Bilgisayar Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1940

Browse

Now showing 1 - 20 of 63

Citation - Scopus: 2
Alternative Data Sources and Psychometric Scales Supported Credit Scoring Models
(IEEE, 2023) Şahin, Türkay; Filiz, Gözde; Çakar, Tuna; Özvural, Özden Gebizlioğlu; Nicat, Şahin; Gebizlioǧlu Özvural, Özden
This study aims to evaluate individuals with limited access to banking services and enhance credit scoring models with alternative data sources. A psychometric-based credit scoring model was developed and tested. Despite limited data, significant potential findings were obtained. However, clarification of the distinction between credit payment intention and ability and validation of the results with more data are necessary.
An Exploratory Study on the Effect of Contour Types on Decision Making Via Optic Brain Imaging Method (fnirs)
(eScholarship, 2023) Demircioglu, Esin Tuna; Girişken, Yener; Çakar, Tuna
Decision-making is a combination of our positive anticipations from the future with the contribution of our past experiences, emotions, and what we perceive at the moment. Therefore, the cues perceived from the environment play an important role in shaping the decisions. Contours, which are the hidden identity of the objects, are among these cues. Aesthetic evaluation, on the other hand, has been shown to have a profound impact on decision-making, both as a subjective experience of beauty and as having an evolutionary background. The aim of this empirical study is to explain the effect of contour types on preference decisions in the prefrontal cortex through risk-taking and aesthetic appraisal. The obtained findings indicated a relation between preference decision, contour type, and PFC subregion. The results of the current study suggest that contour type is an effective cue in decision-making, furthermore, left OFC and right dlPFC respond differently to contour types.
Citation - WoS: 52
Citation - Scopus: 66
An Investigation of the Neural Correlates of Purchase Behavior Through Fnirs
(Emerald Group Publishing Ltd, 2018) Cakir, Murat Perit; Yurdakul, Dicle; Girisken, Yener; Çakar, Tuna
Purpose This study aims to explore the plausibility of the functional near-infrared spectroscopy (fNIRS) methodology for neuromarketing applications and develop a neurophysiologically-informed model of purchasing behavior based on fNIRS measurements. Design/methodology/approach The oxygenation signals extracted from the purchase trials of each subject were temporally averaged to obtain average signals for buy and pass decisions. The obtained data were analyzed via both linear mixed models for each of the 16 optodes to explore their separate role in the purchasing decision process and a discriminant analysis to construct a classifier for buy/pass decisions based on oxygenation measures from multiple optodes. Findings Positive purchasing decisions significantly increase the neural activity through fronto-polar regions, which are closely related to OFC and vmPFC that modulate the computation of subjective values. The results showed that neural activations can be used to decode the buy or pass decisions with 85 per cent accuracy provided that sensitivity to the budget constraint is provided as an additional factor. Research limitations/implications The study shows that the fNIRS measures can provide useful biomarkers for improving the classification accuracy of purchasing tendencies and might be used as a main or complementary method together with traditional research methods in marketing. Future studies might focus on real-time purchasing processes in a more ecologically valid setting such as shopping in supermarkets. Originality/value This paper uses an emerging neuroimaging method in consumer neuroscience, namely, fNIRS. The decoding accuracy of the model is 85 per cent which presents an improvement over the accuracy levels reported in previous studies. The research also contributes to existing knowledge by providing insights in understanding individual differences and heterogeneity in consumer behavior through neural activities.
Citation - Scopus: 1
Analytical Approaches in Customer Relationship Management
(IEEE, 2023) Akata, Mustafa Aşkım; Ergin, Kaan; Kaya, Büşra; Kızılay, Ayşe; Çakar, Tuna; Şahin, Zeynep
This study examines the impact of analytical customer relationship management (aCRM) strategies, specifically the segmentation approach using RFM analysis and artificial learning methods, on customer satisfaction, revenue performance, and loyalty in businesses. The research adopts an approach that integrates data from both online and offline channels onto a single platform, providing a holistic view of customer behaviors. Combining the segmentation obtained through RFM analysis and artificial learning methods with timely campaigns has enhanced shopping opportunities for customers and increased customer satisfaction and loyalty. The use of aCRM as a strategic marketing and sales tool has enabled businesses to manage customer relationships more effectively. This paper contributes to the literature in this field by presenting in detail the advantages offered by aCRM, its application methods, and the results obtained.
Analyzing Consumer Behavior: the Impact of Retro Music in Advertisements on a Chocolate Brand and Consumer Engagement
(IEEE, 2023) Girişken, Yener; Soyaltın, Tuğçe Ezgi; Filiz, Gözde; Çakar, Tuna; Türkyılmaz, Ceyda Aysuna
This study presents research utilizing binary classification models to analyze consumer behaviors such as chocolate consumption and retro music ad viewing. Retro music, with its potential to evoke nostalgic feelings in consumers, is used in advertisements, which can have a significant impact on brand perception and consumer engagement. Firstly, a model focusing on chocolate consumption was developed and tested. The model yields significant outcomes. Secondly, a model based on retro music ad viewing status was developed and tested. Significant potential findings were obtained. This study emphasizes the applicability of effective classification models that can be used to understand and predict consumer behaviors, yielding significant outcomes.
Analyzing Customer Churn: a Comparative Study of Machine Learning Models on Pay-Tv Subscribers in Turkey
(IEEE, 2023) Obalı, Emir; Çalışkan, Sibel Kırmızıgül; Karani Yılmaz, Veysel; Kara, Erkan; Meşe, Yasemin Kürtcü; Çakar, Tuna; Yıldız, Ayşenur; Hataş, Tuğce Aydın
Understanding 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.
Citation - Scopus: 1
Artificial Intelligence Driven Multivariate Time Series Analysis of Network Traffic Prediction
(Institute of Electrical and Electronics Engineers Inc., 2024) Filiz, G.; Yıldız, A.; Kara, E.; Altıntaş, S.; Çakar, T.
The primary objective of this research is to employ artificial intelligence, machine learning, and neural networks in order to construct a network traffic prediction model. The analysis of network traffic data obtained from a digital media and entertainment provider operating in Turkey is conducted through the application of multivariate time-series analysis techniques in order to get insights into the temporal patterns and trends. In model development, Vector Autoregression (VAR), Vector Error Correction Model (VECM), Long-Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) algorithms have been utilized. LSTM and GRU models have performed better with low Mean Absolute Percentage Error (MAPE) and high R-squared Score (R2). LSTM model has reached 0.98 R2 and 8.95% MAPE. These results indicate that the models can be utilized in network management optimization as resource allocation, congestion detection, anomaly detection, and quality of service. © 2024 IEEE.
Attention-Enhanced Dual-Head LSTM With Rich Feature Engineering for Risk-Adjusted Stock Return Forecasting
(Institute of Electrical and Electronics Engineers Inc., 2025) Patel J.; Gunes P.; Ertugrul S.; Sayar A.; Benli H.; Makaroglu D.; Cakar T.; Benli, Harun; Gunes, Peri; Patel, Jay; Makaroglu, Didem; Sayar, Alperen; Cakar, Tuna; Ertugrul, Seyit
Stock 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.
Churn Prediction for Subscription-Based Applications Using Machine Learning
(Institute of Electrical and Electronics Engineers Inc., 2025) Gozukara H.; Patel J.; 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
In 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.
Citation - WoS: 2
Citation - Scopus: 2
Classification of Altruistic Punishment Decisions by Optical Neuroimaging and Machine Learning Methods
(IEEE, 2023) Erözden, Ozan; Şahin, Türkay; Akyürek, Güçlü; Filiz, Gözde; Çakar, Tuna
Altruistic punishment (third-party punishment) is important in terms of maintaining social norms and promoting prosocial behavior. This study examined data obtained using the near infrared spectroscopy (fNIRS) method to predict altruistic punishment decisions. It was found that specific neural activity patterns were significantly related to decisions regarding the punishment of the perpetrator. This research contributes to the development of social decision-making models and helps advance our understanding of the cognitive and neural processes involved in third-party punishments.
Citation - Scopus: 4
Classification of Skin Lesion Images With Deep Learning Approaches
(University of Latvia, 2022) Kulavuz, Bahadır; Ertuğrul, Berkay; Bakırman, Tolga; Çakar, Tuna; Doğan, Metehan; Bayram, Bülent; Bayram, Buket
Skin cancer is one of the most dangerous cancer types in the world. Like any other cancer type, early detection is the key factor for the patient's recovery. Integration of artificial intelligence with medical image processing can aid to decrease misdiagnosis. The purpose of the article is to show that deep learning-based image classification can aid doctors in the healthcare field for better diagnosis of skin lesions. VGG16 and ResNet50 architectures were chosen to examine the effect of CNN networks on the classification of skin cancer types. For the implementation of these networks, the ISIC 2019 Challenge has been chosen due to the richness of data. As a result of the experiments, confusion matrices were obtained and it was observed that ResNet50 architecture achieved 91.23% accuracy and VGG16 architecture 83.89% accuracy. The study shows that deep learning methods can be sufficiently exploited for skin lesion image classification. © 2022 Baltic Journal of Modern Computing. All rights reserved.
Combining Similar Trajectories and XGBoost via Residual Learning for Traffic Flow Forecasting
(Institute of Electrical and Electronics Engineers Inc., 2025) Işlak U.; Yilmaz E.; Arslan I.; Çakar T.; Çakar, Tuna; Işlak, Ümit; Yilmaz, Elif; Arslan, Ilker
In 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.
Citation - Scopus: 1
Consumer Neuroscience Perspective for Brands: How Do Brands Influence Our Brains?
(IGI Global, 2020) Çakar, Tuna; Girişken, Yener
Neuroscientific tools have increasingly been used by marketing practitioners and researchers to understand and explain several different questions that have been issued for a specific company or a general understanding. In this respect, the neuroscientific approach has been evaluated as a potential tool for understanding the neural mechanisms directly related to marketing with its contribution to providing novel perspectives. The chapter addresses one of the most relevant subjects, brands, for issuing the strategic role of applied neuroscience in marketing and consumer behavior. The first section of this chapter focuses on a novel definition of brand, and the next section covers the brand image, brand perception, and brand loyalty. The second section summarizes the main findings regarding the neuroscience of brands. In the final section, the findings from a related experiment have been provided for the potential roles of neuromarketing for developing marketing strategies for brands.
Curvature Effect on Aesthetic Perception
(Cognitive Science Society, 2022) Demircioğlu, Tuna Esin; Çakar, Tuna; Girişken, Yener
Aesthetic perception is an inseparable part of the decision-making process in daily life. It also is an important partof the beauty and therefore tastes. The determination of preferences is directly related to the subregions of the PFC.The contour is the essential visual attribute for accurately perceiving the form of an object. It has been known thatsharp angles cause an implicit perception of threat, and perceived security is related to aesthetic pleasure. The aim ofthe study is to investigate the effect of contour type on decision making and aesthetic perception in PFC. The studyusing the fNIRS method has shown that there is a marginal significant relation between liking, contour type, and PFCareas (F(3.81)=2.225, p>.092, η2=.076). Current findings suggest that left mPFC, FPC, and right dlPFC have a significantcontribution to the liking of curved objects.
Customer Segmentation and Churn Prediction via Customer Metrics
(IEEE, 2022) Bozkan, Tunahan; Cakar, Tuna; Sayar, Alperen; Ertugrul, Seyit
In this study, it is aimed to predict whether customers operating in the factoring sector will continue to trade in the next three months after the last transaction date, using data-driven machine learning models, based on their past transaction movements and their risk, limit and company data. As a result of the models established, Loss Analysis (Churn) of two different customer groups (Real and Legal factory) was carried out. It was estimated by the XGBoost model with an F1 Score of 74% and 77%. Thanks to this modeling, it was aimed to increase the retention rate of customers through special promotions and campaigns to be made to these customer groups, together with the prediction of the customers who will leave. Thanks to the increase in retention rates, a direct contribution to the transaction volume on a company basis was ensured.
Citation - WoS: 5
Citation - Scopus: 7
Designing restorative landscapes for students: A Kansei engineering approach enhanced by VR and EEG technologies
(Elsevier, 2024) Karaca, Elif; Çakar, Tuna; Karaca, Mehmet; Gul, Hasan Huseyin Mirac; Hüseyin Miraç Gül, Hasan
This study explores the alignment of specific landscape features within school environments with the core elements of Attention Restoration Theory (ART) that includes Coherence, Fascination, Compatibility, and Being Away. Utilizing Kansei Engineering, this research integrates emotional analysis into landscape design by employing Virtual Reality (VR) and Electroencephalogram (EEG) technologies to record students' responses to different landscape simulations. Analytical techniques, including the Taguchi Method and Analysis of Variance (ANOVA), were applied to evaluate the data. The findings have revealed that students associate a sense of enclosure with a coherent landscape and openness with a fascinating landscape, the lawn's significance was also highlighted for coherent landscape. However, limited insights were gained regarding Compatibility and Being Away. The study advocates for diverse cognitive zones within school landscapes to promote mental restoration, emphasizing the need for varied design elements that cater to the elevated experience of students.
Detecting the Effect of Voice-Over in Tv Ads Via Optic Brain Imaging (fnirs) and In-Depth Interview Methods
(Istanbul Univ, 2016) Çakar, Tuna; Girisken, Yener
Voice-overs are used extensively to increase the effectiveness of the TV ads especially in the last decade. The main purpose is to provide the brand message via a clear feature that will inevitably grab the attention of the viewers. The current study contains the neuro tests of 12 TV ads in banking and finance sectors on 168 participants in 8 groups. Optic brain imaging (fNIRS) and in-depth interviews were the methodologies utilized during the test of these TV ads. The obtained results indicate that the use of voice-over during the TV ads possibly causes the decrease in attention and emotional engagement levels of the participants.
Determination of Alzheimer's Disease Levels by Ordinal Logistic Regression and Artificial Learning Algorithms
(Ieee, 2024) Bulut, Nurgül; Çakar, Tuna; Arslan, Ilker; Akinci, Zeynep Karaoglu; Oner, Kevser Setenay
This 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.
Developing Autonomous Steering Algorithm To Improve Cornering Slip Performance of a Four-Wheel Car Using Neural Network Tools
(Institute of Electrical and Electronics Engineers Inc., 2025) Alatciyan D.R.; Emeryan B.J.; Barbaros B.; Cakar T.; Kilic N.; Emeryan, Burak Jirayr; Kilic, Namik; Alatciyan, Diran Robin; Barbaros, Bugra; Cakar, Tuna
This study investigates a neural network-based predictive steering control using simulation data generated from ADAMS Car. A Long Short-Term Memory (LSTM) architecture is employed to estimate steering angle and longitudinal velocity from sequential input features, with the goal of analyzing the model's behavior in cornering scenarios. The experimental setup includes multiple simulation runs under varying configurations, particularly exploring the effect of different sliding window sizes on prediction performance. Results show that the proposed model can effectively capture temporal patterns in the input data and produce consistent estimations across test conditions. While the study is limited to a simulation environment, it provides initial insights into how AI-based models may support steering control tasks and lays the groundwork for future extensions involving additional vehicle dynamics inputs. © 2025 IEEE.
Development of a Knowledge-Based Multimodal Deep Learning System for Automatic Breast Lesion Segmentation and Diagnosis in Mg/Dmr Images
(IEEE, 2023) Orhan, Gözde; Çavuşoğlu, Mustafa; Sürmeli, Hulusi Emre; Çakar, Tuna; Araz, Nusret; Bayram, Bülent
Deep learning networks (DLNs) rely on labeled training datasets as their fundamental building blocks. While various databases exist worldwide, there is currently no domestic solution available in our country. This project aims to create a domestic database by automatically segmenting breast lesions in MG/DMR images based on their types and developing a knowledge-based multimodal DL-based integrated computer-aided diagnosis system to analyze the images, thereby providing the system with continuous learning capability. Different brands of devices exist for MG/DMR, necessitating the multimodal operation of image processing/artificial intelligence algorithms. To achieve this goal, the network was trained first, and then prelearned data were transferred to enable the training of data from different networks once accurate results are obtained. The developed system has the potential to enable the automatic detection of breast lesions, ensuring fast and high diagnostic accuracy. Additionally, it might also facilitate the retrospective analysis of patients' periodic check-up results.

Browse

Browsing Bilgisayar Mühendisliği Bölümü Koleksiyonu by Institution Author "Çakar, Tuna"