Browsing by Author "Mulugeta, Selam"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Automatic Classification of Ethiopian Traditional Music Using Audio-Visual Features and Deep Learning
    (Addis Ababa University, 2020-06-06) Mulugeta, Selam; Getahun, Fekade (PhD)
    Music bridges the gap between linguistic and cultural gap and helps connect people. Ethiopia is a country with more than 80 tribes each having their own unique musical sound and style of dance. Distinguishing one from another is not an easy task especially in the era of streaming where lots of music are recorder and released each day through the Internet. Machine learning and recently deep learning is a subfield of machine learning that came to tackle the problem of automating tedious classification tasks previously done by programmers manually crafting the classification rules. Deep learning algorithms automatically learn the classification rules by just looking at the data. In this work, we address the automatic classification of Ethiopian traditional music to their respective locality using audio-visual features. To achieve that we use a deep neural network architecture composed of both convolutional neural network (CNN) and recurrent neural network (RNN). This architecture has an audio feature extracting component, that is composed of a parallel deep CNN and RNN which takes mel-spectrogram of an audio signal as an input and a video feature extracting component. The video feature extracting component uses transfer learning to extract visual information from a pre-trained network (VGG-16) then passes these features to a Long Short-Term Memory (LSTM) recurrent network so that sequential information will be extracted. Features from both modules will then be merged and the class of the music video will be predicted. We did an experiment to know the performance of the proposed system. We collected music data that represent Ethiopian traditional music from Internet-based music archive such as YouTube and personal music collections. After passing the collected data through a pre-processing step, we trained the proposed system, which uses both audio-visual feature and a system that only uses visual feature or audio feature. The performance of the video data only classifier was 78% while the audio data only classifier was 85% and by adding audio feature to the video data only classifier we were able to increase the accuracy of the proposed system by 7 units making its performance 85%.
  • No Thumbnail Available
    Item
    Ethiopian and Egyptian Media Coverage of the Grand Ethiopian Renaissance Dam Tripartite Negotiation: The Case of Reporter Newspaper and Ahram Online
    (AAU, 2021-07) Mulugeta, Selam; Abote, Arka(PhD)
    This study set out to examine how The Reporter Newspaper and Ahram Online framed the Grand Ethiopian Renaissance Dam tripartite negotiation, between January 08, 2020 and August 25, 2020- in purposive sampling selected. Guided by the time frame, all news articles that entertain the GERD Tripartite negotiation downloaded from the two media websites. Theories of agenda setting and framing have been employed as theoretical frameworks for this study. The study employed both quantitative and qualitative methods to gather and analyze the data. Purposive sampling was used to select the media and the news items for this research. The study revealed that Right frame, development frame, technical frame, internationalization frame and distrust frame were used by the two media outlets. In order to structure the stories related to the tripartite negotiation it was found out that internationalization frame was the most predominant frame used by Ahram online and used secondly by the Reporter newspaper. Ahram online has used internationalization Frame in its reports for three purposes. The Reporter predominantly used the water rights frame. It remarks that Ethiopia has a natural and sovereign right of using its natural water resources. On the contrary, the right frame helped Alahram to demonstrate the negative consequence of GERD on the " historical " water right of Egypt. It is important to create a platform that can help Ethiopia, Egypt and Sudan media professional work together in order to capitalize the positive contribution of media in resolving tension and to build trust among the three countries people.
  • No Thumbnail Available
    Item
    Non-adherence to Antidepressant Treatment and its Predictors among Outpatients with Depressive Disorders, a Hospital-based Ccross-sectional Study in Addis Ababa, Ethiopia
    (Addis Abeba University, 2020-10) Mulugeta, Selam; Prof.Araya, Mesfin(MD, Ph.D, Professor of Psychiatry, Department of Psychiatry, AAU); Dr.Milkias, Barkot (MD, Assistant Professor of Psychiatry, Department of Psychiatry, AAU)
    BACKGROUND: In Ethiopia, there is inadequate information on non-adherence to antidepressant treatment in patients with depressive disorders. Having awareness of the pattern of adherence is important in future prognosis, quality of life and functionality in these patients. This study will be conducted to assess the prevalence of Non-Adherence to Antidepressant treatment and its predictors among Psychiatry Outpatients with Depressive Disorders. METHODS: A hospital-based cross-sectional quantitative study was conducted at the psychiatry clinic of Tikur Anbessa Specialized Hospital. A sample of 216 consecutive outpatients with Depressive disorders who visited the Psychiatry clinic since June 2019 and who had at least two visits prior to their last visit were enrolled. Data was collected using questionnaires through inperson and phone call interviews. The eight-item Morisky scale, a scale extensively used in the Ethiopian setting, was used to assess the pattern of medication adherence. Other specially developed tools were used to obtain sociodemographic and clinical information from electronic medical records and patient interviews. Data was analyzed using the Statistical Package for the Social Sciences (SPSS), Version - 25. Univariate and multivariable analyses were carried out to assess factors associated with non-adherence. RESULTS: Ninety percent of the participants who were taking antidepressant medication were found to have a primary diagnosis of Major Depressive Disorder. Based on the 8-item Morisky Medication Adherence Scale, the prevalence of non-adherence was found to be 84.7%. Living distance between 11 to 50 kms from hospital (AOR= 11, 95% CI (29,46.6)), post-secondary level of education (AOR= 8.3, 95% CI (1, 64.4)), taking multiple medications (AOR= 6.1, 95% CI (1, 34.9)) were found to have significantly increased odds of non-adherence. CONCLUSION: The prevalence of non-adherence is very high among patients with depressive disorders. Non-adherence was significantly associated with factors such as increased living distance from the hospital, relatively higher educational level, and polypharmacy. Proper and patent centered psychoeducation to patients, addressing the communication gap between patients and doctors, clinicians’ adherence to prescribing guidelines, avoiding polypharmacy unless indicated, and working on accessibility of treatment for common mental disorders is essential to decrease non-adherence. Larger analytical studies to further establish causal relationships to nonadherence and its impact on depression treatment outcomes are recommended.