Browsing by Author "Birhanu, Solomon"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Assessment of factors determine farmers adoption behavior of soil and water conservation practices in Libo Kemkem Woreda
    (Addis Ababa University, 2016-06) Birhanu, Solomon; Legass, Asmamaw (PhD)
    Soil is an important resource which provides the required needs for human beings. But its degradation is one of the major environmental problem challenging agricultural production and productivity in many parts of Ethiopia. Even though a number of soil and water conservation methods were introduced and practiced, the study area has been experiencing declining soil fertility. This is due to continuous cropping of farm land, high population pressure, cultivation of highly inclined and marginal lands and absence of continued use of soil and water conservation measures. The main objective of the study was to assess factors that determine the adoption of soil and water conservation practices in Libo Kemkem woreda. The data used for this study was collected via interview, focus group discussion and questionnaire from Household heads, DAs, and Agriculture and Rural Development office. 136 household head sample respondents; 111(81.6%) male and 25(18.4%) female were selected from four kebeles which have different agro-climatic zone. Among them 94(69.1%) were adopters and 42(30.9%) were non-adopters of the introduced SWC practices. The collected data was analyzed by binary logistic regression model, t-test and chi-square tests. The results of logistic regression model showed that sex of HH heads, age of HH head, slope of the farm land, plan of HH heads to continue in farming activities, training and extension services were among the major factors that positively and significantly influenced adoption of soil and water conservation measures in the study area. Whereas, farm size, engaging in off-farm activities and access to credit service were found to be negatively influencing farmers’ adoption decision of SWC measures. The odd ratio result indicated that a one year increase in age of the HH heads increase adoption of SWC structures by the factor of 6.244 and male headed HHs adopt SWC structures more than female headed HHs by the factor of 3.254 times. Access to training and extension services made the study area HH heads to adopt SWC structures 1.902 and 6.292 greater times than those HH heads who had not got extension services and training. Having of plan to continue in farming activities and slope of farm land enabled the HH heads of the study area to adopt SWC structures more than those HH heads who had not plan to continue in farming and then those who had not steep slope farm plot by the factor of 1.882 and 8.978 respectively. Whereas an increasing in farm size, engaging in off-farm activities and Access to credit decrease adoption of SWC structures by the factors of (-1.187), (- 1.131) and (-3.416) respectively. From the result of the study it was possible to conclude that sex, age, slope, plan, distance, training, off-farm activities and extension services were the major factors that influenced farmers’ adoption of soil and water conservation practices. Thus to effectively address issues of adoption of soil and water conservation practices, it is possible to recommended that, the study area Agriculture and Rural Development office, non-governmental organizations and other concerned bodies should take in to consideration the factors that discourage farmers adoption of SWC measures. Key words: Adoption, Soil erosion, Soil and water conservation, Libo Kemkem District
  • No Thumbnail Available
    Item
    Hidden Markov Model Based Large Vocabulary, Speaker Independent, Continuous Amharic Speech Recognition
    (Addis Ababa University, 2003-06) Seifu, Zegaye; Biru, Tesfaye; Birhanu, Solomon; Taddesse, Knfe
    This study investigated the possibility of developing large vocabulary, speaker independent and continuous speech recognizer for Amharic language. The recognizer was developed using Hidden Markov Model; and the Hidden Markov Modeling Toolkit was used to implement it. In the process, a corpus developed by Solomon Tefera was used to get the required data for training and testing the models. It was a database comprised of 8000 utterances that were used for training and 500 plus sentences for development and evaluation. The data was preprocessed in line with the requirements of the HTK toolkit. In order to support the acoustic models, a bigram language model was constructed. In addition, pronunciation dictionary was prepared and used as an input. Since the recognizer was meant to recognize large vocabulary and continuous speech, phonemes were opted as the basic unit of recognition. However phonemes are known to be context independent units, given that the environment in which a sound is put makes a difference in the way it is pronounced. Thus after the monophone based speech recognizer was built, it was promoted to triphone based system in which the left and right contexts were considered and modeled. Besides, the mixture components of the states of the models were incremented in view of optimizing the performance of the recognizers.