Christopher A. Moturi

Use of Artificial Neural Networks for Short-Term Electricity Load Forecasting of Kenya National Grid Power System

This paper developed a supervised Artificial Neural Networkbased model for Short-Term Electricity Load Forecasting, and evaluated the performance of the model by applying the actual load data of the Kenya National Grid power system to predict the load of one day in advance. Raw data was collected, cleaned and loaded onto the model. The model was trained under the WEKA environment and predicted the total load for Kenya National Grid power system. The test results showed that the hour-by-hour approach is more suitable and efficient for a day-ahead load forecasting. Forecast results demonstrated that the model performed remarkably well with increased number of iterations. The result suggests that incremental training approach of a neural network model should be implemented for online testing application to acquire a universal final view on its applicability.

Use of Mapreduce for Data Mining and Data Optimization on a Web Portal

paper studied the design, implementation and evaluation of a MapReduce tool targeting distributed systems, and multi- core system architectures. MapReduce is a distributed programming model originally proposed by Google for the ease of development of web search applications on a large number of clusters of computers. We addressed the issues of limited resource for data optimization for efficiency, reliability, scalability and security of data in distributed, cluster systems with huge datasets. The studys experimental results predicted that the MapReduce tool developed improved data optimization. The system exhibits undesired speedup with smaller datasets, but reasonable speedup is achieved with a larger enough datasets that complements the number of computing nodes reducing the execution time by 30% as compared to normal data mining and processing. The MapReduce tool is able to handle data growth trendily, especially with larger number of computing nodes. Scaleup gracefully grows as data and number of computing nodes increases. Security of data is guaranteed at all computing nodes since data is replicated at various nodes on the cluster system hence reliable. Our implementation of the MapReduce runs on distributed cluster computing environment of a national education web portal and is highly scalable.

Use of data mining to check the prevalence of prostate cancer: Case of Nairobi County

Prostate cancer has been on the rise in the past years and alarming cases being found in men in their 20s. The problem is that most of the cases are diagnosed in their late stages thus the mortality rate being high. In recent years data driven analytic studies have become a common complement with novel research where different tools and algorithms are taking a centre stage in cancer research. In this research, the main objective was to use data mining to derive patterns which were used in building a prognostic tool that helps in identification of the Gleason score once screened and deciding the treatment technique. In this research, we used two popular data mining tools (R Environment and WEKA) which exhibited almost same results. The dataset contained around 485 records and 7 variables. In WEKA, a 10-fold cross-validation was used in model building and comparison between ANN and J48. The results showed that ANN is the most accurate predictor compared to J48 in all the instances displaying varying levels in the different zones created. This study contributes to society, academics and cancer research which ultimately assist in reduction of mortality rates by use of pattern recognitions which leads to better decision making. Furthermore, this is a potential impact in helping the GOK (Government of Kenya) in establishing where they should correctly place the cancer diagnosis and treatment equipment that were rolled out by the National government early 2015.

An evaluation of the quality of management information systems used by SACCOs in Kenya

Purpose – Savings and Credit Cooperatives (SACCOs) in developing countries require core banking Management Information Systems (MISs) to run their business, serve their clients and provide differentiated products and services to gain competitive advantage. Considering that SACCOs in Kenya lack the necessary resources to acquire the best information systems, the purpose of this paper is to evaluate MISs currently in use in the SACCO subsector to determine how well they are serving. Design/methodology/approach – Using the ISO/IEC 25010 Software Product Quality Model, the quality of MISs operated by 215 Deposit-Taking SACCOs in the Kenya was evaluated to determine their level of performance. Findings – The results indicated that the MISs currently in use by the SACCOs serve them well in terms of functionality, efficiency, reliability, ease of use and portability. However, vendor support, technical training and implementation process are a big concern to the SACCOs. Practical implications – The SACCOs in Keny...

Toward a data governance model for the Kenya health professional regulatory authorities

Purpose The purpose of this paper is to determine the status, drivers, and barriers to data governance at the health professional regulatory authorities in Kenya. This study aims to develop a model that can be used to establish a formal data governance program at these regulatory authorities. Design/methodology/approach This study used data governance decision areas based on the study of Khatri and Brown (2010). Qualitative and quantitative research methods were used in this study to collect data. Findings This paper identified maintenance of quality of data, achieving customer satisfaction, ensuring data security and control, and achieving operational efficiency as the drivers of data governance at the regulatory authorities. The authorities are faced with lack of data governance awareness, lack of management ownership and support, as well as limited funding and resource allocations as barriers to data governance. This study proposed that for the authorities to increase their data governance, they need to identify their data as an asset, initiate more data quality management mechanism, restrict access to their data, create awareness, and increase management, ownership and support. Practical implications A data governance program for healthcare workforce data is necessary for healthcare planning which influences national policy in the healthcare and the overall delivery of health services in a country. Originality/value The paper proposes a model that health professional regulators in developing countries that are facing limited resources can be used to establish a formal data governance program.

ISO 9001: 2008 Implementation and Impact on the University of Nairobi: a Case Study

Purpose – The purpose of this paper is to present the experience and impact of implementing the ISO 9001: 2008 Standard at the University of Nairobi, in relation to effectiveness on service delivery, operational performance, automation, implementation challenges and related emerging issues. Design/methodology/approach – The paper adopted a case study design approach based on qualitative analysis of internal audit reports, internal surveys and feedback, surveillance audits conducted by the certifying body, and rankings by external bodies, over a period of seven years. Findings – Significant achievements have been realized with regard to institutionalization of quality into the university processes, work environment, documentation and record management, customer satisfaction, infrastructure and facilities, use of ICT as a prime mover of performance improvement, and ranking of the university. Opportunities for improvement as well as critical success factors are presented. Practical implications – The paper r...

Information and communication technology talent management alignment with outsourcing: case of a power company in Kenya

Increase in ICT investments and new talent management strategies have seen companies adopt ICT outsourcing strategy to improve ICT performance and business value. Best practice in technology solutions requires an organisation to address issues of technology-enabled talent management. The elusive crucial link between ICT Talent Management (ICTTM) and ICT Outsourcing (ICTO) could greatly improve ICT Performance if effectively aligned. This paper developed a best practice model for effectively aligning ICTTM with ICTO for improved ICT performance. This research adopted case study approach amongst staff in HR, ICT and Customer Services functional areas in the Kenyan national power distributor, Kenya Power. Questionnaires were used for collecting data. Descriptive statistics and factor analysis were used for analysis. The findings helped to develop a model which on adoption would contribute to improved ICT Performance and achievement of Information Technology Enabled Services (ITES) and therefore enable businesses through improved quality services.

Mobile based Notifiable Disease Surveillance – Case for Kenya

Identifying infectious disease outbreaks in their early stages is an important task, both for governments and international organizations working in the health sector. This study reviewed the notifiable disease reporting systems in Kenya with an aim of understanding their strengths and weaknesses. We evaluated the performance of the present notifiable disease reporting systems, assessed the preparedness of the disease notifiers for the task of reporting notifiable diseases, assessed the readiness of people who participate in disease reporting in the use of computers and mobile systems in disease surveillance, and we developed a mobile based disease surveillance prototype that can report and analyze notifiable disease data to recognize disease outbreaks early. The study targeted medical personnel who presently participate in the reporting and analysis of notifiable disease data in the Nairobi Metropolitan Region. Mobile systems are best to improve the disease reporting and analysis process because of their low cost, widespread use and minimum training required.

Embracing Continuous Auditing: A Case for Public Sector in Kenya

Aims: The objective of this study was to assess the current state of continuous auditing in the state departments in Kenya and to adapt a framework to implement continuous auditing by the Public Sector Audit Organization. Study Design: Adoption of existing model and survey using questionnaires. Place and Duration of Study: Kenya, 2013. Methodology: Existing continuous auditing models were studied and the Integrated Continuous Auditing, Monitoring and Assurance Conceptual Model was adopted for use. The model was tested using data collected using questionnaires. Data was collected from 76 auditors in the Public Sector Audit Organization. A database system of a government Ministry was used to demonstrate how data can be obtained directly from a client system. Results: The study found the need for training in the skills required for continuous auditing and the acquisition of IT resources and infrastructure were necessary in realizing continuous auditing. Conclusion: The paper shows that Public Sector Audit Organization in Kenya, like institutions in other countries such as USA [8] and Australia [11], are preparing to advance from traditional audit to continuous auditing. The Integrated Continuous Auditing, Monitoring and Assurance Conceptual Model would offer a good starting point.

Embracing Contingency Planning for University Information Resources

Aims: This paper discusses the concept of contingency planning for information systems in a university context, uncovers the critical information systems within a university that are most vulnerable, identifies contingency planning models, and establishes a systematic approach that would be followed when implementing a contingency plan program in a university environment. Study Design: Adapted conceptual model. Place and Duration of Study: The University of Nairobi between April and July 2012. Methodology: The adapted model was applied to the University of Nairobi, ICT Centre. The study used primary data that was collected through self-administered questionnaires; one set was administered to the end users spanning across seven departments and another set was distributed to ICT staff. Results: This study identified the critical university information systems, identified the minimal IT resources that support the critical information systems, established a systematic approach that should be followed when implementing a contingency plan program in university environments, and developed a model contingency plan. Conclusion: The findings of this research would be of major importance to university policy makers and stakeholders who would be able to make sound decisions and policies regarding the protection of information assets from an informed point of view. Original Research Article British Journal of Applied Science & Technology, 4(3): 492-509, 2014 493