Research results (AI4D Africa) / Résultats de recherche (IAPD Afrique)
Permanent URI for this collection
Browse
Recent Submissions
Item The state of AI in Africa report 2023(2023) Centre for Intellectual Property and Information Technology LawAfrica is embracing Artificial Intelligence in ways unique to the continent and is by no means showing signs to slow down. This executive summary provides a brief overview of the report on the State of AI in Africa prepared by the Centre for Intellectual Property and Information Technology Law (CIPIT). The report highlights the potential of AI technologies to transform various sectors in Africa, such as business operations, healthcare, education, legal and judicial services, and transportation. However, the report also identifies significant gaps in access to knowledge/information, data, education, training, and human resources necessary for AI development and adoption.Item Labeled spectral dataset with cassava disease occurrences using virus titre determination protocol(2023-07) Owomugisha, Godliver; Nakatumba-Nabende, Joyce; Dhikusooka, Joshua Jeremy; Taravera, Estefania; Nuwamanya, Ephraim; Mwebaze, ErnestIn this work, we present a novel dataset composed of spectral data and images of cassava crops with and without diseases. Together with the description of the dataset, we describe the protocol to collect such data in a controlled environment and in an open field where pests are not controlled. Crop disease diagnosis has been done in the past through the analysis of plant images taken with a smartphone camera. However, in some cases, disease symptoms are not visible. Furthermore, for some cassava diseases, once symptoms have manifested on the aerial part of the plant, the root which is the edible part of the plant has been totally destroyed. The goal of collecting this multimodality of the crop disease is early intervention, following the hypothesis that diseased crops without visible symptoms can be detected using spectral information. We collected visible and near-infrared spectra captured from leaves infected with two common cassava diseases namely; Cassava Brown Streak Disease and Cassava Mosaic Disease, as well as from healthy plants. Together, we also captured leaf imagery data that corresponds to the spectral information. In our experiments, biochemical data is collected and taken as the ground truth. Finally, agricultural experts provided a disease score per plant leaf from 1 to 5, 1 representing healthy and 5 severely diseased. The process of disease monitoring and data collection took 19 and 15 consecutive weeks for screenhouse and open field, respectively, until disease symptoms were visibly seen by the human eye.Item Light spectrometer device for crop disease monitoring(2023) Dhikusooka, Joshua J; Nuwamanya, Ephraim; Talavera, Estefania; Owomugisha, GodliverPortable devices for the early detection of crop diseases are needed to support the farmers working in the field. Spectrometers showed their potential in the detection of crop diseases. However, high interpretation skills are needed to use the currently available spectrometers. In this project, we propose a portable device that obtains a spectrum wavelength of 700 nanometers describing the information of the crop. The output of this tool is integrated into a smartphone in the form of an app, making it accessible for use in the field in real applications.Item Multi-level association rule mining for the discovery of strong underrepresented patterns : the case study of small dairy farms in Tanzania(2023) Malamsha, Glory C.; Nyambo, Devotha G.Increasing the milk production of small dairy producers is necessary to cover the increase in milk demand in Tanzania. Currently, the population of people in both Tanzania and the world has increased and is predicted to increase more in the year 2050. The use of multilevel association rule mining methods to mine strong patterns among smallholder dairy farmers could help in identifying the best dairy farming practices and increase their milk production by adopting them. This study employed multi-level association rule mining to discover strong rules in three clusters, resulting in three levels of rules in each cluster. These three clusters were high, medium, and low milk producers. Rules were obtained for feeding practices, milk production, and breeding and health practices. These rules represent strong patterns among smallholder dairy farmers that could help them improve their dairy farming practices and have a gradual increase in milk production, from low to medium and from medium to higher milk production. Smallholder dairy producers would be provided with recommendations on their dairy farming practices, using rules based on the cluster to which they belong that could help them achieve higher milk production.Item Data balancing techniques for predicting student dropout using machine learning(MDPI, 2023-02-27) Mduma, Neema; Sarasa Cabezuelo, Antonio; Rodríguez Barbero, Ramón González del CampoPredicting student dropout is a challenging problem in the education sector. This is due to an imbalance in student dropout data, mainly because the number of registered students is always higher than the number of dropout students. Developing a model without taking the data imbalance issue into account may lead to an ungeneralized model. In this study, different data balancing techniques were applied to improve prediction accuracy in the minority class while maintaining a satisfactory overall classification performance. Random Over Sampling, Random Under Sampling, Synthetic Minority Over Sampling, SMOTE with Edited Nearest Neighbor and SMOTE with Tomek links were tested, along with three popular classification models: Logistic Regression, Random Forest, and Multi-Layer Perceptron. Publicly accessible datasets from Tanzania and India were used to evaluate the effectiveness of balancing techniques and prediction models. The results indicate that SMOTE with Edited Nearest Neighbor achieved the best classification performance on the 10-fold holdout sample. Furthermore, Logistic Regression correctly classified the largest number of dropout students (57348 for the Uwezo dataset and 13430 for the India dataset) using the confusion matrix as the evaluation matrix. The applications of these models allow for the precise prediction of at-risk students and the reduction of dropout rates.Item AI for Anglophone Africa : unlocking its adoption for responsible solutions in academia-private sector(Frontiers, 2023-04-11) Sinde, Ramadhani; Diwani, Salim; Leo, Judith; Kondo, Tabu; Elisa, Noe; Matogoro, Jabhera; Pokkuluri, Kiran SreeIn recent years, AI technologies have become indispensable in social and industrial development, yielding revolutionary results in improving labor efficiency, lowering labor costs, optimizing human resource structure, and creating new job demands. To reap the full benefits of responsible AI solutions in Africa, it is critical to investigate existing challenges and propose strategies, policies, and frameworks for overcoming and eliminating them. As a result, this study investigated the challenges of adopting responsible AI solutions in the Academia-Private sectors for Anglophone Africa through literature reviews, expert interviews, and then proposes solutions and framework for the sustainable and successful adoption of responsible AI.Item Data privacy in Africa’s ed-tech platforms : children’s right to privacy(2022) Wairegi, AngelineIn the past decade, there has been a significant increase in the use of educational technology (Edtech) platforms on the African continent. A number of these platforms utilize Artificial Intelligence (AI) and have revolutionized the global education sector. When a website or platform is intended for children, it must comply with national data protection laws, which are intended to safeguard children's personal information in the digital space. While there are valuable opportunities to use AI in ways that benefit children, there are crucial questions we must ask and answer in order to better safeguard children from the potential negative effects of AI.Item Framing AI discourse : a study of AI discourse Twitter platform in Kenya and South Africa(2022) Wairegi, Angeline; Ondili, Mitchel; Zalo, Magaret; Karanja, NatashaArtificial Intelligence (AI) has become a main feature of news coverage and social media discourse. News and social media coverage can drive the ongoing discussions about the use of AI and influence attitudes towards it. The study used mixed methodology (automatic content analysis and manual coding) to establish the framing of AI on Twitter in Kenya and South Africa. The analysis mainly focused on determining the different local and regional narratives in tweets and retweets in the countries of study pertaining to AI in different categories. The study substantiated the claims, and general views, espoused in the analyzed tweets with data from local and international resources to determine their veracity. A total of 256 tweets from Kenya and 516 tweets from South Africa pertaining to AI sent between 2016 – 2021 were analyzed. These tweets were categorized into 7 different groups: (i) automation and job replacement, (ii) education, (iii) AI and development, (iv) commercial services, (v) health, (vi) AI and governance, and (vii) ethics and regulation, and then further delineated according to 3 sentiments: positive, negative or neutral tweet. The sentiments conveyed by the compiled tweets across these 7 categories was assessed. Study findings showed that, in general, there is still a tendency toward an optimistic view of the possible impact of AI on solving problems in Kenya and South Africa. The differences in negative and positive sentiments across the different categories skews, for the most part, toward higher positive sentiments in Kenya on a particular topic than in South Africa. Finally, the sentiments, both positive and negative, espoused in these tweet mirror those of Global North countries concerning AI, even when the on-the-ground-realities do not support these concerns.