Sürdürülebilir Kalkınma Amaçları
Yayınlar
- MakaleYalnız künye2020Scopus SJRQ1A deep convolutional neural network model for automated identification of abnormal EEG signals
Yıldırım, Özal; Baloglu, Ulas Baran; Acharya, U. Rajendra
Electroencephalogram (EEG) is widely used to monitor the brain activities. The manual examination of these signals by experts is strenuous and time consuming. Hence, machine learning techniques can be used to improve the accuracy of detection. Nowadays, deep learning methodologies have been used in medical field to diagnose the health conditions precisely and aid the clinicians. In this study, a new deep one-dimensional convolutional neural network (1D CNN) model is proposed for the automatic recognition of normal and abnormal EEG signals. The proposed model is a complete end-to-end structure which classifies the EEG signals without requiring any feature extraction. In this study, we have used the EEG signals from temporal to occipital (T5–O1) single channel obtained from Temple University Hospital EEG Abnormal Corpus (v2.0.0) EEG dataset to develop the 1D CNN model. Our developed model has yielded the classification error rate of 20.66% in classifying the normal and abnormal EEG signals.
AtıfScopus164OpenAlex211
İncele - MakaleAçık Erişim2020Scopus SJRQ1Automated detection of COVID-19 cases using deep neural networks with X-ray images
Ozturk, Tulin; Talo, Muhammed; Yildirim, Eylul Azra; Baloglu, Ulas Baran; Yildirim, Ozal; Rajendra Acharya, U.
The novel coronavirus 2019 (COVID-2019), which first appeared in Wuhan city of China in December 2019, spread rapidly around the world and became a pandemic. It has caused a devastating effect on both daily lives, public health, and the global economy. It is critical to detect the positive cases as early as possible so as to prevent the further spread of this epidemic and to quickly treat affected patients. The need for auxiliary diagnostic tools has increased as there are no accurate automated toolkits available. Recent findings obtained using radiology imaging techniques suggest that such images contain salient information about the COVID-19 virus. Application of advanced artificial intelligence (AI) techniques coupled with radiological imaging can be helpful for the accurate detection of this disease, and can also be assistive to overcome the problem of a lack of specialized physicians in remote villages. In this study, a new model for automatic COVID-19 detection using raw chest X-ray images is presented. The proposed model is developed to provide accurate diagnostics for binary classification (COVID vs. No-Findings) and multi-class classification (COVID vs. No-Findings vs. Pneumonia). Our model produced a classification accuracy of 98.08% for binary classes and 87.02% for multi-class cases. The DarkNet model was used in our study as a classifier for the you only look once (YOLO) real time object detection system. We implemented 17 convolutional layers and introduced different filtering on each layer. Our model (available at (https://github.com/muhammedtalo/COVID-19)) can be employed to assist radiologists in validating their initial screening, and can also be employed via cloud to immediately screen patients.
AtıfScopus2286OpenAlex2595
İncele - Derleme MakaleYayıncıda açık erişim2020Scopus SJRQ1Application of deep learning techniques for heartbeats detection using ECG signals-analysis and review
Murat, Fatma; Yildirim, Ozal; Talo, Muhammed; Baloglu, Ulas Baran; Demir, Yakup; Acharya, U. Rajendra
Deep learning models have become a popular mode to classify electrocardiogram (ECG) data. Investigators have used a variety of deep learning techniques for this application. Herein, a detailed examination of deep learning methods for ECG arrhythmia detection is provided. Approaches used by investigators are examined, and their contributions to the field are detailed. For this purpose, journal papers have been surveyed according to the methods used. In addition, various deep learning models and experimental studies are described and discussed. A five-class ECG dataset containing 100,022 beats was then utilized for further analysis of deep learning techniques. The constructed models were examined with this dataset, and results are presented. This study therefore provides information concerning deep learning approaches used for arrhythmia classification, and suggestions for further research in this area.
AtıfScopus318OpenAlex328İncele - MakaleYalnız künye2019Scopus SJRQ4CONVOLUTIONAL LONG-SHORT TERM MEMORY NETWORKS MODEL FOR LONG DURATION EEG SIGNAL CLASSIFICATION
Baloglu, Ulas Baran; Yildirim, Ozal
Background and objective: Deep learning structures have recently achieved remarkable success in the field of machine learning. Convolutional neural networks (CNN) in image processing and long-short term memory (LSTM) in the time-series analysis are commonly used deep learning algorithms. Healthcare applications of deep learning algorithms provide important contributions for computer-aided diagnosis research. In this study, convolutional long-short term memory (CLSTM) network was used for automatic classification of EEG signals and automatic seizure detection. Methods: A new nine-layer deep network model consisting of convolutional and LSTM layers was designed. The signals processed in the convolutional layers were given as an input to the LSTM network whose outputs were processed in densely connected neural network layers. The EEG data is appropriate for a model having 1-D convolution layers. A bidirectional model was employed in the LSTM layer. Results: Bonn University EEG database with five different datasets was used for experimental studies. In this database, each dataset contains 23.6 s duration 100 single channel EEG segments which consist of 4097 dimensional samples (173.61 Hz). Eight two-class and three three-class clinical scenarios were examined. When the experimental results were evaluated, it was seen that the proposed model had high accuracy on both binary and ternary classification tasks. Conclusions: The proposed end-to-end learning structure showed a good performance without using any hand-crafted feature extraction or shallow classifiers to detect the seizures. The model does not require filtering, and also automatically learns to filter the input as well. As a result, the proposed model can process long duration EEG signals without applying segmentation, and can detect epileptic seizures automatically by using the correlation of ictal and interictal signals of raw data.
AtıfWoS17OpenAlex19İncele - BildiriAçık Erişim2019Person Recognition via Facial Expression Using ELM Classifier Based CNN Feature Maps
Baloglu, Ulas Baran; Yildirim, Ozal; Uçar, AySegul; Miche, Y; Cao, J; Vong, CM; Lendasse, A
Extreme learning machine (ELM) and deep learning methods are well-known with their efficiency, accuracy, and speed. In this study, we focus on the application of ELM to a deep learning structure for person recognition with facial expressions. For this purpose, a new convolutional neural network (CNN) model containing Kernel ELM classifiers was constructed. In this model, ELM was not used only as a fully connected layer replacement and energy function was employed to generate feature maps for the ELM. There are two advantages of the proposed model. First, it is fast and successful in face recognition studies. Second, it can drastically improve the performance of a partially-trained CNN model. Consequently, the proposed model is very suitable for CNN models, where the learning process requires a lot of time and computational power. The model is tested with the Grimace data set and experimental results are presented in details.
AtıfOpenAlex3İncele - MakaleYalnız künye2019Scopus SJRQ1Classification of myocardial infarction with multi-lead ECG signals and deep CNN
Baloglu, Ulas Baran; Talo, Muhammed; Yildirim, Ozal; Tan, Ru San; Acharya, U Rajendra
Myocardial infarction (MI), commonly known as heart attack, causes irreversible damage to heart muscles and even leads to death. Rapid and accurate diagnosis of MI is critical to avoid death. Blood tests and electrocardiogram (ECG) signals are used to diagnose acute MI. However, for an increase in blood enzyme values, a certain time must pass after the attack. This time lag may delay MI diagnosis. Hence, ECG diagnosis is still very important. Manual ECG interpretation requires expertise and is prone to inter-observer variability. Therefore, computer aided diagnosis may be useful in automatic detection of MI on ECG. In this study, a deep learning model with an end-to-end structure on the standard 12-lead ECG signal for the diagnosis of MI is proposed. For this purpose, the most commonly used technique, convolutional neural network (CNN) is used. Our trained CNN model with the proposed architecture yielded impressive accuracy and sensitivity performance over 99.00% for MI diagnosis on all ECG lead signals. Thus, the proposed model has the potential to provide high performance on MI detection which can be used in wearable technologies and intensive care units.
AtıfScopus457OpenAlex476İncele - MakaleYalnız künye2019Scopus SJRQ1A new approach for arrhythmia classification using deep coded features and LSTM networks
Yildirim, Ozal; Baloglu, Ulas Baran; Tan, Ru-San; Ciaccio, Edward J.; Acharya, U. Rajendra
Background and objective: For diagnosis of arrhythmic heart problems, electrocardiogram (ECG)signals should be recorded and monitored. The long-term signal records obtained are analyzed by expert cardiologists. Devices such as the Holter monitor have limited hardware capabilities. For improved diagnostic capacity, it would be helpful to detect arrhythmic signals automatically. In this study, a novel approach is presented as a candidate solution for these issues. Methods: A convolutional auto-encoder (CAE)based nonlinear compression structure is implemented to reduce the signal size of arrhythmic beats. Long-short term memory (LSTM)classifiers are employed to automatically recognize arrhythmias using ECG features, which are deeply coded with the CAE network. Results: Based upon the coded ECG signals, both storage requirement and classification time were considerably reduced. In experimental studies conducted with the MIT-BIH arrhythmia database, ECG signals were compressed by an average 0.70% percentage root mean square difference (PRD)rate, and an accuracy of over 99.0% was observed. Conclusions: One of the significant contributions of this study is that the proposed approach can significantly reduce time duration when using LSTM networks for data analysis. Thus, a novel and effective approach was proposed for both ECG signal compression, and their high-performance automatic recognition, with very low computational cost.
AtıfScopus377OpenAlex388İncele - MakaleYalnız künye2019Scopus SJRQ3Application of deep transfer learning for automated brain abnormality classification using MR images
Talo, Muhammed; Baloglu, Ulas Baran; Yıldırım, Özal; Rajendra Acharya, U.
Magnetic resonance imaging (MRI) is the most common imaging technique used to detect abnormal brain tumors. Traditionally, MRI images are analyzed manually by radiologists to detect the abnormal conditions in the brain. Manual interpretation of huge volume of images is time consuming and difficult. Hence, computer-based detection helps in accurate and fast diagnosis. In this study, we proposed an approach that uses deep transfer learning to automatically classify normal and abnormal brain MR images. Convolutional neural network (CNN) based ResNet34 model is used as a deep learning model. We have used current deep learning techniques such as data augmentation, optimal learning rate finder and fine-tuning to train the model. The proposed model achieved 5-fold classification accuracy of 100% on 613 MR images. Our developed system is ready to test on huge database and can assist the radiologists in their daily screening of MR images.
AtıfScopus473OpenAlex508İncele - MakaleAçık Erişim2019Scopus SJRQ1Convolutional neural networks for multi-class brain disease detection using MRI images
Talo, Muhammed; Yildirim, Ozal; Baloglu, Ulas Baran; Aydin, Galip; Acharya, U Rajendra
The brain disorders may cause loss of some critical functions such as thinking, speech, and movement. So, the early detection of brain diseases may help to get the timely best treatment. One of the conventional methods used to diagnose these disorders is the magnetic resonance imaging (MRI) technique. Manual diagnosis of brain abnormalities is time-consuming and difficult to perceive the minute changes in the MRI images, especially in the early stages of abnormalities. Proper selection of the features and classifiers to obtain the highest performance is a challenging task. Hence, deep learning models have been widely used for medical image analysis over the past few years. In this study, we have employed the AlexNet, Vgg-16, ResNet-18, ResNet-34, and ResNet-50 pre-trained models to automatically classify MR images in to normal, cerebrovascular, neoplastic, degenerative, and inflammatory diseases classes. We have also compared their classification performance with pre-trained models, which are the state-of-art architectures. We have obtained the best classification accuracy of 95.23% ± 0.6 with the ResNet-50 model among the five pre-trained models. Our model is ready to be tested with huge MRI images of brain abnormalities. The outcome of the model will also help the clinicians to validate their findings after manual reading of the MRI images.
AtıfScopus276OpenAlex301İncele - MakaleAçık Erişim2019Scopus SJRQ2Automated detection of diabetic subject using pre-trained 2D-CNN models with frequency spectrum images extracted from heart rate signals
Yildirim, Ozal; Talo, Muhammed; Ay, B.; Baloglu, Ulas Baran; Aydin, G.; Acharya, U. Rajendra
In this study, a deep-transfer learning approach is proposed for the automated diagnosis of diabetes mellitus (DM), using heart rate (HR) signals obtained from electrocardiogram (ECG) data. Recent progress in deep learning has contributed significantly to improvement in the quality of healthcare. In order for deep learning models to perform well, large datasets are required for training. However, a difficulty in the biomedical field is the lack of clinical data with expert annotation. A recent, commonly implemented technique to train deep learning models using small datasets is to transfer the weighting, developed from a large dataset, to the current model. This deep learning transfer strategy is generally employed for two-dimensional signals. Herein, the weighting of models pre-trained using two-dimensional large image data was applied to one-dimensional HR signals. The one-dimensional HR signals were then converted into frequency spectrum images, which were utilized for application to well-known pre-trained models, specifically: AlexNet, VggNet, ResNet, and DenseNet. The DenseNet pre-trained model yielded the highest classification average accuracy of 97.62%, and sensitivity of 100%, to detect DM subjects via HR signal recordings. In the future, we intend to further test this developed model by utilizing additional data along with cloud-based storage to diagnose DM via heart signal analysis.
AtıfScopus145OpenAlex152İncele - 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.
AtıfScopus255OpenAlex265İncele - MakaleAçık Erişim2019Scopus SJRQ2Automated Depression Detection Using Deep Representation and Sequence Learning with EEG Signals
Ay, Betul; Yildirim, Ozal; Talo, Muhammed; Baloglu, Ulas Baran; Aydin, Galip; Puthankattil, Subha D.; Acharya, U. Rajendra
Depression affects large number of people across the world today and it is considered as the global problem. It is a mood disorder which can be detected using electroencephalogram (EEG) signals. The manual detection of depression by analyzing the EEG signals requires lot of experience, tedious and time consuming. Hence, a fully automated depression diagnosis system developed using EEG signals will help the clinicians. Therefore, we propose a deep hybrid model developed using convolutional neural network (CNN) and long-short term memory (LSTM) architectures to detect depression using EEG signals. In the deep model, temporal properties of the signals are learned with CNN layers and the sequence learning process is provided through the LSTM layers. In this work, we have used EEG signals obtained from left and right hemispheres of the brain. Our work has provided 99.12% and 97.66% classification accuracies for the right and left hemisphere EEG signals respectively. Hence, we can conclude that the developed CNN-LSTM model is accurate and fast in detecting the depression using EEG signals. It can be employed in psychiatry wards of the hospitals to detect the depression using EEG signals accurately and thus aid the psychiatrists.
AtıfScopus279OpenAlex291İncele - 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 Erişim2018Scopus SJRQ1An Agent-Based Pythagorean Fuzzy Approach for Demand Analysis with Incomplete Information
Baloglu, Ulas Baran; Demir, Yakup
Analyzing demand in environments with incomplete information is a challenging task. This paper proposes a novel agent-based Pythagorean fuzzy approach for analyzing this kind of demand. First, a Bayesian game is described with a large number of finite players, and this is followed by a Pythagorean fuzzy-based decision mechanism. Unlike the classical methods in the literature, the proposed method in this paper neither assumes nor forecasts the demand in a system. Instead, it tries to analyze the demand when there is limited availability of input data, or processing data are computationally expensive. The study ends with an application of the proposed system to an electricity grid. Electricity prices used as an incentive to construct an agent-based system that efficiently reduces the peak amounts in a smart grid by analyzing the demand. Test results provide evidence that the proposed approach is promising to design demand response systems.
AtıfScopus18WoS18OpenAlex19İncele - MakaleAçık Erişim2018Scopus SJRQ1Lightweight privacy-preserving data aggregation scheme for smart grid metering infrastructure protection
Baloglu, Ulas Baran; Demir, Yakup
The electric industry's planned shift to smart grid metering infrastructure raised several concerns especially about preserving the privacy. Various data perturbation and aggregation solutions are being developed to address these concerns. The drawback of these solutions is that a simple random noise scheme cannot protect privacy, and there is a need for more advanced perturbation techniques to increase hardware costs of smart metering devices. The proposed data aggregation scheme combines the power of perturbation techniques with crypto-systems in an efficient and lightweight way so that it becomes applicable for devices with limited hardware, such as smart meters. We investigated the privacy preserving capabilities of the proposed aggregation scheme with Holt-Winters and Seasonal Trend Decomposition using Loess prediction methods. The results indicate that the proposed scheme is resilient to both filtering and true value attacks.
AtıfScopus25WoS14OpenAlex25İncele - MakaleAçık Erişim20172D-DOST Özellik Çıkarımı Yöntemi ve LS-SVM Sınıflandırıcı Tabanlı Doku Sınıflandırma Sistemi
Baloglu, Ulas Baran; Yıldırım, Özal
Bu çalışmada, doku görüntülerinin sınıflandırılması için 2D-DOST (İki Boyutlu Ayrık Orthonormal Stockwell Dönüşümü) ve LS-SVM (En Küçük Kareler Destek Vektör Makineleri) tabanlı yeni bir sınıflandırıcı sistemi önerilmiştir. Önerilen sistem, özellik çıkarımı ve sınıflandırma olmak üzere iki ana bölümden oluşmaktadır. Özellik çıkarımı aşamasında, görüntüleri temsil eden ait ayırt edici özellik vektörleri 2D-DOST tabanlı özellik çıkarım yöntemi ile elde edilmektedir. Sınıflandırma aşamasında ise yüksek başarım oranı ve doğruluğa sahip olan LS-SVM sınıflandırıcısı ile doku görüntüleri sınıflandırılmaktadır. LS-SVM’nin eğitimi her bir doku görüntüsüne ait ayırt edici özellik vektörleri üzerinde gerçekleştirilmiştir. Test verisi olarak hazırlanan doku görüntüleri eğitilmiş LS-SVM sınıflandırıcının girişine uygulanmıştır. Önerilen yöntemin performans testleri için alt-görüntüler ile elde edilen farklı veri setleri üzerinde gerçekleştirilmiştir. Bu veri setleri hem normal doku görüntülerini hem de gürültülü doku görüntülerini içermektedir. Veri setleri içerisindeki alt görüntüler Brodatz ve Kylberg doku veri tabanlarından türetilmiştir. Gürültülü verilerin oluşturulmasında, farklı seviyelerde Gaussian ve Tuz&Biber gürültüsü kullanılmıştır. Çalışma sonuçları, önerilen 2D-DOST ve LS-SVM tabanlı sınıflandırıcının doku görüntülerini yüksek başarım oranı ile sınıflandırabildiğini ve gürültüye karşı gürbüz olduğunu göstermektedir.
AtıfOpenAlex4İncele - BildiriYalnız künye2017An Identity-Based Encryption Scheme with Performance Optimization for Privacy Preservation in Smart Grid Communication
Baloglu, Ulas Baran; Demir, Yakup; Paleologu, C; McClellan, S
Smart grids are expected to replace existing electrical grids with advanced mechanisms and intelligent entities, which have excessive data processing and communication tasks. It is important for the sensitive consumer data, such as meter readings, to be secured at these intelligent entities. Novel digital communication mechanisms should be developed to protect privacy. Existing smart grid architectures do not have sufficient and efficient security functionalities for data transmission. In this paper, we propose an Identity-Based Encryption scheme, which is more promising than the classical form regarding performance and security. The proposed scheme focuses on the data structure of meter readings and optimizes this structure to achieve a better privacy preservation. This novel structure further improves the performance of the scheme by reducing communication overhead caused by public key creation and distribution operations, as evaluations demonstrated.
AtıfWoS1İncele - BildiriAçık Erişim2017Economic Analysis of Hybrid Renewable Energy Systems with V2G Integration Considering Battery Life
Baloglu, Ulas Baran; Demir, Yakup; Caetano, N.S.; Faculty of Engineering University of Porto (FEUP), LEPABE, Rua Dr. Roberto Frias, Porto; Polytechnic Institute of Porto (IPP), CIETI, School of Engineering (ISEP), Rua Dr. Antonio Bernardino de Almeida 431, Porto; Felgueiras, M.C.; Forment, M.A.
Hybrid renewable energy systems considered as candidate solutions for environmental problems. Solar energy and wind energy are important components of these systems, but both of them cause fluctuations in the grid. Batteries of Electric Vehicles (EVs) can be connected to the grid to create an ancillary resource. These systems known as Vehicle to Grid (V2G) and they could be the most suitable solution to the fluctuation problems of renewable resources. In this paper, economic analysis of V2G is investigated from various perspectives. The findings of this study indicate that battery aging costs of a V2G system can be minimized with an intelligent energy management system, and these systems are both economically and environmentally better alternatives to fossil-fuelled generators.
AtıfScopus15WoS13OpenAlex16İncele - BildiriYalnız künye2017A fuzzy queueing based model for controlling power demand of electric vehicle charging
Baloglu, Ulas Baran; Demir, Yakup; Napoli, C.; University of Catania, Department of Mathematics and Informatics, Viale Andrea Doria 6, Catania; Wozniak, M.; Silesian University of Technology, Institute of Mathematics, Kaszubska 23, Gliwice; Damasevicius, R.; Kaunas University of Technology, Software Engineering Department, Studentu 50 415, Kaunas; Tramontana, E.
The rapid penetration of electric vehicles may lead to peak problems in a traditional grid so that some of the smart grid research is focused on charging strategies for electric vehicles. The charging problem is suitable for using a queue structure, and fuzzy queueing can be implemented for this purpose. This paper presents a fuzzy queueing based model, which can also control the power demand of electric vehicle charging. A charging model should guarantee that all charging requirements can be satisfied before vehicles leaving the charging stations. Simulation results exhibit that the proposed model decreases average waiting time of vehicles and also the proposed model utilize charging stations better than a traditional queueing model.