Yazar "Kaya, Yasin" seçeneğine göre listele
Listeleniyor 1 - 18 / 18
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A Channel Selection Method for Emotion Recognition From EEG Based on Swarm-Intelligence Algorithms(IEEE-Inst Electrical Electronics Engineers Inc, 2021) Yildirim, Esen; Kaya, Yasin; Kılıç, FatihIncreasing demand for human-computer interaction applications has escalated the need for automatic emotion recognition as emotions are essential for natural communication. There are various information sources that can be used for recognizing emotions, such as speech, facial expressions, body movements, and physiological signals. Among those physiological signals are more reliable for better affective communication with machines since they are almost impossible to control. Therefore, automatic emotion recognition from EEG signals has been a topic intensely investigated. Emotions are experiences that arise various cognitive functions observed in different frequency bands involving multiple brain areas and recognition from EEG with high accuracies is only possible with a large number of features extracted from the whole brain in various bands. Emotion regulation also requires integration of cognitive functions and thus functional connectivity between regions should also be considered. In this paper, we extract 736 features based on spectral power and phase-locking values. We particularly focus on finding salient features for emotion recognition using swarm-intelligence (SI) algorithms. We applied well-known classification algorithms for recognizing positive and negative emotions using the feature sets that are selected by these algorithms. Besides, features that are selected by all of them commonly are used as a new feature set. We report accuracies between 56.27% and 60.29% on the average; noting that by decreasing the feature size by 87.17% (from 736 to 94.40) an average accuracy of 60.01 +/- 8.93 was obtained with the random forest classifier. We also highlight the efficient electrode locations for emotion recognition. As a result, we define 11 channels as dominant and promising classification results are obtained.Öğe A deep convolutional neural network model for hand gesture recognition in 2D near-infrared images(Iop Publishing Ltd, 2021) Can, Celal; Kaya, Yasin; Kılıç, FatihThe hand gesture recognition (HGR) process is one of the most vital components in human-computer interaction systems. Especially, these systems facilitate hearing-impaired people to communicate with society. This study aims to design a deep learning CNN model that can classify hand gestures effectively from the analysis of near-infrared and colored natural images. This paper proposes a new deep learning model based on CNN to recognize hand gestures improving recognition rate, training, and test time. The proposed approach includes data augmentation to boost training. Furthermore, five popular deep learning models are used for transfer learning, namely VGG16, VGG19, ResNet50, DenseNet121, and InceptionV3 and compared their results. These models are applied to recognize 10 different hand gestures for near-infrared images and 24 ASL hand gestures for colored natural images. The proposed CNN model, VGG16, VGG19, Resnet50, DenseNet121, and InceptionV3 models achieve recognition rates of 99.98%, 100%, 99.99%, 91.63%, 82.42% and 81.84%, respectively on near-infrared images. For colored natural ASL images, the models achieve recognition rates of 99.91%, 99.31%, 98.67%, 91.97%, 93.37%, and 93.21%, respectively. The proposed model achieves promising results spending the least amount of time.Öğe A MobileNet-based CNN model with a novel fine-tuning mechanism for COVID-19 infection detection(Springer, 2023) Kaya, Yasin; Gursoy, ErcanCOVID-19 is a virus that causes upper respiratory tract and lung infections. The number of cases and deaths increased daily during the pandemic. Once it is vital to diagnose such a disease in a timely manner, the researchers have focused on computer-aided diagnosis systems. Chest X-rays have helped monitor various lung diseases consisting COVID-19. In this study, we proposed a deep transfer learning approach with novel fine-tuning mechanisms to classify COVID-19 from chest X-ray images. We presented one classical and two new fine-tuning mechanisms to increase the model's performance. Two publicly available databases were combined and used for the study, which included 3616 COVID-19 and 1576 normal (healthy) and 4265 pneumonia X-ray images. The models achieved average accuracy rates of 95.62%, 96.10%, and 97.61%, respectively, for 3-class cases with fivefold cross-validation. Numerical results show that the third model reduced 81.92% of the total fine-tuning operations and achieved better results. The proposed approach is quite efficient compared with other state-of-the-art methods of detecting COVID-19.Öğe A modified feature selection method based on metaheuristic algorithms for speech emotion recognition(Elsevier Sci Ltd, 2021) Yildirim, Serdar; Kaya, Yasin; Kılıç, FatihFeature selection plays an important role to build a successful speech emotion recognition system. In this paper, a feature selection approach which modifies the initial population generation stage of metaheuristic search algorithms, is proposed. The approach is evaluated on two metaheuristic search algorithms, a nondominated sorting genetic algorithm-II (NSGA-II) and Cuckoo Search in the context of speech emotion recognition using Berlin emotional speech database (EMO-DB) and Interactive Emotional Dyadic Motion Capture (IEMOCAP) database. Results show that the presented feature selection algorithms reduce the number of features significantly and are still effective for emotion classification from speech. Specifically, in speaker-dependent experiments of the EMO-DB, recognition rates of 87.66% and 87.20% are obtained using selected features by modified Cuckoo Search and NSGA-II respectively, whereas, for the IEMOCAP database, the accuracies of 69.30% and 68.32% are obtained using SVM classifier. For the speaker-independent experiments, we achieved comparable results for both databases. Specifically, recognition rates of 76.80% and 76.82% for EMO-DB and 59.37% and 59.52% for IEMOCAP using modified NSGA-II and Cuckoo Search respectively. (C) 2020 Elsevier Ltd. All rights reserved.Öğe A novel automated CNN arrhythmia classifier with memory-enhanced artificial hummingbird algorithm(Pergamon-Elsevier Science Ltd, 2023) Kiymac, Evren; Kaya, YasinCardiac arrhythmias indicate cardiovascular disease which is the leading cause of mortality worldwide, and can be detected by an electrocardiogram (ECG). Automated deep learning methods have been developed to overcome the disadvantages of manual interpretation by medical experts. The performance of the networks strongly depends on hyperparameter optimization (HPO), and this NP-hard problem is suitable for metaheuris-tic (MH) methods. In this study, a novel method is proposed for the HPO of a convolutional neural network (CNN) arrhythmia classifier using an MH algorithm. The approach utilizes our variant of an MH method, named the memory-enhanced artificial hummingbird algorithm, which has an additional memory unit that stores the evaluations of the solutions and reduces the computation time significantly. The study also proposes a novel fitness function that considers both the accuracy rate and the total number of parameters of each candidate network. Experiments were conducted on raw ECG samples from the MIT-BIH arrhythmia database. The proposed method was compared with five other MH methods and achieved equal or outperforming results, with classification accuracy reaching 98.87%. The proposed method yielded promising results in finding a high-performing solution with relatively lower complexity.Öğe A Novel Hybrid Optic Disc Detection and Fovea Localization Method Integrating Region-Based Convnet and Mathematical Approach(Springer, 2023) Dinc, Baris; Kaya, YasinOptic disc (OD), fovea, and blood vessels are major anatomical structures in a fundus image. In retinal image processing, automated detection of structural parts is crucial in analyzing image patterns and abnormalities caused by eye diseases such as glaucoma, macular edema, and diabetic retinopathy. This paper presents a robust and efficient OD detection and fovea localization method integrating region-based deep convolutional neural networks and a mathematical approach. The proposed model consists of two stages: In the first stage, we generated multiple OD region proposals and then detected the OD based on the boundary box with the highest score using Faster R-CNN. In the second stage, we calculated the localization of the fovea employing a mathematical model considering the coordinates of the predicted OD region. We used four publically available fundus image databases, ORIGA-light, DRIVE, DIARET-DB1, and MESSIDOR, to evaluate our model. The proposed hybrid model was trained with 70% images of the ORIGA-light database and tested on 30% images of ORIGA-light and all images of the other databases. To show the robustness of the model, all databases were divided into two parts, as normal and diseased samples. The presented model achieved a reliable and flexible performance in detecting the OD, with overall IoU results of 88.5, 75.5, 84.4, and 86.8% on ORIGA-light, DRIVE, DIARET-DB1, and MESSIDOR databases, respectively. Moreover, the average fovea localization results in terms of IoU were 58.1, 66.1, 71, and 73.2% on ORIGA-light, DRIVE, DIARET-DB1, and MESSIDOR databases, respectively. The experimental tests demonstrate that the proposed approach achieves promising results for both normal and diseased images.Öğe A novel method for optic disc detection in retinal images using the cuckoo search algorithm and structural similarity index(Springer, 2020) Kaya, YasinAccurate and reliable optic disk (OD) localization is vital for eye disease monitoring and fundus image analysis. This paper describes a novel technique to localize the OD in retinal images using the cuckoo search algorithm and the structural similarity index measure (SSIM). SSIM uses the average OD value to compare with candidate OD. Hence, the average OD values were calculated from randomly selected images. The average OD values and the colored retina fundus images were given as input to the proposed algorithm. The adaptive histogram equalization method was applied to ensure that the brightness and contrast values in all images were within a similar range. Next, candidate OD centers were calculated using the search algorithm and the similarity value between each candidate OD and the average OD was determined. Finally, the computed similarity was maximized by the search algorithm and the true OD center was found. The performance of the OD detection algorithm was evaluated on three public datasets. The experimental results showed that proposed method achieved comparable performance, without employing complex image pre-processing, compared with the state-of-the-art techniques. Specifically, the accuracy of 100%, 100%, and 97.5% were obtained for ONHSD, DRIONS and DRIVE datasets, respectively.Öğe A novel multi population based particle swarm optimization for feature selection(Elsevier, 2021) Kılıç, Fatih; Kaya, Yasin; Yildirim, SerdarFeature selection is an integral part of any machine learning system and the success of such systems highly depends on the relevance of features with the target domain. Feature selection can be classified as NP-Hard problem since a large number of possible solutions exists especially when the feature space is high dimensional. In addition to standard feature selection algorithms, evolutionary algorithms have also yielded promising results. In this paper, a novel multi population based particle swarm optimization (MPPSO) is proposed for feature selection. In this method, multi population start with initial solutions generated by random and Relieff based initialization and searches solution space simultaneously using both populations. 26 UCI and 3 ASU datasets are used to evaluate the performance of the method. The results show that MPPSO generally achieves better average classification accuracies than the other algorithms. Specifically, for the datasets with a large number of features, MPPSO achieves the smallest number of selected features with highest classification accuracies compared to other algorithms. (c) 2021 Elsevier B.V. All rights reserved.Öğe A novel multi-head CNN design to identify plant diseases using the fusion of RGB images(Elsevier, 2023) Kaya, Yasin; Gursoy, ErcanPlant diseases and insect pests cause a significant threat to agricultural production. Early detection and diagnosis of these diseases are critical and can reduce economic losses. The recent development of deep learning (DL) benefits various fields, such as image processing, remote sensing, medical diagnosis, and agriculture. This work proposed a novel approach based on DL for plant disease detection by fusing RGB and segmented images. A multi-headed DenseNet-based architecture was developed, considering two images as input. We evaluated the model on a public dataset, PlantVillage, consisting of 54183 images with 38 classes. The fivefold cross-validation technique achieved an average accuracy, recall, precision, and f1-score of 98.17%, 98.17%, 98.16%, and 98.12%, respectively. The proposed approach can distinguish various plant diseases with different characteristics by image fusion. The high success rate with low standard deviation proves the robustness of the model, and the model can be integrated into plant disease detection and early warning system.Öğe An overview of deep learning techniques for COVID-19 detection: methods, challenges, and future works(Springer, 2023) Gursoy, Ercan; Kaya, YasinThe World Health Organization (WHO) declared a pandemic in response to the coronavirus COVID-19 in 2020, which resulted in numerous deaths worldwide. Although the disease appears to have lost its impact, millions of people have been affected by this virus, and new infections still occur. Identifying COVID-19 requires a reverse transcription-polymerase chain reaction test (RT-PCR) or analysis of medical data. Due to the high cost and time required to scan and analyze medical data, researchers are focusing on using automated computer-aided methods. This review examines the applications of deep learning (DL) and machine learning (ML) in detecting COVID-19 using medical data such as CT scans, X-rays, cough sounds, MRIs, ultrasound, and clinical markers. First, the data preprocessing, the features used, and the current COVID-19 detection methods are divided into two subsections, and the studies are discussed. Second, the reported publicly available datasets, their characteristics, and the potential comparison materials mentioned in the literature are presented. Third, a comprehensive comparison is made by contrasting the similar and different aspects of the studies. Finally, the results, gaps, and limitations are summarized to stimulate the improvement of COVID-19 detection methods, and the study concludes by listing some future research directions for COVID-19 classification.Öğe Brain-GCN-Net: Graph-Convolutional Neural Network for brain tumor identification(Elsevier Ltd, 2024) Gürsoy, Ercan; Kaya, YasinBackground: The intersection of artificial intelligence and medical image analysis has ushered in a new era of innovation and changed the landscape of brain tumor detection and diagnosis. Correct detection and classification of brain tumors based on medical images is crucial for early diagnosis and effective treatment. Convolutional Neural Network (CNN) models are widely used for disease detection. However, they are sometimes unable to sufficiently recognize the complex features of medical images. Methods: This paper proposes a fused Deep Learning (DL) model that combines Graph Neural Networks (GNN), which recognize relational dependencies of image regions, and CNN, which captures spatial features, is proposed to improve brain tumor detection. By integrating these two architectures, our model achieves a more comprehensive representation of brain tumor images and improves classification performance. The proposed model is evaluated on a public dataset of 10847 MRI images. The results show that the proposed model outperforms the existing pre-trained models and traditional CNN architectures. Results: The fused DL model achieves 93.68% accuracy in brain tumor classification. The results indicate that the proposed model outperforms the existing pre-trained models and traditional CNN architectures. Conclusion: The numerical results suggest that the model should be further investigated for potential use in clinical trials to improve clinical decision-making. © 2024 Elsevier LtdÖğe Detection of Bundle Branch Block using Higher Order Statistics and Temporal Features(Zarka Private Univ, 2021) Kaya, YasinBundle Branch Block (BBB) beats are the most common Electrocardiogram (ECG) arrhythmias and can be indicators of significant heart disease. This study aimed to provide an effective machine-learning method for the detection of BBB beats. To this purpose, statistical and temporal features were calculated and the more valuable ones searched using feature selection algorithms. Forward search, backward elimination and genetic algorithms were used for feature selection. Three different classifiers, K-Nearest Neighbors (KNN), neural networks, and support vector machines, were used comparatively in this study. Accuracy, specificity, and sensitivity performance metrics were calculated in order to compare the results. Normal sinus rhythm (N), Right Bundle Branch Block (RBBB), and Left Bundle Branch Block (LBBB) ECG beat types were used in the study. All beats containing these three beat types in the MIT-BIH arrhythmia database were used in the experiments. All of the feature sets were obtained at a promising classification accuracy for BBB classification. The KNN classifier using backward elimination-selected features achieved the highest classification accuracy results in the study with 99.82%. The results showed the proposed approach to be successful in the detection of BBB beats.Öğe HBDFA: An intelligent nature-inspired computing with high-dimensional data analytics(Springer, 2024) Dinc, Baris; Kaya, YasinThe rapid development of data science has led to the emergence of high-dimensional datasets in machine learning. The curse of dimensionality is a significant problem caused by high-dimensional data with a small sample size. This paper proposes a novel hybrid binary dragonfly algorithm (HBDFA) in which a distance-based similarity evaluation algorithm is embedded before the dragonfly algorithm (DA) searching behavior to select the most discriminating features. The two-step feature selection mechanism of HBDFA enables the method to explore the feature space reduced by the distance-based similarity evaluation algorithm. The model was evaluated on two datasets. The first dataset contained 200 reports from 4 evenly distributed categories of Daily Mail Online: COVID-19, economy, science, and sports. The second dataset was the publicly available Spam dataset. The proposed model is compared with binary versions of four popular metaheuristic algorithms. The model achieved an accuracy rate of 96.75% by reducing 66.5% of the top 100 features determined on the first dataset. Results on the Spam dataset reveal that HBDFA gives the best classification results with over 95% accuracy. The experimental results show the superiority of HBDFA in searching high-dimensional data, improving classification results, and reducing the number of selected features.Öğe Human activity recognition from multiple sensors data using deep CNNs(Springer, 2024) Kaya, Yasin; Topuz, Elif KevserSmart devices with sensors now enable continuous measurement of activities of daily living. Accordingly, various human activity recognition (HAR) experiments have been carried out, aiming to convert the measures taken from smart devices into physical activity types. HAR can be applied in many research areas, such as health assessment, environmentally supported living systems, sports, exercise, and security systems. The HAR process can also detect activity-based anomalies in daily life for elderly people. Thus, this study focused on sensor-based activity recognition, and we developed a new 1D-CNN-based deep learning approach to detect human activities. We evaluated our model using raw accelerometer and gyroscope sensor data on three public datasets: UCI-HAPT, WISDM, and PAMAP2. Parameter optimization was employed to define the model's architecture and fine-tune the final design's hyper-parameters. We applied 6, 7, and 12 classes of activity recognition to the UCI-HAPT dataset and obtained accuracy rates of 98%, 96.9%, and 94.8%, respectively. We also achieved an accuracy rate of 97.8% and 90.27% on the WISDM and PAMAP2 datasets, respectively. Moreover, we investigated the impact of using each sensor data individually, and the results show that our model achieved better results using both sensor data concurrently.Öğe Initialization of MLP Parameters Using Deep Belief Networks for Cancer Classification(Springer Science and Business Media Deutschland GmbH, 2021) Dinç, Barış; Kaya, Yasin; Yıldırım, SerdarDeep belief network (DBN) is deep neural network structure consisting of a collection of restricted Boltzmann machine (RBM). RBM is two-layered simple neural networks which are formed by a visible and hidden layer, respectively. Each visible layer receives a lower-level feature set learned by previous RBM and passes it through to top layers turning them into a more complex feature structure. In this study, the proposed method is to feed the training parameters learned by DBN to multilayer perceptron as initial weights instead of starting them from random points. The obtained results on the bioinformatics cancer dataset show that using initial weights trained by DBN causes more successful classification results than starting from random parameters. The test accuracy using proposed method increased from 77.27 to 95.45%. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Öğe Retraction Note: A MobileNet-based CNN model with a novel fine-tuning mechanism for COVID-19 infection detection (Soft Computing, (2023), 27, 9, (5521-5535), 10.1007/s00500-022-07798-y)(Springer Science and Business Media Deutschland GmbH, 2024) Kaya, Yasin; Gürsoy, ErcanThe publisher has retracted this article in agreement with the Editor-in-Chief. The article was submitted to be part of a guest-edited issue. An investigation by the publisher found a number of articles, including this one, with a number of concerns, including but not limited to compromised editorial handling and peer review process, inappropriate or irrelevant references or not being in scope of the journal or guest-edited issue. Based on the investigation’s findings the publisher no longer has confidence in the results and conclusions of this article. The authors disagree with this retraction. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.Öğe Sinüs Kosinüs Algoritması ile Çok Katmanlı Algılayıcı Eğitimi(2021) Kıymaç, Evren; Kaya, YasinYapay sinir ağlarının (YSA) eğitilmeleri açısından, meta-sezgisel yöntemlerin geleneksel, eğim tabanlı yöntemlere göre üstünlükleri, bilimsel yazındaki çok sayıda çalışma ile gösterilmiştir. Bu çalışmanın amacı, bir YSA türü olan Çok Katmanlı Algılayıcı (ÇKA) eğitimindeki başarım açısından, bir meta-sezgisel en iyileştirme yöntemi olan Sinüs Kosinüs Algoritması (SKA) ile iki başka yöntemin (parçacık sürü en iyileştirmesi (PSEİ) ve yarasa algoritması (YA)) karşılaştırılmasıdır. Bütün yöntemlerin, Kaliforniya Üniversitesi, Irvine, Yapay Öğrenme Kaynağı üzerinden alınan beş hastalık ile ilgili veri kümesinde (göğüs kanseri, diyabet, karaciğer, omurga ve parkinson) ikili sınıflandırmadaki başarım değerlendirmeleri yapılmıştır. Deney sonuçlarında, SKA ile eğitilen ÇKA’lar %97’ye varan yüksek doğruluk oranlarına ulaşmıştır. Yöntem, YA’dan büyük çoğunlukla daha yüksek, PSEİ’den büyük çoğunlukla daha düşük başarım göstermiştir. PSEİ yöntemi genel olarak daha yüksek başarı gösterse de, SKA yöntemi de bir veri kümesinde en yüksek, kalan veri kümelerinin biri dışında hepsinde ikinci en yüksek eğitim başarımını göstermiştir. İncelenen yöntem arama uzaylarında, hem yüksek keşfetme ve yerel en iyiden kaçınma, hem de amaçlanan değerlere yüksek yakınsama hızları göstermektedir. Bu sonuçlar, SKA’nın ÇKA eğitiminde yetkin ve etkili olabildiğini ortaya koymaktadır.Öğe SUPER-COUGH: A Super Learner-based ensemble machine learning method for detecting disease on cough acoustic signals(Elsevier Sci Ltd, 2024) Topuz, Elif Kevser; Kaya, YasinSound classification has obtained considerable attention in recent years due to its wide range of applications in various fields, such as speech recognition, sound surveillance, music analysis, and environmental monitoring. Because of its success, audio classification can also be employed in medical applications. Coughing is the most common disease symptom, and cough sounds might be used to diagnose them. This research focuses on identifying observable features of cough and classifying them into positive, negative, or symptomatic categories. A novel ensemble learning model based on the super learner (SL) is proposed to diagnose the disease using cough sounds utilizing various audio features such as Frequency Distribution, Time Domain Features, Spectral Features, and Time-Frequency Features. The SL method is a cross -validated approach to stacked generalization, and it can select an optimal learner from a set of learners and improve performance by selecting and merging models using cross -validation. The proposed SL model comprises DT, RF, LR, SVM, ET, and k -NN algorithms. We use the public Coughvid dataset, and the proposed model achieves a correct classification rate for symptomatic cases, which was 90.90%, and the positive predictive value for COVID-19 cases was 84.50%. The SL3 model attains 72%, 78%, 73%, 74.4%, and 78.85% precision, recall, f1 -score, accuracy, and average AUC values, respectively. The numerical results show that the proposed model might be implemented to diagnose various other diseases that can be determined from respiratory sounds.
