Sivas Cumhuriyet University Research Information System
Not a member yet
61356 research outputs found
Sort by
SCIENTIFIC PUBLICATION MAP OF ARTIFICIALINTELLIGENCE AND MULTI-CRITERIA DECISION-MAKINGSTUDIES
No full textEvaluation of Socioeconomic Conditions and Land Use of Beekeeping Activities in Artvin-Şavşat Region
No full textEvaluation of Risk Determinants and Molecular Characterisation for Non-Primate Hepacivirus Infection in Turkish Horses.
No full textCOMBINED USE OF KANGAROO CARE AND BREASTFEEDINGASSISTED SYSTEM / DRIP SYSTEM TOENSURE BREASTFEEDING CONTINUITY
No full textBankaların Risk Alma Davranışını Etkileyen Faktörler: Türk Bankacılık Sektöründen Kanıtlar
No full textBu araştırma, 2010-2023 dönemi için Türkiye'deki ticari bankaların risk almasını etkileyen faktörleri ampirik olarak analiz etmektedir. Geliştirilen panel veri regresyon modellerinde banka risk alma ölçütü olarak ters Z skoru kullanılırken, bağımsız değişken olarak çeşitli banka düzeyi ve makro düzey değişkenler kullanılmıştır. Bu makalede geliştirilen modeller, tüm bankaları içeren ana örneklem ve oluşturulan alt örneklemler için ayrı ayrı tahmin edilmiştir. Sabit etkili regresyonlardan elde edilen sonuçlara göre, banka büyüklüğü, banka sermayesi, banka mevduatı ve net faiz marjı değişkenleri ana örneklem açısından banka risk alma düzeyini azaltma eğilimindedir. Ancak likidite riski, kredi riski, enflasyon oranı, ekonomik büyüme ve COVID-19 pandemi krizi banka risk alma düzeyini artırma eğilimindedir. Halka açık, halka açık olmayan, yerli ve yabancı bankalardan oluşan alt örneklemlerden elde edilen bulgular, banka büyüklüğü, banka sermayesi ve net faiz marjının banka risk alma düzeyini azaltma eğiliminde olduğunu göstermektedir ki bu da ana örneklemden elde edilen bulguları desteklemektedir. Son olarak, bu makalenin sonuçları, bankaların risk alma davranışlarının kontrol edilmesi, bankacılık sektöründe istikrarın sağlanması ve sürdürülebilir bir bankacılık sektörünün oluşturulması açısından banka yönetimi, düzenleyici mekanizmalar ve politika yapıcılar için önemli çıkarımlara sahiptir.This research employs an empirical approach to analyse the factors affecting the risk- taking of commercial banks in Turkey for the period 2010-2023. The inverse Z score was utilised as a measure of bank risk-taking in the developed panel data regression models, while various bank-level and macro-level variables were employed as independent variables. The developed models in this article are estimated separately for the main sample, which includes all banks, and for the sub-samples that have been formed. According to the results based on fixed effects regressions, bank size, bank capital, bank deposit and net interest margin variables tend to reduce the level of bank risk taking in terms of the main sample. However, liquidity risk, credit risk, inflation rate, economic growth and the COVID-19 pandemic crisis tend to increase the level of bank risk taking. Findings from subsamples of listed, non-listed, domestic and foreign banks indicate that bank size, bank capital and net interest margin tend to reduce the level of bank risk taking, which supports the findings from the main sample. Finally, the results of this article have important implications for bank management, regulatory mechanisms and policy makers in terms of controlling the risk-taking behavior of banks, ensuring stability in the banking sector and building a sustainable banking sector
Prediction of obesity levels based on physical activity and eating habits with a machine learning model integrated with explainable artificial intelligence
No full textObjectives: This study aims to build a machine learning (ML) prediction model integrated with explainable artificial intelligence (XAI) to categorize obesity levels from physical activity and dietary patterns. The inclusion of XAI methodologies facilitates a comprehensive understanding of the risk factors influencing the model predictions and thus increases transparency in the identification of obesity risk factors.Methods: Six ML models were used: Bernoulli Naive Bayes, CatBoost, Decision Tree, Extra Trees Classifier, Histogram-based Gradient Boosting and Support Vector Machine. For each model, hyperparameters were tuned by random search methodology and model effectiveness was evaluated by repeated holdout testing. SHAP (SHapley Additive Annotations) and LIME (Local Interpretable Model Independent Annotations) interpretability methods were used to generate local and global feature importance measures.Results: The CatBoost model exhibited the highest overall performance and achieved superior results in accuracy, precision, F1 score and AUC metrics. Nonetheless, other models such as Decision Tree and Histogram-based Gradient Boosting also yielded strong and competitive results. The results also highlighted age, weight, height and specific food patterns as key predictors of obesity. In terms of interpretability, LIME showed superior in fidelity, whereas SHAP showed improved sparsity and consistency across models, facilitating a comprehensive understanding of trait importance.Conclusion: This research demonstrates that ML algorithms, when integrated with XAI technologies, can accurately predict obesity levels and explain important contributing risk factors. The use of SHAP and LIME increases model transparency, facilitating the identification of specific lifestyle patterns linked to obesity risk. These findings help to formulate more precise intervention techniques guided by a reliable and understandable predictive framework.</p
Genetic and Morphological Diversity of Tenthredopsis (Tenthredinidae: Symphyta: Hymenoptera) Species: A Case Study in Anatolia
No full textThe genus Tenthredopsis (Tenthredinidae: Hymenoptera), characterized by a Palearctic distribution, is widely recognized as a taxonomic challenge due to its limited morphological variation. This study aims to evaluate the phylogenetic and biogeographical characteristics of Tenthredopsis species in Anatolia by analyzing their morphological and molecular traits. Initially, morphotypes were defined based on morphological characters, and the taxonomic validity of each morphotype was assessed through phylogenetic analyses using three mitochondrial gene regions. The findings revealed congruence between morphological and molecular data. The study identified the distribution of 27 taxa within Anatolia, comprising 17 confirmed and 10 potential taxa, represented by 250 individuals belonging to the genus Tenthredopsis. The results underscore Anatolia's significance as a hotspot for genetic and morphological diversity within the genus Tenthredopsis and highlight its critical role in the evolutionary adaptations of these species. Additionally, the observed distribution patterns further support the importance of Anatolia as a refugium during the last glacial periods
