WoS İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14627/6
Browse
3 results
Search Results
Article Machine Learning Model for Predicting Multidrug Resistance in Clinical Klebsiella pneumoniae Isolates(MDPI, 2026) Akkaya, Yuksel; Aydin, Irfan; Tanyildizi-Kokkulunk, Handan; Erturk, Ayse; Kilic, Ibrahim HalilBackground/Objectives: Klebsiella pneumoniae is an opportunistic pathogen increasingly resistant to carbapenems and broad-spectrum antibiotics, complicating timely infection management. In critical cases like septic shock, where initiating effective antibiotics within 3 h improves survival, culture-based resistance testing is often too slow. This study evaluates machine learning (ML) algorithms for faster antimicrobial resistance prediction than conventional methods. Methods: In this retrospective study, antibiogram results of 607 Klebsiella pneumoniae isolates collected between 2017 and 2024 were combined with demographic and clinical information of the patients from whom the isolates were obtained. Four different ML algorithms, namely Decision Tree (DT), Support Vector Classifier (SVC), K-Nearest Neighbors (KNN) and Random Forest (RF), were applied to classify the resistance status for 22 antibiotics. Model performances were evaluated using accuracy, precision, recall, F-score, AUC and feature importance metrics. Results: The RF model showed the highest overall performance in accurately predicting resistance to 22 antibiotics, achieving an average AUC value of 0.96. In particular, it predicted resistance to treatment-critical antibiotics such as Ertapenem (100%), Imipenem (93%) and Meropenem (95%) with high accuracy. Conclusions: ML models, especially RF, offer a powerful tool for rapid antibiotic resistance prediction, supporting accurate empirical treatment decisions and antimicrobial stewardship.Article From Data to Autonomy: Integrating Demographic Factors and AI Models for Expert-Free Exercise Coaching(MDPI, 2026) Ozbalkan, Ugur; Turna, Ozgur CanThis study investigates the performance of three deep learning architectures-LSTM with Attention, GRU with Attention, and Transformer-in the context of real-time, self-guided exercise classification, using coordinate data collected from 103 participants via a dual-camera system. Each model was evaluated over ten randomized runs to ensure robustness and statistical validity. The GRU + Attention and LSTM + Attention models demonstrated consistently high test accuracy (mean approximate to 98.9%), while the Transformer model yielded significantly lower accuracy (mean approximate to 96.6%) with greater variance. Paired t-tests confirmed that the difference between LSTM and GRU models was not statistically significant (p = 0.9249), while both models significantly outperformed the Transformer architecture (p < 0.01). In addition, participant-specific features, such as athletic experience and BMI, were found to affect classification accuracy. These findings support the feasibility of AI-based feedback systems in enhancing unsupervised training, offering a scalable solution to bridge the gap between expert supervision and autonomous physical practice.Article Evaluation of the Barriers to Maintenance 4.0 for the Textile Industry via Pythagorean Fuzzy SWARA(MDPI, 2025) Turan, Hakan; Buyukselcuk, Elif Caloglu; Çaloğlu Büyükselçuk, ElifMaintenance 4.0 studies have become a focus for managers and employees when developing effective and efficient maintenance policies. In this study, the barriers to Maintenance 4.0 applications in the textile industry are investigated, and these barriers are weighted using the Stepwise Weight Assessment Ratio Analysis (SWARA) method based on Pythagorean fuzzy numbers. Solutions to address these barriers are presented. As a result of this study, Organizational and Managerial emerged as the most important main criterion. Operational was identified as the second most significant main criterion, followed by Technical Competence. Data-Related and Cybersecurity ranked fourth in terms of importance. On the other hand, Human Resources and Training and Financial were found to be the least important main criteria. These two criteria received lower importance scores compared to the others, with Financial being the criterion with the lowest overall significance. Sensitivity analyses were performed for six different scenarios by changing the importance weights of the decision-makers. The ranking of the criteria only slightly changed with the weights; this means that the results obtained in Case 1 are robust and reliable. Even in Case 6, where the expert weight ratios were completely reversed, the results did not change significantly. This highlights an important point regarding the reliability of the assessment.