Robert Oboko

A model for predicting utilization of mHealth interventions in low-resource settings: case of maternal and newborn care in Kenya

BackgroundIn low-resource settings, there are numerous socioeconomic challenges such as poverty, inadequate facilities, shortage of skilled health workers, illiteracy and cultural barriers that contribute to high maternal and newborn deaths. To address these challenges, there are several mHealth projects particularly in Sub-Sahara Africa seeking to exploit opportunities provided by over 90% rate of mobile penetration. However, most of these interventions have failed to justify their value proposition to inspire utilization in low-resource settings.MethodsThis study proposes a theoretical model named Technology, Individual, Process-Fit (TIPFit) suitable for user-centred evaluation of intervention designs to predict utilization of mHealth products in low-resource settings. To investigate the predictive power of TIPFit model, we operationalized its latent constructs into variables used to predict utilization of an mHealth prototype called mamacare. The study employed single-group repeated measures quasi-experiment in which a random sample of 79 antenatal and postnatal patients were recruited from a rural hospital. During the study conducted between May and October 2014, the treatment involved sending and receiving SMS alerts on vital signs, appointments, safe delivery, danger signs, nutrition, preventive care and adherence to medication.ResultsMeasurements taken during the study were cleaned and coded for analysis using statistical models like Partial Least Squares (PLS), Repeated Measures Analysis of Variance (RM-ANOVA), and Bonferroni tests. After analyzing 73 pretest responses, the model predicted 80.2% fit, and 63.9% likelihood of utilization. However, results obtained from initial post-test taken after three months demonstrated 69.1% fit, and utilization of 50.5%. The variation between prediction and the actual outcome necessitated improvement of mamacare based on feedback obtained from users. Three months later, we conducted the second post-test that recorded further drop in fit from 69.1 to 60.3% but utilization marginally improved from 50.5 to 53.7%.ConclusionsDespite variations between the pretest and post-test outcomes, the study demonstrates that predictive approach to user-centred design offers greater flexibility in aligning design attributes of an mHealth intervention to fulfill user needs and expectations. These findings provide a unique contribution for decision makers because it is possible to prioritize investments among competing digital health projects.

Extending moodle grouping functionality using artificial intelligent techniques

Learning Management Systems such as Modular Object-Oriented Dynamic Learning Environment (Moodle) only supports random group assignment or instructor based assignment method. However, with the understanding that random assignment method only increases the likelihood of heterogeneity in the group, while instructor based method involves the instructors and it is not dynamic, there is need to develop a group formation mechanism which can guarantee heterogeneity based on learners collaboration competence level, has dynamism in grouping students and has less instructor involvement. In view of this, this paper discusses how to extend Moodle grouping functionality in discussion forums using an intelligent grouping algorithm which has the capability to mine discussion forum data in Moodle and cluster students to different clusters based on learners collaboration competence level. In addition we demonstrate how these clusters are formed and utilized to form heterogeneous groups which are automatically added in Moodle Database. An interface has also been created in Moodle to allow instructors to automatically create clusters and form groups based on these clusters.

Regulating group cognitive conflicts using intelligent agents in collaborative M-learning

Group cognitive conflicts occur when a learner in a collaborative mobile learning environment becomes aware of a discrepancy between his/her existing cognitive framework and new information or experience. The cognitive conflicts stimulate the learning process by making an individual to move from his/her learning sphere and participate with others in the learning process. However, there is a big challenge on how students handle and resolve conflicts during collaborative learning. Intelligent agents have been used in this paper to provide support for group interactions by regulating the group conflicts. An experimental design with one control group and two experimental groups (role playing and guided negotiation) is used to compare levels of group knowledge construction. The findings showed improved levels of knowledge construction where regulated conflicts were used compared to where they were not used.

Revisitant les facteurs affectant l’utilisation des Tics sur l’information relative aux intrants agricoles par les paysans dans les pays en voie de développement

Malgre une exposition des paysans aux Tics sur l’information de production agricole, la contribution de ceux-ci dans ce domaine n’est encore satisfaisante. Par consequent, une etude a ete menee pour informer notre audience sur les facteurs affectant l’utilisation de ces Tics par une revision des Tics et les articles publies sur ces Tics en utilisant la Theorie Ancree. Les facteurs avantage relatif, compatibilite, simplicite, l’influence sociale, observabilite, alphabetisation, savoir-faire Tics et qualite de l’information affectent positivement l’utilisation de ces Tics tandis que et le cout excessif des Tics affectent negativement leurs utilisations.Despite farmers’ exposition to ICTs on agricultural input information, their contribution to the access and use of agricultural input information is far from expectation. This study therefore, reviewed these ICTs in developing countries to extract the factors that affect ICTs’ adoption by small-scale famers using the Grounded Theory. The factors Relative Advantage, Compatibility, Simplicity, Social Influence, Observability, Literacy, ICTs’ Skills were identified as affecting positively ICTs’ use while the High Cost was identified as negatively affecting these ICTs.

Designing adaptive learning support through machine learning techniques

The use of web 2.0 technologies in web based learning systems has made learning more learner-centered. In a learner centered environment, there is need to provide appropriate support to learners based on individual learner characteristics in order to maximize learning. This requires a Web-based learning system to have an adaptive interface to suit individual learner characteristics in order to accommodate diversity of learner needs and abilities and to maintain an appropriate context for interaction and for achieving personalized learning. The purpose of this paper is to discuss how machine learning techniques can provide adaptive learning support in a Web-based learning system. In this research, two machine learning algorithms namely: Heterogeneous Value Difference Metric (HVDM) and Naive Bayes Classifier (NBC) were used. HVDM was used to determine those learners who were similar to the current learner while NBC was used to estimate the likelihood that the learner would need to use additional materials for the current concept. To demonstrate the concept we used a course in object oriented programming (OOP).

Dynamic Heuristics: Greedy Search: A Mobile Information Retrieval Algorithm for Ambient Learning Systems

Research supervision services like providing study materials can be enhanced through mobile information retrieval algorithms. An example is semantic searching algorithms, which require the user to input one or two real world concepts. Systems that implement mobile learning approaches like ambient learning can use semantic searching algorithms to support research supervision services through mobile phones. However, there is low adoption of such approaches in some of the African universities. This has been attributed to limited technical limitations of mobile devices that include mobile phones. For instance, complex interfaces, restricted input and small screens on mobile phones make it difficult to enter search keywords when the user is in a hurry. As an attempt to address these limitations, this paper describes dynamic heuristics - greedy search algorithm that automatically generate search keywords. The algorithm can be used to allow flexible mobile information retrieval on a typical ambient learning system.