Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
14 results
Search Results
Conference Object Generating Lost Urban Fabric: Exploration of Generative Adversarial Networks as a Design Tool in Post-Disaster Urban Recovery(Education and Research in Computer Aided Architectural Design in Europe, 2025) Takış, F.N.; Akyüz, S.This study investigates the use of GANs, particularly the Pix2PixHD, for reconstructing urban fabric and preserving urban memory in post-disaster contexts, focusing on Hatay, Türkiye, after the 2023 earthquakes. Models were trained on pre-disaster urban maps and tested on incomplete post-earthquake data to regenerate damaged urban areas. Evaluation metrics, including FID scores, SSIM values, and visual inspections, demonstrated the model's ability to produce contextually accurate designs. The trained model effectively maintained road networks, building geometries, and spatial coherence. In addition to spatial consistency, the model produced outputs with sharp edges and high visual clarity. These results highlight the significant potential of GANs as generative design tools, offering valuable support to urban planners and architects in balancing urgent reconstruction needs with the long-term preservation of urban identity and memory in disaster-affected areas. © 2025, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.Article Deep-Learning Detection of Open-Apex Teeth on Panoramic Radiographs Using YOLO Models(Springer, 2025-12-23) Edik, Merve; Celebi, Fatma; Cukurluoglu, AykaganObjectivesThe use of deep learning in detecting teeth with open apices can prevent the need for additional radiographs for patients. The presented study aims to detect open-apex teeth using You Only Look Once (YOLO)-based deep learning models and compare these models.MethodsA total of 966 panoramic radiographs were included in the study. Open-apex teeth in panoramic radiographs were labeled. During the labeling process, they were divided into 6 classes in the maxilla and mandible, namely incisors, premolars, and molars. AI models YOLOv3, YOLOv4, and YOLOv5 were used. To evaluate the performance of the three detection models, both overall and separately for each class in the test dataset, precision, recall, average precision (mAP), and F1 score were calculated.ResultsYOLOv4 achieved the highest overall performance with a mean average precision (mAP) of 87.84% at IoU (Intersection over Union) 0.5 (mAP@0.5), followed by YOLOv5 with 85.6%, and YOLOv3 with 84.46%. Regarding recall, YOLOv4 also led with 90%, while both YOLOv3 and YOLOv5 reached 89%. Moreover, the F1 score was the highest for YOLOv4 (0.87), followed by YOLOv3 (0.86) and YOLOv5 (0.85).ConclusionsIn this study, YOLOv3, YOLOv4, and YOLOv5 were evaluated for the detection of open-apex teeth, and their mAP, recall, and F1 scores exceeded 84%. Deep learning-based systems can provide faster and more accurate results in the detection of open-apex teeth. This may help reduce the need for additional radiographs from patients and aid dentists by saving time.Article Citation - WoS: 8Citation - Scopus: 9Priceless: Privacy Enhanced AI-Driven Scalable Framework for IoT Applications in Serverless Edge Computing Environments(John Wiley & Sons Ltd, 2024-02-14) Golec, Muhammed; Golec, Mustafa; Xu, Minxian; Wu, Huaming; Gill, Sukhpal Singh; Uhlig, SteveServerless edge computing has emerged as a new paradigm that integrates the serverless and edge computing. By bringing processing power closer to the edge of the network, it provides advantages such as low latency by quickly processing data for time-sensitive Internet of Things (IoT) applications. Additionally, serverless edge computing also brings inherent problems of edge and serverless computing such as cold start, security and privacy that are still waiting to be solved. In this paper, we propose a new Blockchain-based AI-driven scalable framework called PRICELESS, to offer security and privacy in serverless edge computing environments while performing cold start prediction. In PRICELESS framework, we used deep reinforcement learning for the cold start latency prediction. For experiments, a cold start dataset is created using a heart disease risk-based IoT application and deployed using Google Cloud Functions. Experimental results show the additional delay that the blockchain module brings to cold start latency and its impact on cold start prediction performance. Additionally, the performance of PRICELESS is compared with the current state-of-the-art method based on energy cost, computation time and cold start prediction. Specifically, it has been observed that PRICELESS causes 19 ms of external latency, 358.2 watts for training, and 3.6 watts for prediction operations, resulting in additional energy consumption at the expense of security and privacy.Article Citation - WoS: 1Citation - Scopus: 1Intelligent Traffic Light Systems Using Edge Flow Predictions(Elsevier, 2024-01) Thahir, Adam Rizvi; Coskun, Mustafa; Kilic, Sultan Kubra; Gungor, Vehbi CagriIn this paper, we propose a novel graph-based semi-supervised learning approach for traffic light management in multiple intersections. Specifically, the basic premise behind our paper is that if we know some of the occupied roads and predict which roads will be congested, we can dynamically change traffic lights at the intersections that are connected to the roads anticipated to be congested. Comparative performance evaluations show that the proposed approach can produce comparable average vehicle waiting time and reduce the training/learning time of learning adequate traffic light configurations for all intersections within a few seconds, while a deep learning-based approach can be trained in a few days for learning similar light configurations.Conference Object Citation - Scopus: 1Empowering Dialogic Feedback in FLW With LLM(CEUR-WS, 2025) Sökücü, GamzeThis doctoral study aims to address significant challenges in foreign/second language (L2) writing (FLW/SLW) instruction by leveraging artificial intelligence. The central problem this study addresses is the lack of active learner engagement and the resource-intensive nature of traditional feedback methods, which can lead to teacher burnout and ineffective student learning outcomes. Existing feedback practices often fall short in providing detailed, timely, and comprehensible feedback, which hinders students' ability to critically analyze and act upon it. The study proposes a shift from monologic to dialogic feedback, facilitated by large-language models (LLMs), to promote continuous iterations of editing and rewriting, thus enhancing linguistic and cognitive development. The goal is to reveal the potential of LLMs in facilitating effective dialogic feedback approaches in L2 writing. To achieve this, the study aims to develop a theoretical framework and design principles for AI-enabled dialogic feedback systems, create an AI-writing tool based on this framework, and test its effectiveness through experimental sessions. Ultimately, the study seeks to understand the impact of AI-enhanced feedback on L2 learners' writing progress, their perceptions and experiences, and the emerging interaction patterns during the feedback process. This research holds the potential to transform feedback practices in language learning, contributing to more effective and engaging L2 writing instruction. © 2025 Elsevier B.V., All rights reserved.Article Citation - WoS: 8Citation - Scopus: 8Edgebus: Co-Simulation Based Resource Management for Heterogeneous Mobile Edge Computing Environments(Elsevier, 2024-12) Ali, Babar; Golec, Muhammed; Gill, Sukhpal Singh; Wu, Huaming; Cuadrado, Felix; Uhlig, SteveKubernetes has revolutionized traditional monolithic Internet of Things (IoT) applications into lightweight, decentralized, and independent microservices, thus becoming the de facto standard in the realm of container orchestration. Intelligent and efficient container placement in Mobile Edge Computing (MEC) is challenging subjected to user mobility, and surplus but heterogeneous computing resources. One solution to constantly altering user location is to relocate containers closer to the user; however, this leads to additional underutilized active nodes and increases migration's computational overhead. On the contrary, few to no migrations are attributed to higher latency, thus degrading the Quality of Service (QoS). To tackle these challenges, we created a framework named EdgeBus(1), which enables the co-simulation of container resource management in heterogeneous MEC environments based on Kubernetes. It enables the assessment of the impact of container migrations on resource management, energy, and latency. Further, we propose a mobility and migration cost-aware (MANGO) lightweight scheduler for efficient container management by incorporating migration cost, CPU cores, and memory usage for container scheduling. For user mobility, the Cabspotting dataset is employed, which contains real-world traces of taxi mobility in San Francisco. In the EdgeBus framework, we have created a simulated environment aided with a real-world testbed using Google Kubernetes Engine (GKE) to measure the performance of the MANGO scheduler in comparison to baseline schedulers such as IMPALA-based MobileKube, Latency Greedy, and Binpacking. Finally, extensive experiments have been conducted, which demonstrate the effectiveness of the MANGO in terms of latency and number of migrations.Article Citation - WoS: 85Citation - Scopus: 140Edge AI: A Taxonomy, Systematic Review and Future Directions(Springer, 2024-10-18) Gill, Sukhpal Singh; Golec, Muhammed; Hu, Jianmin; Xu, Minxian; Du, Junhui; Wu, Huaming; Uhlig, SteveEdge Artificial Intelligence (AI) incorporates a network of interconnected systems and devices that receive, cache, process, and analyse data in close communication with the location where the data is captured with AI technology. Recent advancements in AI efficiency, the widespread use of Internet of Things (IoT) devices, and the emergence of edge computing have unlocked the enormous scope of Edge AI. The goal of Edge AI is to optimize data processing efficiency and velocity while ensuring data confidentiality and integrity. Despite being a relatively new field of research, spanning from 2014 to the present, it has shown significant and rapid development over the last five years. In this article, we present a systematic literature review for Edge AI to discuss the existing research, recent advancements, and future research directions. We created a collaborative edge AI learning system for cloud and edge computing analysis, including an in-depth study of the architectures that facilitate this mechanism. The taxonomy for Edge AI facilitates the classification and configuration of Edge AI systems while also examining its potential influence across many fields through compassing infrastructure, cloud computing, fog computing, services, use cases, ML and deep learning, and resource management. This study highlights the significance of Edge AI in processing real-time data at the edge of the network. Additionally, it emphasizes the research challenges encountered by Edge AI systems, including constraints on resources, vulnerabilities to security threats, and problems with scalability. Finally, this study highlights the potential future research directions that aim to address the current limitations of Edge AI by providing innovative solutions.Article Citation - WoS: 23Citation - Scopus: 32Can Artificial Intelligence and Green Finance Affect Economic Cycles?(Elsevier Science inc, 2024-12) Chishti, Muhammad Zubair; Dogan, Eyup; Binsaeed, Rima H.The COVID-19 recession and the Ukraine-Russia War (URW) crisis have added a new layer of complexity to global economic cycles, necessitating the evolution of economic systems and proactive responses to emerging economic challenges. In this context, the recent article introduces artificial intelligence (AI) as a new driver of economic cycles and analyzes its dynamic role alongside the Belt and Road Initiative (BRI), the Paris Agreement (PA), green finance (GB), and economic shocks (ES) in determining global economic cycles. The article employs novel econometric tools, namely the CAViaR-TVP-VAR model, the Quantile Coherence method, panel Quantile on Quantile Kernel-Based Regularized Least Squares (PQQKRLS), and the Quantile-Quantile Granger causality (QQGC) test for robust findings. The outcomes reveal that AI influences economic cycles in the short run while significantly mitigating these cycles in the medium and long run. Furthermore, the BRI exhibits a positive link with economic cycles during the short and medium run; however, it can contribute to economic stability in the long run by impeding economic fluctuations. Similarly, green finance and the PA show mixed influences across various time horizons, except for the long run, which confirms their negative association with economic cycles. Additionally, ES has a direct link with economic cycles across most periods. The robustness check based on the QQGC test and PQQKRLS method supports the main results. Our results identify AI, BRI, and the PA as new drivers of economic cycles with the potential to counter global economic cycles. Therefore, based on these findings, the study proposes several policy implications tailored to different time horizons.Conference Object Citation - Scopus: 2ATGRUVAE: Reducing Noise and Improving Forecasting Performance in Stock Data(Institute of Electrical and Electronics Engineers Inc., 2024-10-26) Akkaş, Huseyin; Kolukisa, Burak; Bakir-Güngör, BurcuNowadays, to maximize their income, investors and researchers try to predict the future prices of stocks in the market using artificial intelligence algorithms. However, noise in stock price fluctuations negatively a ffects t he accuracy of the forecasts. To this end, Attention Based Variational Autoencoders with Gated Recurrent Units (ATGRUVAE) method is developed to remove the noise in stock price fluctuations a nd compared with variational, basic and noise removing autoencoders. Exper-iments are conducted using historical stock prices of well-known companies such as Apple, Google and Amazon and 9 different indicator values derived from these stock prices. The noise cleaned stocks are then trained and tested on Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM) and Linear Regression (LR) models. The results show that the proposed ATGRUVAE model outperforms all three models and demonstrates its ability to capture complex patterns in stock market data. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 19A Novel Feature Design and Stacking Approach for Non-Technical Electricity Loss Detection(Institute of Electrical and Electronics Engineers Inc., 2018-05) Aydin, Zafer; Güngör, Vehbi ÇağrıNon-technical electricity losses continue to jeopardize economic and social well-being of many countries. In this work, we develop machine learning classifiers that can identify anomalous electricity consumption in Turkey. Starting from weekly electricity usage data, we develop new features that capture statistical and frequency domain characteristics of the customers and their consumption patterns. We analyze the effect of reducing number of feature descriptors through dimensionality reduction and feature selection techniques. To overcome the class imbalance problem, we implement several ensemble methods and compare their prediction accuracy to those of the standard classifiers. The proposed features and combining strengths of different classifiers bring significant improvements on performance metrics, which is demonstrated through detailed simulations on shopping mall sector. We anticipate that advances in this field will contribute to the economies considerably. © 2018 Elsevier B.V., All rights reserved.