One of the most expensive and fatal natural disasters in the world is forest fires. For this reason, early discovery of forest fires helps minimize mortality and harm to ecosystems and forest life. The present research enriches the body of knowledge by evaluating the effectiveness of an efficient wildfire and smoke detection solution implementing ensembles of multiple convolutional neural network architectures tackling two different computer vision tasks in a stage format. The proposed architecture combines the YOLO architecture with two weights with a voting ensemble CNN architecture. The pipeline works in two stages. If the CNN detects the existence of abnormality in the frame, then the YOLO architecture localizes the smoke or fire. The addressed tasks are classification and detection in the presented method. The obtained model’s weights achieve very decent results during training and testing. The classification model achieves a 0.95 F1-score, 0.99 accuracy, and 0.98e sensitivity. The model uses a transfer learning strategy for the classification task. The evaluation of the detector model reveals strong results by achieving a 0.85 mean average precision with 0.5 threshold (mAP@0.5) score for the smoke detection model and 0.76 mAP for the combined model. The smoke detection model also achieves a 0.93 F1-score. Overall, the presented deep learning pipeline shows some important experimental results with potential implementation capabilities despite some issues encountered during training, such as the lack of good-quality real-world unmanned aerial vehicle (UAV)-captured fire and smoke images.

Fatigue detection in elderly individuals is critical for preventing health complications and enhancing quality of life. This study presents a comprehensive approach to monitoring and classifying fatigue states using electrocardiogram (ECG) signals, leveraging advanced machine learning techniques. The proposed methodology involves five key stages: ECG signal acquisition, preprocessing, feature extraction, dimensionality reduction using Principal Component Analysis (PCA), and classification through recurrent neural network models. Among the evaluated models, the Gated Recurrent Unit (GRU), the Long Short-Term Memory (LSTM) model, and the standard Recurrent Neural Network (RNN) model exhibited the performance, of 98.86%, 97.73%, and 82.76%. respectivily. The results underscore the GRU model’s superior ability to classify fatigue states accurately, highlighting its potential for real-time applications in elderly care. This study emphasizes the importance of robust signal processing and advanced neural architectures in developing efficient fatigue detection systems, paving the way for improved health monitoring solutions for aging populations.