http://etd.aau.edu.et:80/dspace/handle/123456789/7 Search the Channel search http://etd.aau.edu.et:80/dspace/simple-search http://etd.aau.edu.et:80/dspace/handle/123456789/4748 Title: DEVELOPING A PREDICTIVE MODEL FOR FERTILITY PREFERENCE OF WOMEN OF REPRODUCTIVE AGE USING DATA MINING TECHNIQUES <br/> <br/>Authors: TARIKU, DEBELA <br/> <br/>Abstract: Background: Fertility is one of the major factors that determine the overall size, distribution and/or structure of a population. High fertility in developing countries(particularly, in the poorest of those countries) poses detrimental consequences like a high fraction of women experiencing pregnancies of order five and above and a greater likelihood of short interpregnancy intervals. These are threat to the health of mothers and their children. At a macrolevel, high fertility also contributes to high population growth which in turn results in slow economic growth, environmental degradation and unemployment, among others. Assessing fertility preference helps identify the proportion of women who demand for children and those who intend to limit childbearing. This aids in developing and implementing appropriate intervention programs for the purpose of achieving reductions in fertility levels necessary to slow population growth. Objective: To explore the possibility of applying data mining techniques in developing a model that can predict fertility preferences of women of reproductive age from EDHS2011 women’s survey dataset collect by CSA. Methodology: For this study, a six-step hybrid knowledge discovery process model was adopted. Through the steps, a dataset containing 15 attributes and 16515 records of women was constructed for building models. Results: Three data mining classification algorithms, J48, Naïve Byes and neural Network (Multilayer Perceptron), were tested using 10-fold-cross-validation. The classifiers were implemented on the dataset with all and selected features. Several experiments were constructed and the accuracy achieved on selected feature subset was 75.92%, 77.34%, 78.03% for Naïve Bayes, Multilayer Perceptron and J48, respectively. Conclusion: In this study, feature selection generally improved prediction performance of the classifiers. J48 model with accuracy of 78.03% was found to be relatively better predictor of fertility preference of women. This research study did indicate that data mining can be applied to women’s dataset to identify determinants of fertility preference and classify women according to their childbearing preferences. Age, number of living children, education, child death experience, marital status, sex of child and region are found to be the most important factors that determine fertility preference of women. <br/> <br/>Description: A thesis submitted to the School of Graduate Studies of Addis Ababa University in Partial Fulfillment of the Requirements for the Degree of Master of Science in Health Informatics http://etd.aau.edu.et:80/dspace/handle/123456789/4708 Title: DESIGNINIG A STEMMING ALGORITHM FOR SILT’E LANGUAGE <br/> <br/>Authors: MUZEYN, KEDIR <br/> <br/>Abstract: Variant word forms that are likely to be encountered in indexing and retrieval are one of the causes of the problems that are involved in the use of freetext retrieval system. The variant word structure s used in indexing and searching are to be expected in determining the relevance of a document to a user query that specifies just a single form. Shrinking the variant words in to one form advances the performance of IR system and this can be achieved by conflation techniques, which is usually stemming that is established in this work. Stemmers are used in information retrieval to reduce as many related words and word forms as possible to a standard form, which can then be used in the retrieval process. This research explores the possibility of developing a stemmer to conflate variant words of Silt’e language. Silt’e belongs to the Semitic language group. These languages have a common grammatical system based on a root-pattern structure. Consonants bear the basic meaning while vowels form different patterns. Stems are built from consonantal roots before other word forms are built. Silt’e uses affixation and reduplication to derive different word forms from stems. Common affixations are prefix, suffix, and infix. Silt’e uses extensive concatenation of affixes and can result in relatively long words, which often contain an amount of semantic information equivalent to a whole English phrase, clause or sentence. As a result of this complex morphological structure, a single Silt’e word can have very large variants. To design the stemmer, a sample text was collected from different sources and research paper that explains the morphology of Silt’e language also used and affixes and stopwords collected from this research paper and the sample text document to develope the stemmer. The stemmer, developed in this study is iterative and uses context sensitive and recoding rules that remove prefix, suffix and reduplication of letters (type 1 and type 2). In this experiment the stripping procedure were applied in order: prefix, suffix and finally letter reduplication. The stemmer was tested on a sample data of 1486 words, which were selected randomly from the sample texts. The result of the experiment shows that, the stemmer performs at accuracy of 85.71%, and brings a dictionary reduction of 34.99% for stem words. Lastly conclution and the possible recommendation for future work were reported. <br/> <br/>Description: A thesis submitted to School of Graduate Studies of Addis Ababa University in partial fulfillment of the Requirement for the Degree of Master of Science in Information Science http://etd.aau.edu.et:80/dspace/handle/123456789/4707 Title: INFORMATION NEEDS AND SEEKING BEHAVIOR AMONG HEALTH PROFESSIONALS WORKING AT GOVERNMENTAL HOSPITAL AND HEALTH CENTERS IN BAHIR DAR TOWN, AMHARA REGION, ETHIOPIA. <br/> <br/>Authors: MULUSEW, ANDUALEM <br/> <br/>Abstract: Background: Universal access to information for health professionals is a pre requisite for meeting the MDGs and achieving health for all strategy. In developing countries, a large proportion of the population, including health professionals have no or only poor access to health information resources due to poor infrastructures, economic related, poor attention, etc Objective: The purpose of this study is to assess information needs and seeking behavior of health professionals working at Governmental Hospitals and Health Centers in Bahir Dar town, Amhara Region, Ethiopia. Methods: A cross sectional study design using quantitative and qualitative approaches was carried out to achieve the research objectives using 350 study participants. Self-administered questionnaire and observation checklist were instruments to collect the required data. Manually edited data were entered in to computer using Epi-info version 3.5.1; further cleaned and exported to SPSS statistics version19; then cleaned again and analyzed as needed. Frequencies, cross tabulation, chi-square, Odds ratio with 95%CI, and Binary logistic regression analysis were done to describe and assess associations among variables of interest. Results: Nearly all (97.3%) of respondents reported that they need health information to update themselves and support daily activities. More than half (54%) encountered problems on their daily activities due to information limitation. Major barriers to access information were geographical, organizational, personal, economic related, educational status and time. Only 145 (42.8%) respondents have access to internet at different places with various frequencies and have shown statistically significant association (p <0.05) with age, sex, monthly income, computer literacy and access, patient seen per day, working experience, and working site. Majority of study participants have too much limited access to different information resources, especially library and internet. More than half (57.7%) respondents seek information by consulting their hard copies when there is a need. About 151(44.5%) respondents prefer to access on job trainings and soft copies next to hardcopies. Conclusions and recommendations: Almost all respondents need to access health information and more than 80% of study areas have no library, internet and computer services. Therefore, great attentions and efforts must be done to help those starved health professionals working at those areas. <br/> <br/>Description: A THESIS SUBMITTED TO SCHOOL OF GRADUATE STUDIES OF ADDIS ABABA UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTERS OF SCIENCE IN HEALTH INFORMATICS. http://etd.aau.edu.et:80/dspace/handle/123456789/4705 Title: A WEB-BASED NATIONAL DATA CENTER FRAMEWORK TO INTEGRATE HEALTH RELATED PUBLICATIONS IN ETHIOPIA <br/> <br/>Authors: -Birhan, Atnafu <br/> <br/>Abstract: Background—Managing and integration health information has been possible and improved through different technologies such as web-based systems and computer applications. The objective of this study is to search for a solution to integrate health related publications from various nationwide hospitals and health associations and institutes using a central web-based national data center for publications to mobilize the new fragmented, but interrelated health publications. Methods— There are many hospitals, health associations and institutes throughout Ethiopia; but the activities in these institutes within health care delivery and management are almost similar. Therefore, variables and definitions for activities are almost identical for the proposed Web-based National Data Center application. For this reason, only limited numbers of health institutes are taken from Addis Ababa for data gathering using purposive and stratified sampling methods. Data were collected and analyzed to obtain representative input requirements to design the new system. Based on the results of the analysis, common services, practices, information technology usage, locally available and international health websites and publications were identified; methods for data security are assessed, interpreted and devised.. Results — This is the first web-based national data center proposed to integrate health related publications from local and foreign sources in Ethiopian context. The health sector is vast and broad that encompasses different resources. In this thesis, based on the results of the requirements analysis, the web-based national data center for health related publications system is proposed as a solution for integration of health related publications. Only one of the segments of the health resources, publication, is addressed using webbased application. Even though there are many services which can be done in the same area yet, the researcher believes that this application may serve as a pilot to design and implement a full-fledged system. Therefore, this application is open, flexible and amendable for any change which is found to be essential. <br/> <br/>Description: A thesis Submitted to the School of Graduate Studies Addis Ababa University in Partial Fulfillment of the Requirement for the Degree of Master of Science in Health Informatics