Browsing by Author "Bekele, Rahel"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Application of Bayesian Networks (BN) Technology in Predicting Major Factors Behind Poor ART Adherence Trends in Ethiopia - the case of SNNPR region(AAU, 2009-03-12) Biru, Amanuel; Bekele, RahelThis research presented the concepts of knowledge breakthrough based on the Bayesian Networks technology to extract valid models of knowledge. The application domain of the research is the health sector, one of the potential sectors to apply Bayesian Network Technology. The research generally aimed at investigating the potential applicability of Bayesian Network technology in developing a model that can support the prediction of ART clients’ adherence tends in Ethiopia. The research was conducted in selected hospitals of SNNP Regional Health Bureau. The methodology used to conduct this research consists of four major steps: Data Source Identification, Data Collection, Data Preprocessing and Model Building/Testing. A total of 1561 records, having 15 attributes each, were used for building, training and testing a Bayesian Network model. The Bayesian Network learning process was done for complete data (the data for which the training data containing no missing values) which again applied constraint-based approach. This approach performs conditional independence tests on the data. Then it will search for a network that is consistent with the observed dependencies and independencies (applying d-separation concept). Conditional independence relationships among the attributes can serve as constraints to construct a Bayesian Network. The belief network modelling software employed for the purpose of training and testing the BN model was the Belief Network PowerSoft, which applies a constraint-based XII approach. Three-Phase-Dependency-Analysis (TPDA) in BN PowerConstructor was employed in developing the model. The BN PowerPredictor, on the other hand, was used to evaluate the prediction accuracy of the model. BN PreProcessor was also there to preprocess the data so as to make it ready for model building purpose. Model testing was implemented in two phases- the first phase without involvement of expert knowledge (i.e., without node ordering, in which, the algorithm learns both structure and parameters), and the second phase by eliciting domain expert knowledge (i.e., involving node ordering, in which, the algorithm learns only the parameters). For both cases, to ensure consistency across the data during the selection of the test and training sets, experiments were carried out by splitting the data into 10 partitions, i.e., a percentage split (10-fold) was used to partition the dataset into training and test data. Each partition, in turn, was used for testing while the remainder was used for training. This process was repeated ten times for the learning algorithm and, at the end, every instance was used exactly once for testing. Finally, the average result of the 10-fold cross validation was considered. Accordingly, the average predictive accuracy for the model without an expert intervention (Experiment I) was 72.80% at 95% confidence level. According to this model, the adherence (to the medication) of an ART client is directly affected by two factors: Addiction (drug or alcoholic behaviour) and loss of job due to ill-health. Next, TPDA algorithm (Experiment-II) was implemented by allowing elicitation of expert knowledge. Accordingly, the predictive accuracy of the modified model was 75.9% which is a better result. XIII Significant enhancements in prediction and reduction in error rates in the modified model was taken as the indication of the significance of a domain experts’ intervention during model building. According to the later model (Experiment II), adherence of an ART client is directly affected by six factors: Addiction (drug or alcoholic behaviour), loss of job due to illhealth, Residence of a patient, Knowledge the client has concerning HIV, Employment status of the client, and Family dependence (independence). From the model developed, it was observed that Bayesian Network is a powerful predictor even in the absence of a domain expert. With a proper intervention of domain experts, it was noticed to perform even better.Item Avian Diversity and Abundance in Addis Ababa Abattoirs, Addis Ababa Ethiopia(Addis Ababa University, 2019-09-09) Bekele, Rahel; Afework, Bezawork (PhD)Study on Avian diversity and abundance in Addis Ababa Abattoir was carried out from February 2019 to July 2019. The Addis Ababa abattoir is a home to different kinds of birds due to the presence of scraps of animals in abattoirs. Point count method, was employed to record the diversity and relative abundance of individual bird species. The site supports eight species of birds that are grouped under three orders and four families. Know a day six of them are common in the area. Themost commonly observed avian species were hooded vulture, (Necrosyrte monachus), Marabou stork, (Liptoptilos crumeniferus) Wattled Ibis, .(Bostrychia carunculata) pied crow, (Corvus capensis) African white backed vulture (Corvus albus),and sacred Ibis ( Threskiornis aethiopicus) The abundant species were hooded vulture and African white backed vulture. Dry season had the highest species diversity and evenness (H=4.64), (E=0.59) and Species abundance (4557).The lowest species diversity, and abundance were recorded in wet season (H=2.4, E=0.18, and species abundance =1073, respectively). Feeding activity was from 10:30 – 11:30h at the mornning. The urbanization and cleared scrapes of animals or less amount of food availability affected bird community in depriving roosting trees. Most of the vultures were observed coming from south west direction of the study area.Item Information Technology Application in Institutions of Higher Learning in Ethiopia with Special Reference to Computer Applications.(Addis Ababa University, 1992-06) Bekele, Rahel; Neelameghan, A. (Prof.)Every society and individual need information in the performance of its day to day tasks. Timely, reliable and pertinent information is required to be presented in a form and format convenient to the potential user(s). Information is needed for gaJ,-nful d$C~_don making, effec);ive aDd ef~-icient planning and management and increasing productivity in all sectors and all walks of life; it is needed to support education at all levels, to enhance the quality of life and to create an informed citizenry to sustain democracy. In this regard computers are becoming increasingly more efficient and effeqtive tools for the processing, storing, and retr~eving ,if: ~ , ~.'" 1" and delivery of information in various fields of human computer technology is the principal core, provide a unique opportunity for developing countries to accelerate their socio economic development. However, there are constraints and difficulties that hinder the acquisition, maintenance and effective application of the technology. The present stUdy surveyed through questionnaires, interviews, and site visits the current level of application of computers in Institutions of Higher Learning in Ethi opia . The situation is not satisfactory as a whole.':'!i& ast:-i7t.list';\l~i1t o f "'. highet' body at the nationa l .- -- ~.:- ~ ~ -~ -- .... .- . ~""' .... ~ lev~l. t (l promote cooperation in computer technology in institutions of higher learning in Ethiopia should be cons idered. The body's functions will be to promote and guide the development of computer related resources and their application in order to anticipate and meet t;Jle fut\lre needs of Higher Learning Institutions. Additionally, the body can help in mediating and catalyzing exchange of ideas and informati on among institutions within and outside the country.Item Role of Internal Control Systems on Performance of Ethiopian Shipping and Logistics Services Enterprise .(Addis Ababa University, 2017-01) Bekele, Rahel; Birhanu, Habtamu (PhD)Effective internal control system can play a very crucial role in every organization to realize organizational goals, one of which is achieving financial performance objectives. The main purpose of this study was to determine the impact of internal control systems on financial performance on Ethiopian shipping and Logistics Services Enterprises as a case study. Specific objectives include evaluating the existing internal control system in the organization and investigating the relationship between the five internal control elements and financial performance. The study used explanatory research design research design by using both descriptive and quantitative methods where primary data is collected using Likert-scale questionnaires distributed and interviews made with employees in the finance department. Secondary data was gathered from company's financial statements and publications. The dependent variable was financial performance measured in-terms of profitability and ROA. The predictors or independent variables were the five elements of internal control system, control environment, control activities, risk assessment, monitoring and information and communication. The target population was 40 employees in the finance department and census design was adopted. The study period covers 9 years 2005-2013. Effectiveness of the elements of internal control system was analyzed from the descriptive statistics result. Multiple regression analysis was done to determine the relationship and the significance level of elements of internal control system towards financial performance. The result revealed that internal control system contributed only31% variation on financial performance. The descriptive result shows there is weak internal control system in the organization. The study recommend more commitment by the management in monitoring internal control system and continue working on improving for the effectiveness of the internal control system so, the company will achieve better performance