Pneumonia is a microorganism infection that causes chronic inflammation of the human lung cells. Chest X-ray imaging is the most well-known screening approach used for detecting pneumonia in the early stages. While chest-Xray images are mostly blurry with low illumination, a strong feature extraction approach is required for promising identification performance. A new hybrid explainable deep learning framework is proposed for accurate pneumonia disease identification using chest X-ray images. The proposed hybrid workflow is developed by fusing the capabilities of both ensemble convolutional networks and the Transformer Encoder mechanism. The ensemble learning backbone is used to extract strong features from the raw input X-ray images in two different scenarios: ensemble A (i.e., DenseNet201, VGG16, and GoogleNet) and ensemble B (i.e., DenseNet201, InceptionResNetV2, and Xception). Whereas, the Transformer Encoder is built based on the self-attention mechanism with multilayer perceptron (MLP) for accurate disease identification. The visual explainable saliency maps are derived to emphasize the crucial predicted regions on the input X-ray images. The end-to-end training process of the proposed deep learning models over all scenarios is performed for binary and multi-class classification scenarios. The proposed hybrid deep learning model recorded 99.21% classification performance in terms of overall accuracy and F1-score for the binary classification task, while it achieved 98.19% accuracy and 97.29% F1-score for multi-classification task. For the ensemble binary identification scenario, ensemble A recorded 97.22% accuracy and 97.14% F1-score, while ensemble B achieved 96.44% for both accuracy and F1-score. For the ensemble multiclass identification scenario, ensemble A recorded 97.2% accuracy and 95.8% F1-score, while ensemble B recorded 96.4% accuracy and 94.9% F1-score. The proposed hybrid deep learning framework could provide promising and encouraging explainable identification performance comparing with the individual, ensemble models, or even the latest AI models in the literature. The code is available here: https://github.com/chiagoziemchima/Pneumonia_Identificaton.

This paper provides a comprehensive review of the research progress, current state-of-the-art, and future research directions of energy storage systems. With the widespread adoption of renewable energy sources such as wind and solar power, the discourse around energy storage is primarily focused on three main aspects: battery storage technology, electricity-to-gas technology for increasing renewable energy consumption, and optimal configuration technology. The paper employs a visualization tool (CiteSpace) to analyze the existing works of literature and conducts an in-depth examination of the energy storage research hotspots in areas such as electrochemical energy storage, hydrogen storage, and optimal system configuration. It presents a detailed overview of common energy storage models and configuration methods. Based on the reviewed articles, the future development of energy storage will be more oriented toward the study of power characteristics and frequency characteristics, with more focus on the stability effects brought by transient shocks. This review article compiles and assesses various energy storage technologies for reference and future research.

Recently, various strategies for energy management have been proposed to improve energy efficiency in smart grids. One key aspect of this is the use of microgrids. To effectively manage energy in a residential microgrid, advanced computational tools are required to maintain the balance between supply and demand. The concept of load disaggregation through non-intrusive load monitoring (NILM) is emerging as a cost-effective solution to optimize energy utilization in these systems without the need for extensive sensor infrastructure. This paper presents an energy management system based on NILM and the Internet of Things (IoT) for a residential microgrid, including a photovoltaic (PV) plant and battery storage device. The goal is to develop an efficient load management system to increase the microgrid’s independence from the traditional electrical grid. The microgrid model is developed in the electromagnetic transient program PSCAD/EMTDC to analyze and optimize energy performance. Load disaggregation is obtained by combining artificial neural networks (ANNs) and particle swarm optimization (PSO) to identify appliances for demand-side management. An ANN is applied in NILM as a load identification task, and PSO is used to optimize the ANN algorithm. This combination enhances the NILM technique’s accuracy, which is verified using the mean absolute error method to assess the difference between the predicted and measured power consumption of appliances. The NILM output is then transferred to consumers through the ThingSpeak IoT platform, enabling them to monitor and control their appliances to save energy and costs.

Recently, the International Energy Agency (IEA) released a comprehensive roadmap for the global energy sector to achieve net-zero emission by 2050. Considering the sizeable share of (Sub-Sahara) Africa in the global population, the attainment of global energy sector net-zero emission is practically impossible without a commitment from African countries. Therefore, it is important to study and analyze feasible/sustainable ways to solve the energy/electricity poverty in Africa. In this paper, the energy poverty in Africa and the high renewable energy (RE) potential are reviewed. Beyond this, the generation of electricity from the abundant RE potential in this region is analyzed in hourly timestep. This study is novel as it proposes a Sub-Sahara Africa (SSA) central grid as one of the fastest/feasible solutions to the energy poverty problem in this region. The integration of a sizeable share of electric vehicles with the proposed central grid is also analyzed. This study aims to determine the RE electricity generation capacities, economic costs, and supply strategies required to balance the projected future electricity demand in SSA. The analysis presented in this study is done considering 2030 and 2040 as the targeted years of implementation. EnergyPLAN simulation program is used to simulate/analyze the generation of electricity for the central grid. The review of the energy poverty in SSA showed that the electricity access of all the countries in this region is less than 100%. The analysis of the proposed central RE grid system is a viable and sustainable option, however, it requires strategic financial planning for its implementation. The cheapest investment cost from all the case scenarios in this study is $298 billion. Considering the use of a single RE technology, wind power systems implementation by 2030 and 2040 are the most feasible options as they have the least economic costs. Overall, the integration of the existing/fossil-fueled power systems with RE technologies for the proposed central grid will be the cheapest/easiest pathway as it requires the least economic costs. While this does not require the integration of storage systems, it will help the SSA countries reduce their electricity sector carbon emission by 56.6% and 61.8% by 2030 and 2040 respectively.