Background: Although computational models are advancing air quality prediction, achieving the desired performance or accuracy of prediction remains a gap, which impacts the implementation of machine learning (ML) air quality prediction models. Several models have been employed and some hybridized to enhance air quality and air quality index predictions. The objective of this paper is to systematically review machine and deep learning techniques for spatiotemporal air prediction challenges. Methods: In this review, a methodological framework based on PRISMA flow was utilized in which the initial search terms were defined to guide the literature search strategy in online data sources (Scopus and Google Scholar). The inclusion criteria are articles published in the English language, document type (articles and conference papers), and source type (journal and conference proceedings). The exclusion criteria are book series and books. The authors’ search strategy was complemented with ChatGPT-generated keywords to reduce the risk of bias. Report synthesis was achieved by keyword grouping using Microsoft Excel, leading to keyword sorting in ascending order for easy identification of similar and dissimilar keywords. Three independent researchers were used in this research to avoid bias in data collection and synthesis. Articles were retrieved on 27 July 2024. Results: Out of 374 articles, 80 were selected as they were in line with the scope of the study. The review identified the combination of a machine learning technique and deep learning techniques for data limitations and processing of the nonlinear characteristics of air pollutants. ML models, such as random forest, and decision tree classifier were among the commonly used models for air quality index and air quality predictions, with promising performance results. Deep learning models are promising due to the hyper-parameter components, which consist of activation functions suitable for nonlinear spatiotemporal data. The emergence of low-cost devices for data limitations is highlighted, in addition to the use of transfer learning and federated learning models. Again, it is highlighted that military activities and fires impact the O₃ concentration, and the best-performing models highlighted in this review could be helpful in developing predictive models for air quality prediction in areas with heavy military activities. Limitation: This review acknowledges methodological challenges in terms of data collection sources, as there are equally relevant materials on other online data sources. Again, the choice and use of keywords for the initial search and the creation of subsequent filter keywords limit the collection of other relevant research articles.

Health information system deployment has been driven by the transformation and digitalization currently confronting healthcare. The need and potential of these systems within healthcare have been tremendously driven by the global instability that has affected several interrelated sectors. Accordingly, many research studies have reported on the inadequacies of these systems within the healthcare arena, which have distorted their potential and offerings to revolutionize healthcare. Thus, through a comprehensive review of the extant literature, this study presents a critique of the health information system for healthcare to supplement the gap created as a result of the lack of an in-depth outlook of the current health information system from a holistic slant. From the studies, the health information system was ascertained to be crucial and fundament in the drive of information and knowledge management for healthcare. Additionally, it was asserted to have transformed and shaped healthcare from its conception despite its flaws. Moreover, research has envisioned that the appraisal of the current health information system would influence its adoption and solidify its enactment within the global healthcare space, which is highly demanded.

This paper assessed existing EWS challenges and opportunities in cloud computing through the PSALSAR framework for systematic literature review and meta-analysis. The research used extant literature from Scopus and Web of Science, where a total of 2516 pieces of literature were extracted between 2004 and 2022, and through inclusion and exclusion criteria, the total was reduced to 98 for this systematic review. This review highlights the challenges and opportunities in transferring in-house early warning systems (that is, non-cloud) to the cloud computing infrastructure. The different techniques or approaches used in different kinds of EWSs to facilitate climate-related data processing and analytics were also highlighted. The findings indicate that very few EWSs (for example, flood, drought, etc.) utilize the cloud computing infrastructure. Many EWSs are not leveraging the capability of cloud computing but instead using online application systems that are not cloud-based. Secondly, a few EWSs have harnessed the computational techniques and tools available on a single platform for data processing. Thirdly, EWSs combine more than one fundamental tenet of the EWS framework to provide a holistic warning system. The findings suggest that reaching a global usage of climate-related EWS may be challenged if EWSs are not redesigned to fit the cloud computing service infrastructure.

Sustainable energy development consists of design, planning, and control optimization problems that are typically complex and computationally challenging for traditional optimization approaches. However, with developments in artificial intelligence, bio-inspired algorithms mimicking the concepts of biological evolution in nature and collective behaviors in societies of agents have recently become popular and shown potential success for these issues. Therefore, we investigate the latest research on bio-inspired approaches for smart energy management systems in smart homes, smart buildings, and smart grids in this paper. In particular, we give an overview of the well-known and emerging bio-inspired algorithms, including evolutionary-based and swarm-based optimization methods. Then, state-of-the-art studies using bio-inspired techniques for smart energy management systems are presented. Lastly, open challenges and future directions are also addressed to improve research in this field.

Early warning systems (EWS) facilitate societies’ preparedness and effective response capabilities to climate risks. Climate risks embody hazards, exposure, and vulnerability associated with a particular geographical area. Building an effective EWS requires consideration of the factors above to help people with coping mechanisms. The objective of this paper is to propose an approach that can enhance EWSs and ensure an effective climate risk resilience development. The paper focuses on the Southern African Development Community (SADC) region and highlights the issues with EWS, identifying weaknesses and characteristics of EWS to help in climate risk adaptation strategies. The SADC region was chosen as the context because it is a climate variability and change hotspot with many vulnerable populations residing in rural communities. Trending themes on building climate risk resilience were uncovered through scientific mapping and network analysis of published articles from 2008 to 2022. This paper contributes to on-going research on building climate risks resilience through early warning systems to identify hidden trends and emerging technologies from articles in order to enhance the operationalization and design of EWS. This review provides insight into technological interventions for assessing climate risks to build preparedness and resilience. From the review analysis, it is determined that there exists a plethora of evidence to support the argument that involving communities in the co-designing of EWS would improve risk knowledge, anticipation, and preparedness. Additionally, Fourth Industrial Revolution (4IR) technologies provide effective tools to address existing EWS’ weaknesses, such as lack of real-time data collection and automation. However, 4IR technology is still at a nascent stage in EWS applications in Africa. Furthermore, policy across societies, institutions, and technology industries ought to be coordinated and integrated to develop a strategy toward implementing climate resilient-based EWS to facilitate the operations of disaster risk managers. The Social, Institutional, and Technology model can potentially increase communities’ resilience; therefore, it is recommended to develop EWS.

Waste management is one of the challenges facing countries globally, leading to the need for innovative ways to design and operationalize smart waste bins for effective waste collection and management. The inability of extant waste bins to facilitate sorting of solid waste at the point of collection and the attendant impact on waste management process is the motivation for this study. The South African University of Technology (SAUoT) is used as a case study because solid waste management is an aspect where SAUoT is exerting an impact by leveraging emerging technologies. In this article, a convolutional neural network (CNN) based model called You-Only-Look-Once (YOLO) is employed as the object detection algorithm to facilitate the classification of waste according to various categories at the point of waste collection. Additionally, a nature-inspired search method is used as learning rate for the CNN model. The custom YOLO model was developed for waste object detection, trained with different weights and backbones, namely darknet53.conv.74, darknet19_448.conv.23, Yolov4.conv.137 and Yolov4-tiny.conv.29, respectively, for Yolov3, Yolov3-tiny, Yolov4 and Yolov4-tiny models. Eight (8) classes of waste and a total of 3171 waste images are used. The performance of YOLO models is considered in terms of accuracy of prediction (Average Precision—AP) and speed of prediction measured in milliseconds. A lower loss value out of a percentage shows a higher performance of prediction and a lower value on speed of prediction. The results of the experiment show that Yolov3 has better accuracy of prediction as compared with Yolov3-tiny, Yolov4 and Yolov4-tiny. Although the Yolov3-tiny is quick at predicting waste objects, the accuracy of its prediction is limited. The mean AP (%) for each trained version of YOLO models is Yolov3 (80%), Yolov4-tiny (74%), Yolov3-tiny (57%) and Yolov4 (41%). This result of mAP (%) indicates that the Yolov3 model produces the best performance results (80%). In this regard, it is useful to implement a model that ensures accurate prediction to develop a smart waste bin system at the institution. The experimental results show the combination of KSA learning rate parameter of 0.0007 and Yolov3 is identified as the accurate model for waste object detection and classification. The use of nature-inspired search methods, such as the Kestrel-based Search Algorithm (KSA), has shown future prospect in terms of learning rate parameter determination in waste object detection and classification. Consequently, it is imperative for an EdgeIoT-enabled system to be equipped with Yolov3 for waste object detection and classification, thereby facilitating effective waste collection.