Sürdürülebilir Kalkınma Amaçları
Yazarlar
Yayınlar
- MakaleAçık Erişim2026Scopus SJRQ1A leakage-free analytics framework for subject-wise electrocardiogram-based sleep apnea detection using machine learning
Melek, Negin
Sleep apnea is associated with impaired sleep quality and elevated cardiovascular risk, creating a need for reliable automated screening approaches. Although electrocardiogram (ECG)-based detection methods have shown promising results, reported performance values can be affected by evaluation strategies that allow information leakage between training and testing data. This study investigates ECG-based sleep apnea detection under strict subject-wise conditions using the PhysioNet Apnea-ECG database. Thirty-five annotated single-lead ECG recordings sampled at 100 Hz were divided into non-overlapping 60-s segments according to minute-wise apnea labels. Statistical ECG descriptors and time-domain heart rate variability features were extracted and evaluated using k-nearest neighbors (KNN), support vector machine (SVM), and Random Forest (RF) classifiers. In addition, a lightweight one-dimensional convolutional neural network (1D-CNN) was trained directly on filtered ECG segments. Repeated holdout validation with subject-level train-test separation was adopted, and normalization parameters were estimated exclusively from training data in each repetition to prevent information leakage. Model performance was assessed using accuracy, balanced accuracy, precision, recall, specificity, F1-score, ROC-AUC, Cohen's kappa, and Golden Distance (GD). In the representative subject-wise evaluation, Random Forest achieved the most balanced performance, yielding the highest balanced accuracy (0.70) together with the lowest GD (0.56). Across the repeated subject-wise holdout experiments, SVM achieved the strongest average overall performance, producing the highest mean accuracy (0.72), balanced accuracy (0.69), ROC-AUC (0.77), and Cohen's kappa (0.39), and the lowest mean GD value (0.58). The lightweight 1D-CNN converged stably during training, but its performance on unseen subjects remained lower than that of the handcrafted feature-based models.
- MakaleYalnız künye2025Scopus SJRQ3One-step kinetic analysis of Listeria innocua growth as a surrogate for Listeria monocytogenes on arugula leaves with background microbiota: model development and validation
Ozturk, Samet
This study investigated the growth kinetics of L. monocytogenes and L. innocua on fresh arugula leaves under abusive conditions, considering the presence of background microbiota (BM) including (APC (Aerobic Plate Count), TPC (Total Psychrotrophic Count), and LAB (Lactic Acid Bacteria)). Additionally, the feasibility of using L. innocua as a surrogate for L. monocytogenes was evaluated for industrial practices. Predictive models were developed to assess the effect of temperature and time on the growth kinetics of both microorganisms. Experiments were conducted in triplicate to observe growth kinetics at temperatures from 5 to 35°C. The growth curves were analyzed using one-step analysis with the USDA IPMP-Global Fit software, employing the Huang full/no-lag phase growth as the primary models and the Huang sub-optimal (HSRM) and Ratkowsky sub-optimal square-root as the secondary models. An additional set of isothermal data, collected at 15°C and 20°C, was used to validate the models. Results showed that the minimum growth temperatures were 2.91±0.50°C for L. monocytogenes and 2.88±0.50°C for L. innocua, while 2.05±0.89, 1.93±0.98 and 3.55±1.97°C for APC, TPC and LAB, respectively. The specific growth rates of L. monocytogenes and L. innocua ranged from 0.01 to 0.93 h⁻¹. The root mean square error (RMSE) of model validation and development was less than 0.3 log CFU/g, indicating that the combination of the Huang growth model with HSRM could accurately predict the growth of L. monocytogenes under abusive conditions. Validated models can provide useful input to quantitative risk assessment tools to predict the growth of L. monocytogenes on arugula leaves in the presence of BM during distribution or storage. The findings of this study support the use of L. innocua with R2=0.961 as a suitable surrogate in industrial practices for fresh produce.
AtıfScopus1WoS1
İncele