WoS İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/394
Browse
12 results
Search Results
Article Citation - WoS: 27Citation - Scopus: 30Super 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: 1Citation - Scopus: 1Spec17Tre: A New Dataset in Hardware Security and Using Deep Learning for Detecting Spectre Attacks(Springer Heidelberg, 2025-05-21) Aktas-Aydin, Hatice; Yalcin, GulayComputer performance has become a significant subject of study due to the processing of big data, the complexity of calculations and the importance of time efficiency. Many companies are improving processor operating principles to increase performance. The most common methods for this purpose are speculative execution and cache usage. While these techniques improve performance, they also introduce certain security vulnerabilities. Spectre is an attack that exploits vulnerabilities created by speculative execution, affecting all modern processor architectures. Research has shown that using machine learning to detect these attacks can be quite effective, although the features are typically gathered at the software level, which may limit detection since some performance parameters are not conveyed to the software. This study presents an analysis of Spectre attacks and their detection using machine learning and deep learning methods at the hardware level. Experiments are conducted using GEM5, a full-system hardware simulator, to ensure that only hardware-visible performance parameters are also collected. Attack detection is performed using Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) methods. The LSTM method is used in conjunction with SVM and Convolutional Neural Network (CNN) techniques, and all models were tested on a new dataset, Spec17Tre, created using "519.lbm" from the SPEC CPU2017 benchmarks. The study achieved a 95% accuracy rate in attack detection using the LSTM + CNN hybrid model, which also yielded an F1 score of 0.999 for detecting applied Spectre attack scenarios.Article Citation - WoS: 3Citation - Scopus: 9Probabilistic 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: 26Citation - Scopus: 48Metabolic Imaging Based Sub-Classification of Lung Cancer(IEEE-Inst Electrical Electronics Engineers Inc, 2020) Bicakci, Mustafa; Ayyildiz, Oguzhan; Aydin, Zafer; Basturk, Alper; Karacavus, Seyhan; Yilmaz, BulentLung cancer is one of the deadliest cancer types whose 84% is non-small cell lung cancer (NSCLC). In this study, deep learning-based classification methods were investigated comprehensively to differentiate two subtypes of NSCLC, namely adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). The study used 1457 F-18-FDG PET images/slices with tumor from 94 patients (88 men), 38 of which were ADC and the rest were SqCC. Three experiments were carried out to examine the contribution of peritumoral areas in PET images on subtype classification of tumors. We assessed multilayer perceptron (MLP) and three convolutional neural network (CNN) models such as SqueezeNet, VGG16 and VGG19 using three kinds of images in these experiments: 1) Whole slices without cropping or segmentation, 2) cropped image portions (square subimages) that include the tumor and 3) segmented image portions corresponding to tumors using random walk method. Several optimizers and regularization methods were used to optimize each model for the diagnostic classification. The classification models were trained and evaluated by performing stratified 10-fold cross validation, and F-score and area-under-curve (AUC) metrics were used to quantify the performance. According to our results, it is possible to say that inclusion of peritumoral regions/tissues both contributes to the success of models and makes segmentation effort unnecessary. To the best of our knowledge, deep learning-based models have not been applied to the subtype classification of NSCLC in PET imaging, therefore, this study is a significant cornerstone providing thorough comparisons and evaluations of several deep learning models on metabolic imaging for lung cancer. Even simpler deep learning models are found promising in this domain, indicating that any improvement in deep learning models in machine learning community can be reflected well in this domain as well.Article Citation - WoS: 3Citation - Scopus: 3Distinguishing Resting State From Motor Imagery Swallowing Using EEG and Deep Learning Models(IEEE-Inst Electrical Electronics Engineers Inc, 2024) Aslan, Sevgi Gokce; Yilmaz, BulentThe primary aim of this study was to assess the classification performance of deep learning models in distinguishing between resting state and motor imagery swallowing, utilizing various preprocessing and data visualization techniques applied to electroencephalography (EEG) data. In this study, we performed experiments using four distinct paradigms such as natural swallowing, induced saliva swallowing, induced water swallowing, and induced tongue protrusion on 30 right-handed individuals (aged 18 to 56). We utilized a 16-channel wearable EEG headset. We thoroughly investigated the impact of different preprocessing methods (Independent Component Analysis, Empirical Mode Decomposition, bandpass filtering) and visualization techniques (spectrograms, scalograms) on the classification performance of multichannel EEG signals. Additionally, we explored the utilization and potential contributions of deep learning models, particularly Convolutional Neural Networks (CNNs), in EEG-based classification processes. The novelty of this study lies in its comprehensive examination of the potential of deep learning models, specifically in distinguishing between resting state and motor imagery swallowing processes, using a diverse combination of EEG signal preprocessing and visualization techniques. The results showed that it was possible to distinguish the resting state from the imagination of swallowing with 89.8% accuracy, especially using continuous wavelet transform (CWT) based scalograms. The findings of this study may provide significant contributions to the development of effective methods for the rehabilitation and treatment of swallowing difficulties based on motor imagery-based brain computer interfaces.Article Citation - WoS: 10Citation - Scopus: 13Deep Learning Based Semantic Segmentation and Quantification for MRD Biochip Images(Elsevier Sci Ltd, 2022-08) Celebi, Fatma; Tasdemir, Kasim; Icoz, KutayMicrofluidic platforms offer prominent advantages for the early detection of cancer and monitoring the patient response to therapy. Numerous microfluidic platforms have been developed for capturing and quantifying the tumor cells integrating several readout methods. Earlier, we have developed a microfluidic platform (MRD Biochip) to capture and quantify leukemia cells. This is the first study which employs a deep learning-based segmentation to the MRD Biochip images consisting of leukemic cells, immunomagnetic beads and micropads. Implementing deep learning algorithms has two main contributions; firstly, the quantification performance of the readout method is improved for the unbalanced dataset. Secondly, unlike the previous classical computer vision -based method, it does not require any manual tuning of the parameters which resulted in a more generalized model against variations of objects in the image in terms of size, color, and noise. As a result of these benefits, the proposed system is promising for providing real time analysis for microfluidic systems. Moreover, we compare different deep learning based semantic segmentation algorithms on the image dataset which are acquired from the real patient samples using a bright-field microscopy. Without cell staining, hyper-parameter optimized, and modified U-Net semantic segmentation algorithm yields 98.7% global accuracy, 86.1% mean IoU, 92.2% mean precision, 92.2% mean recall and 92.2% mean F-1 score measure on the patient dataset. After segmentation, quantification result yields 89% average precision, 97% average recall on test images. By applying the deep learning algorithms, we are able to improve our previous results that employed conventional computer vision methods.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: 4Citation - Scopus: 7Combining 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 - WoS: 23Citation - Scopus: 35A 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.Article Citation - WoS: 15Citation - Scopus: 14A Review of Mammographic Region of Interest Classification(Wiley Periodicals, inc, 2020-02-18) Yengec Tasdemir, Sena B.; Tasdemir, Kasim; Aydin, ZaferEarly detection of breast cancer is important and highly valuable in clinical practice. X-ray mammography is broadly used for prescreening the breast and is also attractive due to its noninvasive nature. However, experts can misdiagnose a significant proportion of the cases, which may either cause redundant examinations or cancer. In order to reduce false positive and negative rates of mammography screening, computer-aided breast cancer detection has been studied for more than 30 years and many methods have been proposed by the researchers. In this review, region of interest (ROI) classification methods, which operate on a predefined or segmented ROIs with a focus on mass classification are surveyed. A total of 72 high quality journal and conference papers are selected from the Web of Science (WOS) database that meet several inclusion criteria. A comparative analysis is provided based on ROI extraction methods, data sets and machine learning techniques employed, the prediction accuracies, and usage frequency statistics. Based on the performances obtained on publicly available data sets, the ROI classification problem from mammogram images can be considered as approaching to be solved. Nonetheless, it can still be used as complementary information in breast cancer detection from the whole mammograms, which has room for improvement. This article is categorized under: Application Areas > Science and Technology Technologies > Machine Learning Technologies > Classification