Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
9 results
Search Results
Publication Metadata only SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes(Institute of Electrical and Electronics Engineers Inc., 2020) Jeny, Afsana Ahsan; Sakib, Abu Noman Md; Junayed, Masum Shah; Lima, Khadija Akter; Ahmed, Ikhtiar; Islam, Md Baharul; Jeny, Afsana Ahsan, Department of CSE, Daffodil International University, Dhaka, Bangladesh; Sakib, Abu Noman Md, Department of Cse, Khulna University of Engineering and Technology, Khulna, Bangladesh; Junayed, Masum Shah, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Lima, Khadija Akter, Department of CSE, Daffodil International University, Dhaka, Bangladesh; Ahmed, Ikhtiar, Department of CSE, Daffodil International University, Dhaka, Bangladesh; Islam, Md Baharul, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey, American University of Malta, Cospicua, MaltaSkin Cancer is one of the most common types of cancer. A solution for this globally recognized health problem is much required. Machine Learning techniques have brought revolutionary changes in the field of biomedical researches. Previously, It took a significant amount of time and much effort in detecting skin cancers. In recent years, many works have been done with Deep Learning which made the process a lot faster and much more accurate. In this paper, We have proposed a novel Convolutional Neural Networks (CNN) based approach that can classify four different types of Skin Cancer. We have developed our model SkNet consisting of 19 convolution layers. In previous works, the highest accuracy gained on 1000 images was 80.52%. Our proposed model exceeded that previous performance and achieved an accuracy of 95.26% on a dataset of 4800 images which is the highest acquired accuracy. © 2021 Elsevier B.V., All rights reserved.Publication Metadata only Deep Covariance Feature and CNN-based End-to-End Masked Face Recognition(Institute of Electrical and Electronics Engineers Inc., 2021) Junayed, Masum Shah; Sadeghzadeh, Arezoo; Islam, Md Baharul; Struc, V.; Ivanovska, M.; Junayed, Masum Shah, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Sadeghzadeh, Arezoo, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Islam, Md Baharul, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey, College of Data Science and Engineering, American University of Malta, Cospicua, MaltaWith the emergence of the global epidemic of COVID-19, face recognition systems have achieved much attention as contactless identity verification methods. However, covering a considerable part of the face by the mask poses severe challenges for conventional face recognition systems. This paper proposes an automated Masked Face Recognition (MFR) system based on the combination of a mask occlusion discarding technique and a deep-learning model. Initially, a pre-processing step is carried out in which the images pass three filters. Then, a Convolutional Neural Network (CNN) model is proposed to extract the features from unoccluded regions of the faces (i.e., eyes and forehead). These feature maps are employed to obtain covariance-based features. Two extra layers, i.e., Bitmap and Eigenvalue, are designed to reduce the dimension and concatenate these covariance feature matrices. The deep covariance features are quantized to codebooks combined based on Bag-of-Features (BoF) paradigm. Finally, a global histogram is created based on these codebooks and utilized for training an SVM classifier. The proposed method is trained and evaluated on Real-World-Masked-Face-Recognition-Dataset (RMFRD) and Simulated-Masked-Face-Recognition-Dataset (SMFRD) achieves an accuracy of 95.07% and 92.32 %, respectively, showing its competitive performance compared to the state-of-the-art. Experimental results prove that our system has high robustness against noisy data and illumination variations. © 2025 Elsevier B.V., All rights reserved.Publication Metadata only Stereoscopic Video Quality Assessment Using Modified Parallax Attention Module(Springer Science and Business Media Deutschland GmbH, 2022) Imani, Hassan; Zaim, Selim; Islam, Md Baharul; Junayed, Masum Shah; Durakbasa, N.M.; Gençyılmaz, M.G.; Imani, Hassan, Computer Vision Lab, Bahçeşehir Üniversitesi, Istanbul, Turkey; Zaim, Selim, Faculty of Engineering and Natural Sciences, Bahçeşehir Üniversitesi, Istanbul, Turkey; Islam, Md Baharul, Computer Vision Lab, Bahçeşehir Üniversitesi, Istanbul, Turkey; Junayed, Masum Shah, Computer Vision Lab, Bahçeşehir Üniversitesi, Istanbul, TurkeyDeep learning techniques are utilized for most computer vision tasks. Especially, Convolutional Neural Networks (CNNs) have shown great performance in detection and classification tasks. Recently, in the field of Stereoscopic Video Quality Assessment (SVQA), 3D CNNs are used to extract spatial and temporal features from stereoscopic videos, but the importance of the disparity information which is very important did not consider well. Most of the recently proposed deep learning-based methods mostly used cost volume methods to produce the stereo correspondence for large disparities. Because the disparities can differ considerably for stereo cameras with different configurations, recently the Parallax Attention Mechanism (PAM) is proposed that captures the stereo correspondence disregarding the disparity changes. In this paper, we propose a new SVQA model using a base 3D CNN-based network, and a modified PAM-based left and right feature fusion model. Firstly, we use 3D CNNs and residual blocks to extract features from the left and right views of a stereo video patch. Then, we modify the PAM model to fuse the left and right features with considering the disparity information, and using some fully connected layers, we calculate the quality score of a stereoscopic video. We divided the input videos into cube patches for data augmentation and remove some cubes that confuse our model from the training dataset. Two standard stereoscopic video quality assessment benchmarks of LFOVIAS3DPh2 and NAMA3DS1-COSPAD1 are used to train and test our model. Experimental results indicate that our proposed model is very competitive with the state-of-the-art methods in the NAMA3DS1-COSPAD1 dataset, and it is the state-of-the-art method in the LFOVIAS3DPh2 dataset. © 2022 Elsevier B.V., All rights reserved.Publication Metadata only Performance Assessment of Physiotherapy and Rehabilitation Exercises with Deep Learning, Derin Öǧrenme ile Fizyoterapi ve Rehabilitasyon Egzersizleri için Performans Deǧerlendirme(Institute of Electrical and Electronics Engineers Inc., 2022) Aytutuldu, Ilhan; Aydin, Tarkan; Aytutuldu, Ilhan, Bilgisayar Mühendisliǧi Bölümü, Gebze Teknik Üniversitesi, Gebze, Turkey; Aydin, Tarkan, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyPhysiotherapy and rehabilitation process is critical for patients in postoperative recovery or the treatment of a wide variety of musculoskeletal disorders. However, providing access to a clinician for each rehabilitation session is a heavy burden and high cost to individuals. Also, it is very important to remotely check whether the exercises are performed correctly, especially during periods of lock-down due to the current pandemic, to provide motivation in the rehabilitation progress of the patients and to ensure that the recommended exercises contribute to the treatment. In this study, deep learning-based performance assessment of rehabilitation exercises has been proposed by using RGB videos obtained with low cost off-the-shelf cameras instead of high-cost, hard-to-reach depth cameras or wearable contact sensors. The proposed deep learning (DL) network models, PtConvNet, PtHybNet and PtBiLSTM, utilize three dimensional (3D) skeletal joint positions of patients extracted from exercise videos. Performance scores given by the physiotherapists have been used as the ground-truth in the training of the framework. We showed that the performance estimates of the learning models reliably follow the actual values and that the DL models confirm the ability to evaluate rehabilitation exercises. © 2022 Elsevier B.V., All rights reserved.Publication Metadata only Retinal Image Restoration using Transformer and Cycle-Consistent Generative Adversarial Network(Institute of Electrical and Electronics Engineers Inc., 2022) Alimanov, Alnur; Islam, Md Baharul; Alimanov, Alnur, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Islam, Md Baharul, Bahçeşehir Üniversitesi, Istanbul, TurkeyMedical imaging plays a significant role in detecting and treating various diseases. However, these images often happen to be of too poor quality, leading to decreased efficiency, extra expenses, and even incorrect diagnoses. Therefore, we propose a retinal image enhancement method using a vision transformer and convolutional neural network. It builds a cycle-consistent generative adversarial network that relies on unpaired datasets. It consists of two generators that translate images from one domain to another (e.g., low- to high-quality and vice versa), playing an adversarial game with two discriminators. Generators produce indistinguishable images for discriminators that predict the original images from generated ones. Generators are a combination of vision transformer (ViT) encoder and con-volutional neural network (CNN) decoder. Discriminators include traditional CNN encoders. The resulting improved images have been tested quantitatively using such evaluation metrics as peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and qualitatively, i.e., vessel segmentation. The proposed method successfully reduces the adverse effects of blurring, noise, illumination disturbances, and color distortions while signifi-cantly preserving structural and color information. Experimental results show the superiority of the proposed method. Our testing PSNR is 31.138 dB for the first and 27.798 dB for the second dataset. Testing SSIM is 0.919 and 0.904, respectively. The code is available at https://github.com/AAleka/Transformer-Cycle-GAN © 2023 Elsevier B.V., All rights reserved.Publication Metadata only Audio Speech Signal Analysis for Early Autism Spectrum Disorder Detection(Institute of Electrical and Electronics Engineers Inc., 2023) Jaby, Assil; Islam, Md Baharul; Jaby, Assil, Computer Vision Lab, Bahçeşehir Üniversitesi, Istanbul, Turkey; Islam, Md Baharul, Bahçeşehir Üniversitesi, Istanbul, Turkey, Florida Gulf Coast University, Fort Myers, United StatesAutism Spectrum Disorder (ASD) is a neurodevel-opmental disorder that affects social interaction, communication, and behavior. Recent studies have shown that vocal and auditory features can be used to identify people with ASD. However, existing approaches are limited by their subjective nature, reliance on expert interpretation, and the laborious process of data gathering. This study presents a deep learning-based technique for ASD detection, which utilizes a hybrid vision transformer and convolutional neural network (CNN) architecture. The Swin transformer extracts high-level features and attention maps from audio samples, which the CNN uses as input. We trained and evaluated our model using audio samples from both ASD and typically developing (TD) children, achieving competitive accuracy in distinguishing between the two groups. Our findings suggest that the proposed method has the potential to complement existing diagnostic tools and improve early ASD detection in children. Moreover, our results indicate that deep learning-based techniques and standard diagnostic tools can offer a reliable and objective approach to detecting ASD. The suggested model could be implemented in clinical settings as a screening tool to aid in the early diagnosis of ASD. © 2023 Elsevier B.V., All rights reserved.Publication Metadata only Anterior Segment Eye Abnormality Detection(Association for Computing Machinery, 2023) Corbaci, Tolga; Corbaci, Tolga, School of Medicine, Bahçeşehir Üniversitesi, Istanbul, TurkeyVision is the most critical sense helping us to understand the world around us. Ophthalmology is an area of medicine that deals with the eye and vision. In many remote areas, people do not have access to ophthalmologists, and many go blind for preventable reasons. Awareness about eye health and early diagnosis is essential in eye health to prevent blindness. An artificial intelligence (AI) algorithm that can quickly detect eye disease is valuable and necessary. Anterior segment eye images are essential and easily obtained without additional equipment. In this study, I aimed to build an artificial intelligence algorithm to detect eye diseases from mobile photographs. I extracted and combined anterior segment eye photos from various publicly available datasets and labeled 3938 images as Normal (healthy) and 1094 images as Abnormal (unhealthy). I increased the data diversity by augmenting it with random flips and rotations: and then prepared it for AI training. I re-trained the algorithms trained in ImageNet Visual Recognition Challenge with the transfer learning method. I compared custom and pre-trained models. After evaluating the performance of the models with the test set, 98% accuracy and 97% F1 score were obtained with the Inception-ResNetV2 model. © 2023 Elsevier B.V., All rights reserved.Publication Metadata only Diagnosis of Dyslexia using 2D EEG Feature Map and Convolutional Neural Network(Institute of Electrical and Electronics Engineers Inc., 2024) Cura, Ozlem Karabiber; Yaşar Çiklaçandir, Fatma Günseli; Eroğlu, Günet; Cura, Ozlem Karabiber, Department of Biomedical Engineering, İzmir Kâtip Çelebi Üniversitesi, Izmir, Turkey; Yaşar Çiklaçandir, Fatma Günseli, Department of Computer Engineering, İzmir Kâtip Çelebi Üniversitesi, Izmir, Turkey; Eroğlu, Günet, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyNeuroscience has been significantly impacted by developments in computational techniques and machine learning algorithms, especially in the early diagnosis and classification of neurological illnesses. This study has been conducted to classify EEG data obtained from theta, alpha, beta1, beta2, and gamma bands to diagnose dyslexic and normal children. In addition to examining the individual classification performances of the data taken from these five bands, the classification success of the set created by combining the data from all bands has also been examined. The well-known models such as AlexNet, GoogleNet, and ResNet18 are compared with the revised version of ResNet18 developed in the study and the classification of handcrafted features with support vector machine (SVM). When the models’ performances are compared, it is seen that Revised ResNet18 gives results with the highest accuracy value in all bands except the Gamma band. Additionally, it has been observed that the classification success of handcrafted features is lower than the success of CNN-based models. © 2024 Elsevier B.V., All rights reserved.Publication Metadata only Improving the Robustness of CNN-Based Human Detection in Multiple Raw UWB Radar Datasets(Institute of Electrical and Electronics Engineers Inc., 2024) Yousefi, Mohammad; Dogan, Emine Berjin; Gelal, Ece; Karamzadeh, Saeid; Yousefi, Mohammad, Department of Artificial Intelligence Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Dogan, Emine Berjin, Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Gelal, Ece, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Karamzadeh, Saeid, Silicon Austria Labs GmbH, Graz, Austria, Bahçeşehir Üniversitesi, Istanbul, TurkeyUltra-wideband (UWB) radar technology has gained significant attention for human detection, vital sign monitoring, and activity recognition applications. In this study, a robust deep-learning model capable of detecting human presence in different environments is developed. The model uses only the raw data obtained directly from the radar without preprocessing. The model is trained and tested on different datasets collected via the UWB radar. Transfer learning has been applied to fine-tune the model on datasets to improve the performance and generalization of the model. This study demonstrates the effectiveness of transfer learning in adapting UWB radar-based human detection models to different environments. © 2025 Elsevier B.V., All rights reserved.