Bilgisayar Mühendisliği Bölümü Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1940
Browse
139 results
Search Results
Article Effect of Belief in Free Will on the Intensity of Third-Party Punishment(Istanbul University Press, 2025) Çakar, Tuna; Erözden, Ozan; Akyürek, Güçlü; Özen, Zeynep; Şahin, Türkay; Keskin, İrem Nur; Ünlü, Meryem; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 05. Faculty of Law; 01. MEF UniversityThe institutionalized criminal justice mechanisms are built on two psychological and social traits: third-party punishment (TPP) and belief in free will (BFW). TPP is the administration of a sanction to a transgressor by an individual not affected by the transgression. BFW posits that humans are in control of their actions. Previous studies have indicated that BFW influences TPP. The aim of this study is to investigate whether the level of BFW has an impact on the magnitude of punishment in TPP tasks. Furthermore, it questions whether the degree of affective arousal of the punisher creates an additional effect on the magnitude of the punishment. Our basic hypothesis is that the BFW and punishment magnitude are positively correlated. We also hypothesize that the expected positive correlation between BFW and punishment magnitude will be more manifest in low-affect scenarios than in high-affect ones. Participants (N = 726) were given 49 hypothetical crime scenarios categorized as low- and high-affect cases. Upon reading each scenario, the participants were tasked to attribute a penalty between the two given options. Our results showed that the level of BFW was positively correlated with the degree of punishment administered in the hypothetical crime scenarios and that the average punishment magnitude for participants with a low level of BFW increased in the high-affect crime scenarios. We assume that our results would shed light on the underlying causes of public reactions to criminal sentencing policies, thus helping lawmakers in enacting better regulations in this respect. 2025. Çakar, T., Akyürek, G., Erözden, O., Şahin, T., Keskin, İ. N., Ünlü, M., Özen, D. H. & Özen, Z.Conference Object Citation - WoS: 1Neural Language Generation for a Turkish Task-Oriented Dialogue System(PROCEEDINGS OF THE WORKSHOP ON INTELLIGENT INFORMATION PROCESSING AND NATURAL LANGUAGE GENERATION, 2020) Çakar, Tuna; Demir, Şeniz; Bilgin, Batuhan; Çakar, Tuna; Demir, Şeniz; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF UniversityRapidly growing language and speech-enabled technologies contribute to the development of task-oriented dialogue systems. The demand for better user engagement has been increasing at an accelerating pace and this brings new remarkable challenges including the generation of informative and natural system utterances. In this work, our ultimate goal is to develop a Turkish task-oriented dialogue system that enables users to navigate over a map in order to get informed about dining venues that best match their preferences and make reservations based on received recommendations. This paper presents the pipeline architecture of our dialogue system with a particular focus on the language generator. We utilize an open source framework for building the components of our system and develop a sequence-to-sequence (Seq2Seq) neural model for language generation. This pioneering work is the first that proposes the use of a neural generation model in a Turkish conversational system. Our evaluations suggest that Turkish neural generation from meaning representations given in the form of dialogue acts is effective, but still in need of further improvements.Master Thesis EAFT: Evolutionary algorithms for GCC flag tuning(MEF Üniversitesi, 2023) Çakar, Tuna; Çakar, Tuna; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF UniversityThe runtime of written codes is a matter of great importance, especially for code that is compiled once and executed multiple times. It is very important for developers to ensure that the resources required by a code are used as efficiently as possible, and that the runtime is as low as possible. Developers who use compilers such as GCC or LLVM to compile and run code written in C or C++ can optimize their code manually and, with certain optimization pointers, are able to make it run faster. This will provide the shorter runtime, but completıng this manual optimization is within the abilities of every developer since determining the right combination from more than 200 flags requires significant expertise. Many studies have tackled this issue. In this study, Evolutionary Algorithms for GCC Flag Tuning (EAFT) have been developed as a solution to this problem. This Autotuner, which is completely open-source, runs the code provided by the end user according to the specifications also selected by the end user, and searches for the most suitable optimization markers. For the code to be given In line with this study, which specifically addresses the end user, the user can input the code path directly from the Terminal, as well as specify the selection method and the crossover to be used. These choices can be made without the need to alter the code. The genetic algorithm and particle swarm optimization to be used is also presented to the user in EAFT, and unlike in other studies, genetic algorithm contain not one but several models.Conference Object Churn Prediction for Subscription-Based Applications Using Machine Learning(Institute of Electrical and Electronics Engineers Inc., 2025) Özlem, Şirin; Çakar, Tuna; Kara E.; Yildiz A.; Mese Y.K.; Obali E.; Cakar T.; Gozukara, Hamza; Mese, Yasemin Kurtcu; Patel, Jay; Kara, Erkan; Yildiz, Aysenur; Cakar, Tuna; Obali, Emir; 02.01. Department of Industrial Engineering; 02. Faculty of Engineering; 01. MEF University; 02.02. Department of Computer EngineeringIn this study, a predictive model was developed using machine learning techniques to forecast customer churn in subscription-based video streaming services. The data such as user login records, content viewing information, subscription details, and content-related features were used to interpret usage patterns and customer churn was defined based on subscription renewal status and renewal timing. Several usage-based features are extracted for users and several algorithms were used for modeling, such as Random Forest, CatBoost, XGBoost, Logistic Regression, K-Nearest Neighbors, and Gradient Boosting. Occurring class imbalance on the target variable is handled via BorderLineSMOTE. The model's performance was evaluated using training-test accuracy plots, classification reports, and hyperparameter tuning. Even though most of the models performed similarly, the CatBoost model emerged as the top performer, achieving a macro F1-score of 0.60. However, while effective in identifying churners, the models struggled to precisely classify non-churning customers, a common challenge in imbalanced datasets even after applying oversampling techniques. The analysis of feature importance yielded a crucial insight, early and consistent user engagement is the strongest predictor of customer retention. These findings provide valuable, actionable insights for streaming platforms, emphasizing that retention strategies should focus on maximizing engagement immediately after a user subscribes. © 2025 IEEE.Conference Object Attention-Enhanced Dual-Head LSTM With Rich Feature Engineering for Risk-Adjusted Stock Return Forecasting(Institute of Electrical and Electronics Engineers Inc., 2025) Drias, Yassine; Çakar, Tuna; Ertugrul S.; Sayar A.; Benli H.; Makaroglu D.; Cakar T.; Benli, Harun; Gunes, Peri; Patel, Jay; Makaroglu, Didem; Sayar, Alperen; Cakar, Tuna; Ertugrul, Seyit; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF UniversityStock return forecasting is a challenging task due to the complex, nonlinear, and volatile nature of financial markets. In this paper, we propose a comprehensive deep learning framework that integrates: a two-layer Long Short-Term Memory (LSTM) network augmented with a learnable attention mechanism, a dual-head output for simultaneous regression of next-day returns and classification of price direction, with an extensive suite of technical and macro-financial features. Our feature set comprises lagged log-returns, trend indicators (simple and exponential moving averages), momentum oscillators (RSI, MACD), volatility measures (rolling variance and GARCH conditional volatility), price bands (Bollinger Bands, Donchian channels), volume metrics (On-Balance Volume, Volume Rate of Change), Hidden Markov Model regime states, market index returns, and calendar effects. We train and validate the model using a rolling-window cross-validation scheme with early stopping and hyperparameter tuning to ensure temporal robustness. Empirical results on a large multi-stock dataset demonstrate that our attention-enhanced, dual-task LSTM outperforms single-task LSTMs and traditional machine learning benchmarks, achieving lower forecasting error and more stable generalization. © 2025 IEEE.Conference Object Rag Based Interactive Chatbot for Video Streaming Services(Institute of Electrical and Electronics Engineers Inc., 2025) Çakar, Tuna; Özlem, Şirin; Kara E.; Yildiz A.; Köseoǧlu O.; Makaroǧlu D.; Çakar T.; Gözükara, Hamza; Patel, Jay; Makaroǧlu, Didem; Kara, Erkan; Yildiz, Ayşenur; Çakar, Tuna; Köseoǧlu, Ozan; 02.01. Department of Industrial Engineering; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF UniversityThe proliferation of content within video streaming services presents a significant challenge for users seeking personalized recommendations and specific information. This research addresses this challenge by developing a Retrieval-Augmented Generation (RAG) chatbotn designed to enhance user experience through conversational AI. The primary contribution of this work is a novel Retrieval-Augmented Generation (RAG) architecture featuring a dual-retrieval system that combines semantic search for descriptive requests and structured queries for fact based inquiries. This approach grounds the Large Language Model (LLM) in a factual knowledge base, mitigating the risk of hallucinations. The system is engineered to handle empty data retrieval scenarios by dynamically relaxing search filters, ensuring a robust user experience. The effectiveness of this RAG approach was validated through a comprehensive set of automated evaluations. The system demonstrates high precision in ranked list retrieval with questions like "Recommend me the top 5 action movies with highest IMDb scores", achieving an average NDCG@k of 0.837. While the chatbot shows strong semantic understanding by achieving 91% accuracy with contextual clues such as "Which Batman movies are directed by Christopher Nolan?", its performance with more ambiguous, plot-only queries (59.5% accuracy) indicates clear opportunities for future refinement. These results confirm that the dual-tool architecture successfully combines the flexibility of semantic search with the precision of structured queries, paving the way for more intuitive and efficient content discovery on streaming platforms. © 2025 IEEE.Conference Object Combining Similar Trajectories and XGBoost via Residual Learning for Traffic Flow Forecasting(Institute of Electrical and Electronics Engineers Inc., 2025) Çakar, Tuna; Yilmaz E.; Arslan I.; Çakar T.; Çakar, Tuna; Işlak, Ümit; Yilmaz, Elif; Arslan, Ilker; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF UniversityIn this study, we propose novel hybrid forecasting models that integrate the method of similar trajectories with machine learning techniques, particularly the XGBoost algorithm, for traffic flow prediction. Traditional statistical models, such as ARIMA, often struggle to accurately capture the complex, non-linear patterns characteristic of traffic flow data. To address these limitations, we develop an additive hybrid forecasting framework that combines the strengths of linear models (similar trajectories method) and non-linear models (XGBoost). Our proposed methods are evaluated on two different stations from the California PEMS dataset. Experimental results demonstrate that the proposed hybrid models consistently outperform individual benchmark models, including ARIMA, standalone similar trajectories, and XGBoost. The superiority of the hybrid approach, particularly the XGBST model, is further validated through the Diebold-Mariano statistical test, confirming significant predictive improvements at various significance levels. Additionally, using weighted Euclidean distance within the similar trajectories method further enhanced forecasting accuracy. The interpretability and flexibility of our hybrid framework make it especially suitable for practical implementation in traffic management systems. These findings underline the effectiveness of hybrid modeling strategies in traffic flow forecasting and suggest future research directions, such as comprehensive hyperparameter optimization and broader validation across diverse datasets. © 2025 IEEE.Conference Object A Multimodal AI and ML Framework for Fashion Image Segmentation, Recommendation, and Similarity Recognition(Institute of Electrical and Electronics Engineers Inc., 2025) Özlem, Şirin; Çakar, Tuna; Memis E.C.; Fatih Capal M.; Cakar T.; Gunay S.; Coskun H.; Gunay, Savas; Memis, Emir Cetin; Fatih Capal, Mehmet; Soyhan, Mustafa Eren; Coskun, Hasan; Cakar, Tuna; Ay, Tarik Bugra; 02.01. Department of Industrial Engineering; 02. Faculty of Engineering; 01. MEF University; 02.02. Department of Computer EngineeringThis study presents a scalable multimodal Artificial Intelligence (AI) and Machine Learning (ML) framework designed to enhance decision making in the fashion industry. The proposed system integrates garment segmentation, multimodal feature extraction, and similarity recommendation into a unified pipeline. Using Segformer for segmentation, along with the convolutional neural network (CNN)-based feature extraction models ResNet152V2 and Xception, and the transformer-based vision-language model LLaVA, the framework generates visual and semantic embeddings of garments. These representations are processed through similarity detection using OpenAI embedding models and stored in the Pinecone vector database for efficient retrieval. Real-time similarity scoring is enabled through FastAPI endpoints, offering interactive search capabilities. Preliminary results demonstrate the system's strong ability to identify conceptually and visually similar items across a large catalog, providing actionable insights for designers. This framework lays the groundwork for intelligent, interpretable, and production-ready AI systems in the fashion industry. © 2025 IEEE.Conference Object Predicting Customer Churn in Retail Using Machine Learning on Transaction Data(Institute of Electrical and Electronics Engineers Inc., 2025) Çakar, Tuna; Gozukara H.; Patel J.; Kizilay A.; Sahin Z.; Tosun B.; Cakar T.; Gozukara, Hamza; Kizilay, Ayse; Patel, Jay; Bozan, Mehmet Talha; Cakar, Tuna; Tosun, Busra; Sahin, Zeynep; 01. MEF University; 02.02. Department of Computer Engineering; 02. Faculty of EngineeringCustomer churn prediction is critical for businesses to retain customers and reduce revenue loss. This paper presents a retail customer churn prediction study. We preprocess transactional data from a retail dataset comprising approximately 19.7 million transactions involving over 1 million customers. Temporal behavioral features, such as purchase frequency, monetary value, product variety, and promotional engagement metrics, are engineered using a four-month observation window. A Random Forest classifier is trained, utilizing balanced class weighting to address churn class imbalance. The churn label is defined as customers not purchasing in the subsequent six-month period. Our Random Forest model achieves approximately 84% accuracy, 86% precision, 85% recall, and an F1- score of 85%. Additionally, an XGBoost model achieves similar accuracy (≈ 84%) but higher recall (93%) and F1-score (89%), indicating improved churn prediction. The confusion matrix illustrates clear model performance. This study demonstrates that carefully engineered RFM-based features and ensemble learning approaches significantly enhance churn prediction in retail contexts. © 2025 IEEE.Conference Object Graph Theory-Based Fraud Detection in Banking Check Transactions(Institute of Electrical and Electronics Engineers Inc., 2025) Drias, Yassine; Çakar, Tuna; Ertugrul S.; Sayar A.; Gunes P.; Seydioglu S.; Cakar T.; Gunes, Peri; Memis, Emir Cetin; Sayar, Alperen; Cakar, Tuna; Ertugrul, Seyit; Seydioglu, Sarper; Behsi, Zeynep; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF UniversityTraditional banking fraud detection systems rely on rule-based approaches that analyze individual transactions in isolation, failing to capture complex relationship patterns indicative of coordinated fraud schemes such as check-kiting and artificial credit score manipulation. We p resent our study, a novel similarity-based graph theory approach that constructs weighted networks between check issuers using Jaccard Similarity Index and employs advanced graph analysis to identify suspicious entity clusters without requiring complete transaction relationship data. Our approach combines Jaccard Similarity Index for behavioral pattern analysis (addressing payee information unavailability) with comprehensive graph analysis including centrality measures, community detection, and anomaly identification. Through comprehensive evaluation on real banking data containing 458,399 transactions from 121,647 unique issuers - the largest confirmed dataset in fraud detection literature - we demonstrate the effectiveness of our methodology. Following parameter optimization using grid search methodology (similarity threshold: 0.55, risk percentile: 0.75), our study achieves competitive detection rates in optimal configurations with an average F1-score of 0.447 (±0.164) and peak performance reaching an F1-score of 0.557, while providing superior network topology analysis with 0.923 clustering coefficient. The system operates under significant data privacy constraints, lacking personal identification information (names, account numbers, IDs) and complete payee data. Despite these limitations, our study outperforms traditional approaches by leveraging similarity-based indirect relationships, and we project that performance could reach 85-95% levels with complete data access. © 2025 IEEE.