In January 2021 and January 2022, COVID-19 caused roughly 13,000 and 6,000 deaths respectively per day. In August 2022, 26,000 deaths per day were estimated to be caused by COVID-19, followed by 13,000 deaths per day in February 2024. The timely identification and treatment of malignant diseases can potentially lower the mortality rate. Nonetheless, the use of manual methods for diagnosing these conditions requires a meticulous and comprehensive examination, making it susceptible to errors, burdensome for healthcare professionals, and timeintensive. Hence, the objective of this study is to design and deploy a novel deep-learning model for the detection of COVID-19 thoracic diseases. A Convolutional Neural Network (CNN) with less trainable parameters was implemented. This proposed model was deployed on a mobile device using Android Studio and Flutter for the detection of COVID-19 thoracic diseases. Specificity, accuracy, precision, sensitivity, f1-score, ROC, and PR curves were used to evaluate the model's performance. Moreover, the carbon footprint as well as how responsible the proposed model is according to Responsible AI rules was also assessed. The model's evaluation results show an overall accuracy of 93.27 %, specificity of 97.33 %, precision of 93.75 %, sensitivity of 94.42 %, F1-Score of 94.06 %, ROC rate of 98.0 %, PR rate of 96.8 %. The evaluation of the mobile application shows higher generalizability on the COVID-19 dataset. Also, the overall FACETS Score representing responsible AI is 83 % and the carbon footprint (representing the amount of carbon emission emitted into the environment during model training and testing) of 416.73 g with equivalent tree months of 0.45 was obtained. This application with better performance and a low carbon footprint was deployed using Android Studio and Flutter and can assist physicians in the diagnosis of COVID-19 and related diseases.

Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI

Artificial Intelligence (AI) has been evident in the agricultural sector recently. The objective of AI in agriculture is to control crop pests/diseases, reduce cost, and improve crop yield. In developing countries, the agriculture sector faces numerous challenges in the form of knowledge gap between farmers and technology, disease and pest infestation, lack of storage facilities, among others. In order to resolve some of these challenges, this paper presents crop pests/disease datasets sourced from local farms in Ghana. The dataset is presented in two folds; the raw images which consists of 24,881 images (6,549-Cashew, 7,508-Cassava, 5,389-Maize, and 5,435-Tomato) and augmented images which is further split into train and test sets. The latter consists of 102,976 images (25,811-Cashew, 26,330-Cassava, 23,657-Maize, and 27,178-Tomato), categorized into 22 classes. All images are de-identified, validated by expert plant virologists, and freely available for use by the research community.

Colorectal cancer is the third most diagnosed malignancy in the world. Polyps (either malignant or benign) are the primary cause of colorectal cancer. However, the diagnosis is susceptive to human error, less effective, and falls below recommended levels in routine clinical procedures. In this paper, a Capsule network enhanced with radon transforms for feature extraction is proposed to improve the feasibility of colorectal cancer recognition. The contribution of this paper lies in the incorporation of the radon transforms in the proposed model to improve the detection of polyps by performing efficient extraction of tomographic features. When trained and tested with the polyp dataset, the proposed model achieved an overall average recognition accuracy of 94.02%, AUC of 97%, and an average precision of 96%. In addition, a posthoc analysis of the results exhibited superior feature extraction capabilities comparable to the state-of-the-art and can contribute to the field of explainable artificial intelligence. The proposed method has a considerable potential to be adopted in clinical trials to eliminate the problems associated with the human diagnosis of colorectal cancer.

Computers in education, along with soft-computing technology applications, have revolutionised global interconnectedness and the need for a well-educated workforce. Many studies worldwide explore technology in education, often relying on systematic reviews, though concerns about selection bias have emerged. This article takes a different approach, employing bibliometric analysis to delve into the trends, key authors, institutions, and themes of soft-computing technology applications in education (SCTAE) research in Africa. Initially, 7 435 papers were downloaded from Scopus and then narrowed down to 1 358 using the PRISMA model and defined criteria. Utilising the VOSViewer text mining tool, the article maps out prolific authors, institutions, and thematic networks. It provides detailed findings and outlines opportunities, challenges, and future research prospects in SCTAE in the African context.

The global impact of the COVID-19 pandemic has been felt in diverse ways. Although the death rate in Africa has not been as devastating as predicted by the World Health Organization (WHO), its economic and social impact has been fully felt by the African continent. As the world goes through the vaccination process to achieve herd immunity, Africa has not only faced problems like the inability to produce and procure vaccines, but some countries in the west are doubting the authenticity of the vaccination process and even vaccine certificates coming from various countries on the continent. The approach of using centralized systems to validate COVID-19 vaccine certificates makes these systems susceptible to Denial of Service (DoS), modification, and Man-in-the-Middle (MiTM) attacks. To curb this problem, we proposed a blockchain-based digital COVID-19 vaccination certificate verification system called BLOCOVID. The proposed system uses the decentralized approach of distributed ledgers to ensure that vaccine certificates are secured, immutable, and verifiable. Our proposed system stores vaccine serial numbers and their corresponding certificates as hash values. These hash values are stored on the blockchain network as transaction values. The authenticity of a vaccine certificate is determined by the availability of the hash values of the certificate and its corresponding vaccine serial number on the blockchain network. The proposed system was simulated using the BlockSim simulator. To begin with, the simulation results show that the proposed system can ensure system availability, thereby minimizing DoS attacks. Secondly, the proposed system can ensure the integrity of vaccine certificates by allowing third parties to verify the authenticity of these certificates. The simulation results show that even with 10240 nodes, the average transaction time was 137.2ms, with a total transaction rate of 9911.034 transactions per second.

Background: Most subscriber identification module (SIM) which usually finds their way to mobile phone users are primarily unregistered or pre-registered. Criminals buy these SIM cards, which have fake personal information, activate them and then use them as a channel of attacking vulnerable mobile phone users. Objective: to investigate the existing standards of the registration process, the weakness and how fraudsters leverage the shortcomings of the existing registration to attack unsuspecting subscribers. Methods: The study also proposed an automated theoretical model as an augmented model to ensure the SIM registration process and implementation become secure. Results: In our investigation, we identified that there had been a rise in fraudulent activities in Ghana, and the criminals have adapted to the new trend of committing a crime using mobile phones. The research presented a proposed conceptual model and algorithm for the new SIM registration. The study further conducted a comparative analysis of the principal component adopted to measure the robustness of the registration platform. The criminals mostly use social engineering tactics to trick their victims into disclosing sensitive information or sending money for services yet to be rendered. MNOs request an ID card before registering and activating SIMs, yet criminals can outwit the registration processes and get SIM cards registered through unapproved channels. Conclusion: We found out that the robustness of our model shall prevent SIM pre-registration and unapproved SIM activation due to verification mechanisms in the proposed model. A cognitive learningsystem has automated the registration process that can identify multiple registrations and prevent unapproved activation. Keywords: SIM Fraud; SIM card; Cognitive System; Mobile Network Operators; Intelligent decisionmaking; SIM Registration

Deep learning (DL) models are currently not widely deployed for critical tasks such as in health. This is attributable to the "black box," making it difficult to gain the trust of practitioners. This paper proposes the use of visualizations to enhance performance verification, improve monitoring, ensure understandability, and improve interpretability needed to gain practitioners' confidence. These are demonstrated through the development of a CapsNet model for the recognition of gastrointestinal tract infection. The gastrointestinal tract comprises several organs joined in a long tube from the mouth to the anus. It is susceptive to diseases that are difficult for medics to diagnose, since it is not easy to have physical access to the sick regions. Consequently, manual access and analysis of images of the unhealthy parts requires the skills of an expert, as it is tedious, prone to errors, and costly. Experimental results show that visualizations in the form of post-hoc interpretability can demonstrate the reliability and interpretability of the CapsNet model applied to gastrointestinal tract diseases. The outputs can also be explained to gain practitioners' confidence in paving the way for its adoption in critical areas of society.

Capsule Networks are neural networks that have the advantage of learning spatial and hierarchical information from data. They can learn and extract knowledge from smaller datasets (unlike other neural network algorithms); however, they perform poorly on complex and low-resolution images due to a problem called “crowding.” Crowding is attributed to the CapsNets’ attempt to read every object in an image (including background objects), resulting in poor performance. Therefore, this paper proposes a patch-based capsule network and a new squash function (power-B) to decompose an input image into smaller parts enabling the model to focus more on the relevant regions of interest. Experimental results show that the proposed model has efficient feature extraction capabilities, reduced computational time, and a fewer trainable number of parameters. The model’s performance is comparable to the state-of-the-art capsule network models by achieving overall recognition accuracies of 94.62%, 75.68%, and 92.82% for fashion-MNIST, CIFAR 10, and polyp datasets, respectively.

Though flooding is seen as a common environmental threat globally, it has dramatically increased recently due to climate change, impacting underdeveloped and developing countries dangerously. For example, in most developing countries like Ghana, flooding has affected over four million people in terms of property damage, loss of lives, income and spread of diseases, resulting in economic harm beyond USD780 million. At least one major flood disaster does occur yearly. The recurring incidences of flooding and associated calamitous socio-economic risks and anticipated increase of its prevalence soon in cities of developing countries such as Ghana have necessitated an intelligence system to offer efficient and early warning of its occurrence. In this study, we explore the potential of the machine learning (ML) computing paradigm to propose a flooding prediction model. Specifically, four state-of-the-art ML algorithms, namely long short-term memory (LSTM), extreme gradient boosting (XGBoost), random forest (RF) and extremely randomised trees (Extra Trees), are used to implement four different flood prediction models. We measure the performance of our developed models with multiple statistical performance evaluators. The experimental results show the potential of the developed models for efficient and effective prediction of flooding. The merit of this study lies in the fact that it is the first to the best of our knowledge to use a combination of environmental factors from Ghana and machine learning algorithms to develop intelligent flood models to help stakeholders make informed decisions.

Medical images naturally occur in smaller quantities and are not balanced. Some medical domains such as radiomics involve the analysis of images to diagnose a patient’s condition. Often, images of sick inaccessible parts of the body are taken for analysis by experts. However, medical experts are scarce, and the manual analysis of the images is time-consuming, costly, and prone to errors. Machine learning has been adopted to automate this task, but it is tedious, time-consuming, and requires experienced annotators to extract features. Deep learning alleviates this problem, but the threat of overfitting on smaller datasets and the existence of the “black box” still lingers. This paper proposes a capsule network that uses Local Binary Pattern (LBP), Gabor layers, and K-Means routing in an attempt to alleviate these drawbacks. Experimental results show that the model produces state-of-the-art accuracy for the three datasets (KVASIR, COVID-19, and ROCT), does not overfit on smaller and imbalanced datasets, and has reduced complexity due to fewer parameters. Layer activation maps, a cluster of features, predictions, and reconstruction of the input images, show that our model is interpretable and has the credibility and trust required to gain the confidence of practitioners for deployment in critical areas such as health.

This study uses the classification techniques of data mining to mine data of Computer Science students of Kwame Nkurmah University of Science and Technology, Kumasi, Ghana to ascertain if there is any pattern between the entry grades with which students enter university and their grades upon graduation. The WEKA workbench was used for the analysis to determine relationship between Senior High School (SHS) aggregate, Best 6 and final Cumulative Weighted Average (CWA) of students. It highlighted the performance of students admitted from the three categories (A, B, C) of SHS in the country using J48 decision tree, Instance based learner and Multi-Layer Perceptron algorithms. The classification models developed with the algorithms were used to predict students final CWA upon graduation and performances of algorithms were compared and contrasted using accuracy, scalability, speed, robustness and interpretability. Results indicated a weak correlation between Best 6 aggregate and Final CWA. It was discovered that students from Category C of SHS performed better (graduating with First class or 2nd Class Upper) compared with students from Category A and B schools. The J48 decision tree algorithm was adjudged the overall best algorithm.