini-size compressors is drastically reduced. It causes serious problems for small systems where compressed air is needed. In this study, design and manufacturing of a mini-size rotary swing type compressor were carried out in order to contribute to the solution of the related problem. In the phase of design, the value of pressure to be created by the compressor and the energy to be consumed by it were calculated. After the manufacturing was carried out by using industrial counters, various pressure experiments were performed on the compressor. As a result of the experiments carried out by using brushless DC motor and semi-hermetic tank at 4000 rpm, the compressor operating with 23,7% efficiency created 6 bar pressure by consuming 120 W power. The compressor manufactured for small systems will be able to be used easily in various sectors that can work up to 6 bar pressure. By changing the piston size without changing the compressor size, high pressures such as 12-13 bar will be obtained and it will be possible to be used in many sectors including cooling systems.
Research Interests:
In this study, the closed loop speed control of the separately excited Direct Current (DC) motor controlled by a four-quadrant DC motor drive circuit was performed in MATLAB / SIMULINK software. For this purpose, two control circuits were... more
In this study, the closed loop speed control of the separately excited Direct Current (DC) motor controlled by a four-quadrant DC motor drive circuit was performed in MATLAB / SIMULINK software. For this purpose, two control circuits were designed using PI controller. The first one is the bipolar switching circuit and the second one is the unipolar switching circuit. The control signals obtained from these circuits were applied to the single-phase four-quadrant DC chopper power circuit to drive the separately excited DC motor at reference speed. Comparison of the both switching methods has been implemented based on the data obtained from the simulation results of fourquadrant operation of the DC motor. As a result of the comparison, it has been seen that output voltage and frequency responses were better than the bipolar switching method (BSM) due to doubling of switching frequency of output voltage of the unipolar switching method (USM).
Research Interests:
Capillaroscopy device shoot videos of capillaries of oral mucosa and nailfold of patient over the related skin without any pain. The image frames of videos are used by experts for early detection or treatment of some diseases such as... more
Capillaroscopy device shoot videos of capillaries of oral mucosa and nailfold of patient over the related skin without any pain. The image frames of videos are used by experts for early detection or treatment of some diseases such as diabetics, rheumatism and etc. Since this process is implemented in manually, decision support systems that helps the experts for diagnosis have been subjects of studies of biomedical researches. First step of these systems is the successful segmentation process on these images that will be used for classification of disease depending on 8 parameters such as the number of capillaries in a certain area, the distance between the two vessels, the size of the capillaries and etc. This study aims to contribute decision support system for experts by presenting a successful segmentation. In this study Otsu, Fuzzy C-mean, Fast Marching, Region Growing and H-Minima methods have been used for segmentation of capillarocopic images. The segmentation accuracy ratios of upper mentioned methods were obtainedas %80,47, %67,44, %63,23, %44,11 and 96.76%, respectively. When the results were examined, it was observed that the H-Minima method, which had not previously been applied in capillary images, reached the highest accuracy parameter value.
Research Interests:
Qualitative bankruptcy prediction rules represent experts' problem-solving knowledge to predict qualitative bankruptcy. The objective of this research is predicting qualitative bankruptcy using 4 different Artificial Intelligence (AI)... more
Qualitative bankruptcy prediction rules represent experts' problem-solving knowledge to predict qualitative bankruptcy. The objective of this research is predicting qualitative bankruptcy using 4 different Artificial Intelligence (AI) techniques Qualitative Bankruptcy namely; Naive Bayes Classifier (NBC), Multilayer Perceptron (MLP), J48 and Classification via Regression (CR). Correctly Classified Instances were found as 96.5714 %, 94.8571 %, 95.4286 % and 96% for NBC, MLP, J48 and CR, respectively. These results have shown that NBC has the most successful prediction ratio among the four techniques regarding to classification. By using NBCs we can generate better rules with more qualitative factors and redundancy and overlapping of the rules can also be avoided.
Research Interests:
Research Interests:
In this study, single and also multi-objective (MO) genetic algorithms (GAs) were used for optimisation of performance and emissions of a diesel engine. Population space and initial population of both GAs were obtained by Artificial... more
In this study, single and also multi-objective (MO) genetic algorithms (GAs) were used for optimisation of performance and emissions of a diesel engine. Population space and initial population of both GAs were obtained by Artificial Neural Network (ANN). Specific fuel consumption (Sfc), NOx, power (P), torque (Tq) and air-flow rate (Afr) were reduced to %7.7, %8.51, %30, %4 and %7.4 respectively whereas HC increased at the rate of %10.5 by traditional single objective GA. HC, CO2, P and Sfc were reduced to %17.6, %30.05, %31.8 and %14.5 respectively whereas NOx increased at the rate of %13 by using multiobjective GA with Nondominated Sorting Genetic Algorithm II (NSGA II). %14.5 fuel reduction against %31 power reduction have never been obtained in the previous studies. This shows the effective usage of MOGA with NSGA II in optimisation of fuel diesel engine performance parameters.
Research Interests:
Research Interests:
In this study, performance and emission characteristics of an internal combustion (IC) diesel engine and petrol-driven engine were modeled by Artificial Neural Network (ANN). Diesel engine input parameters are air flow rate (Aflr), boost... more
In this study, performance and emission characteristics of an internal combustion (IC) diesel engine and petrol-driven engine were modeled by Artificial Neural Network (ANN). Diesel engine input parameters are air flow rate (Aflr), boost pressure (Pb), fuel rate (Frt), cycle (Cy) and load (L) whereas input parameters of the petrol-driven engine are advance (A) and cycle (Cy). Engine torque (Tq), power (P), specific fuel consumption (Sfc), emission values such as HC, CO2 and NOx of diesel engine and engine torque (Tq), power (P), specific fuel consumption (Sfc) and HC of petrol-driven have been investigated. R square values of Tq, P, Sfc, HC, CO2 and NOx of diesel engine were %99.9, %99.45, %99.32, %99.84, %99.71 and %99.26 respectively when ANN was used for modeling. R square values of Tq, P, Sfc and Hc of petrol-driven engine %97.24, %99.56, %98.19 and %97.19 respectively. The back-propagation learning algorithm with Hyperbolic tangent activation functions (for hidden layer neurons and output neuron) and 5:12:1 combination have been used in the topology of the network of diesel engine. The back-propagation learning algorithm with Logistic-Hyperbolic tangent activation functions (hidden layer neurons and output neuron) and 2:6:1 combination have been used in the topology of the network of petrol-driven engine. After having statistical t-test for outputs of both ANN, it has been seen that the obtained results are approximately %99.5 and %98.5 consisted (matched) with experimental data of diesel and petrol-driven engine. Main contribution of this work includes; 1) Dynamic load value was used as input parameters for diesel engine and so engine performance modeling and emission characteristic determination were done by regarding changing load, 2) The highest prediction values of output parameters are reached for both engine type regarding to the previous studies and 3) None of the previous studies include modeling of diesel and petrol-driven engine.
Research Interests:
ABSTRACT Comparision of numerical tehnique and Al techniques for determination of performance and emission characteristics of a diesel engine has been done in this study. Three different techniques namely multiple regression analysis,... more
ABSTRACT Comparision of numerical tehnique and Al techniques for determination of performance and emission characteristics of a diesel engine has been done in this study. Three different techniques namely multiple regression analysis, adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) were used for modeling aims. Engine torque (Tq), power (P), specific fuel consumption (Sfc), emission values such as HC, CO2 and NOx have been investigated. R2 values of Tq, P, Sfc, HC, CO2 and NOx were obtained as 99.9, 99.45, 99.32, 99.84, 99.71 and 99.26 respectively when ANN was used. Main contribution of this study includes; 1) First study that makes comperision between a numerical technique and Al tehniques. 2) Dynamic load value was used as input parameter. So that both engine performance modeling and emission characteristic determination were done regarding to changing load. 3) Highest prediction for values of output parameters were reached.