Thesis (MTech (Information Technology))--Cape Peninsula University of Technology, 2012. / Home-Based Healthcare (HBHC) is an important aspect of South Africa's healthcare system. HBHC is the provision of care services to patients by trained or semi-trained caregivers at home. In South Africa HBHC was introduced in 2001 to address many problems with traditional healthcare such as overcrowding in public health facilities. South Africa has one of the highest HIV/AIDS infection rates in the world, which is often accompanied by opportunistic infections such as tuberculosis. HBHC is envisaged to address these challenges, thus relieving the burden on primary healthcare. HBHC is itself faced with many problems which include poor information or data management, unclear information flows, and insufficient information storage. It is also not clear how caregivers use data elements and there is no coherent indigenous knowledge base for the capturing, implementation and utilisation of data elements in local HBHC providers. This is particularly important to caregivers who rely on frameworks of indigenous knowledge in interpreting and making decisions on how to provide a care service to patients. In reality, caregivers operate in indigenous environments requiring the utilisation of local knowledge. This study explores the relationships between, and approaches to, data elements in different HBHC providers and communities. Three interpretive case studies in the Eastern and Western Cape Provinces of South Africa were conducted. Semistructured interviews, focus groups, participant observation and document analysis were used for data collection. The primary research question was: What happens when caregivers from various communities interact with data elements when providing a care service? Caregivers' indigenous knowledge and use of data elements was then harnessed in a knowledge base. The results from this study can be used by HBHC managers to develop their forms and training materials as the initial set of data elements used in HBHC has been identified. Caregivers from different communities can also learn how these data elements are used in other communities.

Thesis (MTech (Information Technology))--Cape Peninsula University of Technology, 2016. / Access to healthcare is regarded as a basic and essential human right. It is widely known that ICT solutions have potential to improve access to healthcare, reduce healthcare cost, reduce medical errors, and bridge the digital divide between rural and urban healthcare centres. The access to personal healthcare records is, however, an astounding challenge for both patients and healthcare professionals alike, particularly within resource-restricted environments (such as rural communities). Most rural healthcare institutions have limited or non-existent access to electronic patient healthcare records. This study explored the accessibility of personal healthcare records by patients and healthcare professionals within a rural community hospital in the Eastern Cape Province of South Africa. The case study was conducted at the St. Barnabas Hospital with the support and permission from the Faculty of Informatics and Design, Cape Peninsula University of Technology and the Eastern Cape Department of Health. Semi-structured interviews, observations, and interactive co-design sessions and focus groups served as the main data collection methods used to determine the accessibility of personal healthcare records by the relevant stakeholders. The data was qualitatively interpreted using thematic analysis. The study highlighted the various challenges experienced by healthcare professionals and patients, including time-consuming manual processes, lack of infrastructure, illegible hand-written records, missing records and illiteracy. A number of recommendations for improved access to personal healthcare records are discussed. The significance of the study articulates the imperative need for seamless and secure access to personal healthcare records, not only within rural areas but within all communities.

Orientador: Ricardo da Silva Torres / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-17T10:19:12Z (GMT). No. of bitstreams: 1 Panaggio_RicardoLuisZanetti_M.pdf: 1050987 bytes, checksum: f88ede3a681c880be4489f30662ec451 (MD5) Previous issue date: 2010 / Resumo: A diferença entre o conjunto de dados disponíveis e o conjunto dos dados que interessam a um usuário é enorme e, em geral, cresce diariamente, uma vez que o volume de dados produzidos todos os dias só aumenta. Identificar todo o conjunto de dados de interesse de um usuário utilizando mecanismos tradicionais é muito difícil - talvez impossível. Nesse cenário, ferramentas que possam ajudar usuários a identificar itens de interesse, como sistemas de recomendação, têm um grande valor. Esta dissertação apresenta um modelo genérico que pode ser utilizado para a criação de sistemas de recomendação, e sua instanciação utilizando técnicas de agrupamento. Essa dissertação apresenta também a validação desse modelo, a partir de sua implementação e experimentação com dados das bases Movielens e Jester. As principais contribuições são: definição de um modelo de recomendação baseado em grafos, até onde se sabe mais rico e mais genérico que os encontrados na literatura; especificação e implementação de uma arquitetura modular de um sistema de recomendação baseada nesse modelo, com enfoque em técnicas de agrupamento de dados; validação da arquitetura e do modelo de recomendação propostos, comparando eficácia e eficiência de técnicas de agrupamento de dados em sistemas de recomendação / Abstract: The difference between the data available and the set of interesting data to a certain user is enormous and, in general, is becoming greater daily, as the amount of data produced increases. Identifying all the interesting data set using traditional mechanisms is difficult- sometimes impossible. In this scenario, providing tools that can help users on identifying items that are of interest, such as recommendation systems, is of great importance. This dissertation presents a generic model that can be used to create recommender systems, and its instantiation using clustering techniques. It also discusses the validation of this model, by showing results obtained from experiments with data from Movielens and Jester datasets. The main contributions are: a graph-based generic model for recommender systems, which is more generic and richer than the ones found in literature; the specification and implementation of a modular architecture for recommender systems based on that model, focused on clustering techniques; validation of both model and architecture, by comparing efficiency and effectiveness of clustering-based recommender systems / Mestrado / Sistemas de Recuperação da Informação / Mestre em Ciência da Computação

Orientador: Ricardo da Silva Torres / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-08T22:04:09Z (GMT). No. of bitstreams: 1 Ferreira_CristianoDalmaschio_M.pdf: 3661487 bytes, checksum: 589a6834c502d67559dbb716e1dd4645 (MD5) Previous issue date: 2007 / Resumo: A técnica de realimentação de relevância tem sido utilizada com o intuito de incorporar a subjetividade da percepção visual de usuários à recuperação de imagens por conteúdo. Basicamente, o processo de realimentação de relevância consiste na: (i) exibição de um pequeno conjunto de imagens; (ii) rotulação dessas imagens pelo usuário, indicando quais são relevantes ou não; (iii) e finalmente, aprendizado das preferências do usuário a partir das imagens rotuladas e seleção de um novo conjunto de imagens para exibição. O processo se repete até que o usuário esteja satisfeito. Esta dissertação apresenta dois arcabouços para recuperação de imagens por conteúdo com realimentação de relevância. Esses arcabouços utilizam programação genética para assimilar a percepção visual do usuário por meio de uma combinação de descritores. A utilização de programação genética é motivada pela sua capacidade exploratória do espaço de busca uma vez que esse espaço se adequa ao objetivo principal dos arcabouços propostos: encontrar, dentre todas as possíveis funções de combinação de descritores, aquela que melhor representa as características visuais que um usuário deseja ressaltar na realização de uma consulta. Os arcabouços desenvolvidos foram validados por meio de uma série de experimentos, envolvendo três diferentes bases de imagens e descritores de cor, forma e textura para a caracterização do conteúdo dessas imagens. Os arcabouços propostos foram comparados com três outros métodos de recuperação de imagens por conteúdo com realimentação de relevância, considerando-se a eficiência e a efetividade no processo de recuperação. Os resultados experimentais mostraram a superioridade dos arcabouços propostos. As contribuições dessa dissertação são: (i) estudo sobre diferentes técnicas de realimentação de relevância; (ii) proposta de dois arcabouços para recuperação de imagens por conteúdo com realimentação de relevância baseado em programação genética; (iii) implementação dos métodos propostos, validando-os por meio de uma série de experimentos e comparações com outros métodos / Abstract: Relevance Feedback has been used to incorporate the subjectivity of user visual perception in content-based image retrieval tasks. The relevance feedback process consists in the following steps: (i) showing a small set of images; (ii) indication of relevant or irrelevant images by the user; (iii) and finally, learning the user needs from her feedback, and selecting a new set of images to be showed. This procedure is repeated until the user is satisfied. This dissertation presents two content-based image retrieval frameworks with relevance feedback. These frameworks employ Genetic Programming to discover a combination of descriptors that characterize the user perception of image similarity. The use of genetic programming is motivated by its capability of exploring the search space, which deals with the major goal of the proposed frameworks: find, among all combination functions of descriptors, the one that best represents the user needs. Several experiments were conducted to validate the proposed frameworks. These experiments employed three different images databases and color, shape and texture descriptors to represent the content of database images. The proposed frameworks were compared with three other content-based image retrieval methods regarding their efficiency and effectiveness in the retrieval process. Experiment results demonstrate the superiority of the proposed methods. The contributions of this work are: (i) study of different relevance feedback techniques; (ii) proposal of two content-based image retrieval frameworks with relevance feedback, based on genetic programming; (ii) implementation of the proposed methods and their validation with several experiments, and comparison with other methods / Mestrado / Banco de Dados / Mestre em Ciência da Computação

M.Bibl. (Information Science) / Difficulties in satisfying the information needs of the engineer operating in the developing world led to a requirement to determine through research what information technologies are available and now they might be implemented to meet these needs, A growing recognition by engineers operating in the developing world of the importance of information and information sources for economic and social development fuels their need for engineering information. The information explosion s problems of scatter, diversity, volume and cost are very real in the developing world and are exaggerated by the prevailing economic, social, political and cultural conditions in developing countries. A literature study established the most striking characteristics of developing countries and special attention was given to Africa and Botswana. Factors hampering the developing world in gaining access to information and become part of the world "information economy" was identified. A literature study was also conducted to establish what information technology was available world wide, what has already been tried and tested, and which information technologies have the potential to be introduced in developing countries. It was found that despite the problems and obstacles which exist when introducing IT to developing countries, scientific and technological information services cannot get by without the use of IT. Certain information technologies such as CD-ROM, which seems to be promising in providing access to bibliographic and full text materials, need to be introduced. The use of information technology could also be successful to assist in educating people in developing countries about the importance and benefits of information systems for survival by providing easy access to coping and helping information as well as enriching and edifying information. An empirical study by structured interview was carried out on a representative sample of consulting engineers working in Botswana. Their information needs, access to engineering information sources and IT availability were establish. Evaluation of the responses to the structured interview reveal that engineers in Botswana are quite a diverse group, but that they could be grouped together by virtue of certain common characteristics such as place of work, civil engineering disciplines, membership of professional organisations, country in which engineering qualification was obtained and home language.

Philosophiae Doctor - PhD / The existing District Health Information System in South Africa can be described as a facility based Information System, focusing on the clinics and hospitals and not on the community. Consequently, only those who access health services through these facilities are included in the system. Many children do not have access to basic health and social services and consequently, are denied their right to good health. Additionally, they are excluded from the routine Health Information System. Policy and resource decisions made by the District Managers, based on the current health facility information, reinforces the exclusion of these already marginalised children. The premise behind this research is that vulnerability of children can be tackled using two interconnected strategies. The first is through the creation of awareness of the situation of children and the second through mobilising the commitment and action of government and society to address this situation. These strategies can be supported by designing an Information System for action; an Information System that can be used to advocate and influence decisions and policies for the rights of these children; an Information System that includes all children. An interpretive participatory action research approach, using a case study in a rural municipality in South Africa, was adopted for the study of a child-health Community-Based Information System. The context in which the community is placed, as well as the structures which are embedded in it, was examined using Structuration Theory. This theory also influenced the design of the Information System. As the aim of the research is to change the Information System to include vulnerable children, a Critical Social Theoretical and longitudinal perspective was adopted. In particular, concepts from Habermas, such as the creation of a public sphere and the ’Ideal Speech Situation’, informed the methodology chosen and were used to analyse the research undertaken. Based on the research conducted in this municipality, four main changes to the Health Information System were made. These were: • determination of the community’s own indicators; • changes in data collection forms; • creation of forums for analysis and reflection, and; • changes in the information flows for improved feedback. Other practical contributions of the research are the development of local capacities in data collection and analysis, the development of practical guidelines on the design of a child-health Community-Based Information System, and the development of strategies for enabling participation and communication. In line with the action research approach adopted, and the desire to link theory and practice, the research also contributed on a theoretical level. These contributions include extending the use of Structuration Theory, in conjunction with Habermas’ Critical Social Theory, to the empirical context of South Africa; addressing the gap of Community-Based Information Systems in Information System design; extending the debate on participation and communication in Information Systems to ’developing’ countries, and developing generalisations from a qualitative case study. / South Africa

Knowledge Management is associated with organisational initiatives in response to the demands of a knowledge-based economy in which the potential value of knowledge as a source for competitive advantage is recognised. However, the lack of a common understanding about knowledge itself, its characteristics and how it is constructed has led to diverse approaches about how to "manage" it. This study presents a critical overview of traditional and contemporary KM approaches. The main focus of this study was to discover and apply a suitable methodology for assessing an organisation's knowledge processing environment. This includes an analysis of the current practices and behaviours of people within the organisation relating to the creation of new knowledge and integrating such knowledge into day-to-day work. It also includes inferring from the above practices those policies and programmes that affect knowledge outcomes. This research makes extensive use of the Knowledge Life Cycle (KLC) framework and the Policy Synchronisation Method (PSM) developed by advocates of the New Knowledge Management movement. A case study approach was followed using a range of data collection methods, which included personal interviews, a social network survey and focus group discussions. The selected case is the small IT department at the East London campus of Rhodes University. Evidence from the case suggests that the knowledge processing environment within the IT department is unhealthy. The current knowledge processing practices and behaviours are undesirable and not geared towards the creation of new knowledge and the integration of such knowledge within the business processes of the IT department. There is little evidence of individual and organisational learning occurring and the problem solving process itself is severely hampered by dysfunctional knowledge practices. The study concludes that the above state of affairs is a reflection of the quality and appropriateness of policies and programmes in the extended organisation. Equally, the local definition of rules, procedures and the execution thereof at a business unit level is mostly lacking. The study illustrates that a systematic assessment of the knowledge processing environment provides the organisation with a sound baseline from where knowledge-based interventions can be launched.

This research is concerned with some aspects of the retrieval of information from database systems by casual, naive computer users. A "casual user" is defined as an individual who only wishes to execute queries perhaps once or twice a month, and a "naive user" is someone who has little or no expertise in operating a computer and, more specifically for the purposes of this study, is not practiced at querying a database. The research initially focuses on a specific group of casual, naive users, namely a group of clinicians, and analyzes their characteristics as they pertain to the retrieval of information from a computer database. The characteristics thus elicited are then used to create the requirements for a database interface that would, potentially, be acceptable to this group. An interface having the desired requirements is then proposed. This interface consists, from a user's perspective, of three basic components. A graphical model gives a picture of the database structure. Windows give the ability to view different areas of the database, physically group together items that come under one logical heading and provide the user with immediate access to the data item names used by the system. Finally, a natural language query language provides a means of entering a query in a syntax (that of ordinary English) which is familiar to the user. The graphical model is a logical abstraction of the database. Unlike other database interfaces, it is not constrained by the model (relational, hierarchical, network) underlying the database management system, with the one caveat that the graphical model should not imply any connections which cannot be supported by the management system. Versions of the interface are implemented on both eight-bit and sixteen-bit microcomputers, and testing is conducted in order to validate the acceptability of the interface and to discover the level of graphical model which the users find most acceptable. The results of this testing are reported and further areas for research suggested.

Doctors can experience difficulty in accessing medical information of new patients. One reason for this is that the management of medical records is mostly institution-centred. The lack of access to medical information may negatively affect patients in several ways. These include new medical tests that may need to be carried out at a cost to the patient and doctors prescribing drugs to which the patient is allergic. This research investigates how patients can play an active role in sharing their personal health records (PHRs) with doctors located in geographically separate areas. In order to achieve the goal of this research, existing literature concerning medical health records and standards was reviewed. A literature review of techniques that can be used to ensure privacy of health information was also undertaken. Interview studies were carried out with three medical practices in Port Elizabeth with the aim of contextualising the findings from the literature study. The Design Science Research methodology was used for this research. A Hybrid Model for Managing Personal Health Records in South Africa is proposed. This model allows patients to view their PHRs on their mobile phones and medical practitioners to manage the patients’ PHRs using a web-based application. The patients’ PHR information is stored both on a cloud server and on mobile devices hence the hybrid nature. Two prototypes were developed as a proof of concept; a mobile application for the patients and a web-based application for the medical practitioners. A field study was carried out with the NMMU health services department and 12 participants over a period of two weeks. The results of the field study were highly positive. The successful evaluation of the prototypes provides empirical evidence that the proposed model brings us closer to the realisation of ubiquitous access to PHRS in South Africa.

Orientador: Ricardo da Silva Torres / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-18T15:54:47Z (GMT). No. of bitstreams: 1 Kozievitch_NadiaPuchalski_D.pdf: 7513500 bytes, checksum: c6d45f0141cb99375cfcabb03d93ca73 (MD5) Previous issue date: 2011 / Resumo: Atualmente, com os avanços tecnológicos, há disponível uma quantidade grande e heterogênea de dados multimídia. Estes dados podem ser provenientes de fontes diversificadas, desempenhando um papel fundamental em sistemas de informação, tais como repositórios de Bibliotecas Digitais. Com o objetivo de reutilizar, integrar, agregar e unificar diferentes recursos sob o mesmo conceito, objetos complexos surgiram para facilitar a abstração de agregações, utilizando componentes de diferentes domínios, e unificando-os sob o mesmo conceito. Em especial, os objetos complexos de imagens são um exemplo representativo de fonte de dados que geralmente é integrada com componentes heterogêneos, tais como metadados, links e softwares de manipulação de imagem. A busca de imagens é um serviço importante, amplamente explorado em sistemas de Biblioteca Digital. A recuperação de imagens por conteúdo aborda a busca automática de imagens, considerando propriedades visuais (como textura e cor). Este trabalho trata de três aspectos relacionados a objetos complexos: (i) a formalização de conceitos; (ii) a comparação de tecnologias relacionadas; e (iii) a especificação e a implementação de um protótipo, que encapsula e publica objetos complexos de imagens manipulados em sistemas de busca de imagens por conteúdo. A infraestrutura proposta baseia-se em uma estrutura de componentização específica - Digital Content Component (DCC) - para encapsular o processo de busca de imagens por conteúdo e o objeto complexo de imagem. Posteriormente, os dados são publicados como itens de um repositório de dados, usando o protocolo Open Archives Initiative Protocol for Metadata Harvesting (OAI-PMH). A solução proposta prevê (i) um acesso homogêneo ao processo de busca de imagens por similaridade, e fontes de dados (imagens, metadados e descritores); (ii) a distribuição e coleta de metadados de objetos complexos de imagens, juntamente com as medidas de similaridade e vetores de características; e (iii) a centralização do processamento, encapsulamento, publicação e coleta do objeto complexo de imagem. Finalmente, é ilustrado o reuso dos componentes da infraestrutura proposta no domínio de biodiversidade, na integração de bibliotecas digitais de impressões digitais, na busca multimodal e em estórias de vídeo / Abstract: The large amount of heterogeneous data from different resources available today play a key role in information systems, such as Digital Library repositories. In order to reuse, integrate, aggregate, and unify different resources under the same concept, complex objects (COs) have emerged to facilitate aggregation abstraction, embracing components from different domains, and unifying them under the same concept. In special, image COs are a representative example of data source which is generally integrated with different components, such as metadata, links, and image manipulation software. Image search is an important service, widely explored in Digital Library systems. The so-called Content-Based Image Retrieval (CBIR) addresses the automatic search of images, trying to retrieve collection images by taking into account their visual properties (such as texture and color). This work is concerned with tackling three aspects related to complex objects: (i) formal definitions; (ii) comparison of related technologies; and (iii) the specification and implementation of a framework, which encapsulates and publishes complex image objects resulting from the CBIR process. Our infrastructure relies on a specific component technology - Digital Content Component (DCC) - to encapsulate the CBIR process and wrap image COs. Later, the data is exposed as items in a data repository, using Open Archives Initiative Protocol for Metadata Harvesting (OAI-PMH). The proposed solution provides (i) an homogeneous access to CBIR process and heterogenous data sources (image collection, metadata, descriptors); (ii) the harvesting of complex image objects (ICOs), along with the similarity distances and feature vectors; and (iii) the centralization of ICO processing, packaging, publishing, and harvesting. Finally, we illustrate the reuse of our infrastructure components in biodiversity domain, in a fingerprint digital library integration, with multimodal search, and video stories / Doutorado / Ciência da Computação / Doutor em Ciência da Computação