Browsing by Author "Belay, Ayalew (PhD)"
Now showing 1 - 20 of 24
Results Per Page
Sort Options
Item Bug Triage Model Using Machine Learning Techniques(Addis Ababa University, 2021-08-27) Andualem, Meseret; Belay, Ayalew (PhD)A customer, analyst, or developer makes an error while using the system or generating software artifacts, which is a common chain of reaction to software bugs. This error may cause a system fault, resulting in an unexpected state. This unanticipated situation could lead to a bug, which is a visible and unwelcome event from the user's perspective. When a bug is detected, the user creates a bug report that includes the error messages issued by the software. These bugs must be dealt with in a proper manner. Bug triage is one of them. Triaging is the process of categorizing and prioritizing bug reports in order to assign priority and route them to the appropriate developer for resolution. Many researchers have developed a number of bug triage models in recent years. However, because bugs in bug repositories aren't necessarily bugs, new strategies to identify the actuality of the bug are still needed. As a result, we present a bug triage model that uses machine learning techniques to identify actual bugs from non-bugs by assessing the severity field and then assigning to the right developer based on the developer's tossing history. Preprocessor, feature extractor, dataset constructor, bug detector, and bug assigner are the components of the suggested model. Data tokenizing, stop word removal, and stemming are the main operations in the preprocessing component. The feature extraction component then extracts the feature vectors from the supplied bug report, while the dataset constructor splits the dataset into training (80%) and testing (20%) sets by converting the javascript object notation (JSON) file into sets. Finally, based on the recognized component retrieved from the bug report's short description, the MNB classifier is used to classify the bug report into BUG and NON BUG and automatically propose developers who have the necessary competence for processing a bug report. The feasibility of our proposed model has been validated on Eclipse covering 315228 bug reports. We show that our techniques can detect bugs and assign them to them with a prediction accuracy of up to 95.67 percent.Item Bug Triage Model Using Machine Learning Techniques(Addis Ababa University, 8/27/2021) Andualem, Meseret; Belay, Ayalew (PhD)A customer, analyst, or developer makes an error while using the system or generating software artifacts, which is a common chain of reaction to software bugs. This error may cause a system fault, resulting in an unexpected state. This unanticipated situation could lead to a bug, which is a visible and unwelcome event from the user's perspective. When a bug is detected, the user creates a bug report that includes the error messages issued by the software. These bugs must be dealt with in a proper manner. Bug triage is one of them. Triaging is the process of categorizing and prioritizing bug reports in order to assign priority and route them to the appropriate developer for resolution. Many researchers have developed a number of bug triage models in recent years. However, because bugs in bug repositories aren't necessarily bugs, new strategies to identify the actuality of the bug are still needed. As a result, we present a bug triage model that uses machine learning techniques to identify actual bugs from non-bugs by assessing the severity field and then assigning to the right developer based on the developer's tossing history. Preprocessor, feature extractor, dataset constructor, bug detector, and bug assigner are the components of the suggested model. Data tokenizing, stop word removal, and stemming are the main operations in the preprocessing component. The feature extraction component then extracts the feature vectors from the supplied bug report, while the dataset constructor splits the dataset into training (80%) and testing (20%) sets by converting the javascript object notation (JSON) file into sets. Finally, based on the recognized component retrieved from the bug report's short description, the MNB classifier is used to classify the bug report into BUG and NON BUG and automatically propose developers who have the necessary competence for processing a bug report. The feasibility of our proposed model has been validated on Eclipse covering 315228 bug reports. We show that our techniques can detect bugs and assign them to them with a prediction accuracy of up to 95.67 percent.Item Chatbot Based Customer Service Model Using Deep Learning the Case of Ethiopian Airlines(Addis Ababa University, 7/6/2021) Mekuanent, Natnael; Belay, Ayalew (PhD)Chatbot systems implemented for different purposes and plays significant role in terms of accessibility, reliability, and offers cost efficient auto services. The usage of chatbots grown rapidly in various fields in recent years, including Marketing, Supporting Systems, Education, Health Care, Cultural Heritage, and Entertainment. Therefore, we are motivated to design, develop, and implement automated Deep Learning based chatbots for Ethiopian airlines customer services. The reason to select Ethiopian airlines is even though it has a best customer service currently, the chatbot service will enhance improving its services more. This study aimed on designing and implementing a chatbot based model using deep learning methods which can facilitate customer service for enhancing Ethiopian airlines services. For this study, 30,000 question and answer pair statements has been collected from Ethiopian Airlines FAQ and from Kaggle websites. The collected documents have been passed through the appropriate data preparation. The dataset has split into 80% for training and 20% for testing sets. The researcher applied two different neural network techniques. The two neural network techniques experimented in this research are Long Short-Term Memory (LSTM) techniques and Convolutional Neural Network (CNN). To evaluate the performance of each technique, the researcher used various performance evaluation metrics such as Precession, Recall, F-score, Accuracy. The feature extraction techniques used for neural network techniques are word embedding, bag of words and word2vec methods. The evaluated Neural network techniques accomplished accuracy for LSTM 83.25% and CNN 85.20%. According to the performance result from the techniques applied, the CNN technique achieved better accuracy compared to LSTM and we applied CNN to deploy our model.Item Chatbot Based Customer Service Model Using Deep Learning the Case of Ethiopian Airlines(Addis Ababa University, 2021-07-06) Mekuanent, Natnael; Belay, Ayalew (PhD)Chatbot systems implemented for different purposes and plays significant role in terms of accessibility, reliability, and offers cost efficient auto services. The usage of chatbots grown rapidly in various fields in recent years, including Marketing, Supporting Systems, Education, Health Care, Cultural Heritage, and Entertainment. Therefore, we are motivated to design, develop, and implement automated Deep Learning based chatbots for Ethiopian airlines customer services. The reason to select Ethiopian airlines is even though it has a best customer service currently, the chatbot service will enhance improving its services more. This study aimed on designing and implementing a chatbot based model using deep learning methods which can facilitate customer service for enhancing Ethiopian airlines services. For this study, 30,000 question and answer pair statements has been collected from Ethiopian Airlines FAQ and from Kaggle websites. The collected documents have been passed through the appropriate data preparation. The dataset has split into 80% for training and 20% for testing sets. The researcher applied two different neural network techniques. The two neural network techniques experimented in this research are Long Short-Term Memory (LSTM) techniques and Convolutional Neural Network (CNN). To evaluate the performance of each technique, the researcher used various performance evaluation metrics such as Precession, Recall, F-score, Accuracy. The feature extraction techniques used for neural network techniques are word embedding, bag of words and word2vec methods. The evaluated Neural network techniques accomplished accuracy for LSTM 83.25% and CNN 85.20%. According to the performance result from the techniques applied, the CNN technique achieved better accuracy compared to LSTM and we applied CNN to deploy our model.Item Deep Learning Based Emotion Detection Model for Amharic Text(Addis Ababa University, 2021-08-26) Tesfu, Eyob; Belay, Ayalew (PhD)Emotions are so important that whenever we need to make a decision, we want to feel other‟s emotions. This is not only true for individuals but also for organizations. Due to the rapid growth of internet peoples expirees their emotions using different social media networks, reviews, blogs, online and so on. The need for finding relevant sources, extracts related sentences with emotion, summarizes them and organize them to useful form is becoming very high. Emotion detection can play an important role in satisfying these needs. The process of emotion detection involves categorizing emotional sentences into predefined categories such as sadness, anger, disgust, happiness, so on based on the emotional terms that appear within the comment. So that it‟s difficult to manually identifying emotion of a million of users and aggregating them towards a rapid and efficient decision is quite a challenging task due to the rapid growth of Amharic language usage in social media. In this research work, an emotion detection model is proposed for determining the emotion expressed in the Amharic texts or comment. In this study, we proposed deep learning based emotion detection model for Amharic text using CNN with word embedding. The proposed model includes different tasks. The first task is text pre-processing which consists of commonly used text pre-processing tasks in many natural language processing applications. We perform text pre-processing in Amharic text and train the document using a word embedding in order to generate word embedding model. The embedding result provides a contextually similar word for every word in the training set then we implement our CNN model for emotion classification. The common evaluation metrics such as accuracy, recall, F1 score and precision were used to measure our proposed model performance. Deep learning based emotion detection model for Amharic text prototype is developed and used to tests the system performance using the collected Amharic text comments. Finally, this study with four categories (sadness, anger, disgust, and happiness) of classification shows a result of 71.11% accuracy. Also did better when the number of classification is two (positive and negative) shows result of 87.46% accuracy. We also evaluate our model using RNN to compare with our CNN model.Item Deep Learning Based Emotion Detection Model for Amharic Text(Addis Ababa University, 8/26/2021) Tesfu, Eyob; Belay, Ayalew (PhD)Emotions are so important that whenever we need to make a decision, we want to feel other‟s emotions. This is not only true for individuals but also for organizations. Due to the rapid growth of internet peoples expirees their emotions using different social media networks, reviews, blogs, online and so on. The need for finding relevant sources, extracts related sentences with emotion, summarizes them and organize them to useful form is becoming very high. Emotion detection can play an important role in satisfying these needs. The process of emotion detection involves categorizing emotional sentences into predefined categories such as sadness, anger, disgust, happiness, so on based on the emotional terms that appear within the comment. So that it‟s difficult to manually identifying emotion of a million of users and aggregating them towards a rapid and efficient decision is quite a challenging task due to the rapid growth of Amharic language usage in social media. In this research work, an emotion detection model is proposed for determining the emotion expressed in the Amharic texts or comment. In this study, we proposed deep learning based emotion detection model for Amharic text using CNN with word embedding. The proposed model includes different tasks. The first task is text pre-processing which consists of commonly used text pre-processing tasks in many natural language processing applications. We perform text pre-processing in Amharic text and train the document using a word embedding in order to generate word embedding model. The embedding result provides a contextually similar word for every word in the training set then we implement our CNN model for emotion classification. The common evaluation metrics such as accuracy, recall, F1 score and precision were used to measure our proposed model performance. Deep learning based emotion detection model for Amharic text prototype is developed and used to tests the system performance using the collected Amharic text comments. Finally, this study with four categories (sadness, anger, disgust, and happiness) of classification shows a result of 71.11% accuracy. Also did better when the number of classification is two (positive and negative) shows result of 87.46% accuracy. We also evaluate our model using RNN to compare with our CNN model.Item Design and Implementation of Online Electronic Medical Record System in Ethiopia(Addis Ababa University, 2021-08-15) Eshetu, Behailu; Belay, Ayalew (PhD)An Electronic Medical Record system is an application that is a complete repository of patient‟s medical documents which contains patients' medical history, a summary of all their visits. This information can be shared across different health care organizations. Recently, electronic medical records are considered as a key to increasing quality care. It improves the accuracy medical records, reduces data replication, support fast data retrieval and decreases the risk of lost paper works. Due to the presence of multiple health care service providing organizations, patients move from one medical institution to the other in need of better service and from place to place due to work and other life circumstances. Because of that maintaining patients' lifetime medical record becomes much difficult. Especially, in a developing country like Ethiopia, patient medical record keeping is done manually. This makes medical records susceptible to damage and loss and difficulty of retrieval when needed. We employed the waterfall development approach to develop the Online Electronic Medical Record system. First, we studied the existing system through observation and revision of documents collected from different medical institutions. Based on the collected data we prepared a system analysis and design document. Then we developed the Online Electronic Medical Record following the system design document specifications. Finally, an evaluation of the Online Medical Record system is conducted using a questionnaire involving 5 user categories and 10 voluntary participants from each user group. The result of the evaluation shown that the Online Electronic Medical Record System is easy to use, effective, accurate and help the professionals save their time.Item Design and Implementation of Online Electronic Medical Record System in Ethiopia(Addis Ababa University, 8/15/2021) Eshetu, Behailu; Belay, Ayalew (PhD)An Electronic Medical Record system is an application that is a complete repository of patient‟s medical documents which contains patients' medical history, a summary of all their visits. This information can be shared across different health care organizations. Recently, electronic medical records are considered as a key to increasing quality care. It improves the accuracy medical records, reduces data replication, support fast data retrieval and decreases the risk of lost paper works. Due to the presence of multiple health care service providing organizations, patients move from one medical institution to the other in need of better service and from place to place due to work and other life circumstances. Because of that maintaining patients' lifetime medical record becomes much difficult. Especially, in a developing country like Ethiopia, patient medical record keeping is done manually. This makes medical records susceptible to damage and loss and difficulty of retrieval when needed. We employed the waterfall development approach to develop the Online Electronic Medical Record system. First, we studied the existing system through observation and revision of documents collected from different medical institutions. Based on the collected data we prepared a system analysis and design document. Then we developed the Online Electronic Medical Record following the system design document specifications. Finally, an evaluation of the Online Medical Record system is conducted using a questionnaire involving 5 user categories and 10 voluntary participants from each user group. The result of the evaluation shown that the Online Electronic Medical Record System is easy to use, effective, accurate and help the professionals save their time.Item Design of a Model for Mobile Money Interoperability: the Case of Mobile Money Service Providers Operating in Ethiopia(Addis Ababa University, 2017-12-05) Hunde, Mesfin; Belay, Ayalew (PhD)Mobile money services have been spread rapidly in many developing countries and the service is best suited for developing nations to bring large number of population to financial services. Many mobile money service providers have deployed and providing the service by partnering with financial institutions. However, the services were deployed as a scheme with different platform, operating rules, agents and customers and operating independently. As a result, a money transfer from a customer of one scheme to a customer of another scheme is not possible. Similarly, agents are exclusive to specific mobile money operator; they cannot serve customers of other scheme. In addition, customers who do not have a SIM card with a mobile handset at hand are not being benefited from the services. To well understand the service requirements, exhaustive literature review has been carried out and gained a better insight in the area of mobile money services. In addition, policy, procedure and operational manual of mobile money operators and guide lines of regulatory organ has been studied, challenges and the business rule of mobile money services, the way operators are doing their business has been observed. Having the objective of solving the problems in mind and understanding how the business is in operation in the market, an interoperability model that can best suit the market was proposed and detailed algorithms were designed, tested and implemented which made interoperability among mobile money platforms possible.Item Design of a Model for Mobile Money Interoperability: the Case of Mobile Money Service Providers Operating in Ethiopia(Addis Ababa University, 12/5/2017) Hunde, Mesfin; Belay, Ayalew (PhD)Mobile money services have been spread rapidly in many developing countries and the service is best suited for developing nations to bring large number of population to financial services. Many mobile money service providers have deployed and providing the service by partnering with financial institutions. However, the services were deployed as a scheme with different platform, operating rules, agents and customers and operating independently. As a result, a money transfer from a customer of one scheme to a customer of another scheme is not possible. Similarly, agents are exclusive to specific mobile money operator; they cannot serve customers of other scheme. In addition, customers who do not have a SIM card with a mobile handset at hand are not being benefited from the services. To well understand the service requirements, exhaustive literature review has been carried out and gained a better insight in the area of mobile money services. In addition, policy, procedure and operational manual of mobile money operators and guide lines of regulatory organ has been studied, challenges and the business rule of mobile money services, the way operators are doing their business has been observed. Having the objective of solving the problems in mind and understanding how the business is in operation in the market, an interoperability model that can best suit the market was proposed and detailed algorithms were designed, tested and implemented which made interoperability among mobile money platforms possible.Item Developing a Computer-Aided Diagnosis Model for Tb Using Region-Based Convolutional Neural Network(Addis Ababa University, 2020-11-04) Muse, Ibrahim; Belay, Ayalew (PhD)Tuberculosis (TB) is an infectious disease caused by the bacteria Mycobacterium tuberculosis or simply M. tuberculosis. It is primarily an infection of the lungs, but it can also affect other parts of the body. TB is one of the leading causes of death in developing countries, although most are preventable if diagnosed early and treated. Among the available tools, Sputum smear microscopy is widely used for TB diagnosis. Manual TB screening is tedious work and prone to error due to workload and a dearth of properly trained technicians, manual recognition of the bacillus from the microscopic image takes a long time and requires expert handling of the equipment for the TB identification. To overcome the manual detection issues and develop an automatic TB diagnosis model, we used deep neural networks. We proposed an automatic TB diagnosis and segmentation model composed of Mask R-CNN, Hungrain Algorithm, and Hard example mining for the microscopic image. The proposed model works in a sequential manner where it first detects, classifies, and segments the bacillus objects then the Hungarian Algorithm and Hard example mining is used to further enhance the performance and overcome the problem of high False Positive rate. We carried out experiments to evaluate the performance of our proposed model, we used the metrics of recall, precision, and F-score. We collected the sputum images ZNSM-iDB dataset which is publicly available dataset in the internet and used it for both training and testing. Our experimental results show values of 99.25%, 91.04%, 94.96% for recall, precision, and f-score respectively. which is a significant improvement by the proposed approach compared to existing methods, thus helping in more accurate disease diagnosis.Item Developing a Computer-Aided Diagnosis Model for Tb Using Region-Based Convolutional Neural Network(Addis Ababa University, 11/4/2020) Muse, Ibrahim; Belay, Ayalew (PhD)Tuberculosis (TB) is an infectious disease caused by the bacteria Mycobacterium tuberculosis or simply M. tuberculosis. It is primarily an infection of the lungs, but it can also affect other parts of the body. TB is one of the leading causes of death in developing countries, although most are preventable if diagnosed early and treated. Among the available tools, Sputum smear microscopy is widely used for TB diagnosis. Manual TB screening is tedious work and prone to error due to workload and a dearth of properly trained technicians, manual recognition of the bacillus from the microscopic image takes a long time and requires expert handling of the equipment for the TB identification. To overcome the manual detection issues and develop an automatic TB diagnosis model, we used deep neural networks. We proposed an automatic TB diagnosis and segmentation model composed of Mask R-CNN, Hungrain Algorithm, and Hard example mining for the microscopic image. The proposed model works in a sequential manner where it first detects, classifies, and segments the bacillus objects then the Hungarian Algorithm and Hard example mining is used to further enhance the performance and overcome the problem of high False Positive rate. We carried out experiments to evaluate the performance of our proposed model, we used the metrics of recall, precision, and F-score. We collected the sputum images ZNSM-iDB dataset which is publicly available dataset in the internet and used it for both training and testing. Our experimental results show values of 99.25%, 91.04%, 94.96% for recall, precision, and f-score respectively. which is a significant improvement by the proposed approach compared to existing methods, thus helping in more accurate disease diagnosis.Item Grid Based Node Deployment Approach Using Homogeneous Wireless Sensor Network(Addis Ababa University, 2020-10-10) Atnafu, Kebede; Belay, Ayalew (PhD)Wireless Sensor Network is one of the mechanisms to monitor different Wireless Sensor Network application such as environmental and habitat monitoring. In which cooperatively pass their data through the network to a main location or sink where the data can be observed and analysed. Sensor placement is an important task in WSN applications. The number of sensors and their location will affect the performance, accuracy, and cost of the deployment. One of the important issues in WSNs application is node deployment which decides where the sensor nodes should be placed in order to satisfy the desired requirements like maximize the efficient coverage area ratio and minimize the size of the network and cost. The effectiveness of these networks is determined to a large extent by the coverage provided by the sensor deployment scheme. Determining the required number of sensors to be deployed is a critical decision for wireless sensor networks In this thesis we develop a homogenius sensor node deployment scheme using grid based deployment scheme where all of the sensor nodes have similar processing and hardware capabilities by placing node in Hexagonal scheme, which cover with minimum number of sensor node and reduces the cost of sensor node. The number of sensor node used evaluated by comparing with previous system in which the proposed work used minimum number of sensor node for covering the region than from previous one. The proposed system consider the shape of the monitored land and we integrate PEGASSIS, hierarchical clustering routing protocol, where each sensor node transfer data to neighbourhood node. We used MATLAB for implementation of the proposed system and performance evaluation. From the evaluation result, the proposed homogenius node deployment approach has a minimum number of node, cost effective and better coverage than the existing shape based node deployment approach.Item Grid Based Node Deployment Approach Using Homogeneous Wireless Sensor Network(Addis Ababa University, 10/10/2020) Atnafu, Kebede; Belay, Ayalew (PhD)Wireless Sensor Network is one of the mechanisms to monitor different Wireless Sensor Network application such as environmental and habitat monitoring. In which cooperatively pass their data through the network to a main location or sink where the data can be observed and analysed. Sensor placement is an important task in WSN applications. The number of sensors and their location will affect the performance, accuracy, and cost of the deployment. One of the important issues in WSNs application is node deployment which decides where the sensor nodes should be placed in order to satisfy the desired requirements like maximize the efficient coverage area ratio and minimize the size of the network and cost. The effectiveness of these networks is determined to a large extent by the coverage provided by the sensor deployment scheme. Determining the required number of sensors to be deployed is a critical decision for wireless sensor networks In this thesis we develop a homogenius sensor node deployment scheme using grid based deployment scheme where all of the sensor nodes have similar processing and hardware capabilities by placing node in Hexagonal scheme, which cover with minimum number of sensor node and reduces the cost of sensor node. The number of sensor node used evaluated by comparing with previous system in which the proposed work used minimum number of sensor node for covering the region than from previous one. The proposed system consider the shape of the monitored land and we integrate PEGASSIS, hierarchical clustering routing protocol, where each sensor node transfer data to neighbourhood node. We used MATLAB for implementation of the proposed system and performance evaluation. From the evaluation result, the proposed homogenius node deployment approach has a minimum number of node, cost effective and better coverage than the existing shape based node deployment approach.Item Information Filtering of Social Media Amharic Texts Based on Sentiment Analysis(Addis Ababa University, 7/17/2020) Wonago, Hiwot; Belay, Ayalew (PhD)In the last five years, the ever growing usage of social media in Ethiopia has fueled the country‘s problem against the peaceful coexistence of its people. Illegitimate social media usage has played a significant role in widening the distress between the people. As a result, the government has increasingly relied on the temporary closure of social media sites; nationwide internet shutdowns and filtering websites to suppress polarizing voices and the misuse of social media as the tension among many ethnic groups become more visible. As such, there is a need to develop an intelligent system that automatically detects such inappropriate (offensive) contents by classifying them into socially-offensive, religiouslyoffensive, politically-offensive and non-offensive categories and filter Toxic online contents. We explain the challenges of the Amharic text that is available on the internet and the role of sentiment analysis in mining Amharic dataset on social media. Using different supervised machine learning techniques, this study analyzed performance variations of the algorithms on Amharic texts. The objective of this paper is to apply the concept of sentiment analysis on Amharic text on social media and presents a comparative study on machine learning algorithms. The created social media content filtering system has been tested on Facebook posts of each class, and it has been observed that SVM with word2vec has performed best in comparison to other classifiers, achieving average precision of (72%), but did worse on recall(63.4%). The experimental evaluation shows how the proposed approach is effective and the results are quite satisfactory.Item Information Filtering of Social Media Amharic Texts Based on Sentiment Analysis(Addis Ababa University, 2020-07-17) Wonago, Hiwot; Belay, Ayalew (PhD)In the last five years, the ever growing usage of social media in Ethiopia has fueled the country‘s problem against the peaceful coexistence of its people. Illegitimate social media usage has played a significant role in widening the distress between the people. As a result, the government has increasingly relied on the temporary closure of social media sites; nationwide internet shutdowns and filtering websites to suppress polarizing voices and the misuse of social media as the tension among many ethnic groups become more visible. As such, there is a need to develop an intelligent system that automatically detects such inappropriate (offensive) contents by classifying them into socially-offensive, religiouslyoffensive, politically-offensive and non-offensive categories and filter Toxic online contents. We explain the challenges of the Amharic text that is available on the internet and the role of sentiment analysis in mining Amharic dataset on social media. Using different supervised machine learning techniques, this study analyzed performance variations of the algorithms on Amharic texts. The objective of this paper is to apply the concept of sentiment analysis on Amharic text on social media and presents a comparative study on machine learning algorithms. The created social media content filtering system has been tested on Facebook posts of each class, and it has been observed that SVM with word2vec has performed best in comparison to other classifiers, achieving average precision of (72%), but did worse on recall(63.4%). The experimental evaluation shows how the proposed approach is effective and the results are quite satisfactory.Item Location Based Patient Assistant Mobile Application(Addis Ababa University, 2021-07-12) Dessalegn, Woinshet; Belay, Ayalew (PhD)Location Based Services (LBS) include applications that provide relevant location related information of peoples and materials. It is accessible with mobile devices through the mobile network and it is important to reduce our efforts during various tasks such as: assisting patients, finding particular address of some place, routing, getting and knowing different service offers on the different products. There are different works presented related to patient assistant system by different peoples. But the proposed works could not allow patients or users to get the nearest health facility information depends on their health facility service choice and their current location; could not provide a service to show optimal route between patient current location and health facility location and could not allow to provide important information about hospitals, health centers, pharmacies and blood banks in a single system. The aim of this Location Based Patient Assistant Mobile Application is to provide accurate and relevant information to patients or users based on their current location and choice of health facility service type without wasting their time, cost and life. This PAMA has mobile application side and desktop web application side. The mobile application side focuses on: accessing important information about the nearest health facility depends on the user or patient current location and their choice of health facility service type, showing the nearest health facility location and showing optimal route on a map. The web application part of the system helps authorized persons to manage health facilities’ service type, number of beds and other important health facilities related information. While developing the prototype of the application implemented different location based tools and development environments applied. During the development of the location based patient assistant application built in mobile GPS and Google map API uses to find the current location of the patient or user and MapBox Application Program Interfaces (API) used to show the route and the nearest health facility location freely without incurring additional cost on a Map. The application evaluated using functionality testing and usability testing. The testing result shows this application is important to assist patients or users to get current location related information of health facilities without wasting their time and cost.Item Location Based Patient Assistant Mobile Application(Addis Ababa University, 7/12/2021) Dessalegn, Woinshet; Belay, Ayalew (PhD)Location Based Services (LBS) include applications that provide relevant location related information of peoples and materials. It is accessible with mobile devices through the mobile network and it is important to reduce our efforts during various tasks such as: assisting patients, finding particular address of some place, routing, getting and knowing different service offers on the different products. There are different works presented related to patient assistant system by different peoples. But the proposed works could not allow patients or users to get the nearest health facility information depends on their health facility service choice and their current location; could not provide a service to show optimal route between patient current location and health facility location and could not allow to provide important information about hospitals, health centers, pharmacies and blood banks in a single system. The aim of this Location Based Patient Assistant Mobile Application is to provide accurate and relevant information to patients or users based on their current location and choice of health facility service type without wasting their time, cost and life. This PAMA has mobile application side and desktop web application side. The mobile application side focuses on: accessing important information about the nearest health facility depends on the user or patient current location and their choice of health facility service type, showing the nearest health facility location and showing optimal route on a map. The web application part of the system helps authorized persons to manage health facilities’ service type, number of beds and other important health facilities related information. While developing the prototype of the application implemented different location based tools and development environments applied. During the development of the location based patient assistant application built in mobile GPS and Google map API uses to find the current location of the patient or user and MapBox Application Program Interfaces (API) used to show the route and the nearest health facility location freely without incurring additional cost on a Map. The application evaluated using functionality testing and usability testing. The testing result shows this application is important to assist patients or users to get current location related information of health facilities without wasting their time and cost.Item Mosque Building Detection Using Deep Convolutional Neural Network(Addis Ababa University, 10/10/2020) Ergete, Samrawit; Belay, Ayalew (PhD)Object detection is a computer technology related to computer vision and image processing that detects and defines objects such as humans, buildings and cars from images and videos. Object detection is breaking into a wide range of industries, with use cases ranging from personal security to productivity in the workplace. Facial recognition or face detection is one of an object detection examples, which can be utilized as a security measure to let only certain people into a classified area of building. It can also be used within a visual search engine to help consumers find a specific item they’re on the hunt for. In this work we propose detection system start from collecting and preparing data to detecting mosque building by using deep convolutional neural network (DCNN). Mosque building detection is done using Faster RCNN model. Faster RCNN is trained on 1848 dataset collected from different websites and by directly taking pictures and splinted into 90% for training and 10% for testing. Experimental results have proved the efficiency of the proposed technique, where the accuracy of the proposed scheme has achieved mAP of 0.70.Item Mosque Building Detection Using Deep Convolutional Neural Network(Addis Ababa University, 2020-10-10) Ergete, Samrawit; Belay, Ayalew (PhD)Object detection is a computer technology related to computer vision and image processing that detects and defines objects such as humans, buildings and cars from images and videos. Object detection is breaking into a wide range of industries, with use cases ranging from personal security to productivity in the workplace. Facial recognition or face detection is one of an object detection examples, which can be utilized as a security measure to let only certain people into a classified area of building. It can also be used within a visual search engine to help consumers find a specific item they’re on the hunt for. In this work we propose detection system start from collecting and preparing data to detecting mosque building by using deep convolutional neural network (DCNN). Mosque building detection is done using Faster RCNN model. Faster RCNN is trained on 1848 dataset collected from different websites and by directly taking pictures and splinted into 90% for training and 10% for testing. Experimental results have proved the efficiency of the proposed technique, where the accuracy of the proposed scheme has achieved mAP of 0.70.