The recent studies indicate that the protein secondary structure provides very important advantages in determining the function of a protein, treating numerous diseases and drug design. Determining the secondary structure in the laboratory environment is both costly and challenging. Therefore, the prediction of protein secondary structure has been an important study field of bioinformatics and computational biology for many years. The aim of this paper was to provide a contribution to the prediction of protein secondary structure using the nature-inspired methods. The data in the first phase were trained with clonal selection algorithm (CSA) which was modeled by being inspired by the live immune system. The classification was then performed with multilayer perceptron which is one of the deep learning methods modeled by being inspired by the biological nervous system. The results obtained indicated that training of the data with CSA prior to classification contributed positively to classification success.

Personal protective equipment (PPE) detection requires architectures balancing accuracy and computational efficiency for real-time safety monitoring. This study presents the first comprehensive benchmarking and systematic comparative evaluation of YOLO26 (released January 2026) against YOLOv11 across diverse PPE detection scenarios, with the primary goal of providing evidence-based deployment guidelines rather than proposing a new architecture. A total of 30 model configurations were evaluated across 5 model scales, 2 architectures, and 3 datasets under rigorously controlled conditions using identical hardware (NVIDIA A100-80GB), hyperparameters, and COCO-pretrained initialization across CHV (133 images, 6 classes), SHEL5K (1000 images, 3 classes), and SH17 (1620 images, 17 classes) datasets. Results reveal consistent scale-dependent patterns: YOLOv11 excels at nano and small scales across all datasets, while YOLO26 achieves superiority at large and X-Large scales with advantages ranging from 1.3 to 3.1 percent mAP50–95. An exploratory negative correlation ($r=-0.98$, $n=3$) between dataset size and YOLO26 performance advantage was observed; given the small number of data points, this should be interpreted as a preliminary finding warranting further investigation rather than a statistically robust relationship. YOLOv11 provides 15 to 20 percent faster training and 9 to 18 percent faster inference, while YOLO26 demonstrates superior parameter efficiency (0.0237 vs. 0.0233 mAP per million parameters). Findings provide evidence-based, conditional deployment guidance for industrial safety applications: YOLOv11 is recommended for latency-constrained edge scenarios at nano/small scales, while YOLO26 is preferred for accuracy-critical applications at large/X-Large scales with limited training data. These recommendations address key challenges in few-shot learning, small object detection, and data-scarce deployment regimes, and are intended as practical guidelines rather than claims of general architectural superiority.

Customer churn is a critical concern in the Software as a Service (SaaS) sector, potentially impacting long-term growth within the cloud computing industry. The scarcity of research on customer churn models in SaaS, particularly regarding diverse feature selection methods and predictive algorithms, highlights a significant gap. Addressing this would enhance academic discourse and provide essential insights for managerial decision-making. This study introduces a novel approach to SaaS churn prediction using the Whale Optimization Algorithm (WOA) for feature selection. Results show that WOA-reduced datasets improve processing efficiency and outperform full-variable datasets in predictive performance. The study encompasses a range of prediction techniques with three distinct datasets evaluated derived from over 1,000 users of a multinational SaaS company: the WOA-reduced dataset, the full-variable dataset, and the chi-squared-derived dataset. These three datasets were examined with the most used in literature, k-nearest neighbor, Decision Trees, Naïve Bayes, Random Forests, and Neural Network techniques, and the performance metrics such as Area Under Curve, Accuracy, Precision, Recall, and F1 Score were used as classification success. The results demonstrate that the WOA-reduced dataset outperformed the full-variable and chi-squared-derived datasets regarding performance metrics.

This study proposes a comprehensive dual-module agricultural decision support system that integrates machine learning algorithms for both crop and fertilizer recommendations. The system addresses critical challenges in modern agriculture by providing evidence-based recommendations to optimize productivity while maintaining sustainability. Four machine learning algorithms (Random Forest, Support Vector Machine, XGBoost, and K-Nearest Neighbors) were implemented and evaluated using comprehensive agricultural datasets containing 2,200 crop samples and 3,100 fertilizer samples. The crop recommendation module achieved 99.32% accuracy using Random Forest, while the fertilizer recommendation module attained 98.75% accuracy. The system incorporates advanced techniques including SMOTE for handling class imbalance, GridSearchCV for hyperparameter optimization, and SHAP analysis for model interpretability. Comparative analysis with existing literature demonstrates competitive performance while offering enhanced explainability and dual functionality. The developed framework provides a foundation for region-specific implementations and represents a practical contribution to intelligent agricultural decision support systems.

Solar energy forecasting plays a crucial role in renewable energy integration and grid stability management. This study presents a comprehensive comparative analysis of machine learning and deep learning models for solar energy production forecasting using meteorological data. The research evaluates eight distinct forecasting approaches, including Long Short-Term Memory (LSTM) networks, XGBoost, linear regression variants (Linear, Ridge, Lasso), and classical time series models (ARIMA, SARIMA, Prophet), on both daily and hourly solar energy datasets. The meteorological dataset incorporates temperature, relative humidity, precipitation, cloud cover, sunshine duration, shortwave radiation, wind speed, and wind direction variables collected from the Kartepe region over seven years (2014-2020). Advanced preprocessing techniques, including feature extraction, lagged variables, moving averages, and robust scaling, were implemented to enhance model performance. The experimental evaluation employed k-fold cross-validation with statistical significance testing and confidence interval analysis to ensure robust model comparison. Results demonstrate that LSTM networks achieve strong performance on hourly data with $R^2 = 0.9622$ and RMSE = 9.92 kWh, effectively capturing complex temporal dependencies. For daily forecasting, Ridge regression exhibits good performance with $R^2 = 0.9997$ and RMSE = 8.53 kWh, demonstrating effective generalization capabilities. XGBoost shows competitive performance on hourly data ($R^2 = 0.9541$, RMSE = 10.94 kWh) while maintaining computational efficiency. Classical time series models, including ARIMA and SARIMA, demonstrate limitations in capturing complex meteorological relationships, particularly in high-frequency datasets. The study reveals that meteorological variables significantly enhance forecasting accuracy compared to approaches relying solely on historical production values. The research provides practical insights for renewable energy system operators and contributes to solar energy forecasting methodologies through detailed performance comparisons across multiple temporal resolutions.