Browsing by Author "Kebede, Gashaw (PhD)"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Application of Data Mining Technology to Identify Significant Patterns in Census or Survey Data : The Case of 2001 Child Labor Survey in Ethiopia(Addis Ababa University, 2003-07) Tefera, Helen; Kebede, Gashaw (PhD); Anagaw, Shegaw (PhD)Knowledge and understa nding of a problem is always the first step in identifying effective solutions . Child labor is both a sign and cause of poverty that should b eliminated as soon as possible. In Ethiopia, there is no much statistical data on chi ld labor practice. To fill this data gap, the FORE, CSA carried out country wide child labor survey in 200 I . This organization uses very simple statistical tools to show summary figures of different variables involved in 2001 child labor survey database. However traditional statistical method s are not good enough to discover complex relationships from large volume databases. The inefficiency of these tools necessitated the development of more powerful methods and techniques that can be used to study relationships and patters through the large volumes of data collected for example for census and survey purposes. In developed world, govemmrnt non-govemment organizations which have access to censuses and surveys are making use of the relatively new a nd modern technology, data mining, to identify important patterns and relationships within the data that is accumulated in large database. The application of data mining techniques to official data such as the 200 I child labor survey has great potential • in supporting good public policy. This research focused on identifying relationships between attributes within the 200 I child labor survey database that can be used to clearly understand the nature of child labor problem in Ethiopia . So the goal of the data mining process in this research was identifying interesting pattems and relationships in the 2001 child labor database. After the identification and understanding of the problem domain and the research objectives, the remaining stages of the research project focused on the following three major phases in data mining process. During the first phase, selection of the appropriate data mining tool which can be used to attain the defined data mining goal and the target dataset used in model building were the major tasks. The next phase, data cleaning and preparation, involved identifying and correcting mis-transmitted information, consolidating and combining records, transforming data from one form to another suitable for the selected data mining tool, handling missing attributes and selecting relevant attributes for generating meaningful association rules. As a final step for data preparation, the selected dataset was categorized into five classes using expectation maximization clustering algorithm implemented in knowledge studio version 3.0. A dataset of 2398 records with 63 attributes were used for clustering purpose. Apriori is an association rule algorithm which is implemented in Weka software. in the third phase, model building and evaluation, the apriori algorithm was used to generate association rules from the clustered as well as non-clustered selected dataset. Different attributes were given to apriori in an effort to generate meaningful rules. The results from this study were encouraging, which strengthened the hypothesis that interesting pattems can be generated from census and survey database by applying one of the data mining techniques: association rule mining. Key words: Data mining, knowledge discovery, association rule, apriori algorithmItem Application of KDD on Crime Data to Support the . Advocacy and Awareness Raising Program of Forum on Street Children Ethiopia(Addis Ababa University, 2003-07) Kifle, Woldekidan; Kebede, Gashaw (PhD); Anagaw, Shegaw (PhD)T his thesis work gives an account of the process followed to determine the application of KDD to support the and advocacy and awareness raising program of FSCE and Addis Ababa Police Commission, and the potential of a data min in g learning scheme to discover regularities that underlie the crime dataset. T he KDD process as described by Fayyad , Piatetsky-Shapiro and Gregory ( 1996) that consists of five major phases , namely understanding of the problem domain , data se lection , data processing, data mining , and discuss ion and interpretation was adopted . T he discovery task was run on the crime database that consist s of 10,87 8 records/tuples in 17 tables describing a total of 25 attributes. Association rule mining, an exploratory data mining technique was applied to accomplish the goal of the research . T o this effect , the Aprion algorithm , which is an implementation of the Association rule in the Weka soft ware, was used. The KDD process can be applied on the crime database to good effect since it can result ill rulest hat can serve as input for the advocacy and awareness raising program . on the basis of subjective (opinions of domain experts) and objective ( support and confidence) measures of interestingnessa number of rule having practical relevance o r that can add to the current knowledge in the problem domain we r identified .Item Design and Development of Hypermedia Learning Tool For Ethiopian Sign Language (Specially Designed for Amharic Speakers)(Addis Ababa University, 2005-06) Asefa, Endale; Kebede, Gashaw (PhD); Van Zijl, Lynette (PhD)Though the degree varies , deaf people in differentiates of the world are facing challenges to communicate wit h hearing people. The situation in Ethiopia is similar' except there has been no remedy tried to bridge the gap. As per the investigation of this research, deaf people face communication problems of various kinds in perusing their day to day activities with their herring acquaintances. It has been observed that the deaf people are denied so many advantages because of the communication gap they have with the hearing people. The problem was more serious in public service rues leek e hospitals , police stations , etc . In other countries, different options have been suggested and used to resolve communication gap between the deaf and herring people. Teaching sign language to herring people has been considered as one of those ways of bridging the communication gaps between the hearing and the deaf people. Beru'ing in mind that Ethiopian Sign Language (ESL) is used as an effective mode of communication for deaf people in Ethiopia, the main aim of this study was intended to bridge minimize the existing communication gap between deaf and herring people (taking health environment as a case) , by creating hypermedia software that can be used to teach ESL. The software is supposed to help health professionals to learn basic health related Ethiopian Sign Language, so that they can communicate to their deaf customers. In order to achieve the aim of the study, this reserpine first reviews the Various related literature. Then user research was done using questionnaire in order to have a good input to the design of appropriate tool. Based on the analysis of the user research, a prototype of the hypermedia tool was developed. The tool was designed using a UML based hypermedia designing methodology . The whole process of developing the tool , including the design, was based on the ISO-13407 standard for user centered design The prototype was developed based on continuous evaluation of the in tended users. More over final evaluation was done using a co-discovery method of usability testing and it has been observed that, the tool was developed to the appropriate skill and need of the intended usersItem Information System for Patient Medical Record of Butajira Rural Hospital(Addis Ababa University, 2004-07) Ketsela, Newayneh; Byass, Peter (PhD); Kebede, Gashaw (PhD)No clinical computing topic is being given more attention than that of computer based medical records. Efficient and effective healthcare depends upon accurate information and timely decision. Computer-based medical records are increasingly becoming a necessary and critical tool in healthcare to achieve those goals. This study aims at examining the current paper-based patient medical record system at Butajira Hospital and develops a patient medical database. The main objective of the study is to propose and develop an improved and effective information system for patient medical record of Butajira Hospital. On the process of analyzing the existing system, document analysis and semi-structured interview data collection methods have been implemented. Structured system analysis and prototype system designs had been selected as system development methodologies. Attempts were made to investigate problems with the existing system and analyze requirements for the proposed system. The study reveals that, the existing paper medical record system is subject to several drawbacks. Potential misplacement, destruction, and storage space consumption of patient charts, illegibility, inconsistency, incompleteness, disorganization and redundancy of information on the chart are major ones. To overcome these and other defects, and meet the analyzed requirements, a computer-based patient record system (CPR) has found to be the best solution. As appropriate software packages for African or developing countries hospitals cannot be found off the shelf, to alleviate this problem, it was decided to develop a database in-house. A RDBMS 'Microsoft Access ' has been used to build a database locally. The capturing format of clinical data is also a point of concern of the study. Both coded and free texts with narration are formats applied to capture patient medical data in the database. Summary, within the database development, intuitive and easy to use interfaces have been created. Valuable recommendations have also been stated for better implementation of the proposed system.