Background/Objective: Sleep is significant for human mental and physical health. Sleep disorders represent a crucial risk to human health, and a large portion of the world population suffers from them. The efficient identification of sleep disorders is significant for effective treatment. However, the precise and automatic detection of sleep disorders remains challenging due to the inter-subject variability, overlapping symptoms, and reliance on single-modality physiological signals. Methods: To address these challenges, a Neurophysiological Residual Gated Attention Multimodal Transformer Encoder (NRGAMTE) model was developed for robust sleep disorder detection using multimodal physiological signals, including Electroencephalogram (EEG), Electromyogram (EMG), and Electrooculogram (EOG). Initially, raw signals are segmented into 30-s windows and processed to capture the significant time- and frequency-domain features. Every modality is independently embedded by a One-Dimensional Convolutional Neural Network (1D-CNN), which preserves signal-specific characteristics. A Modality-wise Residual Gated Cross-Attention Fusion (MRGCAF) mechanism is introduced to select significant cross-modal interactions, while the learnable residual path ensures that the most relevant features are retained during the gating process. Results: The developed NRGAMTE model achieved an accuracy of 94.51% on the Sleep-EDF expanded dataset and 99.64% on the Cyclic Alternating Pattern (CAP Sleep database), significantly outperforming the existing single- and multimodal algorithms in terms of robustness and computational efficiency. Conclusions: The results shows that NRGAMTE obtains high performance across multiple datasets, significantly improving detection accuracy. This demonstrated their potential as a reliable tool for clinical sleep disorder detection.

Currently, the dynamic nature of traffic management demands mobile surveillance capabilities, which are practical for the integration of 5G networks and edge computing advancements. The advancement of Multi-access Edge Computing (MEC) has enabled data processing closer to the source, significantly reducing latency and enhancing responsiveness. Cities require dynamic and difficult monitoring strategies to identify illegally parked vehicles effectively. Mobile surveillance is effectively carried out using platforms such as Unmanned Aerial Vehicles (UAVs) or ground vehicles, which gather multimodal data and transmit it to the closest edge server through a 5G connection for rapid processing. The edge server transmits actionable insights to the control unit with minimal delay, allowing an effective arrangement of real-time reduction strategies. Vehicles equipped with cameras and sensors traverse urban areas, capture roadside data, and transmit it to nearby edge servers through a 5G network for real-time analysis. EfficientDet is employed as the main object detection model to accurately localize vehicles within the video frames. Ontology-based reasoning permits surveillance data and facilitates the construction of knowledge graphs. Semantic queries are stated using SPARQL, and Description Logics (DL) allows recapture information without the need to store full video sequences. The proposed EfficientDet-Based Smart Parking System provides a better accuracy of 98.4% than the existing Onto-ViBeNet (Ontology-enhanced Vehicle Behavior Prediction with YOLOv5s).