Machine Learning Hybrid Model for the Prediction of Chronic Kidney Disease.

To diagnose an illness in healthcare, doctors typically conduct physical exams and review the patient's medical history, followed by diagnostic tests and procedures to determine the underlying cause of symptoms. Chronic kidney disease (CKD) is currently the leading cause of death, with a rapidly increasing number of patients, resulting in 1.7 million deaths annually. While various diagnostic methods are available, this study utilizes machine learning due to its high accuracy. In this study, we have used the hybrid technique to build our proposed model. In our proposed model, we have used the Pearson correlation for feature selection. In the first step, the best models were selected on the basis of critical literature analysis. In the second step, the combination of these models is used in our proposed hybrid model. Gaussian Naïve Bayes, gradient boosting, and decision tree classifier are used as a base classifier, and the random forest classifier is used as a meta-classifier in the proposed hybrid model. The objective of this study is to evaluate the best machine learning classification techniques and identify the best-used machine learning classifier in terms of accuracy. This provides a solution for overfitting and achieves the highest accuracy. It also highlights some of the challenges that affect the result of better performance. In this study, we critically review the existing available machine learning classification techniques. We evaluate in terms of accuracy, and a comprehensive analytical evaluation of the related work is presented with a tabular system. In implementation, we have used the top four models and built a hybrid model using UCI chronic kidney disease dataset for prediction. Gradient boosting achieves around 99% accuracy, random forest achieves 98%, decision tree classifier achieves 96% accuracy, and our proposed hybrid model performs best getting 100% accuracy on the same dataset. Some of the main machine learning algorithms used to predict the occurrence of CKD are Naïve Bayes, decision tree, K-nearest neighbor, random forest, support vector machine, LDA, GB, and neural network. In this study, we apply GB (gradient boosting), Gaussian Naïve Bayes, and decision tree along with random forest on the same set of features and compare the accuracy score.

Telehealth for COVID-19: A Conceptual Framework.

The world has been going through the global crisis of the coronavirus (COVID-19). It is a challenging situation for every country to tackle its healthcare system. COVID-19 spreads through physical contact with COVID-positive patients and causes potential damage to the country's health and economy system. Therefore, to overcome the chance of spreading the disease, the only preventive measure is to maintain social distancing. In this vulnerable situation, virtual resources have been utilized in order to maintain social distance, i.e., the telehealth system has been proposed and developed to access healthcare services remotely and manage people's health conditions. The telehealth system could become a regular part of our healthcare system, and during any calamity or natural disaster, it could be used as an emergency response to deal with the catastrophe. For this purpose, we proposed a conceptual telehealth framework in response to COVID-19. We focused on identifying critical issues concerning the use of telehealth in healthcare setups. Furthermore, the factors influencing the implementation of the telehealth system have been explored in detail. The proposed telehealth system utilizes artificial intelligence and data science to regulate and maintain the system efficiently. Before implementing the telehealth system, it is required that prearrangements be made, such as appropriate funding measures, the skills to know technological usage, training sessions, and staff endorsement. The barriers and influencing factors provided in this article can be helpful for future developments in telehealth systems and for making fruitful progress in fighting pandemics like COVID-19. At the same time, the same approach can be used to save the lives of many frontline workers.

An Adaptive Topology Management Scheme to Maintain Network Connectivity in Wireless Sensor Networks.

The roots of Wireless Sensor Networks (WSNs) are tracked back to US military developments, and, currently, WSNs have paved their way into a vast domain of civil applications, especially environmental, critical infrastructure, habitat monitoring, etc. In the majority of these applications, WSNs have been deployed to monitor critical and inaccessible terrains; however, due to their unique and resource-constrained nature, WSNs face many design and deployment challenges in these difficult-to-access working environments, including connectivity maintenance, topology management, reliability, etc. However, for WSNs, topology management and connectivity still remain a major concern in WSNs that hampers their operations, with a direct impact on the overall application performance of WSNs. To address this issue, in this paper, we propose a new topology management and connectivity maintenance scheme called a Tolerating Fault and Maintaining Network Connectivity using Array Antenna (ToMaCAA) for WSNs. ToMaCAA is a system designed to adapt to dynamic structures and maintain network connectivity while consuming fewer network resources. Thereafter, we incorporated a Phase Array Antenna into the existing topology management technologies, proving ToMaCAA to be a novel contribution. This new approach allows a node to connect to the farthest node in the network while conserving resources and energy. Moreover, data transmission is restricted to one route, reducing overheads and conserving energy in various other nodes' idle listening state. For the implementation of ToMaCAA, the MATLAB network simulation platform has been used to test and analyse its performance. The output results were compared with the benchmark schemes, i.e., Disjoint Path Vector (DPV), Adaptive Disjoint Path Vector (ADPV), and Pickup Non-Critical Node Based k-Connectivity (PINC). The performance of ToMaCAA was evaluated based on different performance metrics, i.e., the network lifetime, total number of transmitted messages, and node failure in WSNs. The output results revealed that the ToMaCAA outperformed the DPV, ADPV, and PINC schemes in terms of maintaining network connectivity during link failures and made the network more fault-tolerant and reliable.

An Efficient and Secure Revocation-Enabled Attribute-Based Access Control for eHealth in Smart Society.

The ever-growing ecosystem of the Internet of Things (IoT) integrating with the ever-evolving wireless communication technology paves the way for adopting new applications in a smart society. The core concept of smart society emphasizes utilizing information and communication technology (ICT) infrastructure to improve every aspect of life. Among the variety of smart services, eHealth is at the forefront of these promises. eHealth is rapidly gaining popularity to overcome the insufficient healthcare services and provide patient-centric treatment for the rising aging population with chronic diseases. Keeping in view the sensitivity of medical data, this interfacing between healthcare and technology has raised many security concerns. Among the many contemporary solutions, attribute-based encryption (ABE) is the dominant technology because of its inherent support for one-to-many transfer and fine-grained access control mechanisms to confidential medical data. ABE uses costly bilinear pairing operations, which are too heavy for eHealth's tiny wireless body area network (WBAN) devices despite its proper functionality. We present an efficient and secure ABE architecture with outsourcing intense encryption and decryption operations in this work. For practical realization, our scheme uses elliptic curve scalar point multiplication as the underlying technology of ABE instead of costly pairing operations. In addition, it provides support for attribute/users revocation and verifiability of outsourced medical data. Using the selective-set security model, the proposed scheme is secure under the elliptic curve decisional Diffie-Hellman (ECDDH) assumption. The performance assessment and top-ranked value via the help of fuzzy logic's evaluation based on distance from average solution (EDAS) method show that the proposed scheme is efficient and suitable for access control in eHealth smart societies.

Energy Efficiency and Reliability Considerations in Wireless Body Area Networks: A Survey.

In this paper, we have reviewed and presented a critical overview of "energy-efficient and reliable routing solutions" in the field of wireless body area networks (WBANs). In addition, we have theoretically analysed the importance of energy efficiency and reliability and how it affects the stability and lifetime of WBANs. WBAN is a type of wireless sensor network (WSN) that is unique, wherever energy-efficient operations are one of the prime challenges, because each sensor node operates on battery, and where an excessive amount of communication consumes more energy than perceiving. Moreover, timely and reliable data delivery is essential in all WBAN applications. Moreover, the most frequent types of energy-efficient routing protocols include crosslayer, thermal-aware, cluster-based, quality-of-service, and postural movement-based routing protocols. According to the literature review, clustering-based routing algorithms are the best choice for WBAhinwidth, and low memory WBAN, in terms of more computational overhead and complexity. Thus, the routing techniques used in WBAN should be capable of energy-efficient communication at desired reliability to ensure the improved stability period and network lifetime. Therefore, we have highlighted and critically analysed various performance issues of the existing "energy-efficient and reliable routing solutions" for WBANs. Furthermore, we identified and compiled a tabular representation of the reviewed solutions based on the most appropriate strategy and performance parameters for WBAN. Finally, concerning to reliability and energy efficiency in WBANs, we outlined a number of issues and challenges that needs further consideration while devising new solutions for clustered-based WBANs.