12 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 10 / 12
Yayın Unsupervised textile defect detection using convolutional neural networks(Elsevier Ltd, 2021-12) Koulali, Imane; Eskil, Mustafa TanerIn this study, we propose a novel motif-based approach for unsupervised textile anomaly detection that combines the benefits of traditional convolutional neural networks with those of an unsupervised learning paradigm. It consists of five main steps: preprocessing, automatic pattern period extraction, patch extraction, features selection and anomaly detection. This proposed approach uses a new dynamic and heuristic method for feature selection which avoids the drawbacks of initialization of the number of filters (neurons) and their weights, and those of the backpropagation mechanism such as the vanishing gradients, which are common practice in the state-of-the-art methods. The design and training of the network are performed in a dynamic and input domain-based manner and, thus, no ad-hoc configurations are required. Before building the model, only the number of layers and the stride are defined. We do not initialize the weights randomly nor do we define the filter size or number of filters as conventionally done in CNN-based approaches. This reduces effort and time spent on hyper-parameter initialization and fine-tuning. Only one defect-free sample is required for training and no further labeled data is needed. The trained network is then used to detect anomalies on defective fabric samples. We demonstrate the effectiveness of our approach on the Patterned Fabrics benchmark dataset. Our algorithm yields reliable and competitive results (on recall, precision, accuracy and f1-measure) compared to state-of-the-art unsupervised approaches, in less time, with efficient training in a single epoch and a lower computational cost.Yayın A novel biometric identification system based on fingertip electrocardiogram and speech signals(Elsevier Inc., 2022-03) Güven, Gökhan; Güz, Ümit; Gürkan, HakanIn this research work, we propose a one-dimensional Convolutional Neural Network (CNN) based biometric identification system that combines speech and ECG modalities. The aim is to find an effective identification strategy while enhancing both the confidence and the performance of the system. In our first approach, we have developed a voting-based ECG and speech fusion system to improve the overall performance compared to the conventional methods. In the second approach, we have developed a robust rejection algorithm to prevent unauthorized access to the fusion system. We also presented a newly developed ECG spike and inconsistent beats removal algorithm to detect and eliminate the problems caused by portable fingertip ECG devices and patient movements. Furthermore, we have achieved a system that can work with only one authorized user by adding a Universal Background Model to our algorithm. In the first approach, the proposed fusion system achieved a 100% accuracy rate for 90 people by taking the average of 3-fold cross-validation. In the second approach, by using 90 people as genuine classes and 26 people as imposter classes, the proposed system achieved 92% accuracy in identifying genuine classes and 96% accuracy in rejecting imposter classes.Yayın Convolutional attention network for MRI-based Alzheimer's disease classification and its interpretability analysis(IEEE, 2021-09-17) Türkan, Yasemin; Tek, Faik BorayNeuroimaging techniques, such as Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET), help to identify Alzheimer's disease (AD). These techniques generate large-scale, high-dimensional, multimodal neuroimaging data, which is time-consuming and difficult to interpret and classify. Therefore, interest in deep learning approaches for the classification of 3D structural MRI brain scans has grown rapidly. In this research study, we improved the 3D VGG model proposed by Korolev et al. [2]. We increased the filters in the 3D convolutional layers and then added an attention mechanism for better classification. We compared the performance of the proposed approaches for the classification of Alzheimer's disease versus mild cognitive impairments and normal cohorts on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. We observed that both the accuracy and area under curve results improved with the proposed models. However, deep neural networks are black boxes that produce predictions that require further explanation for medical usage. We compared the 3D-data interpretation capabilities of the proposed models using four different interpretability methods: Occlusion, 3D Ultrametric Contour Map, 3D Gradient-Weighted Class Activation Mapping, and SHapley Additive explanations (SHAP). We observed that explanation results differed in different network models and data classes.Yayın Convolutional neural network (CNN) algorithm based facial emotion recognition (FER) system for FER-2013 dataset(IEEE, 2022-11-18) Ezerceli, Özay; Eskil, Mustafa TanerFacial expression recognition (FER) is the key to understanding human emotions and feelings. It is an active area of research since human thoughts can be collected, processed, and used in customer satisfaction, politics, and medical domains. Automated FER systems had been developed and have been used to recognize humans’ emotions but it has been a quite challenging problem in machine learning due to the high intra-class variation. The first models were using known methods such as Support Vector Machines (SVM), Bayes classifier, Fuzzy Techniques, Feature Selection, Artificial Neural Networks (ANN) in their models but still, some limitations affect the accuracy critically such as subjectivity, occlusion, pose, low resolution, scale, illumination variation, etc. The ability of CNN boosts FER accuracy. Deep learning algorithms have emerged as the greatest way to produce the best results in FER in recent years. Various datasets were used to train, test, and validate the models. FER2013, CK+, JAFFE and FERG are some of the most popular datasets. To improve the accuracy of FER models, one dataset or a mix of datasets has been employed. Every dataset includes limitations and issues that have an impact on the model that is trained for it. As a solution to this problem, our state-of-the-art model based on deep learning architectures, particularly convolutional neural network architectures (CNN) with supportive techniques has been implemented. The proposed model achieved 93.7% accuracy with the combination of FER2013 and CK+ datasets for FER2013.Yayın A novel similarity based unsupervised technique for training convolutional filters(IEEE, 2023-05-17) Erkoç, Tuğba; Eskil, Mustata TanerAchieving satisfactory results with Convolutional Neural Networks (CNNs) depends on how effectively the filters are trained. Conventionally, an appropriate number of filters is carefully selected, the filters are initialized with a proper initialization method and trained with backpropagation over several epochs. This training scheme requires a large labeled dataset, which is costly and time-consuming to obtain. In this study, we propose an unsupervised approach that extracts convolutional filters from a given dataset in a self-organized manner by processing the training set only once without using backpropagation training. The proposed method allows for the extraction of filters from a given dataset in the absence of labels. In contrast to previous studies, we no longer need to select the best number of filters and a suitable filter weight initialization scheme. Applying this method to the MNIST, EMNIST-Digits, Kuzushiji-MNIST, and Fashion-MNIST datasets yields high test performances of 99.19%, 99.39%, 95.03%, and 90.11%, respectively, without applying backpropagation training or using any preprocessed and augmented data.Yayın An adaptive locally connected neuron model: Focusing neuron(Elsevier B.V., 2021-01-02) Tek, Faik BorayThis paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The experiments include tests of focusing neuron networks of one or two hidden layers on synthetic and well-known image recognition data sets. The results demonstrated that the focusing neurons can move their receptive fields towards more informative inputs. In the simple two-hidden layer networks, the focusing layers outperformed the dense layers in the classification of the 2D spatial data sets. Moreover, the focusing networks performed better than the dense networks even when 70% of the weights were pruned. The tests on convolutional networks revealed that using focusing layers instead of dense layers for the classification of convolutional features may work better in some data sets.Yayın Graph convolutional network based virus-human protein-protein interaction prediction for novel viruses(Elsevier Ltd, 2022-08-13) Koca, Mehmet Burak; Nourani, Esmaeil; Abbasoğlu, Ferda; Karadeniz, İlknur; Sevilgen, Fatih ErdoğanComputational identification of human-virus protein-protein interactions (PHIs) is a worthwhile step towards understanding infection mechanisms. Analysis of the PHI networks is important for the determination of path-ogenic diseases. Prediction of these interactions is a popular problem since experimental detection of PHIs is both time-consuming and expensive. The available methods use biological features like amino acid sequences, molecular structure, or biological activities for prediction. Recent studies show that the topological properties of proteins in protein-protein interaction (PPI) networks increase the performance of the predictions. The basic network projections, random-walk-based models, or graph neural networks are used for generating topologically enriched (hybrid) protein embeddings. In this study, we propose a three-stage machine learning pipeline that generates and uses hybrid embeddings for PHI prediction. In the first stage, numerical features are extracted from the amino acid sequences using the Doc2Vec and Byte Pair Encoding method. The amino acid embeddings are used as node features while training a modified GraphSAGE model, which is an improved version of the graph convolutional network. Lastly, the hybrid protein embeddings are used for training a binary interaction classifier model that predicts whether there is an interaction between the given two proteins or not. The proposed method is evaluated with comprehensive experiments to test its functionality and compare it with the state-of-art methods. The experimental results on the benchmark dataset prove the efficiency of the proposed model by having a 3–23% better area under curve (AUC) score than its competitors.Yayın Analysis of single image super resolution models(IEEE, 2022-11-18) Köprülü, Mertali; Eskil, Mustafa TanerImage Super-Resolution (SR) is a set of image processing techniques which improve the resolution of images and videos. Deep learning approaches have made remarkable improvement in image super-resolution in recent years. This article aims and seeks to provide a comprehensive analysis on recent advances of models which has been used in image superresolution. This study has been investigated over other essential topics of current model problems, such as publicly accessible benchmark data-sets and performance evaluation measures. Finally, The study concluded these analysis by highlighting several weaknesses of existing base models as their feeding strategy and approved that the training technique which is Blind Feeding, which led several model to achieve state-of-the art.Yayın Enhancing real estate listings through image classification and enhancement: a comparative study(Multidisciplinary Digital Publishing Institute (MDPI), 2025-05-22) Küp, Eyüp Tolunay; Sözdinler, Melih; Işık, Ali Hakan; Doksanbir, Yalçın; Akpınar, GökhanWe extended real estate property listings on the online prop-tech platform. On the platform, the images were classified into the specified classes according to quality criteria. The necessary interventions were made by measuring the platform’s appropriateness level and increasing the advertisements’ visual appeal. A dataset of 3000 labeled images was utilized to compare different image classification models, including convolutional neural networks (CNNs), VGG16, residual networks (ResNets), and the LLaVA large language model (LLM). Each model’s performance and benchmark results were measured to identify the most effective method. In addition, the classification pipeline was expanded using image enhancement with contrastive unsupervised representation learning (CURL). This method assessed the impact of improved image quality on classification accuracy and the overall attractiveness of property listings. For each classification model, the performance was evaluated in binary conditions, with and without the application of CURL. The results showed that applying image enhancement with CURL enhances image quality and improves classification performance, particularly in models such as CNN and ResNet. The study results enable a better visual representation of real estate properties, resulting in higher-quality and engaging user listings. They also underscore the importance of combining advanced image processing techniques with classification models to optimize image presentation and categorization in the real estate industry. The extended platform offers information on the role of machine learning models and image enhancement methods in technology for the real estate industry. Also, an alternative solution that can be integrated into intelligent listing systems is proposed in this study to improve user experience and information accuracy. The platform proves that artificial intelligence and machine learning can be integrated for cloud-distributed services, paving the way for future innovations in the real estate sector and intelligent marketplace platforms.Yayın Object recognition with competitive convolutional neural networks(Işık Üniversitesi, 2023-06-12) Erkoç, Tuğba; Eskil, M. Taner; Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Doktora Programı; Işık University, School of Graduate Studies, Ph.D. in Computer EngineeringIn recent years, Artificial Intelligence (AI) has achieved impressive results, often surpassing human capabilities in tasks involving language comprehension and visual recognition. Among these, computer vision has experienced remarkable progress, largely due to the introduction of Convolutional Neural Networks (CNNs). CNNs are inspired by the hierarchical structure of the visual cortex and are designed to detect patterns, objects, and complex relationships within visual data. One key advantage is their ability to learn directly from pixel values without the need for domain expertise, which has contributed to their popularity. These networks are trained using supervised backpropagation, a process that calculates gradients of the network’s parameters (weights and biases) with respect to the loss function. While backpropagation enables impressive performance with CNNs, it also presents certain drawbacks. One such drawback is the requirement for large amounts of labeled data. When the available data samples are limited, the gradients estimated from this limited information may not accurately capture the overall data behavior, leading to suboptimal parameter updates. However, obtaining a sufficient quantity of labeled data poses a challenge. Another drawback is the requirement of careful configuration of hyperparameters, including the number of neurons, learning rate, and network architecture. Finding optimal values for these hyperparameters can be a time-consuming process. Furthermore, as the complexity of the task increases, the network architecture becomes deeper and more complex. To effectively train the shallow layers of the network, one must increase the number of epochs and experiment with solutions to prevent vanishing gradients. Complex problems often require a greater number of epochs to learn the intricate patterns and features present in the data. It’s important to note that while CNNs aim to mimic the structure of the visual cortex, the brain’s learning mechanism does not necessarily involve back-propagation. Although CNNs incorporate the layered architecture of the visual cortex, the reliance on backpropagation introduces an artificial learning procedure that may not align with the brain’s actual learning process. Therefore, it is crucial to explore alternative learning paradigms that do not rely on backpropagation. In this dissertation study, a unique approach to unsupervised training for CNNs is explored, setting it apart from previous research. Unlike other unsupervised methods, the proposed approach eliminates the reliance on backpropagation for training the filters. Instead, we introduce a filter extraction algorithm capable of extracting dataset features by processing images only once, without requiring data labels or backward error updates. This approach operates on individual convolutional layers, gradually constructing them by discovering filters. To evaluate the effectiveness of this backpropagation-free algorithm, we design four distinct CNN architectures and conduct experiments. The results demonstrate the promising performance of training without backpropagation, achieving impressive classification accuracies on different datasets. Notably, these outcomes are attained using a single network setup without any data augmentation. Additionally, our study reveals that the proposed algorithm eliminates the need to predefine the number of filters per convolutional layer, as the algorithm automatically determines this value. Furthermore, we demonstrate that filter initialization from a random distribution is unnecessary when backpropagation is not employed during training.
