Sürdürülebilir Kalkınma Amaçları

• 2

• MakaleAçık Erişim2024/r/gumushane/11925
  A study on effective data preprocessing and augmentation method in diabetic retinopathy classification using pre-trained deep learning approaches

  İncir, Ramazan; Bozkurt, Ferhat

  High glucose levels in the blood not only damage different tissues and organs of the body, but also cause adverse effects on the eye. This condition is called diabetic retinopathy (DR). DR can cause blurred vision, darkening of the field of vision, and severe vision loss. The number of people infected with the disease is increasing in our country and worldwide. The time-consuming physician check-ups and the presence of small lesions indicate the need to develop diagnostic systems. Deep learning-based applications have become the trend for diagnosing and grading diseases from images. This study aims to create a meaningful and sufficient dataset using effective data preprocessing and affine transformation techniques in diabetic retinopathy classification. In this study, classification was performed using seven different pre-trained deep learning architectures. An experimental study of each technique was performed on the EyePACS dataset. An overfitting problem was encountered in the experimental results with the original data set. Thus, data preprocessing and data augmentation processes were carried out in order to eliminate overfitting by considering the imbalance between classes in the dataset. The classification performance obtained from each architecture was observed according to performance metrics of precision, recall, F1 Score, accuracy, and loss. In this study, the best performance was achieved with 97.65% test accuracy with the proposed EfficientNetV2-M network model.

  • 
  İncele
• MakaleAçık Erişim2024/r/gumushane/11711
  Different gait combinations based on multi-modal deep CNN architectures

  Yaprak, Büşranur; Gedikli, Eyüp

  Gait recognition is the process of identifying a person from a distance based on their walking patterns. However, the recognition rate drops significantly under cross-view angle and appearance-based variations. In this study, the effectiveness of the most well-known gait representations in solving this problem is investigated based on deep learning. For this purpose, a comprehensive performance evaluation is performed by combining different modalities, including silhouettes, optical flows, and concatenated image of the Gait Energy Image (GEI) head and leg region, with GEI itself. This evaluation is carried out across different multimodal deep convolutional neural network (CNN) architectures, namely fine-tuned EfficientNet-B0, MobileNet-V1, and ConvNeXt-base models. These models are trained separately on GEIs, silhouettes, optical flows, and concatenated image of GEI head and leg regions, and then extracted GEI features are fused in pairs with other extracted modality features to find the most effective gait combination. Experimental results on the two different datasets CASIA-B and Outdoor-Gait show that the concatenated image of GEI head and leg regions significantly increased the recognition rate of the networks compared to other modalities. Moreover, this modality demonstrates greater robustness under varied carrying (BG) and clothing (CL) conditions compared to optical flows (OF) and silhouettes (SF). Codes available at https://github.com/busrakckugurlu/Different-gait-combinations-based-on-multi-modal-deep-CNN-architectures.git

  İncele
• MakaleYayıncıda açık erişim2023/r/gumushane/12018
  MediNet: transfer learning approach with MediNet medical visual database

  Reis, Hatice Catal; Turk, Veysel; Khoshelham, Kourosh; Kaya, Serhat

  The rapid development of machine learning has increased interest in the use of deep learning methods in medical research. Deep learning in the medical field is used in disease detection and classification problems in the clinical decision-making process. Large amounts of labeled datasets are often required to train deep neural networks; however, in the medical field, the lack of a sufficient number of images in datasets and the difficulties encountered during data collection are among the main problems. In this study, we propose MediNet, a new 10-class visual dataset consisting of Rontgen (X-ray), Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Ultrasound, and Histopathological images such as calcaneal normal, calcaneal tumor, colon benign colon adenocarcinoma, brain normal, brain tumor, breast benign, breast malignant, chest normal, chest pneumonia. AlexNet, VGG19-BN, Inception V3, DenseNet 121, ResNet 101, EfficientNet B0, Nested-LSTM + CNN, and proposed RdiNet deep learning algorithms are used in the transfer learning for pre-training and classification application. Transfer learning aims to apply previously learned knowledge in a new task. Seven algorithms were trained with the MediNet dataset, and the models obtained from these algorithms, namely feature vectors, were recorded. Pre-training models were used for classification studies on chest X-ray images, diabetic retinopathy, and Covid-19 datasets with the transfer learning technique. In performance measurement, an accuracy of 94.84% was obtained in the traditional classification study for the InceptionV3 model in the classification study performed on the Chest X-Ray Images dataset, and the accuracy was increased 98.71% after the transfer learning technique was applied. In the Covid-19 dataset, the classification success of the DenseNet121 model before pre-trained was 88%, while the performance after the transfer application with MediNet was 92%. In the Diabetic retinopathy dataset, the classification success of the Nested-LSTM + CNN model before pre-trained was 79.35%, while the classification success was 81.52% after the transfer application with MediNet. The comparison of results obtained from experimental studies observed that the proposed method produced more successful results. Graphical abstract: [Figure not available: see fulltext.]

  • 
  İncele
• MakaleYalnız künye2022/r/gumushane/11485
  Robust copy-move detection in digital audio forensics based on pitch and modified discrete cosine transform

  Ustubioglu, Beste; Küçükuğurlu, Büşranur; Ulutas, Guzin

  Copy-move forgery is one of the most widely used methods in the field of audio forensic because it is difficult to detect and convenient to apply. However, post-processing operations applied to forged speech to hide traces of forgery make detection of forensic more difficult. In this study, we propose a robust method for detection and localization of the audio copy-move forgery using modified discrete cosine transform (MDCT). For this purpose, we first divide the speech recording into voiced and unvoiced parts by extracting a pitch sequence from the speech recording. After the determination of voiced parts, we extract MDCT coefficients from them and take the mean of the transpose of the coefficient matrix as the feature. These MDCT features are very robust against commonly used post-processing operations (especially audio compressing). Euclidean distance (ED) is applied to compute the similarities between the features. The voiced parts, which give minimum ED are determined as copy-move audio parts. Also, two separate databases (Pitch-based and Voice Activity Detection (VAD-based) are created during the work to evaluate the performance of the proposed method because there is no common database in the field of audio forensic in the literature. Experiment results show that the proposed method gives better results for detection and localization of audio copy-move forgery on different databases compared to other studies in the literature. The proposed method is also robust against common post-processing operations such as noise addition, filtering operation, and especially compression operation.

  İncele