MSIS Theses and Dissertations (2016)

Permanent URI for this collection

http://hdl.handle.net/11071/4562

Browse

Recent Submissions

Now showing 1 - 5 of 10
  • Thumbnail Image
    Item
    A prototype for information capture using natural language processing : a case of Nation online news
    (Strathmore University, 2016) Mbuthia, Samuel K.
    Natural Language Processing is a crucial component in the study of artificial intelligence. The Internet contains an abundance of information from a multitude of sources and a lot of this information is in human language which is not easily interpretable by computers. This is especially the case with unstructured data. Newswire sources, which include news websites and other forms of digital news reporting, provide easily accessible sources of information. This information is reliable because in many cases it is provided by journalists who are governed by professional codes of conduct. Years of reporting news on the Internet has resulted in a lot of information that is free and readily available. However, this information cannot be utilized effectively as it is too much to be processed by usual data mining techniques. This is where Natural Language Processing comes in as an essential tool in mining and processing the plethora of newswire content. This research took an applied approach to try and address the problem of inefficient utilization of newswire content. The research went through several stages each trying to address a specific area of the problem. While the problem being addressed was a global one, a focus on Kenyan news made the tasks manageable and specific but at the same time scalable to a larger setting. The research delved into the creation of a novel prototype that addressed the gaps in currently existing systems and improved on how information processed by Natural Language Processing techniques could be presented and reported. The application of graphical representations by using a number of advanced graphical libraries and application program interfaces as well as the application of machine learning models and algorithms were an integral part of the research. Various tests were undertaken to determine the viability of the prototype and key among them were performance test that monitored the performance of the applied machine learning algorithms. The results of the tests were duly tabulated and reported. While the research was largely successful, it was concluded that a lot more remains to be done to comprehensively address the gaps that exists in the area of research. As such, this research acts as a platform for further research that can gradually fill all the gaps identified as well as those that may be identified in the future.
  • Thumbnail Image
    Item
    E-portfolio model for student assessment in education : a case of Nairobi secondary schools
    (Strathmore University, 2016) Maate, Philip Malinga
    A number of public secondary schools in Kenya lack a properly operational information management system to capture student academic and personal data as an evidence to show one’s learning journey over time. From the current system it is difficult to isolate student’s personal traits or talents such as negotiation skills, public relations, or even other key goals as stipulated in the Kenyan secondary school syllabus like promoting love for and loyalty to the nation. A good information management system inform of e-portfolio in a school would provide data on evidence of student’s abilities in a holistic sense and show a complete picture of what a student is. Such a system would be a better basis for informing interested parties like universities and potential employers of the student’s abilities other than use of test scores only. This study sought to develop an e-portfolio model that could aid in assessment in public secondary schools in Kenya. The study also sought to establish the content requirements for e-portfolios in public secondary schools within Nairobi County. This study adopted exploratory research design of a case study of public secondary schools in Nairobi County. Random sampling was used to select the sample size. Data collection was done through survey method where questionnaires were used. The data was analyzed using descriptive statistics. The results from the analyzed data were used as an indicator to the content requirements of an assessment e-portfolio in public secondary schools.
  • Thumbnail Image
    Item
    Mobile based expert system model for animal health monitoring : cows disease monitoring in Kenya
    (Strathmore University, 2016) Muriu, Peter
    A host of diseases affect livestock in Kenya. These diseases as well as pests cause heavy losses to livestock farmers through deaths, reduced productivity and loss of markets for products. The research aimed at gaining deeper insights into the challenges faced by livestock farmers in Kenya, to understand the methods used for animal health monitoring and disease prediction and to establish the data and information requirements for animal health management at a farm. This study further proposed a mobile based expert system model for animal health monitoring. Mobile uptake in Kenya coupled with significant strides made in mobile telecommunication infrastructure bring new potential to animal health management. The ubiquitous nature and pervasiveness of mobiles enable the use of information and communication technology everywhere, by everyone, and at all times. Using mobile technology, the model automates the process of managing animal health at a farm including recording farm, farmers’ and animal details, predicting animal disease and monitoring of animal health right at the farms. It provides a collaborative platform between a farmer and a veterinary expert. The health of the affected cow is then monitored to recovery. The model was tested through simulation of various modules. Of the 29 participants that took part in this exercise, 69 percent were satisfied that the model fulfilled the intended functions of animal health monitoring. 76 percent of the respondents also found the model easy to use. The model was therefore successful in management of farm, farmers and animal records as well as continuous monitoring of animal health.
  • Thumbnail Image
    Item
    Near-Field Communication based-model for health information portability
    (Strathmore University, 2016) Onyancha, Paul Morumbwa
    Health Information Portability is an important concept in the healthcare sector because of the patient’s ability to carry their medical data when visiting a health care center. Data that can be stored in hitherto time-honored systems such as Health Information Systems and Electronic Medical Record (EMR) systems is diverse and hence a need for a focused approach on the data to be stored and retrieved securely when needed. Empirical evidence shows a lack of clear technological solution for Health Information Portability in the era of efficiency of mobile devices accessing stored EMRs. Near Field Communication (NFC) technology presents a new dimension for enterprises such that with NFC tags, any object can be turned into a digital data point that can transfer information to NFC-enabled mobile devices using short range radio waves. In this research, agile development methodology was used and different systems, models and prototypes incorporating NFC tags, NFC readers, mobile application, encryption and decryption studied and their beneficial aspects borrowed to create a novel application that runs on the doctor’s NFC-enabled phone that can read and write into a patient’s NFC-enabled medical card. Security features such as password, decryption and encryption of data on the NFC card and the vital EMR data necessary as per doctor’s recommendations, which included patient’s name, allergies and blood group, were incorporated. A model developed showing communication from a host PC and a mobile phone client demonstrated the machine-to-machine communication NFC concept. Authentication, data capture and deploy, data view and edit, mobile to host PC connection were tested and all showed a pass. This system will help reduce incidences of duplication of medical tests leading to reduction in medical costs for patients, assist doctors in making quick clinical decisions and also form the basis for future research on NFC in healthcare.
  • Thumbnail Image
    Item
    E-Learning technologies adoption framework for enhanced productivity of small and medium enterprises in Kenya
    (Strathmore University, 2016) Thuo, Nicholas Mbugua
    The potential of e-learning in transforming the performance of Small and Medium Enterprises (SMEs) through its effects on employee productivity and hence organizational output is acknowledged in literature in both developing and developed countries. The ubiquitous nature of e-learning offers unlimited opportunity for employees to engage in learning and act as a catalyst for transformation through lifelong learning. However, there is a dearth of empirical evidence in the Kenyan context on adoption of e-learning in SMEs as well as success. The purpose of this study was therefore to examine usage of e-learning by SMEs and the outcomes as measured by performance of SMEs in Kenya with a view to proposing a framework for enhanced adoption of e-learning in these organizations. The study was guided by the Roger’s Diffusion of Innovation Theory, a theory that identifies the determinants of the uptake of an innovation such as e-learning. The study adopted the descriptive design entailing a survey of 100 HR Managers and 100 employees of SMEs in the 2015-16 top 100 SMEs from a survey done annually by KPMG Kenya and Nation Media Group. A sample of 50 HR Managers and 50 employees were selected for the survey using simple random sampling techniques and purposive sampling respectively. The SME HR questionnaire and the SME Employee questionnaire were used to collect both quantitative and qualitative data on the extent, determinants, and outcomes of use of e-learning in the SMEs. Quantitative data analysis was done through descriptive statistics to demonstrate the extent, outcomes and challenges of adoption of e-learning in SMEs. Qualitative through thematic grouping and descriptions. With regards to the extent of adoption of e-learning in the SMEs the study found limited adoption of e-learning, with only 10 firms out of the study 50 SMEs reporting adoption. On the influence of employer factors on adoption, the perceptions were positive on all aspects such as innovativeness and IT competencies. On the employee aspects of e-learning usage, the study found positive perceptions on ease of use and user satisfaction, which were in turn, proxy measures of satisfaction with the quality of the information on the system and the system itself. On the outcomes of e-learning on employers and employees, the study reported positive perceptions on these outcomes. The most influential barriers were organizational and technical. The study therefore concludes that although there is limited adoption of e-learning among SMEs, there are many positive characteristics among adopting firms. The study therefore recommends more support for infrastructure to support e-learning for SMEs among government and the business sector and more studies on the influence of pedagogical aspects such as content and media design.