Journal of Artificial Intelligence and Metaheuristics

Earthquakes are among the most destructive natural hazards, causing severe damage to communities, loss of life, and major economic consequences. This study evaluates machine-learning models for magnitude prediction using an open-access global earthquake dataset from 2023. Five regressors are compared: Light Gradient Boosting Machine (LightGBM), Support Vector Regression (SVR), k-Nearest Neighbors (KNN), Ridge Regression, and Extra Trees. Training uses stratified cross-validation and hyperparameter optimization. The evaluation covers Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Bias Error (MBE), the coefficient of determination (R2), Nash–Sutcliffe Efficiency (NSE), Willmott Index (WI), Pearson’s correlation coefficient (r), and Relative RMSE (RRMSE). LightGBM performs best in the reported comparison, attaining MSE = 0.0474 and R2 = 0.9241. Its leaf-wise tree construction, scalability, and regularization support generalization to unseen data while maintaining computational efficiency. The results indicate that LightGBM can capture patterns in high-dimensional seismic data and provide a reproducible analytical framework for earthquake-prone regions. In combination with other advanced ML systems, such models may contribute to early-warning research, faster emergency response, and better-informed risk planning. The use of an open dataset and documented modeling steps also supports transparency and collaborative research.

Brain tumor research is essential for timely detection and appropriate treatment. Diagnosis is challenging because tumors vary in morphology, size, location, surface texture, and visual appearance across medical images. This study proposes a combined method for brain tumor detection from MRI images using three publicly available datasets containing 3,966 T1-weighted contrast-enhanced magnetic resonance images (T1-w MRI), classified as glioma, meningioma, pituitary tumor, or no tumor. The diagnostic pipeline applies preprocessing and data augmentation to improve image quality and variability. It then uses a VGG16 deep convolutional neural network to extract features and a Support Vector Machine (SVM) classifier to predict the class. The modified VGG16 output is supplied to the SVM, producing a test accuracy of 97.2%. Results from XGBoost, AdaBoost, Decision Tree, and K-Nearest Neighbors classifiers show that the SVM endpoint classifier performs best among the evaluated alternatives.

Accurate rainfall prediction supports resilient communities, sustainable agriculture, water distribution, and disaster preparedness. Because rainfall depends nonlinearly on interacting meteorological conditions, conventional forecast-ing methods can be inadequate for short-term, localized events. This study develops a machine-learning framework for next-day rainfall classification using daily weather observations from 20 major U.S. cities during 2024–2025. The dataset includes temperature, relative humidity, wind speed, precipitation, cloud cover, and pressure, together with a binary Rain Tomorrow label. Six classifiers are evaluated: Random Forest, Support Vector Machine (RBF kernel), k-Nearest Neighbors, Logistic Regression, Naive Bayes, and Linear SVM. SHapley Additive exPlanations (SHAP) are used to interpret model predictions and feature contributions. Random Forest reports the strongest results, with precision, recall, and F1-score of 1.00; RBF SVM and KNN achieve F1-scores of 0.97 and 0.94, respectively. Logistic Regression, Linear SVM, and Naive Bayes achieve F1-scores between 0.76 and 0.77. SHAP analysis identifies precipitation and humidity as the most influential variables, consistent with meteorological expectations. These results suggest that combining an ensemble classifier with interpretable explanations can support transparent rainfall forecasting for agriculture, urban planning, and emergency response.

The rapid development of smart-city infrastructure and the complexity of urban environments increase the need for automated systems that detect violence in surveillance footage. This paper presents a deep-learning architecture for detecting violence and weapon-related activity in CCTV footage using the Smart-City CCTV Violence Detection (SCVD) dataset. MobileNetV2 extracts spatial features from video frames through TimeDistributed layers, and a stacked Long Short-Term Memory (LSTM) network models temporal dependencies. The system processes 15-frame sequences at a resolution of 128 × 128 pixels. Batch normalization and dropout are used to improve generalization and limit overfitting, while a sigmoid output produces binary classifications. On the SCVD evaluation, the model achieved 99.58% accuracy and a binary cross-entropy loss of 0.0139. The Normal class achieved precision, recall, and F1-score values of 0.99; the Violence class metrics were reported as 1.00 after rounding. These results indicate the potential of compact spatiotemporal models for reliable surveillance and deployment on edge devices such as smart cameras and embedded systems.

Internet of Things devices, which spread across consumer industrial and critical infrastructure domains, have boosted the quantity of diverse network traffic and its high frequency. The increasing scale of IoT networks causes problems securing the diverse data flow within these networks, threatening system performance and management capabilities. Analyzing network traffic with traditional methods based on signature identification and rule detection becomes ineffective for new traffic activity patterns and system behavior. Due to extensive growth in IoT networks, developing intelligent data-based classification systems that can process IoT traffic quickly and at large operational scales becomes essential. A detailed model of flow-level data-based machine learning operations for IoT traffic classification utilizes features extracted from the Army Cyber Institute (ACI) IoT dataset. The dataset encompasses statistical, temporal, and protocol-specific attributes for benign and malicious network flows. Our methodology first conducts a strict data preprocessing stage, which involves numerous operations such as cleaning the data, normalizing it and encoding the labels, and performing a feature correlation analysis before preparing the learning algorithms with a suitable quality and balanced dataset. Various classification models underwent training, including Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Naive Bayes and SGD Classifiers, and statistical learners. Our proposed hybrid ensemble method combines weighted voting between a deep learning neural network, a Random Forest model, and an XGBoost classifier to overcome the limitations of single classifiers. This ensemble model aimed to make the system more resilient while lowering bias and enhancing its ability to understand various IoT traffic patterns. A complete set of evaluation metrics assessed the models, using accuracy, precision, recall, F1-score, Hamming loss, Matthews correlation coefficient (MCC) and Cohen’s Kappa plus balanced accuracy and log loss for assessment. The chosen metrics allowed researchers to monitor model performance from global and detailed perspectives when dealing with imbalanced classes and similar patterns between legitimate and malicious network traffic. The ensemble methodology produces superior results than individual classifiers demonstrated through experimental results under all performance metrics evaluation. The complex nature of network environments demonstrates that model fusion achieves excellent results when tracking non-easy-to-classify traffic patterns. The ensemble approach proves excellent generalization properties and optimized performance for real-time IoT implementations because of its ability to adapt continuously while maintaining high accuracy levels. This proposed framework adds to intelligent IoT traffic analysis research while demonstrating how deep learning and traditional machine learning methods enhance ensemble systems. The system develops an expandable and clear quantitative solution that can be implemented for advanced network security systems and traffic monitoring applications across smart cities industrial settings, and critical infrastructure frameworks.