Diabetic retinopathy (DR) is a diabetes disorder that disturbs human vision. It starts due to the damage in the light-sensitive tissues of blood vessels at the retina. In the beginning, DR may show no symptoms or only slight vision issues, but in the long run, it could be a permanent source of impaired vision, simply known as blindness in the advanced as well as in developing nations. This could be prevented if DR is identified early enough, but it can be challenging as we know the disease frequently shows rare signs until it is too late to deliver an effective cure. In our work, we recommend a framework for severity grading and early DR detection through hybrid deep learning Inception-ResNet architecture with smart data preprocessing. Our proposed method is composed of three steps. Firstly, the retinal images are preprocessed with the help of augmentation and intensity normalization. Secondly, the preprocessed images are given to the hybrid Inception-ResNet architecture to extract the vector image features for the categorization of different stages. Lastly, to identify DR and decide its stage (e.g., mild DR, moderate DR, severe DR, or proliferative DR), a classification step is used. The studies and trials have to reveal suitable outcomes when equated with some other previously deployed approaches. However, there are specific constraints in our study that are also discussed and we suggest methods to enhance further research in this field.

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.

Proactively detecting schizophrenia relapse remains a critical challenge in psychiatric care, where traditional predictive models often fail to capture the complex neurophysiological and behavioral dynamics preceding recurrence. Existing methods typically rely on shallow architectures or unimodal data sources, resulting in limited sensitivity—particularly in the early stages of relapse. In this study, we propose a CNN-Transformer fusion model that leverages the complementary strengths of Convolutional Neural Networks (CNNs) and Transformer-based architectures to process electroencephalogram (EEG) signals enriched with clinical and sentiment-derived features. This hybrid framework enables joint spatial-temporal modeling of relapse indicators, allowing for a more nuanced and patient-specific analysis. Unlike previous approaches, our model incorporates a multi-resource data fusion pipeline, improving robustness, interpretability, and clinical relevance. Experimental evaluations demonstrate a superior prediction accuracy of 97%, with notable improvements in recall and F1-score compared to leading baselines. Moreover, the model significantly reduces false negatives, a crucial factor for timely therapeutic intervention. By addressing the limitations of unimodal and superficial prediction strategies, this framework lays the groundwork for scalable, real-world applications in continuous mental health monitoring and personalized relapse prevention.

The Internet of Underwater Things (IoUTs) enables various underwater objects be connected to accommodate a wide range of applications, such as oil and mineral exportations, disaster detection, and tracing tracking systems. As about 71% of our earth is covered by water and one-fourth of the population lives around this, the IoUT expects to play a vital role. It is imperative to pursue reliable communication in this vast domain, as human beings’ future depends on water activities and resources. Therefore, there is a urgent need for underwater communication to be reliable, end-to-end secure, and collision/void node-free, especially when the routing path is established between sender and sonobuoys. The foremost issue discussed in this area is its routing path, which has high security and bandwidth without simultaneous multiple reflections. Short communication range is also a problem (because of an absence of inter-node adjustment); the acoustic signals have short ranges and maximum-scaling factors that cause a delay in communication. Therefore, we proposed Rotational Orbit-Based Inter Node Adjustment (ROBINA) with variant Path-Adjustment (PA-ROBINA) and Path Loss (PL-ROBINA) for IoUTs to achive reliable communication between the sender and sonobuoys. Additionally, the mathematical-based path loss model was discussed to cover the PL-ROBINA strategy. Extensive simulations were conducted with various realistic parameters and the results were compared with state-of-the-art routing protocols. Extensive simulations proved that the proposed routing scheme outperformed different realistic parameters; for example, packet transmission 45% increased with an average end-to-end delay of only 0.3% respectively. Furthermore, the transmission loss and path loss (measured in dB) were 25 and 46 dB, respectively, compared with other algorithms, for example, EBER² 54%, WDFAD-BDR 54%, AEDG 49%, ASEGD 55%, AVH-AHH-VBF 54.5%, and TANVEER 39%, respectively. In addition, the individual parameters with ROBINA and TANVEER were also compared, in which ROBINA achieved a 98% packet transmission ratio compared with TANVEER, which was only 82%.

Wireless sensor networks deployed in energy-constrained environments face critical challenges relating to sustainability and protection. This paper introduces an innovative blockchain-powered safe energy-swapping protocol that enables sensor nodes to voluntarily and securely trade excess energy, optimizing usage and prolonging lifespan. Unlike traditional centralized management schemes, the proposed approach leverages blockchain technology to generate an open, immutable ledger for transactions, guaranteeing integrity, visibility, and resistance to manipulation. Employing smart contracts and a lightweight Proof-of-Stake consensus mechanism, computational and power costs are minimized, making it suitable for WSNs with limited assets. The system is built using NS-3 to simulate node behavior, energy usage, and network dynamics, while Python manages the blockchain architecture, cryptographic security, and trading algorithms. Sensor nodes checked their power levels and broadcast requests when energy fell under a predefined threshold. Neighboring nodes with surplus power responded with offers, and intelligent contracts facilitated secure exchanges recorded on the blockchain. The Proof-of-Stake-based consensus process ensured efficient and secure validation of transactions without the energy-intensive need for Proof-of-Work schemes. The simulation results indicated that the proposed approach reduces wastage and significantly boosts network resilience by allowing nodes to remain operational longer. A 20% increase in lifespan is observed compared to traditional methods while maintaining low communication overhead and ensuring secure, tamper-proof trading of energy. This solution provides a scalable, safe, and energy-efficient answer for next-generation WSNs, especially in applications like smart cities, precision agriculture, and environmental monitoring, where autonomy of energy is paramount.

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.