Deshendran Moodley

Position paper: researching and developing open architectures for national health information systems in developing african countries

Most African countries have limited health information systems infrastructure. Some health information system components are implemented but often on an adhoc, piecemeal basis, by foreign software developers and designed to solve specific problems. Little attention is usually paid to how these components can fit into an integrated national health information system and interoperate with other components. The Health Enterprise Architecture Laboratory was recently established in the School of Computer Science at the University of KwaZulu-Natal in South Africa to undertake research and build capacity in open health architectures for developing African countries. Based on field experiences and requirements in South Africa, Mozambique and Rwanda, the laboratory is evolving a generic Health Enterprise Architecture Framework and Repository of Tools specifically for low resource settings. In this paper we describe these three initiatives and the expected impact on implementing health information systems in developing African countries.

Using the Sensor Web to Detect and Monitor the Spread of Vegetation Fires in Southern Africa

Key concepts in disaster response are level of preparedness, response times, sustaining the response and coordinating the response. Effective disaster response requires a well-developed command and control framework that promotes the flow of information. The Sensor Web is an emerging technology concept that can enhance the tempo of disaster response. We describe how a satellite-based system for regional vegetation fire detection is being evolved into a fully-fledged Sensor Web application.

An Architecture for Managing Knowledge and System Dynamism in the Worldwide Sensor Web

Sensor Web researchers are currently investigating middleware to aid in the dynamic discovery, integration and analysis of vast quantities of both high and low quality, but distributed and heterogeneous earth observation data. Key challenges being investigated include dynamic data integration and analysis, service discovery and semantic interoperability. However, few efforts deal with managing knowledge and system dynamism. Two emerging technologies that have shown promise in dealing with these issues are ontologies and software agents. This paper presents an integrated ontology driven agent based Sensor Web architecture for managing knowledge and system dynamism. An application case study on wildfire detection is used to illustrate the operation of the architecture.

An Architecture and Reference Implementation of an Open Health Information Mediator: Enabling Interoperability in the Rwandan Health Information Exchange

Rwanda, one of the smallest and most densely populated countries in Africa, has made rapid and substantial progress towards designing and deploying a national health information system. One of the more challenging aspects of the system is the design of an architecture to support: interoperability between existing health information systems already in use in the country; incremental extension into a fully integrated national health information system without substantial re-engineering; and scaling, from a single district in the initial phase, to national level without requiring a fundamental change in technology or design paradigm. This paper describes the key requirements and the design of the current architecture using the ISO/IEC/IEEE 42010 standard architecture descriptions. The architecture takes an Enterprise Service Bus approach. A partial implementation and preliminary analysis of the architecture is given. Since these challenges are experienced by other developing African countries, the next steps involves creating a generic architecture that can be reused for health information exchange in other developing African countries.

Architectural frameworks for developing national health information systems in low and middle income countries

Consolidating currently fragmented health information systems in low and middle-income countries (LMIC) into a coherent national information system will increase operational efficiencies, improve decision-making and will lead to better health outcomes. However, engineering an enterprise information system of the scale and complexity of a national health information system (NHIS) pose unique and complex challenges in LMICs. In this paper, we review current approaches to NHIS development and discuss challenges faced by LMICs to develop their NHIS. Based on current LMIC systems we identify three stages of system evolution and propose that LMICs should follow an evolutionary, middle-out approach to NHIS development supported by appropriate architectural frameworks.

Integrating Statistical Machine Learning in a Semantic Sensor Web for Proactive Monitoring and Control

Proactive monitoring and control of our natural and built environments is important in various application scenarios. Semantic Sensor Web technologies have been well researched and used for environmental monitoring applications to expose sensor data for analysis in order to provide responsive actions in situations of interest. While these applications provide quick response to situations, to minimize their unwanted effects, research efforts are still necessary to provide techniques that can anticipate the future to support proactive control, such that unwanted situations can be averted altogether. This study integrates a statistical machine learning based predictive model in a Semantic Sensor Web using stream reasoning. The approach is evaluated in an indoor air quality monitoring case study. A sliding window approach that employs the Multilayer Perceptron model to predict short term PM2.5 pollution situations is integrated into the proactive monitoring and control framework. Results show that the proposed approach can effectively predict short term PM2.5 pollution situations: precision of up to 0.86 and sensitivity of up to 0.85 is achieved over half hour prediction horizons, making it possible for the system to warn occupants or even to autonomously avert the predicted pollution situations within the context of Semantic Sensor Web.

A System for a Hand Gesture-Manipulated Virtual Reality Environment

Extensive research has been done using machine learning techniques for hand gesture recognition (HGR) using camera-based devices; such as the Leap Motion Controller (LMC). However, limited research has investigated machine learning techniques for HGR in virtual reality applications (VR). This paper reports on the design, implementation, and evaluation of a static HGR system for VR applications using the LMC. The gesture recognition system incorporated a lightweight feature vector of five normalized tip-to-palm distances and a k-nearest neighbour (kNN) classifier. The system was evaluated in terms of response time, accuracy and usability using a case-study VR stellar data visualization application created in the Unreal Engine 4. An average gesture classification time of 0.057ms with an accuracy of 82.5% was achieved on four distinct gestures, which is comparable with previous results from Sign Language recognition systems. This shows the potential of HGR machine learning techniques applied to VR, which were previously applied to non-VR scenarios such as Sign Language recognition.

A knowledge-based system for discovering ecological interactions in biodiversity data-stores of heterogeneous specimen-records: A case-study of flower-visiting ecology

Abstract We modeled expert knowledge of arthropod flower-visiting behavioral ecology and represented this in an event-centric domain ontology, which we describe along with the ontology construction process. Two smaller domain ontologies were created to represent expert knowledge of known flower-visiting insect groups and expert knowledge of the flower-visiting behavioral ecology of Rediviva bees. Two application ontologies were designed, which, together with the domain ontologies, constituted the ontology framework of a prototype semantic enrichment and mediation system that we designed and implemented to improve semantic interoperability between flower-visiting data-stores. We describe and evaluate the system implementation in a case-study of three flower-visiting data-stores, and we discuss the systems scalability, extension and potential impact. We demonstrate how the system is able to dynamically extract complex ecological interactions from heterogeneous specimen data-stores. The conceptual stance and modeling approach are potentially of general use in representing knowledge of animal behavior and ecological interactions, and in engineering semantic interoperability between data-stores containing behavioral ecology data.

An Investigation of Classification Algorithms for Predicting HIV Drug Resistance without Genotype Resistance Testing

The development of drug resistance is a major factor impeding the efficacy of antiretroviral treatment of South Africas HIV infected population. While genotype resistance testing is the standard method to determine resistance, access to these tests is limited in low-resource settings. In this paper we investigate machine learning techniques for drug resistance prediction from routine treatment and laboratory data to help clinicians select patients for confirmatory genotype testing. The techniques, including binary relevance, HOMER, MLkNN, predictive clustering trees PCT, RAkEL and ensemble of classifier chains were tested on a dataset of 252 medical records of patients enrolled in an HIV treatment failure clinic in rural KwaZulu-Natal in South Africa. The PCT method performed best with a discriminant power of 1.56 for two drugs, above 1.0 for three others and a mean true positive rate of 0.68. These methods show potential for application where access to genotyping is limited.

A knowledge-based system for generating interaction networks from ecological data

Abstract Semantic heterogeneity hampers efforts to find, integrate, analyse and interpret ecological data. An application case-study is described, in which the objective was to automate the integration and interpretation of heterogeneous, flower-visiting ecological data. A prototype knowledge-based system is described and evaluated. The systems semantic architecture uses a combination of ontologies and a Bayesian network to represent and reason with qualitative, uncertain ecological data and knowledge. This allows the high-level context and causal knowledge of behavioural interactions between individual plants and insects, and consequent ecological interactions between plant and insect populations, to be discovered. The system automatically assembles ecological interactions into a semantically consistent interaction network (a new design of a useful, traditional domain model). We discuss the contribution of probabilistic reasoning to knowledge discovery, the limitations of knowledge discovery in the application case-study, the impact of the work and the potential to apply the system design to the study of ecological interaction networks in general.