Sürdürülebilir Kalkınma Amaçları
Yazarlar
- Yildirim, Ozal(5)
- Demir, Yakup(3)
- Gunay, Mihriban(3)
- Yordanov, Nikolay(3)
- Zhilevski, Marin(3)
- Baloglu, Ulas Baran(2)
- Ertargin, Merve(2)
- Gul, Muhammet(2)
- Koseoglu, Murat(2)
- Mete, Suleyman(2)
- Mikhov, Mikho(2)
- Ozdemir, Umit(2)
- Acharya, U Rajendra(1)
- Acharya, U. Rajendra(1)
- Akyol, Sinem(1)
- Alatas, Bilal(1)
- Baran, Mateusz(1)
- Benedicenti, L.(1)
- Celebi, Adalet(1)
- Cetin, A. Kadri(1)
- Doğan, Gürkan(1)
- Entani, T.(1)
- Ergen, Burhan(1)
- Eristi, Belkis(1)
- Eristi, Hueseyin(1)
- Eristi, Huseyin(1)
- Ertarğın, Merve(1)
- Huynh, V.(1)
- Hüseyin Bolat(1)
- Imak, Andac(1)
- Imak, Andaç(1)
- Inuiguchi, M.(1)
- Jeenanunta, C.(1)
- Kaya, Sema Kayapinar(1)
- Król, Małgorzata(1)
- Liu, Z.(1)
- Navarro-Arribas, Guillermo(1)
- Niedźwiecki, Michał(1)
- Pezzolesi, Laura(1)
- Pistocchi, Rossella(1)
Yayınlar
- MakaleAçık Erişim2026Scopus SJRQ1Evaluation and Classification of Emergency and Disaster Assembly Areas with ORESTE-Sort
Ozdemir, Umit; Mete, Suleyman; Gul, Muhammet
Emergency and Disaster Assembly Areas (EDAA) are designated safe zones where basic needs can be met until temporary shelters are established following natural or man-made disasters like floods, fires, earthquakes, explosions, or chemical incidents. Promptly relocating disaster victims to these areas is crucial for minimizing loss of life and facilitating effective search and rescue operations by maintaining an uninterrupted flow of information. To prepare for disasters like earthquakes, which cause significant material and emotional damage to large populations, sustainable disaster management must be ensured to evaluate site suitability, correct deficiencies, and avoid inappropriate locations. This study will examine the evaluation criteria for EDAAs established by the Tunceli Provincial Disaster and Emergency Management Authority (AFAD) in terms of area, structure, security, and accessibility, taking into account the region’s specific characteristics. Based on a literature review, eleven criteria have been proposed and ranked using the Besson mean ranking method. Areas have been classified into four categories (e.g., adequate, not suitable) using the optimistic, pessimistic, and comprise approaches of the Assignment Rule Driven by Attitudes (ARDA) and the ORESTE-Sort method. The examination of 19 EDAA provides two perspectives: an optimistic view that recommends classifying eleven areas as first class and using all areas as they are, and a pessimistic view that calls for urgent improvements in three areas and states that one area (EDAA 1) is deemed unsuitable due to its assignment to class (Formula presented.). It is also advised that the second area should not be used, despite being rated as class (Formula presented.), due to its proximity to the river and its slope characteristics. The study also performs a sensitivity analysis of the method and provides recommendations for future research.
AtıfScopus2WoS1
İncele - MakaleAçık Erişim2026Scopus SJRQ2Hybrid Supervised Classification and Deep Embedding–Based Profiling Framework for Electricity Consumption Analysis
Gunay, Mihriban; Yildirim, Ozal; Demir, Yakup; Zhilevski, Marin; Mikhov, Mikho; Yordanov, Nikolay
This study proposes a hybrid deep learning framework that integrates supervised classification and unsupervised profiling for electricity consumption analysis. In the supervised phase, a one-dimensional Convolutional Neural Network combined with Long Short-Term Memory (1D CNN–LSTM) architecture is developed to classify daily load patterns. The performance of the proposed model is compared with traditional machine learning and deep learning approaches, including Support Vector Machine (SVM), k-Nearest Neighbors (KNN), a standalone Long Short-Term Memory (LSTM) model, a Transformer-based model, and a standalone 1D CNN model. Experimental results on the Precon house dataset and the CU-BEMS dataset demonstrate that the proposed hybrid architecture outperforms the benchmark models, achieving classification accuracies of 87.59% and 86.40%, respectively. In the unsupervised phase, the trained CNN–LSTM encoder is utilized as a deep feature extractor. The resulting 32-dimensional latent embeddings are clustered using K-Means, Gaussian Mixture Model (GMM), Agglomerative, Spectral, and Ensemble methods. Clustering robustness is evaluated through bootstrap-based stability analysis using the Adjusted Rand Index (ARI) and the Normalized Mutual Information (NMI). The results demonstrate stable and interpretable electricity consumption profiles, particularly in the residential dataset, where near-perfect clustering stability is observed for K-Means. The proposed framework provides both improved classification performance and robust consumption profiling based on deep embedding, offering a practical tool for energy management.
AtıfScopus1OpenAlex1İncele - BildiriYalnız künye2025Scopus SJRQ4A Hybrid Machine Learning Architecture for Acoustic Fault Diagnosis in Electric Motors: Offline and Online Modes via Mobile Phone
Yordanov, Nikolay; Zhilevski, Marin; Mikhov, Mikho; Ertargin, Merve
This paper proposes a hybrid ML architecture for non-invasive acoustic fault diagnosis in electric motors and machines using a.NET MAUI cross-platform mobile app for short audio capture (5-20s), audio-to-image transformations and dual-mode inference: embedded ML.NET/ONNX models for offline preliminary detection and Azure ML-hosted deep CNN/RNN for online probabilistic multi-fault analysis. The primary objective of this paper is to demonstrate the benefits of the proposed architecture and to show the specific tools which can be used for implementation. Architectures (embedded, cloud, hybrid) are evaluated by listing main advantages and disadvantage, highlighting hybrid approach that combines offline resilience, reduced latency and keeping the possibility for complex analysis by using online hosted model. Sample mobile application design is added to showcase the proposed user experience.
- BildiriAçık Erişim2025Health Status Classification of Electric Motors Using CNN-Based Models and SDP Images Under Varying Noise Conditions
Ertarğın, Merve; Yordanov, Nikolay; Zhilevski, Marin; Benedicenti, L.; Liu, Z.
The increasing application of electric motors across various industrial sectors requires effective monitoring and early diagnostics to prevent potential failures. This study explores the use of Convolutional Neural Network (CNN)-based models together with Symmetrized Dot Pattern (SDP) sound representations for classifying the health status of electric motors under different noise conditions. Acoustic data from a brushless DC motor were transformed into SDP images, which were then used to train CNN models. The dataset included recordings of motors in “Good”, “Broken” and “Heavy Load” conditions, captured under various noise environments such as pure, talking, white noise, atmospheric, and stress test conditions. The classification tasks were conducted under three conditions: assessing motor health status, evaluating both motor health status and noise types, and excluding the stress test noise type for a balanced dataset. The results demonstrated that the CNN models achieved high accuracy rates in classifying motor health status, with the Custom CNN model performing best in simpler tasks and MobileNet excelling in more complex scenarios. The study highlights the feasibility of using SDP images with CNN-based models for fault classification in motors and suggests future research directions for improving classification accuracy through advanced feature extraction techniques and multimodal data representations.
AtıfScopus1İncele - MakaleAçık Erişim2025Scopus SJRQ2Species classification of microalgae using a CNN-based deep learning approach under optimal cultivation conditions
Simsek, Gokce Kendirlioglu; Ertargin, Merve; Pezzolesi, Laura; Pistocchi, Rossella; Yildirim, Ozal; Cetin, A. Kadri
Microalgae possess significant potential in a wide range of applications due to their valuable bioactive compounds. They are utilized in biofuel production to reduce dependence on fossil fuels, in wastewater treatment for the biological removal of heavy metals and pollutants, in carbon capture for mitigating climate change, and in the pharmaceutical and nutraceutical industries as supplements. As their applications expand, the accurate and efficient identification of microalgal species becomes increasingly important. Traditional classification methods are time-consuming and rely heavily on expert knowledge. The main aim of this study is to develop a reliable, fast, and expert-independent deep learning-based approach for the classification of microalgae species using microscopic images. In this context, deep learning techniques, specifically convolutional neural network (CNN)-based models were employed to classify microalgal species. Four widely used pre-trained CNN architectures (ResNet152, DenseNet201, MobileNetV2, and EfficientNetB0), along with a custom-designed CNN, were implemented. The models were trained and tested on a labeled dataset consisting of microscopic images of Chlorella vulgaris, Scenedesmus acutus, and Haematococcus pluvialis. The classification models achieved accuracy rates ranging from 96.87 % (Custom CNN) to 100 % (DenseNet201), demonstrating the potential of CNN-based approaches in automating and improving microalgae species identification.
AtıfScopus5WoS5OpenAlex5İncele - Kitap BölümüYalnız künye2023Determining the Criterion Weights for the Selection of Volunteers in Humanitarian Organizations by the Best-Worst Method
Ozdemir, Umit; Mete, Suleyman; Gul, Muhammet
Today, it is vital for humanitarian organizations operating in many different fields to select volunteers from the determining criteria according to the needs of the institution. Failure to select volunteers in accordance with the institution's needs may cause the volunteers to be unable to continue their duties and interrupt the institution's work. When choosing volunteers, it is essential for effective volunteer management to classify (expert, experienced, inexperienced, and insufficient) them according to the institution’s needs and assign them starting from the volunteer in the best class volunteer when necessary. The aim of this study is to determine the criteria weights in the classification of volunteers who want to participate in search and rescue activities in humanitarian aid organizations according to the criteria determined before their assignment. In this study, a questionnaire is applied to field experts in Turkey to determine the most important and least important criteria, then criteria weights are calculated by using the Best-Worst Method (BWM). The findings obtained as a result of our study are evaluated and suggestions are made on how to improve it for future studies.
AtıfScopus1OpenAlex1İncele - MakaleAçık Erişim2023A new approach based on convolutional neural network and feature selection for recognizing vehicle types
Doğan, Gürkan; Ergen, Burhan
The number of vehicles used in traffic life has reached enormous dimensions today. The increase in the number of vehicles day by day causes some traffic problems along with it; such as traffic congestion, accidents, pollution, and safety. To overcome all these problems, convolutional neural networks (CNN) methods are one of the trend methods used in recent years due to their success. In this study, a new approach is proposed to use this power of CNN in low-power devices. First of all, MobileNetv1, MobileNetv2, and NASNetMobile models were optimized to increase accuracy performance. Then, an approach is proposed in which these optimized mobile CNN approaches are used only as feature extractors, and methods such as combining, selecting, and classifying the obtained features are used together. As a result of the classification made with this approach, the classification accuracy has increased by approximately 5%.
AtıfScopus10OpenAlex12İncele - Yüksek Lisans TeziAçık Erişim2022Makine öğrenme yöntemleri ile Kahramanmaraş ilindeki trafik kazası sonuçlarının analizi ve tahmin edilmesi
Hüseyin Bolat
Trafik kazaları insan yaralanmaları ve ölümlerinin en büyük nedenlerindendir. Dünya üzerinde her yıl 1 milyonun üzerinde ölümlü, 50 milyona yakın yaralanmalı trafik kazası meydana gelmektedir. Bu kazalarda ortalama her 2 saniyede bir trafik kazası yaşanırken her 50 saniyede bir ölümcül kaza ile sonuçlanmaktadır. Bu çalışmada, 2017 ile 2020 yılları arasında Kahramanmaraş il merkezi ve ilçelerinde gerçekleşen 28 adet öznitelikten oluşan 7929 adet trafik kazası WEKA aracında makine öğrenme teknikleri ile analiz edildi. Trafik kazalarının analizinde sınıflandırma, kümeleme, birliktelik kuralı ve görsel karşılaştırma yöntemleri kullanılmaktadır. Sınıflandırma yönteminde Naive Bayes, Destek Vektör Makinesi, K En Yakın Komşu, PART, AdaboostM1, J48 ve Rastgele Orman algoritmaları kullanıldı. Kümeleme yönteminde SimpleKMeans ve EM kümeleme algoritmaları kullanıldı. Birliktelik yönteminde Apriori algoritmaları kullanıldı. Sonuç olarak trafik kazalarının tahmininde sınıflandırma algoritmaların performans ölçütlerine bakıldığında karar ağaçlarından J48 algoritması en başarılı sonuçları elde ederken, NB algoritmasının başarı düzeyi kötü olmasa da diğer algoritmalara oranla daha düşük kalmıştır. Tüm yöntemlerin ortak sonucu gelecekte yaşanabilecek ölümle ve yaralanmalı potansiyel kazaların daha çok sabah saat 04:00 ile 08:00 ve akşam saat 16:00 ile 20:00 arasında, Kahramanmaraş il merkezi ve Onikişubat ilçesinde yerleşim yeri içerisinde, Göksun ilçesindeki yerleşim yeri dışındaki eğimli ve virajlı yollarda ve Pazarcık ilçesindeki yerleşim yeri dışındaki bölünmüş yollarda yaşanma riskinin yüksek olduğu belirlenmiştir. Ayrıca meydana gelen kazalarda sürücülerin trafik ve hız kurallarına uymadığı, trafik lambası, trafik levhası, yaya yolu, emniyet şeridi ve banket gibi yol, çevre ve güvenlik ekipmanlarının yetersiz kaldığı belirlenmiştir.
- MakaleAçık Erişim2022Scopus SJRQ1Dental Caries Detection Using Score-Based Multi-Input Deep Convolutional Neural Network
Imak, Andac; Celebi, Adalet; Siddique, Kamran; Turkoglu, Muammer; Sengur, Abdulkadir; Salam, Iftekhar
Panoramic and periapical radiograph tools help dentists in diagnosing the most common dental diseases, such as dental caries. Generally, dental caries is manually diagnosed by dentists based on panoramic and periapical images. For several reasons, such as carelessness caused by heavy workload and inexperience, manual diagnosis may cause unnoticeable dental caries. Thus, computer-based intelligent vision systems supported by machine learning and image processing techniques are needed to prevent these negativities. This study proposed a novel approach for the automatic diagnosis of dental caries based on periapical images. The proposed procedure used a multi-input deep convolutional neural network ensemble (MI-DCNNE) model. Specifically, a score-based ensemble scheme was employed to increase the achievement of the proposed MI-DCNNE method. The inputs to the proposed approach were both raw periapical images and an enhanced form of it. The score fusion was carried out in the Softmax layer of the proposed multi-input CNN architecture. In the experimental works, a periapical image dataset (340 images) covering both caries and non-caries images were used for the performance evaluation of the proposed method. According to the results, it was seen that the proposed model is quite successful in the diagnosis of dental caries. The reported accuracy score is 99.13%. This result shows that the proposed MI-DCNNE model can effectively contribute to the classification of dental caries.
AtıfScopus107İncele - MakaleYayıncıda açık erişim2022Scopus SJRQ2Dental Material Detection based on Faster Regional Convolutional Neural Networks and Shape Features
Imak, Andaç; Çelebi, Adalet; Türkoğlu, Muammer; Şengür, Abdulkadir
In this paper, a novel approach is proposed to detect the dental materials in dental Panoramic images. In general, dental Panoramic images are examined by the dentists to detect the dental materials of the patients. Examining the dental Panoramic images is a time-consuming procedure and necessitates highly skilled dentists. Thus, computer imaging and decision support systems based on machine learning are in demand for dental applications. In this study, a semi-automatic, image processing and machine learning based approach is proposed for detection of dental materials in dental Panoramic images. More specifically, the dental materials namely dental filling, dental bridge and tooth crown are targeted by the proposed approach. Within the approach developed, the dental Panoramic images used as input are initially pre-processed for noise removal and tooth region is determined using a deep learning approach. To this end, a faster Regional Convolutional Neural Networks (RCNN) method is employed. A tooth region correction procedure is applied after application of faster RCNN to determine the exact location of the tooth region as faster RCNN may produce more tooth regions than one correct tooth region. Graph cut (GC) based image segmentation is applied to segment the tooth region into foreground and background regions. Shape based feature extraction and classification are applied to determine the tooth problem. A dataset has been established in dental faculty hospital of private dental clinics. The proposed approach is simple yet quite effective. In all classification methods, the average accuracy scores were around 90%.
AtıfScopus9WoS7OpenAlex10İncele - BildiriYalnız künye2020Classification of Hand-Drawn Circuit Components by Considering the Analysis of Current Methods
Gunay, Mihriban; Koseoglu, Murat
In this paper, at first, existing classification methods for classifying hand drawn circuits and circuit components are briefly introduced by examining advantages and disadvantages of each classification method. The handled methods are Support Vector Machine method (SVM), nearest neighbor method (KNN) and convolutional neural network method (CNN). Then, in the experimental part of the study, four different hand-drawn circuit components, which are diode, capacitor, resistor and ac voltage source, have been tried to be classified by using CNN method which is a highly recommended classification method in literature. The classification tables and graphics have been presented for the performed study. According to the obtained results and accuracy rate, it is concluded that CNN method can be used reliably to achieve high performance in the classification of hand-drawn circuit components.
AtıfScopus5OpenAlex5İncele - BildiriYalnız künye2020Scopus SJRQ3Dynamic Features Spaces and Machine Learning: Open Problems and Synthetic Data Sets
Kaya, Sema Kayapinar; Navarro-Arribas, Guillermo; Torra, Vicenç; Huynh, V.; Entani, T.; Jeenanunta, C.; Inuiguchi, M.; Yenradee, P.
Dynamic feature spaces appear when different records or instances in databases are defined in terms of different features. This is in contrast with usual (static) feature spaces in standard databases, where the schema of the database is known and fixed. Then, all records in the database have the same set of variables, attributes or features. Dynamic feature mining algorithms are to extract knowledge from data on dynamic feature spaces. As an example, spam detection methods have been developed from a dynamic feature space perspective. Words are taken as features and new words appearing in new emails are, therefore, considered new features. In this case, the problem of spam detection is represented as a classification problem (a supervised machine learning problem). The relevance of dynamic feature spaces is increasing. The large amounts of data currently available or received by systems are not necessarily described using the same feature spaces. This is the case of distributed databases with data about customers, providers, etc. Industry 4.0, Internet of Things, and RFIDs are and will be a source of data in dynamic feature spaces. New sensors added in an industrial environment, new devices connected into a smart home, new types of analysis and new types of sensors in healthcare, all are examples of dynamic feature spaces. Machine learning algorithms are needed to deal with these type of scenarios. In this paper we motivate the interest for dynamic feature mining, we give some examples of scenarios where these techniques are needed, we review some of the existing solutions and its relationship with other areas of machine learning and data mining (e.g., incremental learning, concept drift, topic modeling), we discuss some open problems, and we discuss synthetic data generation for this type of problem.
AtıfScopus4WoS3OpenAlex3İncele - BildiriYalnız künye2020Classification of Hand-Drawn Basic Circuit Components Using Convolutional Neural Networks
Gunay, Mihriban; Koseoglu, Murat; Yildirim, Ozal
In this paper, the Convolutional Neural Network (CNN) architecture, which is one of the deep learning architectures, is used to classify the basic circuit components drawn by hand. During the training and testing stages of the model, a new dataset containing images of 863 circuit components manually drawn by different people is created. The data set contains images of four different classes of circuit components such as resistor, inductor, capacitor and voltage source. All images have been fixed to the same size and converted to grayscale to increase recognition performance and reduce process complexity. In the study, training for four classes is performed with CNN architecture. Based on the CNN architecture, four new CNN models are employed with different the number of layers. The training and validation results of these models are compared separately, the model with the highest training and validation performance is observed with four layer CNN model (CNN-4). This model obtained 84.41% accuracy rate at classification task.
AtıfScopus16WoS5OpenAlex17İncele - MakaleAçık Erişim2019Scopus SJRQ2A deep learning model for automated sleep stages classification using PSG signals
Yildirim, Ozal; Baloglu, Ulas Baran; Acharya, U Rajendra
Sleep disorder is a symptom of many neurological diseases that may significantly affect the quality of daily life. Traditional methods are time-consuming and involve the manual scoring of polysomnogram (PSG) signals obtained in a laboratory environment. However, the automated monitoring of sleep stages can help detect neurological disorders accurately as well. In this study, a flexible deep learning model is proposed using raw PSG signals. A one-dimensional convolutional neural network (1D-CNN) is developed using electroencephalogram (EEG) and electrooculogram (EOG) signals for the classification of sleep stages. The performance of the system is evaluated using two public databases (sleep-edf and sleep-edfx). The developed model yielded the highest accuracies of 98.06%, 94.64%, 92.36%, 91.22%, and 91.00% for two to six sleep classes, respectively, using the sleep-edf database. Further, the proposed model obtained the highest accuracies of 97.62%, 94.34%, 92.33%, 90.98%, and 89.54%, respectively for the same two to six sleep classes using the sleep-edfx dataset. The developed deep learning model is ready for clinical usage, and can be tested with big PSG data.
AtıfScopus255OpenAlex265
İncele - MakaleYayıncıda açık erişim2018Scopus SJRQ2Application of Computational Intelligence Methods for the Automated Identification of Paper-Ink Samples Based on LIBS
Rzecki, Krzysztof; Sośnicki, Tomasz; Baran, Mateusz; Niedźwiecki, Michał; Król, Małgorzata; Łojewski, Tomasz; Acharya, U. Rajendra; Yildirim, Özal; Pławiak, Paweł
Laser-induced breakdown spectroscopy (LIBS) is an important analysis technique with applications in many industrial branches and fields of scientific research. Nowadays, the advantages of LIBS are impaired by the main drawback in the interpretation of obtained spectra and identification of observed spectral lines. This procedure is highly time-consuming since it is essentially based on the comparison of lines present in the spectrum with the literature database. This paper proposes the use of various computational intelligence methods to develop a reliable and fast classification of quasi-destructively acquired LIBS spectra into a set of predefined classes. We focus on a specific problem of classification of paper-ink samples into 30 separate, predefined classes. For each of 30 classes (10 pens of each of 5 ink types combined with 10 sheets of 5 paper types plus empty pages), 100 LIBS spectra are collected. Four variants of preprocessing, seven classifiers (decision trees, random forest, k-nearest neighbor, support vector machine, probabilistic neural network, multi-layer perceptron, and generalized regression neural network), 5-fold stratified cross-validation, and a test on an independent set (for methods evaluation) scenarios are employed. Our developed system yielded an accuracy of 99.08%, obtained using the random forest classifier. Our results clearly demonstrates that machine learning methods can be used to identify the paper-ink samples based on LIBS reliably at a faster rate.
AtıfScopus39İncele - MakaleAçık Erişim2018Heartbeat type classification with optimized feature vectors
Yıldırım, Özal; Baloglu, Ulas Baran
In this study, a feature vector optimization based method has been proposed for classification of the heartbeat types. Electrocardiogram (ECG) signals of five different heartbeat type were used for this aim. Firstly, wavelet transform (WT) method were applied on these ECG signals to generate all feature vectors. Optimizing these feature vectors is provided by performing particle swarm optimization (PSO), genetic search, best first, greedy stepwise and multi objective evoluationary algorithms on these vectors. These optimized feature vectors are later applied to the classifier inputs for performance evaluation. A comprehensive assessment was presented for the determination of optimized feature vectors for ECG signals and best-performing classifier for these optimized feature vectors was determined.
AtıfScopus7OpenAlex7
İncele - MakaleAçık Erişim2016Scopus SJRQ2Automatic mining of accurate and comprehensible numerical classification rules with cat swarm optimization algorithm
Akyol, Sinem; Alatas, Bilal
Optimization is the process of finding the best solution of a problem. There are many optimization algorithms proposed for optimization problems. The metaheuristic algorithm can give solutions close to optimum in an acceptable period of time for large-scaled optimization problems. The metaheuristic optimization algorithms are evaluated in seven different groups which are biology-based, physics-based, swarm-based, social-based, music-based, sport-based, and chemistry-based. The swarm-based optimization algorithms have been developed by observing the behaviors of creatures e.g. birds, fishes, cats, bees etc. Data mining is the process of discovery of meaningful and useful data within huge databases. Classification rules mining is one of the most commonly studied data mining problems and with methods for this problem, users can easily understand the rules extracted from databases. In this work, one of the most recent swarm based optimization algorithm, Cat Swarm Optimization (CSO), has been firstly used for classification rules mining within databases composed of numerical or mixed data types automatically. There is not any preprocess for finding true ranges for appropriate attributes of the rules, this has been automatically done by CSO. Furthermore, the used objective function is very flexible and many different objectives can easily be added to. For this purpose, four numerical databases obtained from UCI data warehouse have been used and accurate and comprehensible classification rules have been mined. The results have been compared with the results obtained from Weka program. Although CSO has not been embedded with any improvement and has firstly implemented in this research area, the obtained results seem promising.
AtıfWoS9OpenAlex4İncele - MakaleAçık Erişim2014Scopus SJRQ1Automatic recognition system of underlying causes of power quality disturbances based on S-Transform and Extreme Learning Machine
Eristi, Huseyin; Yildirim, Ozal; Eristi, Belkis; Demir, Yakup
In this paper, a new S-Transform and Extreme Learning Machine (ST-ELM)-based event recognition approach for the purpose of classifying power quality (PQ) event signals automatically has been proposed. In this approach, the distinctive features of the PQ event signals have been obtained with the S-Transform-based feature extraction. The feature vector obtained with feature extraction has been applied as input to the ELM classifier. Ten different classification procedures were determined within the framework of this study to assess the performance of the ELM classifier on PQ event data. Real PQ event data and synthetic PQ event data obtained from MATIAB/Simulink environment have been used in these procedures. Also, three different PQ event data sets, which are formed by adding noises of 20, 30 and 50 dB to the synthetic PQ event data respectively, have been used in order to assess the performance of the proposed approach on noisy conditions. According to the results of performance evaluations, the proposed ST-ELM-based PQ event recognition system has a very high performance of recognizing PQ event data. Besides, classification of noisy data showed that the proposed approach is robust at recognizing noisy data. The performance of the ST-ELM-based recognition system on PQ data shows that this approach has an effective recognition structure that can be used in real power systems. (C) 2014 Elsevier Ltd. All rights reserved.
AtıfWoS63OpenAlex93İncele - MakaleAçık Erişim2010Scopus SJRQ1Wavelet-based feature extraction and selection for classification of power system disturbances using support vector machines
Eristi, Hueseyin; Uçar, Ayseguel; Demir, Yakup
This paper presents a new approach for the classification of the power system disturbances using support vector machines (SVMs). The proposed approach is carried out at three serial stages. Firstly, the features to be form the SVM classifier are obtained by using the wavelet transform and a few different feature extraction techniques. Secondly, the features exposing the best classification accuracy of these features are selected by a feature selection technique called as sequential forward selection. Thirdly, the best appropriate input vector for SVM classifier is rummaged. The input vector is started with the first best feature and incrementally added the chosen features. After the addition of each feature, the performance of the SVM is evaluated. The kernel and penalty parameters of the SVM are determined by cross-validation. The parameter set that gives the smallest misclassification error is retained. Finally, both the noisy and noiseless signals are applied to the classifier given above stages. Experimental results indicate that the proposed classifier is robust and has more high classification accuracy with regard to the other approaches in the literature for this problem. (C) 2010 Elsevier B.V. All rights reserved.
AtıfWoS119OpenAlex163İncele