Browsing by Author "Yifiru, Martha(Dr)"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Developing Mobile Application for Public Health Emergency Management System for Ethiopia Public Health Institute
    (Addis Ababa University, 2015-07-04) Sebsibe Kibret, Esubalew; Yifiru, Martha(Dr)
    Introduction: Public Health Emergency Management (PHEM) is one of the core business processes in Ethiopia Public Health Institute. The main function is to collect timely information about the occurrence of disease outbreaks throughout the country. This information would help the responsible organizations to take timely action if the number of cases is above the expected threshold level. The major problems in PHEM is lack of adequate communication media among all the responsible stakeholders, problem of getting quality and complete information on time. Objectives: The objective of this project is to analyze, design, and develop a prototype mobile application for Public Health Emergency Management system for Ethiopia Public Health Institute. Methods: All the important data/requirement collection instruments were used for this study. On the basis of the identified instruments we conducted interview for the selected respondents. The sample respondents were selected using purposive sampling techniques. In addition national PHEM guidelines and other related documents were reviewed along with the interview and observation we conducted. This helped us to determine the requirements of the new system. Later on we mentioned the methodology software development life cycle, and water fall approaches were used to develop the prototype mobile application. Analysis and Design of the System: Then after analysis and design models were used like Use cases to describe the basic functions of the information system, and Use case description to show detail description of the activities and functions running in the early warning and surveillance sub-process and other health related services, data flow diagram to depicts the actual flow or movement of data in the system, activity diagram to show business process and work flow. The analysis and design model is finalized by identifying the relevant analysis classes, attributes and their respective operation for designing the new system, architectural design, entity relationship diagram and user interface diagram were applied to elicit the parts of the system. Conclusion: Problem of on time data collection, organization and reporting about disease outbreak data are the main challenges in the public health emergency management system. In the meantime the rapid growth of mobile phones has been contributing a lot in human’s daily activity and organizational business. Therefore, we understood that the application of mobile phones and its application in PHEM would play a vital role to bring a timely collection, organizing and summarizing of data for evidence based decision making processes therefore a prototype mobile application was developed to mitigate the above mentioned problems in PHEM.
  • No Thumbnail Available
    Item
    Towards Improving the Performance of Spontaneous Amharic Speech Recognition
    (Addis Ababa University, 2015-10-04) Gizaw Tohye, Tewodros; Yifiru, Martha(Dr)
    The ultimate goal of automatic speech recognition is towards developing a model that converts speech utterance into a sequence of words. With the objective of transforming Amharic speech into its equivalent sequence of words, this study explored the possibility of improving the performance of Amharic spontaneous speech recognition system using hidden Markov model (HMM). To this end, four experiments have been conducted in order to improve the performance of the recognizer. The first three experiments were conducted using the spontaneous speech corpus consisting of 2007 sentences uttered by 36 people from different sex and age groups. This training data consists of 9460 unique words and it is around 3 hours and 10 minutes speech. For testing, speech of 104 sentences uttered by 14 speakers, consisting of 820 unique words has been used. The experiments have been conducted using different parameter tuning, and using CV-syllables and cross-word tri-phone as recognition units. The fourth experiment has been done by increasing the corpus size. A speech corpus consisting of 3556 sentences uttered by 60 speakers from different sex and age group has been used for training. This training data consists of 12306 unique words and it is around 4 hours and 30 minutes of speech performance improvement has been achieved when cross-word tri-phone acoustic and tri-gram language models has been used in recognition. In this system, 58.67% words are correctly recognized, and 49.13% accuracy for the mixed test set, and 46.08% words are correctly recognized, and 32.42% accuracy for the speaker independent test set. From the experimental result we found that using the tuning techniques, changing the sub-word unit using cross-word tri-phone, and tri-gram language model increases the performance of the recognizer. Even if the study come up with performance improvement there is a need to control the existing large variations in the realized speech waveform due to speaking variability, mood, and environment, in spontaneous speech rather than read speech. Besides these, the available spontaneous speech data set is small in size; so it is better to prepare large size spontaneous speech corpus by automatic transcription.