The healthcare industry has been transitioning from paper-based medical records to electronic health records (EHRs) in most healthcare facilities. However, the current EHR frameworks face challenges in secure data storage, credibility, and management. Interoperability and user control of personal data are also significant concerns in the healthcare sector. Although block chain technology has emerged as a powerful solution that can offer the properties of immutability, security, and user control on stored records, its potential application in EHR frameworks is not yet fully understood. To address this gap in knowledge, this research aims to provide an interoperable blockchain-based EHR framework that can fulfill the requirements defined by various national and international EHR standards such as HIPAA and HL7. The research method employed is a systematic literature review to explore the current state of the art in the field of EHRs, including blockchain-based implementations of EHRs. The study defines the interoperability issues in the existing blockchain-based EHR frameworks, reviews various national and international standards of EHR, and further defines the interoperability requirements based on these standards. The proposed framework can offer safer methods to interchange health information for the healthcare sector and can provide the properties of immutability, security, and user control on stored records without the need for centralized storage. The contributions of this work include enhancing the understanding of the potential application of blockchain technology in EHR frameworks and proposing an interoperable blockchain-based EHR framework that can fulfill the requirements defined by various national and international EHR standards. Overall, this study has significant implications for the healthcare sector, as it can enhance the secure sharing and storage of electronic health data while ensuring the confidentiality, privacy, and integrity of medical records.

Real-world applications often involve imbalanced datasets, which have different distributions of examples across various classes. When building a system that requires a high accuracy, the performance of the classifiers is crucial. However, imbalanced datasets can lead to a poor classification performance and conventional techniques, such as synthetic minority oversampling technique. As a result, this study proposed a balance between the datasets using adversarial learning methods such as generative adversarial networks. The model evaluated the effect of data augmentation on both the balanced and imbalanced datasets. The study evaluated the classification performance on three different datasets and applied data augmentation techniques to generate the synthetic data for the minority class. Before the augmentation, a decision tree was applied to identify the classification accuracy of all three datasets. The obtained classification accuracies were 79.9%, 94.1%, and 72.6%. A decision tree was used to evaluate the performance of the data augmentation, and the results showed that the proposed model achieved an accuracy of 82.7%, 95.7%, and 76% on a highly imbalanced dataset. This study demonstrates the potential of using data augmentation to improve the classification performance in imbalanced datasets.

Clinical methods for dementia detection are expensive and prone to human errors. Despite various computer-aided methods using electroencephalography (EEG) signals and artificial intelligence, a consistent separation of Alzheimer’s disease (AD) and normal-control (NC) subjects remains elusive. This paper proposes a low-complexity EEG-based AD detection CNN called LEADNet to generate disease-specific features. LEADNet employs spatiotemporal EEG signals as input, two convolution layers for feature generation, a max-pooling layer for asymmetric spatiotemporal redundancy reduction, two fully-connected layers for nonlinear feature transformation and selection, and a softmax layer for disease probability prediction. Different quantitative measures are calculated using an open-source AD dataset to compare LEADNet and four pre-trained CNN models. The results show that the lightweight architecture of LEADNet has at least a 150-fold reduction in network parameters and the highest testing accuracy of 98.75% compared to pre-trained models. The investigation of individual layers of LEADNet showed successive improvements in feature transformation and selection for separating AD and NC subjects. A comparison with the state-of-the-art AD detection models showed that the highest accuracy, sensitivity, and specificity were achieved by the LEADNet model.

Skin cancer is a major public health concern around the world. Skin cancer identification is critical for effective treatment and improved results. Deep learning models have shown considerable promise in assisting dermatologists in skin cancer diagnosis. This study proposes SBXception: a shallower and broader variant of the Xception network. It uses Xception as the base model for skin cancer classification and increases its performance by reducing the depth and expanding the breadth of the architecture. We used the HAM10000 dataset, which contains 10,015 dermatoscopic images of skin lesions classified into seven categories, for training and testing the proposed model. Using the HAM10000 dataset, we fine-tuned the new model and reached an accuracy of 96.97% on a holdout test set. SBXception also achieved significant performance enhancement with 54.27% fewer training parameters and reduced training time compared to the base model. Our findings show that reducing and expanding the Xception model architecture can greatly improve its performance in skin cancer categorization.

This study examines the perception and adoption of IoT technologies for crop monitoring among farmers in Jizan, Saudi Arabia. The research investigates the relationship between farmers’ awareness of IoT technologies, their perception of benefits, and willingness to adopt them. It also explores the influence of factors like access to information, training, and the perception of government support on adoption behavior. A structured questionnaire was distributed to 550 farmers, with a response rate of 90.91%. The analysis reveals a significant association between farmers’ awareness of IoT technologies and their perception of benefits. The perceived benefits show a moderate positive relationship with farmers’ willingness to adopt IoT technologies. Access to information, training, and the perception of government support also have a positive influence on adoption. The findings highlight the importance of increasing farmers’ awareness and providing access to information and training on IoT technologies. The study emphasizes the need for government support in facilitating adoption. Recommendations include exploring additional factors, conducting longitudinal studies, and developing tailored training programs. Collaboration among stakeholders and financial support mechanisms is also crucial. This study contributes to the understanding of IoT technology adoption in agriculture, providing insights for policymakers, agricultural extension agencies, and technology providers. By embracing IoT technologies and implementing the recommended actions, farmers in Jizan can enhance their crop monitoring practices, improve productivity, and promote sustainable farming.

The Internet of Things (IoT) depends primarily on low-cost wireless sensors with limited energy capacity to allow pervasive monitoring and intelligent control. Nevertheless, unmanned aerial vehicle (UAV) can be used to connect remote terminals that are outside wireless coverage to IoT networks. This solution provides a means of extending the reach of IoT networks, offering more opportunities for monitoring and control. Despite this benefit, the UAV also suffers from low capacity onboard battery. To overcome these problems, solar energy is integrated with UAV, and wireless-powered communication (WPC) techniques are used for IoT terminals. Also, the non-orthogonal multiple access (NOMA) technique can be employed to address the massive connectivity issue of IoT terminals. By leveraging these advantages, we jointly optimize the three-dimensional UAV trajectory and time allocation for WPC powered IoT devices (IoTDs) underlaying solar-powered UAV. To achieve the target, in this paper, introduces a multiagent federated reinforcement learning (MAFAL) algorithm, which concentrates on maximizing energy efficiency (EE) while minimizing energy consumption, guaranteeing quality of service (QoS), fairness, and trajectory planning. The proposed algorithm aims to optimize the overall performance of the system by learning from the collective experience of multiple agents. Simulation result demonstrated that the proposed method achieves 56.84%, 68.45%, and 73.63% higher EE as compared to MAD2PG, DDPG, and DQN, respectively.