https://repository.ju.edu.et//handle/123456789/1216 2026-04-21T08:45:10Z 2026-04-21T08:45:10Z Tesema, Workineh Tesfaye, Debela https://repository.ju.edu.et//handle/123456789/9528 2025-04-17T11:27:50Z 2017-01-01T00:00:00Z

Word Sense Disambiguation and Semantics for Afan Oromo Words using Vector Space Model Tesema, Workineh; Tesfaye, Debela This paper presents Afan Oromo semantics which is identifying the words semantically related. Semantic is one of the critical application in natural languages, hence it is a fundamental problem for many natural language technology applications. The aim of this work is to develop sense disambiguation which finds the sense of words based on surrounding contexts. Hence, this study used unsupervised approach that exploits sense in a corpus which is not labelled. The idea behind the approach is to overcome the problem of scarcity of training data. The context of a given word is captured using term co-occurrences within a defined window size of words. The similar contexts of target words are computed using vector space model and then clustered. From total clustering, each cluster representing a unique sense. Most of the target words have more than three senses. The result argued that the system yields an accuracy of 85% which was encouraging result. Therefore, for Afan Oromo semantic has come to the conclusion that the sense of words is closely connected to the statistics of word usage. Further study using different approaches that extend this work are needed for a better performance.

2017-01-01T00:00:00Z Tesema, Workineh Silva, Bruno da Jimma, Worku https://repository.ju.edu.et//handle/123456789/9519 2025-04-16T06:32:36Z 2022-01-01T00:00:00Z

Indigenous Knowledge Practices on Weather Forecasting and Drought Disaster Management: The Case of Borana Zone, Oromia Region, Ethiopia Information science Tesema, Workineh; Silva, Bruno da; Jimma, Worku Many people in the world are living with chronic diseases, demanding continuous monitoring, diagnosis, and treat ment. Continuous physiological monitoring is key to providing preventive healthcare and accurate disease diagnosis, which leads to a growing demand for autonomous wearable technology. Wearable devices acquiring physiological information from the patient demand high-power efficiency to operate in a continuous acquisition mode. While power-saving techniques are applied in wearable devices for many application, very few are considered for biomedical applications. In this work, we explore existing techniques of power reduction for wearable medical devices. Our analysis addresses the power reduction of wearable medical devices and their generalization for different medical signal processing applications. In addition, we propose a taxonomy for power-saving techniques. The common categories of power saving techniques are task scheduling, clock management, signal compression, and energy awareness. The presented analysis iden tifies the most appropriate and combined low-power techniques in wearable devices to reduce power consumption.

2022-01-01T00:00:00Z Tushura, Fetene Jimma, Worku Tesema, Workineh https://repository.ju.edu.et//handle/123456789/9497 2025-04-14T07:04:48Z 2022-01-01T00:00:00Z

Indigenous Knowledge Practices on Weather Forecasting and Drought Disaster Management: The Case of Borana Zone, Oromia Region, Ethiopia Tushura, Fetene; Jimma, Worku; Tesema, Workineh Indigenous knowledge is knowledge that is unique to a given society. It is the foundation for local-level decision-making in various situations such as in weather forecasting, agriculture, health care, food preparation, education, natural resource management, etc. The main aim of this study was to explore the indigenous knowledge practices of Borana community in predicting weather and managing drought disasters. Tools such as interview questions, focus group discussion and observation checklist were used. In selecting the study site, the researchers used purposive sampling technique and hence selected two kebeles: Did-Yabello from Yabello woreda and Haro Bakke from Gomole woreda. The result revealed that Borana people make forecasts by using the readings of intestines of slaughtered animals, observation of celestial bodies and changes of part of plants and animal body languages which indicate the occurrence of drought. The finding also showed that biological, atmospheric and astronomic indigenous weather forecasting practices which indicate the coming of drought are very important knowledge for the Borana community as weather information is vital information in preparation and prevention of disaster which is caused due to drought. Based on the information, they use coping strategies to reduce its damage. Problems of unreliability, poor documentation, oral-based knowledge transfer system, the influence of religion and modern education, ageing and extinction of traditional experts were identified as the challenges of Borana traditional weather forecast. Documenting the indigenous knowledge of weather forecasting and integrating it with the meteorology data is recommended in order to reduce the disaster that a drought causes.

2022-01-01T00:00:00Z Feyisa, Seifu Gizaw Jimma, Worku Chaka, Eshetu https://repository.ju.edu.et//handle/123456789/9481 2025-04-09T11:21:20Z 2024-01-01T00:00:00Z

Resistance of Mycobacterium tuberculosis strains to Isoniazid: A systematic review and meta-analysis Feyisa, Seifu Gizaw; Jimma, Worku; Chaka, Eshetu Background: Genotyping and drug susceptibility test of Mycobacterium tuberculosis (MTB) is recommended to understand the prevalence of Isoniazid resistance to facilitate early treatment initiation and controlling the spread of the resistant strain in the community. Although several primary studies reported from different parts of the world, there are few review studies that attempt to summarize the available information to support tuberculosis (TB) control program. Thus, this review aimed to determine the prevalence of isoniazid resistance MTB family and identify the high-risk WHO regions. Methods: Medline/PubMed and EMBASE databases were searched until 22 November 2022 to access all original studies that published in English. The random effects model was used to estimate pooled prevalence of isoniazid (INH) resistance. Sub-groups analyses were done to investigate sources of heterogeneity by the type of MTB genotype and WHO regions. Random effects model was used to pool the prevalence of isoniazid resistance. Publication bias was assessed by Funnel plot, Egger’s test and Begg’s test statistic. Heterogeneity across studies was measured by I2 and data was analyzed by STATA version 14. Results: The pooled prevalence of INH resistance MTB strains was 18% (95%CI: 15–22) with high heterogeneity (I2 = 97.70%). The subgroup analysis by WHO regions showed that the prevalence of INH resistance MTB was: 18% (95%CI: 14–23%) in Western pacific region, 25% (95%CI: 13–38%) in South-East Asian region, 34% (95%CI; 17– 52%) in European region, 8% (95%CI: 5–11%) in African region, 19% (95%CI: 10–27%) in region of America and 10% (95%CI: 9–12%) in Eastern Mediterranean region. Sub-group analysis by MTB genotype showed that 22% (95%CI: 18–26%) Beijing INH resistance, 19% (95%CI: 16–22%) unclassified strains, 27% (95%CI:10–54%) Ural, 15% (95%CI: 1–20%) CAS, 19% (95%CI: 14–24%) LAM, 15% (95%CI:11–19%) EAI 38% (95%CI: 24–51%), MANU, 22% (95%CI: 16–27%) T, 24% (95%CI: 18–31%) Haarlem, 7% (95%CI: 5–10%) Euro-American, and 41% (95%CI: 34–49%) Orphan. Conclusion: The INH resistance was considerable in different regions of the world. The highest prevalence was observed in European, South-East Asia and America WHO regions. Beijing family is the most prevalent of INH resistance in these regions. Intervention is required to reduce INH resistance to achieve end TB strategy.

2024-01-01T00:00:00Z