5862 research outputs found
Sort by
AI-Driven Predictive Maintenance for Workforce and Service Optimization in the Automotive Sector
No full textVehicle owners often use certified service centers throughout the warranty period, which usually extends for five years after buying. Nonetheless, after this timeframe concludes, a large number of owners turn to unapproved service providers, mainly motivated by financial factors. This change signifies a significant drop in income for automakers and their certified service networks. To tackle this issue, manufacturers utilize customer relationship management (CRM) strategies to enhance customer loyalty, usually depending on segmentation methods to pinpoint potential clients. However, conventional approaches frequently do not successfully forecast which clients are most likely to need or utilize maintenance services. This research introduces a machine learning-driven framework aimed at forecasting the probability of monthly maintenance attendance for customers by utilizing an extensive historical dataset that includes information about both customers and vehicles. Additionally, this predictive approach supports workforce planning and scheduling within after-sales service centers, aligning with AI-driven labor optimization frameworks such as those explored in the AI4LABOUR project. Four algorithms in machine learning-Decision Tree, Random Forest, LightGBM (LGBM), and Extreme Gradient Boosting (XGBoost)-were assessed for their forecasting capabilities. Of these, XGBoost showed greater accuracy and reliability in recognizing high-probability customers. In this study, we propose a machine learning framework to predict vehicle maintenance visits for after-sales services, leading to significant operational improvements. Furthermore, the integration of AI-driven workforce allocation strategies, as studied within the AI4LABOUR (reshaping labor force participation with artificial intelligence) project, has contributed to more efficient service personnel deployment, reducing idle time and improving customer experience. By implementing this approach, we achieved a 20% reduction in information delivery times during service operations. Additionally, survey completion times were reduced from 5 min to 4 min per survey, resulting in total time savings of approximately 5906 h by May 2024. The enhanced service appointment scheduling, combined with timely vehicle maintenance, also contributed to reducing potential accident risks. Moreover, the transition from a rule-based maintenance prediction system to a machine learning approach improved efficiency and accuracy. As a result of this transition, individual customer service visit rates increased by 30%, while corporate customer visits rose by 37%. This study contributes to ongoing research on AI-driven workforce planning and service optimization, particularly within the scope of the AI4LABOUR project.European Union [101007961]; Dogus Technology; Scientific Technological Research Council of Turkey (TUBITAK); [119C085]; Marie Curie Actions (MSCA) [101007961] Funding Source: Marie Curie Actions (MSCA)This paper was supported by the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie Through the "Reshaping Labour Force Participation with Artificial Intelligence (AI4LABOUR) Project" under Grant 101007961. This paper was also supported by Dogus Technology and The Scientific Technological Research Council of Turkey (TUBITAK) with project number 119C085.Science Citation Index Expande
Putting Your Best Self or No Self at All? an Analysis of Young Adult’s Dating App Profiles in Turkey
No full textSince the widespread use of dating apps across the globe, presenting one’s best self has become a prior issue in attracting potential partners. The literature generally focuses on a single group’s profiles on a single app and examines the role of gender and sexual orientation in putting one’s best face and body or lying about it. However, very few studies draw attention to the role of cultural geography in profile construction, which may suggest that presenting a self in the first place, or self-disclosure, becomes a more significant issue than presenting an ideal self in some cultural settings. This study examines young adults’ profiles on five dating apps popular in Turkey, where there is a powerful social stigma around LGBTI+ individuals and online dating and a sharp cultural division between Eastern and Western regions. It aims to understand the role of cultural geography across users from different genders and sexual orientations in self-disclosure. Based on a quantitative content analysis of 1976 dating app profiles collected across the country, our study finds statistically significant differences in self-disclosure between men and women, heterosexual and non-heterosexual users, and metropolitan and non-metropolitan individuals. In other words, showing one’s face, body, and other verbal information that might reveal one’s identity is highly influenced by one’s gender, sexual orientation, and geographical location. Our research contributes to the literature by not only underlining the significance of cultural geography but also revealing the intersecting role of gender, sexual orientation, and geographical location in self-disclosure. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, TÜBİTAK, (121K687-TÜBİTAK 3501, E-17446481-050.06.04-11584); Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, TÜBİTAKEmerging Sources Citation Inde
Predicting and Optimizing the Fair Allocation of Donations in Hunger Relief Supply Chains
No full textSamanlioglu, Funda/0000-0003-3838-8824Non-profit hunger relief organizations primarily depend on donors' benevolence to help alleviate hunger in their communities. However, the quantity and frequency of donations they receive may vary over time, thus making fair distribution of donated supplies challenging. This paper presents a hierarchical forecasting methodology to determine the quantity of food donations received per month in a multi-warehouse food aid network. We further link the forecasts to an optimization model to identify the fair allocation of donations, considering the network distribution capacity in terms of supply chain coordination and flexibility. The results indicate which locations within the network are under-served and how donated supplies can be allocated to minimize the deviation between overserved and underserved counties. (c) 2024 International Institute of Forecasters. Published by Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.National Science Foundation, NSF, (CNS 2100855, TI-2234598)NSF EiR: Human Centered Visual Analytics for Evidence Based Decision Making in Humanitarian Relief [CNS 2100855]; NSF Partnerships for Innovation: A Smart Food Distribution System for Allocating Scarce Resources Under Extreme Events [TI-2234598]We would like to thank the anonymous referees whose helpful comments greatly improved the presentation of this manuscript. This research is partially funded by NSF EiR: Human Centered Visual Analytics for Evidence Based Decision Making in Humanitarian Relief (Award No.: CNS 2100855) and NSF Partnerships for Innovation: A Smart Food Distribution System for Allocating Scarce Resources Under Extreme Events (Award No. TI-2234598).Social Science Citation Inde
Anomaly Detection and Performance Analysis With Exponential Smoothing Model Powered by Genetic Algorithms and Meta Optimization
No full textBu çalışma, Numenta Anomaly Benchmark'ın (NAB) gerçek zamanlı trafik veri setleri üzerinde tahminleme yapan Third Order Exponential Smoothing modelinin parametrelerini optimize etmek amacıyla genetik algoritma kullanmaktadır. Ayrıca, genetik algoritma optimizasyon sürecini daha verimli hale getirmek için meta-optimizasyon tekniklerinden yararlanılarak anomali tespitindeki doğruluğu önemli ölçüde artıran yenilikçi bir yaklaşım sunmaktadır. Önerilen metodoloji, trafik yönetim sistemlerinde kritik olan veri akışlarındaki sapmaları tespit etmek için çeşitli trafik veri senaryolarına karşı farklı veri setleri üzerinde test edilmiştir. NAB'nin skorlama sistemini kullanarak yapılan karşılaştırmalı performans analizi, bu araştırmada geliştirilen yöntemin mevcut NAB algoritmalarının çoğundan üstün olduğunu ve NAB'nin önde gelen algoritmalarıyla rekabet edebildiğini göstermektedir. 'standart' için 54.32, 'reward_low_FP' için 53.73 ve 'reward_low_FN' için 69.54 skorları elde eden önerilen yaklaşım, sırasıyla NAB algoritmalarının ortalamasına göre %3.13, %2.70 ve %3.24 oranında bir iyileşme sağlamış, önemli bir gelişme kaydetmiştir. Bulgular, önerilen yaklaşımın sadece yüksek hassasiyetle anormallikleri tespit etmekle kalmayıp, aynı zamanda manuel yeniden kalibrasyon gerektirmeden değişen veri özelliklerine dinamik olarak uyum sağladığını göstermektedir. Bu çalışma, güvenilir izleme sağlayan ve potansiyel olarak etkin trafik yönetimi ve planlamayı kolaylaştıran sağlam bir trafik anomali tespit yöntemi önermektedir. Çalışmanın sonuçları, gerçek zamanlı veri izleme ve anormallik tespiti gerektiren diğer alanlara da genişletilebilir, farklı bağlamlar ve gereksinimlere uyum sağlayabilen ölçeklenebilir bir çözüm sunmaktadır.This study employs a genetic algorithm to optimize the parameters of the Third Order Exponential Smoothing model for predicting on the real-time traffic datasets of the Numenta Anomaly Benchmark (NAB). Moreover, it suggests a new approach to apply meta-optimization techniques to make the genetic algorithm optimization process more efficient so as to get improved accuracy in anomaly detection. The proposed methodology has been tested on various traffic data scenarios across different datasets to detect deviations critical to traffic management systems. Comparisons in performance using NAB's scoring system clearly show that the method developed in this research outperforms most of the existing NAB algorithms and competes with the leading algorithms in NAB. Achieving scores of 54.32 for 'standard', 53.73 for 'reward_low_FP', and 69.54 for 'reward_low_FN', the proposed approach shows an improvement of 3.13%, 2.70%, and 3.24% respectively over the average NAB algorithms, marking a significant enhancement. The findings indicate that the proposed approach not only detects anomalies with high precision but also dynamically adapts to changing data characteristics without requiring manual recalibration. This study proposes a robust traffic anomaly detection method that ensures reliable monitoring and potentially facilitates effective traffic management and planning. The results of the study can be extended to other areas requiring real-time data monitoring and anomaly detection, offering a scalable solution adaptable to different contexts and requirements.This study employs a genetic algorithm to optimize the parameters of the Third Order Exponential Smoothing model for predicting on the real-time traffic datasets of the Numenta Anomaly Benchmark (NAB). The genetic algorithm process was executed with different population sizes and gene sets. In addition, a parameter sensitivity analysis was conducted, through which the ideal number of genes and population size providing the best results within the specified range were determined. Moreover, a novel approach incorporating meta-optimization techniques is proposed to enhance the efficiency of the genetic algorithm optimization process, aiming to achieve improved accuracy in anomaly detection. The proposed methodology has been tested on various traffic data scenarios across different datasets to detect deviations critical to traffic management systems. Performance comparisons using the NAB scoring system demonstrate that the method developed in this study outperforms the majority of existing NAB algorithms, as well as the contemporary approaches of Isolation Forest, Multi-Layer Perceptron Regressor (MLPRegressor), and hybrid K-Nearest Neighbors - Gaussian Mixture Models (KNN + GMM), and is competitive with leading algorithms. The proposed approach, which achieved scores of 54.41 for 'Standard', 53.95 for 'reward_low_FP_rate', and 69.61 for 'reward_low_FN_rate', indicates improvements of 3.67%, 4.45%, and 2.63%, respectively, compared to the average scores of the NAB algorithms. The findings indicate that the proposed approach not only detects anomalies with high precision but also dynamically adapts to changing data characteristics without requiring manual recalibration. This study proposes a robust traffic anomaly detection method that ensures reliable monitoring and potentially facilitates effective traffic management and planning.The results of the study can be extended to other areas requiring real-time data monitoring and anomaly detection, offering a scalable solution adaptable to different contexts and requirements.Science Citation Index Expande
Life Cycle Assessment of Black Tea Production and Consumption in Türkiye: Insights From Waste Management Scenarios
No full textUctug, Fehmi Gorkem/0000-0002-7231-5154This study conducts a life cycle assessment (LCA) of tea production and consumption in T & uuml;rkiye, the world leader in per capita tea consumption. Aiming to identify environmental hotspots and propose sustainable solutions, a cradle-to-grave LCA was performed using CCaLC2 software, CML methodology, and the Ecoinvent 3.0 database. It covers cultivation, processing, transportation, and consumption stages, focusing on key environmental indicators like carbon footprint and acidification potential. The results reveal that consumption dominates the environmental footprint (91%) due to energy-intensive brewing methods. Cultivation and transportation contribute minimally (4% each). This highlights the need for promoting energy-efficient brewing practices and consumer adoption of renewable energy sources. The study also explores the environmental implications of different waste management strategies. Composting emerged as the most beneficial approach for reducing the carbon footprint and photochemical oxidants creation, while incineration might be preferable for other impact categories. This study underscores the importance of addressing energy consumption during tea brewing and encouraging renewable energy use among consumers. Additionally, it promotes composting as a crucial waste management strategy for a more sustainable tea value chain in T & uuml;rkiye. These findings offer valuable insights for policymakers, industry players, and tea drinkers to make informed decisions that minimize environmental impact.Scientific and Technological Research Council of Turkiye (TUBITAK)The authors would like to thank the Scientific and Technological Research Council of Turkiye (TUBITAK) for the financial support that enabled this work; as well as Mr. Ozkan Ozbek and Ms. Esin Sevgi from Adana Hac & imath; Sabanc & imath; Organized Industrial Zone for their support during the data collection stage.Science Citation Index Expande
Predicting User Purchases From Clickstream Data: a Comparative Analysis of Clickstream Data Representations and Machine Learning Models
No full textPredicting purchase events from e-commerce clickstream data is a critical challenge with significant implications for optimizing marketing strategies and enhancing customer experience. This study addresses this challenge by systematically evaluating and comparing multiple data representations - aggregated session attributes, recent user actions, and hybrid combinations - which bridges gaps in the existing literature and demonstrates the superiority of hybrid approaches. Unlike prior research, which typically focuses on single representations, our approach combines aggregated session-level summaries with granular, sequential user actions to capture both long-term and short-term behavioral patterns. Through comprehensive experimentation, we compared multiple machine learning models, including LightGBM, decision trees, gradient boosting, SVC, and logistic regression, using real-world e-commerce clickstream data. Notably, the hybrid representation with LightGBM achieved superior predictive performance, significantly outperforming alternative methods. Feature importance analysis revealed key factors influencing purchase likelihood, such as time since the last event, session duration, and product interactions. This study provides actionable insights into real-time marketing interventions by demonstrating the practical utility of hybrid data representations and efficient tree-based models. Our findings offer a scalable and interpretable framework for e-commerce platforms to enhance purchase predictions and optimize marketing strategies.Science Citation Index Expande
Does Attention Sharing Support Attention Focusing? Investigating the Link Between Infants' Sustained Attention and Joint Attention With Caregivers
No full textSustained attention in infancy is a known predictor of executive functions, self-regulation, and language. This study investigated the relationship between 9-to 16-month-old infants' sustained attention and joint attention in mother-infant dyads. Data were collected from 98 infants (M(SD) = 11.8(1.3) months) and their mothers. Results showed that joint attention during mother-infant play significantly predicted sustained attention during solo play, after accounting for infant age and socioeconomic status. These cross-sectional findings suggest that joint attention may play a role in supporting sustained attention, though the directionality of this relationship warrants further longitudinal investigation.Scientific and Technological Research Council of Turkiye [119K854]We extend our gratitude to Nursena Koc, Gizem Akel Guclu, Suheda Nur Erdogan, Ahmet Mete Durmus, Ardakaan Sonmez, Asena Sayin, Huseyin Unlu, Gunce Ugur, Yasemin Seran Ozyurt, Irmak Kalkan, Irem Gungordu, Ozce Sivis, and DilaraOzalp for their assistance with data collection and coding. We also sincerely thank the families who participated in this study. This work was supported by the Scientific and Technological Research Council of Turkiye (Grant ID: 119K854).Social Science Citation Inde
Anti-Veiling Campaigns in Turkey: State, Society and Gender in the Early Republic
No full textSocial Science Citation Inde
A Real-World Case Study Towards Net Zero: Ev Charger and Heat Pump Integration in End-User Residential Distribution Networks
No full textThe electrification of energy systems is essential for carbon reduction and sustainable energy goals. However, current network asset ratings and the poor thermal efficiency of older buildings pose significant challenges. This study evaluates the impact of heat pump and electric vehicle (EV) penetration on a UK residential distribution network, considering the highest coincident electricity demand and worst weather conditions recorded over the past decade. The power flow calculation, based on Python, is performed using the pandapower library, leveraging the actual distribution network structure of the Hillingdon area by incorporating recent smart meter data from a distribution system operator alongside historical weather data from the past decade. Based on the outcome of power flow calculation, the transformer loadings and voltage levels were assessed for existing and projected heat pump and EV adoption rates, in line with national policy targets. Findings highlight that varied consumer density and diverse usage patterns significantly influence upgrade requirements.UKRI [EP/Y023846/1]; International Science Partnerships Fund (ISPF) Institutional Support Grant (ODA) [2024/25]This research was partly funded by UKRI grant no. EP/Y023846/1 and partly by an International Science Partnerships Fund (ISPF) Institutional Support Grant (ODA) 2024/25 Pump priming Award.Science Citation Index Expande
Acculturation Strategies of International Higher Education Students in Türkiye: the Role of Social Support, Cultural Capital, Self-Esteem, General Trust, and General Self-Efficacy
No full textUnderstanding the factors influencing acculturation strategies among international students cannot be overstated, as successful adaptation is crucial for academic success and overall well-being. Although extensive research has explored these dynamics in various contexts, a notable gap remains in the literature on international students in T & uuml;rkiye. This study aimed to investigate the effects of social support, cultural and economic capital, self-esteem, general trust, and general self-efficacy on the acculturation strategies of international higher-education students in T & uuml;rkiye. Utilizing data from 3,554 international students, various scales and questionnaires were employed, including the Acculturation Strategies Scale, Cultural Capital Questionnaire, Economic Capital Questionnaire, Self-Esteem Scale, General Confidence Scale, General Self-Efficacy Scale, and Social Support Questionnaire. The collected data were analyzed using correlation and multiple regression analyses. The results revealed significant relationships between the examined factors and acculturation strategies adopted by international students. These findings highlight the crucial roles of social support, cultural capital, and psychological attributes in shaping how international students adapt to new cultural environments. The implications of these results underscore the importance of targeted support programs to enhance international students' acculturation experiences and overall well-being in T & uuml;rkiye's higher education context.TUBIdot;TAK (The Scientifc and Technological Research Council of Turkiye) [122K718]This work was supported by TUB & Idot;TAK (The Scientifc and Technological Research Council of Turkiye) within the scope of the project numbered 122K718.Social Science Citation Inde