Bilgisayar Mühendisliği Bölümü Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1940
Browse
34 results
Search Results
Conference Object Rag Based Interactive Chatbot for Video Streaming Services(Institute of Electrical and Electronics Engineers Inc., 2025-09-17) Gözükara H.; Patel J.; Kara E.; Yildiz A.; Köseoǧlu O.; Makaroǧlu D.; Çakar T.; Gözükara, Hamza; Patel, Jay; Makaroǧlu, Didem; Kara, Erkan; Yildiz, Ayşenur; Çakar, Tuna; Köseoǧlu, OzanThe 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., 2025-11-14) Işlak U.; Yilmaz E.; Arslan I.; Çakar T.; Çakar, Tuna; Işlak, Ümit; Yilmaz, Elif; Arslan, IlkerIn 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 Evaluating Electrophysiological Responses Due To Identity Judgments(Ieee, 2024-05-15) Çakar, Tuna; Hohenberger, AnnetteThis study was conducted to explore how the brain processes decisions about identity, employing event-related potentials (ERPs) as a measure. The aim was to ascertain if the EEG/ERP technique could be used to monitor the cognitive processing of identity judgments as they happen. The investigation focused on comparing two groups of statements: those that used the concept of 'same' and those that used 'different'. The researchers hypothesized that there would be notable differences in the ERPs, particularly around the 400-millisecond mark, correlating with the reaction time disparities observed behaviorally. The ERP data revealed that the 'different' statements generated a unique N400 response when contrasted with the 'same' statements, implying that the participants' cognitive responses to these two types of judgments were not the same.Conference Object Predicting Credit Repayment Capacity With Machine Learning Models(Ieee, 2024-05-15) Filiz, Gozde; Bodur, Tolga; Yaslidag, Nihal; Sayar, Alperen; Çakar, TunaThis study examines the transformation in the financial services sector, particularly in banking, driven by the rapid development of technology and the widespread use of big data, and its impact on credit prediction processes. The developed credit prediction model aims to more accurately predict customers' credit repayment capacities. In pursuit of this goal, demographic and financial data along with credit histories of customers have been utilized to employ data preprocessing techniques and test various classification algorithms. Findings indicate that models developed with XGBoost and CATBoost algorithms exhibit the highest performance, while the effective use of feature engineering techniques is revealed to enhance the model's accuracy and reliability. The research highlights the potential for financial institutions to gain a competitive advantage in risk management and customer relationship management by leveraging machine learning models.Conference Object Citation - Scopus: 1Physical Activity Monitoring With Smartwatch Technology in Adolescents and Obtaining Big Data: Preliminary Findings(Ieee, 2024-05-15) Filiz, Gozde; Arman, Nilay; Ayaz, Nuray Aktay; Yekdaneh, Asena; Albayrak, Asya; Bozkan, Tunahan; Çakar, TunaThis study assesses the potential of smartwatch technology in monitoring adolescents' physical activity and health parameters. It focuses on the role of physical activity in preventing chronic diseases and improving quality of life. The primary aim of the project is to perform statistical analysis of the large data sets collected from both healthy adolescents and those with chronic rheumatic diseases, and to develop a machine learning-based classification model to distinguish between these two groups. This analysis highlights the issue of physical inactivity observed during the Covid-19 pandemic, while showcasing the capacity of technology to offer solutions. The study aims to evaluate the collected data in a way that forms the basis for personalized activity plans for adolescents, demonstrating how wearable technology and big data can be effectively used in health services and to promote physical activity.Conference Object Reliability Study of Psychometric Tests in a Credit Scoring Model(Ieee, 2024-05-15) Nicat, Sahin; Filiz, Gozde; Ozvural, Ozden Gebizlioglu; Çakar, TunaThis study investigates the effectiveness and reliability of using psychometric tests in the credit decision-making processes within the finance sector. Psychometric tests, by measuring individuals' cognitive and psychological traits, hold the potential to broaden access to credit and identify high credit risk. However, after the literature review, it was seen that there was a need for more studies on the reliability and validity of these tests in finance. This study is designed to measure the test-retest reliability of a machine learning model and its inputs that utilize psychometric test results. Within the scope of the research, 115 participants were re-subjected to the same psychometric tests after an average of 6 months. Findings showed that psychometric tests and the machine learning model were generally consistent over time. This work has the potential to fill the gaps in the literature regarding the use of psychometric tests in the finance sector and lays a foundation for future research.Conference Object Citation - Scopus: 2The Application of Two Bayesian Personalized Ranking Approaches Based on Item Recommendation From Implicit Feedback(Ieee, 2024-05-15) Tagtekin, Burak; Sahin, Zeynep; Çakar, Tuna; Drias, YassineThe present study has aimed to provide a different ranking approach that will be used actively in a sector-specific application regarding the optimization of item ranking presented to the users. The current online approach in several different applications still holds a manual ranking algorithm whose parameters are determined by the data specialists with adequate domain-knowledge. The obtained findings from the present study indicate that the optimized Bayesian Personalized Ranking models will be used for providing a suitable, data-driven input for the ranking system that would serve to be personalized. The outcomes of the present study also demonstrate that the model using LearnBPR optimized with a stochastic gradient descent algorithm outperform the other similar methods. The sample model outputs were also investigated by a user sample to ensure that the algorithm was working correctly. The next potential step is to provide a normalization process to include the extracted information to the current ranking system and observe the performance of this new algorithm with the A/B tests conducted.Conference Object Citation - WoS: 1Citation - Scopus: 2Determination of Alzheimer's Disease Levels by Ordinal Logistic Regression and Artificial Learning Algorithms(Ieee, 2024-05-15) Bulut, Nurgül; Çakar, Tuna; Arslan, Ilker; Akinci, Zeynep Karaoglu; Oner, Kevser SetenayThis study compares artificial learning algorithms and logistic regression models in determining different levels of Alzheimer's disease (AD). The research uses demographic, genetic, and neurocognitive inventory results obtained from the National Alzheimer's Coordination Center (NACC) database, along with brain volume/thickness measurements derived from MRI scanners. Deep Neural Networks, Ordinal Logistic Regression, Random Forest, Gaussian Naive Bayes, XGBoost, and LightGBM models were employed to determine the 4 different ordinal levels of AD. Although there were similarities between the accuracy rate, F1 score, AUC value, and sensitivity, specificity, and precision performance measures of each class, the highest classification rate was achieved by the Random Forest model where the oversampling was not applied. (F1 score: 0.86; accuracy: 0.86 and AUC: 0.95). The outputs of the model with the best performance were explained with the SHAP (SHapley Additive exPlanations) method. These findings indicate that non-invasive markers and artificial learning models can be used effectively in early diagnosis and decision support systems to predict different levels of Alzheimer's disease.Conference Object Citation - Scopus: 1Distinguishing Cognitive Processes: a Machine Learning Approach To Decode Fnirs Data for Third-Party Punishment and Credit Decision-Making(Ieee, 2024-05-15) Filiz, Gozde; Son, Semen; Sayar, Alperen; Ertugrul, Seyit; Sahin, Turkay; Akyurek, Guclu; Çakar, TunaFunctional near-infrared spectroscopy (fNIRS) has seen increasingly widespread use in examining brain activity and cognitive processes. However, the existing literature provides insufficient information on distinguishing between different decision-making mechanisms. This study explores the application of fNIRS in differentiating between two distinct decision-making processes: third-party punishment decisions and credit decisions. The research includes analyzing fNIRS data collected during these processes and classifying the associated neural patterns using machine learning. The findings reveal that fNIRS, in conjunction with ML, holds substantial potential to enhance the depth of understanding of decision-making processes in neuroscience research.Conference Object Analyzing Customer Churn: a Comparative Study of Machine Learning Models on Pay-Tv Subscribers in Turkey(IEEE, 2023-12-21) Obalı, Emir; Çalışkan, Sibel Kırmızıgül; Karani Yılmaz, Veysel; Kara, Erkan; Meşe, Yasemin Kürtcü; Çakar, Tuna; Yıldız, Ayşenur; Hataş, Tuğce AydınUnderstanding the reasons for customer churn provides added value in terms of retaining existing customers, as customer attrition leads to revenue loss for companies and incurs marketing costs for acquiring new customers. In this study, the 6-month historical data of a Pay-TV company operating in Turkey was used, and due to the imbalanced nature of the dataset on a label basis, the oversampling method was applied. During the model development phase, various artificial learning algorithms (Random Forest, Logistic Regression, KNearest Neighbors, Decision Tree, AdaBoost, XGBoost, Extra Tree Classifier) were utilized, and their performances were compared. Based on the evaluation of success criteria for each model, it was observed that the tree-based Random Forest, Extra Tree Classifier and XGBoost achieved the highest performance for this dataset.