A Comprehensive Survey on RF Energy Harvesting: Applications and Performance Determinants.

There has been an explosion in research focused on Internet of Things (IoT) devices in recent years, with a broad range of use cases in different domains ranging from industrial automation to business analytics. Being battery-powered, these small devices are expected to last for extended periods (i.e., in some instances up to tens of years) to ensure network longevity and data streams with the required temporal and spatial granularity. It becomes even more critical when IoT devices are installed within a harsh environment where battery replacement/charging is both costly and labour intensive. Recent developments in the energy harvesting paradigm have significantly contributed towards mitigating this critical energy issue by incorporating the renewable energy potentially available within any environment in which a sensor network is deployed. Radio Frequency (RF) energy harvesting is one of the promising approaches being investigated in the research community to address this challenge, conducted by harvesting energy from the incident radio waves from both ambient and dedicated radio sources. A limited number of studies are available covering the state of the art related to specific research topics in this space, but there is a gap in the consolidation of domain knowledge associated with the factors influencing the performance of RF power harvesting systems. Moreover, a number of topics and research challenges affecting the performance of RF harvesting systems are still unreported, which deserve special attention. To this end, this article starts by providing an overview of the different application domains of RF power harvesting outlining their performance requirements and summarizing the RF power harvesting techniques with their associated power densities. It then comprehensively surveys the available literature on the horizons that affect the performance of RF energy harvesting, taking into account the evaluation metrics, power propagation models, rectenna architectures, and MAC protocols for RF energy harvesting. Finally, it summarizes the available literature associated with RF powered networks and highlights the limitations, challenges, and future research directions by synthesizing the research efforts in the field of RF energy harvesting to progress research in this area.

Wireless Communications for Smart Manufacturing and Industrial IoT: Existing Technologies, 5G and Beyond.

Smart manufacturing is a vision and major driver for change in today's industry. The goal of smart manufacturing is to optimize manufacturing processes through constantly monitoring, controlling, and adapting processes towards more efficient and personalised manufacturing. This requires and relies on technologies for connected machines incorporating a variety of computation, sensing, actuation, and machine to machine communications modalities. As such, understanding the change towards smart manufacturing requires knowledge of the enabling technologies, their applications in real world scenarios and the communication protocols and their performance to meet application requirements. Particularly, wireless communication is becoming an integral part of modern smart manufacturing and is expected to play an important role in achieving the goals of smart manufacturing. This paper presents an extensive review of wireless communication protocols currently applied in manufacturing environments and provides a comprehensive review of the associated use cases whilst defining their expected impact on the future of smart manufacturing. Based on the review, we point out a number of open challenges and directions for future research in wireless communication technologies for smart manufacturing.

Machine Learning Based Diabetes Classification and Prediction for Healthcare Applications.

The remarkable advancements in biotechnology and public healthcare infrastructures have led to a momentous production of critical and sensitive healthcare data. By applying intelligent data analysis techniques, many interesting patterns are identified for the early and onset detection and prevention of several fatal diseases. Diabetes mellitus is an extremely life-threatening disease because it contributes to other lethal diseases, i.e., heart, kidney, and nerve damage. In this paper, a machine learning based approach has been proposed for the classification, early-stage identification, and prediction of diabetes. Furthermore, it also presents an IoT-based hypothetical diabetes monitoring system for a healthy and affected person to monitor his blood glucose (BG) level. For diabetes classification, three different classifiers have been employed, i.e., random forest (RF), multilayer perceptron (MLP), and logistic regression (LR). For predictive analysis, we have employed long short-term memory (LSTM), moving averages (MA), and linear regression (LR). For experimental evaluation, a benchmark PIMA Indian Diabetes dataset is used. During the analysis, it is observed that MLP outperforms other classifiers with 86.08% of accuracy and LSTM improves the significant prediction with 87.26% accuracy of diabetes. Moreover, a comparative analysis of the proposed approach is also performed with existing state-of-the-art techniques, demonstrating the adaptability of the proposed approach in many public healthcare applications.

Features of Mobile Apps for People with Autism in a Post COVID-19 Scenario: Current Status and Recommendations for Apps Using AI.

The new 'normal' defined during the COVID-19 pandemic has forced us to re-assess how people with special needs thrive in these unprecedented conditions, such as those with Autism Spectrum Disorder (ASD). These changing/challenging conditions have instigated us to revisit the usage of telehealth services to improve the quality of life for people with ASD. This study aims to identify mobile applications that suit the needs of such individuals. This work focuses on identifying features of a number of highly-rated mobile applications (apps) that are designed to assist people with ASD, specifically those features that use Artificial Intelligence (AI) technologies. In this study, 250 mobile apps have been retrieved using keywords such as autism, autism AI, and autistic. Among 250 apps, 46 were identified after filtering out irrelevant apps based on defined elimination criteria such as ASD common users, medical staff, and non-medically trained people interacting with people with ASD. In order to review common functionalities and features, 25 apps were downloaded and analysed based on eye tracking, facial expression analysis, use of 3D cartoons, haptic feedback, engaging interface, text-to-speech, use of Applied Behaviour Analysis therapy, Augmentative and Alternative Communication techniques, among others were also deconstructed. As a result, software developers and healthcare professionals can consider the identified features in designing future support tools for autistic people. This study hypothesises that by studying these current features, further recommendations of how existing applications for ASD people could be enhanced using AI for (1) progress tracking, (2) personalised content delivery, (3) automated reasoning, (4) image recognition, and (5) Natural Language Processing (NLP). This paper follows the PRISMA methodology, which involves a set of recommendations for reporting systematic reviews and meta-analyses.