Edith Luhanga

• BEng (Hons), MSc, D.Eng
• Research Member at Carnegie Mellon University Africa

Kinyarwanda, as one of the official languages of Rwanda plays a significant role in the country's cultural, educational , and administrative domains. With the increasing demand for information retrieval and natural language understanding in Kinyarwanda, the development of robust Question Answering (QA) systems becomes imperative. Pretrained Languag...

Floods are a recurring natural disaster that pose significant risks to communities and infrastructure. The lack of reliable and accurate data on river systems in developing countries has hindered the development of effective flood early warning systems. This paper presents a data set collected using ultrasonic distance sensors installed at two loca...

Reliable and accurate flood prediction in poorly gauged basins is challenging due to data scarcity, especially in developing countries where many rivers remain insufficiently monitored. This hinders the design and development of advanced flood prediction models and early warning systems. This paper introduces a multi-modal, sensor-based, near-real-...

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 di...

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 di...

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...

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...

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 di...

Biometrics applications are progressively widespread as a means of authenticating end-users owing to the extensive range of benefits over traditional authentication (token-base-authentication). However, the transaction involves taking into account the perceptions and responses of end-users. If end-users are fearful, hesitant about these biometric t...

Background Maternal mortality continues to be a global challenge with about 830 women dying of childbirth and pregnancy complications every day. Tanzania has a maternal mortality rate of 524 deaths per 100,000 live births. Objective Knowing symptoms associated with antenatal risks among pregnant women may result in seeking care earlier or self-adv...

BACKGROUND Educating children on sexual abuse is one of the most daunting challenges among parents and caretakers. Digital games are increasingly being used to influence health behaviours in children and could be an efficient and friendly approach to educating children about sexual abuse protection. However, little is known on how to develop a cult...

Background Globally, 3 out of 20 children experience sexual abuse before the age of 18 years. Educating children about sexual abuse and prevention is an evidence-based strategy that is recommended for ending child sexual abuse. Digital games are increasingly being used to influence healthy behaviors in children and could be an efficient and friendl...

Peer-to-peer learning paradigm is seldom used in studying how farmers can increase yield. In this article, agent-based modelling has been applied to study the chances of dairy farmers increasing annual milk yield by learning better farming strategies from each other. Two sets of strategies were considered; in one set (S), each farmer agent would po...

Currently, the adoption rate of biometric technology has speedily grown in all applications. The technology is considered as an effective measure for the protection against crime. However, there is a concern that it violates the privacy and rights of the individuals. For instance, the possibility of fraud, identity theft, civil liberty violations,...

Biometric template is a digital reference of a distinct feature obtained from a biometric sample stored in the database. The template can arise a serious security risk if raw, unprotected data template is stored in the database. A novel approach of encryption-decryption algorithm with a design pattern of model view template (MVT) is developed. The...

In the past decades, the world has experienced major changes in the advancement of learning technologies which has enabled learners to engage in their learning activities anywhere. The penetration of mobile phone internet users in Tanzania has been increasing from 2 million in 2011 to 23mil in 2017 The adoption of mobile-based learning (M-learning)...

Billions of smartphones, globally, are running out-of-date Operating Systems (OS) which make them vulnerable to cyberattacks. Behaviours of users in updating their OS vary between different geographic locations considering various demographic factors. For instance, developing countries have a very different stance compared to developed ones on how...

Phishing attacks have been persistent for more than two decades despite mitigation efforts from academia and industry. We believe that users fall victim to attacks not only because of lack of knowledge and awareness, but also because they are not attentive enough to security indicators and visual abnormalities on the webpages they visit. This is al...

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 l...

Characterization of smallholder farmers has been conducted in various researches by using machine learning algorithms, participatory and expert-based methods. All approaches used end up with the development of some subgroups known as farm typologies. The main purpose of this paper is to highlight the main approaches used to characterize smallholder...

The increase in terrorism and identity fraud has forced governments worldwide to make a combined effort to enhance the security of national borders. Biometric passports are the emergent identity travel document deployed in guaranteeing the safekeeping of the entry point of the border and limiting the usage of counterfeit documents. This study analy...

The heterogeneity of smallholder dairy production systems complicates service provision, information sharing, and dissemination of new technologies, especially those needed to maximize productivity and profitability. In order to obtain homogeneous groups within which interventions can be made, it is necessary to define clusters of farmers who under...

Characteristics of smallholder dairy farmers across regions are highly similar. However, introduction of improved farm management practices and extension support can be effective if specific constraints are identified for each farm typology. So far, approaches used to formulate farm types and characterize farming systems are not tailored to studyin...

In this paper, we conducted a survey of 206 smartphone users of different demographics in Japan and Tanzania, two countries with different security and privacy expectations, to analyse users' cybersecurity knowledge and attitudes. We studied password choices, smartphone lock behaviour, phishing awareness and attitudes towards public Wi-Fi. We also...

Despite the importance of an up-to-date Operating System (OS) for smartphone security, few users update it whenever it becomes obsolete. We believe intellectual, financial, sociocultural and other factors may highly affect users' behaviour in updating their OS, and these factors might significantly vary among users of different demographics and use...

Social support can improve adherence to physical activity and healthy eating behavior change, and recently, smartphone fitness applications which provide interventions to groups of users are increasingly popular. However the types of social support provided in the applications, and the features/approaches used to offer the support, vary widely. It...

Much research on smart environments has focused on homes and offices. With increasing physical inactivity and its health effects, augmenting gyms to motivate, assist and coach users to track and achieve their fitness goals is important. In this paper, we propose using smart mirrors to automatically detect and count repetitions of exercises, and to...

Consistent food tracking is important for weight loss. Many people struggle with forming and maintaining the habit because it is time consuming and generally un-enjoyable. We describe the design and initial field evaluation of HappyInu, a virtual pet-care game that we developed to promote consistent food tracking. HappyInu uses daily notifications...

Self-monitoring (tracking) of food and activity behavior is an evidence-based strategy for weight loss, and the main strategy employed in weight loss applications (apps). However, tracking is difficult and time-consuming and it is the main cause for abandoning usage of weight loss apps. We conducted a participatory design study with 26 participants...

Behavior change strategies have been found to be effective for weight loss. Over 20 strategies exist but only 4 are commonly included in smartphone weight loss apps. Other strategies such as stimulus control address common reasons users relapse and therefore may help improve the success of weight loss apps. My work focuses on implementing and evalu...

One area of application of the discrete wavelet transform (DWT) has been the detection and classification of physiological signals such as electroencephalography (EEG) signals. Anomalies in EEGs yield very low frequency signals which are ideal for analysis using the DWT. Anomalies in mechanical systems yield high frequency signals. The structure of...