Judith Leo

Advancements in machine learning techniques, availability of more data sets, and increased computing power have enabled a significant growth in a number of research areas. Predicting, detecting, and classifying complex events in earth systems which by nature are difficult to model is one such area. In this work, we investigate the application of different machine learning techniques for detecting and classifying extreme rainfall events in a sub-catchment within the Pangani River Basin, found in Northern Tanzania. Identification and classification of extreme rainfall event is a preliminary crucial task towards success in predicting rainfall-induced river floods. To identify a rain condition in the selected sub-catchment, we use data from five weather stations that have been labeled for the whole sub-catchment. In order to assess which machine learning technique is better suited for rainfall classification, we apply five different algorithms in a historical dataset for the period of 1...

In 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.

Advancements in Machine Learning techniques, availability of more data-sets, and increased computing power have enabled a significant growth in a number research areas. Predicting, detecting and classifying complex events in earth systems which by nature are difficult to model is one of such areas. In this work, we investigate the application of different machine learning techniques for detecting and identifying extreme rainfall events in a sub-catchment within Pangani River Basin, found in Northern Tanzania. Identification and prediction of extreme rainfall event is a preliminary crucial task towards success in predicting rainfall-induced river floods. To identify a rain condition in the selected sub-catchment, we use data from five weather stations which have been labeled for the whole sub-catchment. In order to assess which Machine Learning technique suits better for rainfall identification, we apply five different algorithms in a historical dataset for the period of 1979 to 2014...

Reliable and accurate flood prediction is a challenging task in poorly gauged basins due to data scarcity. Data is an essential component of any AI/ML model today, and the performance of such models hugely depends on the availability of sufficient amount of trusted, representative data. However, unlike a few well-studied rivers, most of the rivers in developing countries are still insufficiently monitored, which significantly hinges the design and development of advanced flood prediction models and early warning systems. This paper presents a multi-modal, sensor-based and near-real time river monitoring system to produce a multi-feature data set for the Kikuletwa river in Northern Tanzania, an area that heavily suffers from frequent floods. Our deployed system, which gather information about river depth levels and weather at several locations, aims at widening the ground truth of the river characteristics and eventually improve the accuracy of flood predictions. We provide details o...

The production of oil and gas around the world have been considered as a major source of air pollution. These Oil & Gas industries release pollutants such as Volatile Organic Compounds, greenhouse gases and particulate matter from various parts of their operations. The World Health Organization (WHO) has identified polluted air as the single largest environmental risk, and hence it is necessary to strive for and maintain good air quality. To manage potential health impacts, it is important to implement proper air quality control management system by understanding the correlations between specific pollutant sources and resulting population exposures. The authorities and oil companies are continuing and strongly committing to research and development to find out reasonably practical measures to reduce pollutions. One of the major challenges they are facing is getting the best solution among different technology applications since it is vital to implement the Best Available Techniques in order to measure Air quality. This paper presents effective mothed of determining the level of pollution in the oil & gas industries with the low power consumption and cost-effective. To do this, we have utilized the comprehensive ICT-based system using principle of WNS with the target air pollutants which include but not limited to particulate matter (PM2.5), methane, Ozone, VOCs and in addition, we have measured the current temperature and humidity as the baseline. The study is to determine the concentration of those air pollutants and to further assess the air quality level in the oil and gas industry since their levels present is proven to pose high adverse environmental and health implication such as climate change effects, acid rain, agricultural loss, physiological effects, air pollution caused by burning of petroleum chemical products causing the destruction of zinc roof, decay of concrete walls/ foundations and economic loss. It is therefore the aim of this paper to engage the use of WSN technology using sensors, xbees wireless communication module, Arduino uno, raspberry pi, Thingspeak cloud, mobile app. Keywords: air pollution; particulate matter; Volatile Organic Compounds; ozone; temperature; humidity; WSN technology; sensors; Arduino uno; raspberry pi; ThingSpeak cloud; mobile app.

Enhancement of health data collection and presentation to support epidemic analysis can benefit many aspects of healthcare in terms of diseases control, decision making and action to be taken. The epidemic analysis is the science that studies the patterns, causes, and effects of health and diseases conditions in defined populations. In most hospitals, there is increasing demand to improve quality of data, the efficiency of collection and presentation. In this study, we aim at integrating new module in the existing Health Information System (HIS) in order to improve data collection and presentation. The module takes advantage of the emerging technologies of mobile application, satellite technology and Geographical Information System (GIS) to capture environmental data. As part of the module we have developed, the mobile app which is integrated with GIS and satellite technology for remote data collection and hence the module can play a vital role in enhancing epidemic analysis.

The objective of this study is to assess the perspectives of users on the feasibility of using integrated environmental factors-based healthcare model to enchance timely cholera epidemics analysis in Tanzania. The study used a mixed-design approach of quantitative and qualitative methods with focus group discussion and interviewer-administered questionnaires. Participants or users included; medical and epidemiological experts, environmental experts, Information and Communication Technology (ICT) experts, and cholera patients from Ilala, Ubungo, Kigamboni, Temeke, and Kinondoni disctricts in Dar es Salaam, Tanzania. In the process, a total of 500 interviews were conducted, consisting of 200 medical experts, 50 environmental experts, 50 ICT experts, and 200 cholera patients, with an average age of 28 years old, and at 3:2 female to male ratio. Overall, our findings showed that Health and Environmental Integrated Modelled Systems (HEIMs) interventions are acceptable, feasible and capab...

Cholera epidemic remains a public threat throughout history, affecting vulnerable population living with unreliable water and substandard sanitary conditions. Various studies have observed that the occurrence of cholera has strong linkage with environmental factors such as climate change and geographical location. Climate change has been strongly linked to the seasonal occurrence and widespread of cholera through the creation of weather patterns that favor the disease’s transmission, infection, and the growth of Vibrio cholerae, which cause the disease. Over the past decades, there have been great achievements in developing epidemic models for the proper prediction of cholera. However, the integration of weather variables and use of machine learning techniques have not been explicitly deployed in modeling cholera epidemics in Tanzania due to the challenges that come with its datasets such as imbalanced data and missing information. This paper explores the use of machine learning tec...