This research introduces a hybrid approach combining bio- and nature-inspired metaheuristic algorithms to enhance scheduling efficiency and minimize energy consumption in Underwater Acoustic Sensor Networks (UASNs). Five hybridized algorithms are designed to efficiently schedule nodes, reducing energy costs compared to existing methods, and addressing the challenge of unscheduled nodes within the communication network. The hybridization techniques such as Elephant Herding Optimization (EHO) with Genetic Algorithm (GA), Firefly Algorithm (FA), Levy Firefly Algorithm (LFA), Bacterial Foraging Algorithm (BFA), and Binary Particle Swarm Optimization (BPSO) are used for optimization. To implement these optimization techniques, the Scheduled Routing Algorithm for Localization (SRAL) is introduced, aiming to enhance node scheduling and localization. This framework is crucial for improving data delivery, optimizing Route REQuest (RREQ) and Routing Overhead (RO), while minimizing Average End-to-End (AE2E) delays and localization errors. The challenges of node localization, RREQ reconstruction at the beacon level, and increased RO, along with End-to-End delays and unreliable data forwarding, have a significant impact on overall communication in underwater environments. The proposed framework, along with the hybridized metaheuristic algorithms, show great potential in improving node localization, optimizing scheduling, reducing energy costs, and enhancing reliable data delivery in the Internet of Underwater Things (IoUT)-based network.

Depression relapse is a common issue during long-term care. We introduce a privacy-aware explainable personalized federated learning (PFL) framework that incorporates layer-wise relevance propagation and Shapley value analysis to provide patient-specific interpretable predictions from EEG. The study is conducted with the publicly available Healthy Brain Network (HBN) dataset, with analysis conducted for n = 100 subjects with resting-state 128-channel EEG with accompanying psychometric scores, and subject-wise 10-fold cross-validation is used to assess the performance of the model. Multi-channel EEG features and standardized symptom scales are jointly modeled to both increase the clinical context of the model and avoid leakage issues. This results in overall accuracy, precision, recall, and F1-score values of 92%, 91%, 93%, and 90.5%, respectively. The attribution maps from the model suggest region-anchored spectral patterns that are associated with relapse risk, providing clinical interpretability, and the federated setup of the model allows for a privacy-aware training setup that is more easily adaptable to multi-site deployment. Together, these results suggest a scalable and clinically feasible approach to trustworthy relapse monitoring with earlier intervention.