Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
12 results
Search Results
Article GraphUnet-SS: A Novel Deep Learning Model for Protein Secondary Structure Prediction Based on U-Net Architecture(Elsevier Ltd, 2026-04) Aydin, Zafer; Görmez, Yasin; Sabzekar, MostafaArticle Frequency-Based Deep Occlusion Awareness Instance Segmentation(MDPI, 2026-02-26) Guzel, Yasin; Aydin, Zafer; Talu, Muhammed FatihOne major challenge faced by deep learning-based methods that detect target objects in the form of bounding boxes is object occlusion. High degrees of occlusion significantly diminish the accuracy of instance segmentation. Nonetheless, complex-valued Fourier descriptors can robustly represent object boundaries using minimal information. In this study, the impact of integrating Fourier descriptors-renowned for their strong representational capacity-with deep network models (UNet) that exhibit high generalization performance on instance segmentation accuracy was investigated. Within the scope of the research, nine network models were designed based on different strategies for utilizing frequency components. These variants fall into four strategy families: (i) UNet-style spectrum regression on fixed low-frequency windows (FUNet), (ii) magnitude-guided frequency selection/ROI construction (FUNet-Thr, FUNet-BBox), (iii) sequence models over tokenized FFT coefficients (BiLSTM Patch/Sorted), and (iv) encoder-only spectrum predictors with different depth/capacity (EncoderFFT1/2). To fairly evaluate the models' performance in segmenting objects subjected to disruptive factors (e.g., occlusion, blurring, noise), a specialized synthetic dataset was prepared. The task is formulated as single-target (single-instance), single-class segmentation. This dataset, automatically generated according to initial parameter values, contains images of objects moving at various speeds within a single frame. Among these models, the one termed FUNet, which relies on partial matching of central frequency components, achieved the highest segmentation accuracy despite the disruptive effects. Under the challenging Dataset 8 setting, the proposed FUNet achieved the highest overlap-based performance (Dice = 0.9329, IoU = 0.8842) among Attention U-Net, U-Net, and FourierNet, with statistically significant gains confirmed by paired per-image tests.Article BrAIn: A Comprehensive Artificial Intelligence-Based Morphology Analysis System for Brain Organoids and Neuroscience(Wiley, 2026-03-12) Polatli, Elifsu; Guner, Huseyin; Bastanlar, Yalin; Karakulah, Gokhan; Evranos, Ali Eren; Kahveci, Burak; Guven, SinanHuman-induced pluripotent stem cells (iPSCs) offer transformative potential for biomedical research, with iPSC-derived organoids providing more physiologically relevant models than traditional 2D cell cultures. Among these, brain organoids (BO) are particularly valuable for drug screening, disease modeling, and investigations into molecular pathways. Accurate representation of brain morphology is critical, as more complex organoid structures better mimic the human brain. Deep learning (DL) and machine learning (ML) approaches have become integral to analyzing organoid morphology, yet tools for comprehensive, time-resolved assessments are scarce. Here, we introduce BrAIn, a DL-based application for analyzing the developmental progression of BOs. BrAIn tracks their evolution from embryoid bodies (EBs) and quantifies parameters including area, Feret diameter, perimeter, roundness, and circularity. It also classifies budding and abnormal morphologies of 3D organoids and detects monolayer neural rosette structures, key features of neuronal differentiation. Designed with accessibility in mind, BrAIn provides a no-code interface, enabling researchers of all technical backgrounds to conduct advanced morphological analyses with ease. Our study demonstrates the application of BrAIn to evaluate the effects of different growth conditions-static, orbital shaker, and microfluidic chip-based-on BO development. Orbital shaker cultures resulted in the largest organoids, while chip-based systems achieved more homogeneous growth. Both conditions produced organoids with greater morphological complexity compared to static culture. BrAIn emerges as a robust, user-friendly tool to quantify BO development and explore how versatile growth conditions influence their morphology and maturation.Article Citation - WoS: 28Citation - Scopus: 31Super Resolution Convolutional Neural Network Based Pre-Processing for Automatic Polyp Detection in Colonoscopy Images(Pergamon-Elsevier Science Ltd, 2021-03) Tas, Merve; Yilmaz, BulentColonoscopy is the most common methodology used to detect polyps on the colon surface. Increasing the image resolution has the potential to improve the automatic colonoscopy based diagnosis and polyp detection and localization. In this study, we proposed a pre-processing approach that uses convolutional neural network based super resolution method (SRCNN) to increase the resolution of the training colonoscopy images before the localization of polyps. We also investigated the use of CNN based models such as the Single Shot MultiBox Detector (SSD) and Faster Regional CNN (RCNN) for real-time polyp detection and localization. Our results showed that using SRCNN method before the training process provides better results in terms of accuracy in both models compared to the low-resolution cases. Furthermore, we reached an F2 score of 0.945 for the correct localization of colon polyps using Faster RCNN with ResNet-101 feature extractor.Article Citation - WoS: 4Citation - Scopus: 10Probabilistic Assessment of Wind Power Plant Energy Potential Through a Copula-Deep Learning Approach in Decision Trees(Cell Press, 2024-04) Sahin, Kubra Nur; Sutcu, MuhammedIn the face of environmental degradation and diminished energy resources, there is an urgent need for clean, affordable, and sustainable energy solutions, which highlights the importance of wind energy. In the global transition to renewable energy sources, wind power has emerged as a key player that is in line with the Paris Agreement, the Net Zero Target by 2050, and the UN 2030 Goals, especially SDG-7. It is critical to consider the variable and intermittent nature of wind to efficiently harness wind energy and evaluate its potential. Nonetheless, since wind energy is inherently variable and intermittent, a comprehensive assessment of a prospective site's wind power generation potential is required. This analysis is crucial for stakeholders and policymakers to make well-informed decisions because it helps them assess financial risks and choose the best locations for wind power plant installations. In this study, we introduce a framework based on Copula-Deep Learning within the context of decision trees. The main objective is to enhance the assessment of the wind power potential of a site by exploiting the intricate and non-linear dependencies among meteorological variables through the fusion of copulas and deep learning techniques. An empirical study was carried out using wind power plant data from Turkey. This dataset includes hourly power output measurements as well as comprehensive meteorological data for 2021. The results show that acknowledging and addressing the non-independence of variables through innovative frameworks like the Copula-LSTM based decision tree approach can significantly improve the accuracy and reliability of wind power plant potential assessment and analysis in other real-world data scenarios. The implications of this research extend beyond wind energy to inform decision-making processes critical for a sustainable energy future.Article Citation - WoS: 4Citation - Scopus: 7IGPRED-Multitask: A Deep Learning Model to Predict Protein Secondary Structure, Torsion Angles and Solvent Accessibility(IEEE Computer Soc, 2023-03-01) Gormez, Yasin; Aydin, ZaferProtein secondary structure, solvent accessibility and torsion angle predictions are preliminary steps to predict 3D structure of a protein. Deep learning approaches have achieved significant improvements in predicting various features of protein structure. In this study, IGPRED-Multitask, a deep learning model with multi task learning architecture based on deep inception network, graph convolutional network and a bidirectional long short-term memory is proposed. Moreover, hyper-parameters of the model are fine-tuned using Bayesian optimization, which is faster and more effective than grid search. The same benchmark test data sets as in the OPUS-TASS paper including TEST2016, TEST2018, CASP12, CASP13, CASPFM, HARD68, CAMEO93, CAMEO93_HARD, as well as the train and validation sets, are used for fair comparison with the literature. Statistically significant improvements are observed in secondary structure prediction on 4 datasets, in phi angle prediction on 2 datasets and in psi angel prediction on 3 datasets compared to the state-of-the-art methods. For solvent accessibility prediction, TEST2016 and TEST2018 datasets are used only to assess the performance of the proposed model.Article Citation - WoS: 6Citation - Scopus: 11Deep Learning Approaches for Vehicle Type Classification With 3D Magnetic Sensor(Elsevier, 2022-11) Kolukisa, Burak; Yildirim, Veli Can; Elmas, Bahadir; Ayyildiz, Cem; Gungor, Vehbi CagriIn the Intelligent Transportation Systems, it is crucial to determine the type of vehicles to improve traffic management, increase human comfort, and enable future development of transport infrastructures. This paper presents a deep learning-based vehicle type classification approach for intermediate road traffic. Specifically, a low-cost, easy-to-install, battery-operated 3-D traffic sensor is designed and developed. In addition, a total of 376 vehicle samples are collected, and the vehicles are identified into three different classes according to their structures: light, medium, and heavy. Firstly, an oversampling method is applied to increase the number of samples in the training set. Then, the signals are converted into time series for LSTM and GRU and 2-D images for transfer learning models. Finally, soft voting is proposed using the LSTM, GRU, and VGG16, which is the best transfer learning method for vehicle type classification. The developed system is portable, power-limited, battery-operated, and reliable. Comparative performance results show that the soft voting ensemble method using a deep learning classifier improves the accuracy and f-measure performances by 92.92% and 93.42%, respectively. Additionally, the battery lifetime of the developed magnetic sensor node can work for up to 2 years.Article Citation - WoS: 6Citation - Scopus: 9Combining N-Grams and Graph Convolution for Text Classification(Elsevier, 2025-05) Sen, Tarik Uveys; Yakit, Mehmet Can; Gumus, Mehmet Semih; Abar, Orhan; Bakal, GokhanText classification, a cornerstone of natural language processing (NLP), finds applications in diverse areas, from sentiment analysis to topic categorization. While deep learning models have recently dominated the field, traditional n-gram-driven approaches often struggle to achieve comparable performance, particularly on large datasets. This gap largely stems from deep learning' s superior ability to capture contextual information through word embeddings. This paper explores a novel approach to leverage the often-overlooked power of n-gram features for enriching word representations and boosting text classification accuracy. We propose a method that transforms textual data into graph structures, utilizing discriminative n-gram series to establish long-range relationships between words. By training a graph convolution network on these graphs, we derive contextually enhanced word embeddings that encapsulate dependencies extending beyond local contexts. Our experiments demonstrate that integrating these enriched embeddings into an long-short term memory (LSTM) model for text classification leads to around 2% improvements in classification performance across diverse datasets. This achievement highlights the synergy of combining traditional n-gram features with graph-based deep learning techniques for building more powerful text classifiers.Article Citation - Scopus: 10Building a Challenging Medical Dataset for Comparative Evaluation of Classifier Capabilities(Elsevier Ltd, 2024-08) Bozkurt, Berat; Coskun, Kerem; Bakal, GokhanSince the 2000s, digitalization has been a crucial transformation in our lives. Nevertheless, digitalization brings a bulk of unstructured textual data to be processed, including articles, clinical records, web pages, and shared social media posts. As a critical analysis, the classification task classifies the given textual entities into correct categories. Categorizing documents from different domains is straightforward since the instances are unlikely to contain similar contexts. However, document classification in a single domain is more complicated due to sharing the same context. Thus, we aim to classify medical articles about four common cancer types (Leukemia, Non-Hodgkin Lymphoma, Bladder Cancer, and Thyroid Cancer) by constructing machine learning and deep learning models. We used 383,914 medical articles about four common cancer types collected by the PubMed API. To build classification models, we split the dataset into 70% as training, 20% as testing, and 10% as validation. We built widely used machine-learning (Logistic Regression, XGBoost, CatBoost, and Random Forest Classifiers) and modern deep-learning (convolutional neural networks - CNN, long short-term memory - LSTM, and gated recurrent unit - GRU) models. We computed the average classification performances (precision, recall, F-score) to evaluate the models over ten distinct dataset splits. The best-performing deep learning model(s) yielded a superior F1 score of 98%. However, traditional machine learning models also achieved reasonably high F1 scores, 95% for the worst-performing case. Ultimately, we constructed multiple models to classify articles, which compose a hard-to-classify dataset in the medical domain. © 2024 Elsevier B.V., All rights reserved.Article Citation - WoS: 24Citation - Scopus: 39A Review of On-Device Machine Learning for IoT: An Energy Perspective(Elsevier, 2024-02) Tekin, Nazli; Aris, Ahmet; Acar, Abbas; Uluagac, Selcuk; Gungor, Vehbi CagriRecently, there has been a substantial interest in on-device Machine Learning (ML) models to provide intelligence for the Internet of Things (IoT) applications such as image classification, human activity recognition, and anomaly detection. Traditionally, ML models are deployed in the cloud or centralized servers to take advantage of their abundant computational resources. However, sharing data with the cloud and third parties degrades privacy and may cause propagation delay in the network due to a large amount of transmitted data impacting the performance of real-time applications. To this end, deploying ML models on-device (i.e., on IoT devices), in which data does not need to be transmitted, becomes imperative. However, deploying and running ML models on already resource-constrained IoT devices is challenging and requires intense energy consumption. Numerous works have been proposed in the literature to address this issue. Although there are considerable works that discuss energy-aware ML approaches for on-device implementation, there remains a gap in the literature on a comprehensive review of this subject. In this paper, we provide a review of existing studies focusing on-device ML models for IoT applications in terms of energy consumption. One of the key contributions of this study is to introduce a taxonomy to define approaches for employing energy-aware on-device ML models on IoT devices in the literature. Based on our review in this paper, our key findings are provided and the open issues that can be investigated further by other researchers are discussed. We believe that this study will be a reference for practitioners and researchers who want to employ energy-aware on-device ML models for IoT applications.