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 is unknown which approach is the best to meet users' requirements. We conducted a mixed methods study to identify user requirements for social support in group fitness applications. We then developed MyFitnessTeam based on these requirements and evaluated it in a six-week field study. We found that participants desired informational and emotional support, and for group fitness applications to provide daily challenges that they could complete with their support network. MyFitnessTeam significantly improved adherence to fitness behaviors, with men having significantly higher adherence levels than women and participants who were inactive at baseline achieving similar adherence levels to the most baseline-active participants. Groups of friends were more likely to exchange informational support but emotional support was low for both friends and strangers, due to lack of knowledge on when and how to offer such support. We propose five design recommendations to promote supportive interactions in group fitness applications.

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 friendly approach to educating children about sexual abuse prevention. However, little is known on the best way to develop a culturally sensitive game that targets children in Africa—where sexual education is still taboo—that would be engaging, effective, and acceptable to parents and caretakers. Objective: This study aimed to develop a socioculturally appropriate, mobile-based game for educating young children (<5 years) and parents and caretakers in Tanzania on sexual abuse prevention. Methods: HappyToto children’s game was co-designed with 111 parents and caretakers (females: n=58, 52.3%; male: n=53, 47.7%) of children below 18 years of age and 24 child experts in Tanzania through surveys and focus group discussions conducted from March 2020 to April 2020. From these, we derived an overview of topics, sociocultural practices, social environment, and game interface designs that should be considered when designing child sexual abuse prevention (CSAP) education interventions. We also conducted paper prototyping and storyboarding sessions for the game’s interface, storylines, and options. To validate the application’s prototype, 32 parents (females: n=18, 56%; males: n=14, 44%) of children aged 3-5 years and 5 children (females: n=2, 40%; males: n=3, 60%) of the same age group played the game for half an hour on average. The parents undertook a pre-post intervention assessment on confidence and ability to engage in CSAP education conversations, as well as exit surveys on the usability and sociocultural acceptability of the game, while children were quizzed on the topics covered and their enjoyment of the game. Results: Parents and caregivers showed interest in the developed game during the conducted surveys, and each parent on average navigated through all the parts of the game. The confidence level of parents in talking about CSAP increased from an average of 3.56 (neutral) before using the game to 4.9 (confident) after using the game. The ability scores, calculated based on a range of topics included in CSAP education talks with children, also increased from 5.67 (out of 10) to 8.8 (out of 10) after the game was played. Both confidence level and ability scores were statistically significant (P<.001). All 5 children were interested in the game and enjoyed the game-provided activities. Conclusions: The HappyToto game can thus be an effective technology-based intervention for improving the knowledge and skills of parents and children in CSAP education.

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 1979 to 2014. We evaluate the performance of the models in terms of precision and recall, reporting random forest and XGBoost as having the best overall performances. However, because the class distribution is imbalanced, a generic multi-layer perceptron performs best when identifying heavy rainfall events, which are eventually the main cause of rainfall-induced river floods in the Pangani River Basin.

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-time river monitoring system that produces a multi-feature data set for the Kikuletwa River in Northern Tanzania, an area frequently affected by floods. The system improves upon existing literature by collecting six parameters relevant to weather and river flood detection: current hour rainfall (mm), previous hour rainfall (mm/h), previous day rainfall (mm/day), river level (cm), wind speed (km/h), and wind direction. These data complement the existing local weather station functionalities and can be used for river monitoring and extreme weather prediction. Tanzanian river basins currently lack reliable mechanisms for accurately establishing river thresholds for anomaly detection, which is essential for flood prediction models. The proposed monitoring system addresses this issue by gathering information about river depth levels and weather conditions at multiple locations. This broadens the ground truth of river characteristics, ultimately improving the accuracy of flood predictions. We provide details on the monitoring system used to gather the data, as well as report on the methodology and the nature of the data. The discussion then focuses on the relevance of the data set in the context of flood prediction, the most suitable AI/ML-based forecasting approaches, and highlights potential applications beyond flood warning systems.

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. We evaluate the performance of the models in terms of precision and recall, reporting Random Forest and XGBoost as the ones with best overall performance. However, since the class distribution is imbalanced, the generic Multi-layer Perceptron performs best when identifying the heavy rainfall events, which are eventually the main cause of rainfall-induced river floods in the Pangani River Basin

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 on the monitoring system used to gather the data as well as report on the methodology and the nature of the data. Finally, we present the relevance of the data set in the context of flood prediction, discussing the most suitable AI/ML-based forecasting approaches, while also highlighting some applications of the data set beyond flood warning systems.