Wireless body area networks (WBANs) are a research area that supports patients with healthcare monitoring. In WBAN, the Internet of Things (IoT) is connected with WBAN for a smart/remote healthcare monitoring system in which various medical diseases are diagnosed. Quality of service (QoS), security and energy efficiency achievements are the major issues in the WBAN-IoT environment. Existing schemes for these three issues fail to achieve them since nodes are resource constrained and hence delay and the energy consumption is minimized. In this paper, a blockchain-assisted delay and energy aware healthcare monitoring (B-DEAH) system is presented in the WBAN-IoT environment. Both body sensors and environment sensors are deployed with dual sinks for emergency and periodical packet transmission. Various processes are involved in this paper, and each process is described as follows: Key registration for patients using an extended version of the PRESENT algorithm is proposed. Cluster formation and cluster head selection are implemented using spotted hyena optimizer. Then, cluster-based routing is established using the MOORA algorithm. For data transmission, the patient block agent (PBA) is deployed and authenticated using the four Q curve asymmetric algorithm. In PBA, three entities are used: classifier and queue manager, channel selector and security manager. Each entity is run by a special function, as packets are classified using two stream deep reinforcement learning (TS-DRL) into three classes: emergency, non-emergency and faulty data. Individual packets are put into a separate queue, which is called emergency, periodical and faulty. Each queue is handled using Reyni entropy. Periodical packets are forwarded by a separate channel without any interference using a multi objective based channel selection algorithm. Then, all packets are encrypted and forwarded to the sink nodes. Simulation is conducted using the OMNeT++ network simulator, in which diverse parameters are evaluated and compared with several existing works in terms of network throughput for periodic (41.75 Kbps) and emergency packets (42.5 Kbps); end-to-end delay for periodic (0.036 s) and emergency packets (0.028 s); packet loss rate (1.1%); residual energy in terms of simulation rounds based on periodic (0.039 J) and emergency packets (0.044 J) and in terms of simulation time based on periodic (8.35 J) and emergency packets (8.53 J); success rate for periodic (87.83%) and emergency packets (87.5%); authentication time (3.25 s); and reliability (87.83%).

Parkinson’s Disease (PD) is a chronic and progressive neurological disorder that impairs the body’s nervous system pathways. This disruption results in multiple complications related to movement and control, manifesting as symptoms such as tremors, rigidity, and impaired coordination. In the initial phases of PD, individuals have trouble with speech and exhibit a slow rate of verbal expression. Dysphonia is seventy to ninety percent of persons with Parkinson’s disease report a speech impairment or modification in speech, and it serves as a preliminary indicator of the disease. Consequently, speech can be a crucial modality in the initial phase of Parkinson’s disease prediction. In literature, diverse Machine Learning models are employed for Parkinson’s disease diagnosis utilizing voice analysis. Challenges such as class imbalance, feature selection, and interpretable predictive analysis still need to be addressed. Furthermore, the precision and reliability of the predictive outcomes are crucial to enhance healthcare services. Consequently, we propose an Explainable balanced Recursive Feature Importance with Logistic Regression (XRFILR) model to address the abovementioned issues. The proposed model extracts the pertinent features using an RFE with a Logistic Regression classifier and evaluates the feature significance in Parkinson’s disease prediction using eXplainable Artificial Intelligence. We employed the seven machine learning classifiers the model offers to diagnose Parkinson’s disease using significant speech data. Among these ML models, the proposed model achieved an accuracy of 96.46%, surpassing existing machine learning techniques.

Alzheimer’s Disease (AD) is a progressive neurological condition that deteriorates memory, cognition, and behavior, especially in older adults. Timely identification is essential to enhance patient outcomes and inform therapy choices. This research introduces an extensive deep learning model for multiclass Alzheimer’s disease stage classification using structural MRI images from the publicly accessible OASIS dataset. The procedure begins with thorough preprocessing, including skull stripping, axial slice extraction, and intensity normalization to guarantee uniform input quality. Deep Convolution Generative Adversarial Network (DCGAN) is used to produce authentic synthetic MRI slices, therefore addressing data imbalance and enhancing class representation and training stability. The EffSwin-XNet model introduces a novel hybrid deep learning framework that strategically fuses EfficientNet-B0 and the Swin Transformer, enabling both local and global feature extraction from MRI brain images. This represents a significant advancement over conventional convolutional neural networks and a feature fusion attention mechanism that adaptively emphasizes discriminative features. Grad-CAM is used for explainability to view the brain areas influencing each categorization judgment, hence increasing therapeutic confidence. The model attains a classification accuracy of 95.3%, surpassing traditional CNN and hybrid benchmarks. This study presents an enhanced, interpretable, and efficient method for stage-wise categorization of Alzheimer’s Disease, demonstrating significant potential for use in clinical decision-support systems for early classification and intervention.

A cognitive radio network (CRN) is integrated with the Internet of Connected Vehicles (IoCV) in order to address spectrum scarcity and communication reliability issues. However, it is limited, possessing less throughput, a low packet delivery ratio, high latency, and high mobility in the spectrum. In this research study, the existing issues are addressed by proposing a 6G cognitive radio network–Internet of connected vehicles (6GCRN–IoCV) approach. Initially, all the entities such as secondary users (SUs), primary users (PUs), and pedestrians are authenticated in blockchain to ensure security. The edge-assisted roadside units (ERSU) initiate clustering only for authenticated SUs using the improved DBSCAN algorithm in consideration of several metrics. The ERSU then generates an intersection-aware map using the spatial and temporal-based logistic regression algorithm (STLR) to reduce collisions in the intersection. The spectrum utilization is improved by performing spectrum sensing in which all the SUs involved in spectrum sensing use lightweight convolutional neural networks (Lite-CNN) in consideration of several metrics and provide the sensing report to the fusion center (FC) in an encrypted manner to reduce the spectrum scarcity and security issues. The communications between the SUs are necessary to avoid risks in the IoCV environment. Hence, optimal routing is performed using the Dingo Optimization Algorithm (DOA), which increases throughput and packet delivery ratio. Finally, communication reliability is enhanced by performing hybrid beamforming, and this exploits the multi-agent-based categorical Deep-Q Network (categorical DQN), which increases spectral efficiency based on its adaptive intelligent behavior. The proposed study is simulated using the SUMO and OMNeT++ simulation tools and the performances are validated with existing works using several performance metrics. The result of the simulation shows that the proposed work performs better than the existing approaches.