Information System
Permanent URI for this collection
Browse
Recent Submissions
Item Morphological Segmentation for Amharic Verb Class Using Recurrent Neural Network (RNN)(Addis Ababa University, 2019-09) Wondimagegnhue Tsegaye; Wondwossen Mulugeta (PhD)Due to the dependency of higher-level NLP task on morphological analysis, lack of an appropriate tool for morphological analysis is a major bottleneck for research work conducted on high level NLP application such as machine translation, speech processing, text summarization and many more. Currently most research works done on morphological analysis for morphologically rich languages (MRL) like Amharic are based on techniques that require high supervisions or rely on rule-based techniques that require detailed enumeration of the rule of the language to be crafted manually. Both of these techniques require a high-quality data in terms of capturing the rules that exist in the language and it also require a significant quantity of training data for better generalization. Both of these requirements are challenging to overcome due to the fact that significant number of MRL like Amharic are under-resourced. Lack of training data in quality and quantity is a major obstacle for research work in low resourced and morphological rich languages. The low resource state and morphological complexity of the language demand techniques that can provide better learning with relatively small number of example and be able to capture the complexity of language. In this paper, we propose RNN based sequence-to-sequence model that provides an encouraging performance in learning complex segmentation with small number of example and with no linguistic annotation, using the state-of-the-art encoder-decoder architecture. We have approached the problem of morphological segmentation as transformation task by considering the surface word as an input and the segmentation as a transformation process to produce a list of segmented morpheme. We prepared a training data by selecting different class of verbs. We have explored different encoder unit in terms directionality, window size, encoder type and size, and different data representation paradigm. The experiment showed that our model can learn a (;Omplex segmentation with no linguistic annotation and with limited number of examples. The model showed 74.2% accuracy on segmentation and 98.7% on morpheme boundary accuracy. We have shown that it is possible to learn morphological segmentation without relying on linguistic annotation. These contribute towards a general solution that can work on language other than Amharic. Our work can be extended to include other common POS classes such as nouns and adjective. Extending the work to include analysis would make the work more relevant for higher level NLP applications such as machine translation, speech recognition and spell checker. Key words: Recurrent Neural Network, Amharic Morphology, Encoder-Decoder Architecture.Item Rainfall Prediction using Combined Satellite and Station Data: Adeep Learning Approach(Addis Ababa University, 2023-07-01) Mubarek Jemal; Melkamu Beyene (PhD)Currently, Ethiopia has high rainfall variance, which is a result of global climate change that has an influence on the environment, property values, and human lives. Accurate rainfall prediction is highly important to smart agriculture practices for developing countries. For rainfall prediction, using station data alone often lacks the required accuracy and spatial coverage, and satellite data has spatial coverage but cannot predict rainfall as accurately as station data. The objective of this research is to develop a model for rainfall prediction using deep learning approaches by combining weather station and satellite data. A design science research methodology was used to develop a rainfall prediction model with 30 years (1990 - 2020) of daily weather station data from the National Meteorological Agency Ethiopian and satellite data from TAMSAT v3.1 and JRA-55 climate models. In data engineering, missing values were handled using mean imputation by dividing the dataset based on the three seasons of Ethiopia. Deep learning approach that includes multi-layer perceptron (MLP), Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), and Bidirectional Long Short Term Memory (BiLSTM) were experimentally evaluated to predict rainfall for selected areas. Lastly, we proposed a model using Bidirectional Long Short Term Memory (BiLSTM) architecture that capable of forecasting daily rainfall for Ethiopia. The performance of the model is evaluated using the state of the art performance evaluation metrics such as; Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Error (MAE), and the results were 0.0472, 0.0025, and 0.021 respectively. We also compared the proposed model with other deep learning approaches like MLP, CNN, and LSTM. The proposed BiLSTM model outperformed LSTM with an RMSE of 0.0015; CNN with RMSE of 0.0023, and MLP with RMSE of 0.0025. The experimental results show that the Bidirectional Long Short Term Memory (BiLSTM) model has a lower RMSE, MSE, and MAE.Item DevOps Implementation Practices and Challenges in the Ethiopian Software Development Industries(Addis Ababa University, 2022-06) Mesfin Tafese; Tibebe Behah (PhD)The objective of this study is to investigate the practices and chal lenges of DevOps implementation in Ethiopian software development companies. This study used a mixed research approach with an explanatory sequential de ign method to collect and analyze data quantitatively and qualitatively. Based on a thorough literature review and empirical data findings, a research guideline was created. The survey questionnaires and interview outlines were designed with the established research objectives in mind, with some adaptations from existing literature and new ones developed as needed. The quantitative component of the study included 107 respondents from ten Ethiopian software development companies that implement the DevOps process either partially or fu lly. Interviews were also conducted to gather information [Tom senior staff, managers, directors, and DevOps implementation teams. The quantitative data sets were analyzed using descriptive methods. OpenCoding approaches were used to examine the qualitative data. The findings revealed challenge in transitioning from traditional developme.rit to a DevOps approach; building DevOps infrastructure and applications with complex processes; and configuring DevOps tools and technology. Furthermore, the researchers discovered that the companies in the study faced a variety of challenges when implementing DevOps in culturerelated practices. Employee resistance to new culture and technology; a culture of team collaboration and commw1ication; a misunderstanding of DevOps envirolUnents and culture; and a lack of organizational commitment to DevOps culture changes were the major challenges. Expert validation and descriptive approaches were used to assess the study'S outcome (proposed guideline). Expert validation was obtained as a result of company mail and survey questionnaires. As a result, the research process and results of this study are thought to be valid, indicating the usability and applicability of the study'S output. This study is expected to produce insights that will assist Ethiopian Software Development Companies' DevOps teams in better understanding and implementing DevOps. Finally, in order to sustain the DevOps implementation process, it is suggested that the proposed guidelines be implemented by prioritizing the team work theme as a priority goal.Item Maturity as a Critical Sustainability Factor for E-Government: Towards A Conceptual Framework(Addis Ababa University, 2022-06) Hiwot Feleke; Lemma Lessa (PhD)Extant literature reveals that many e-government initiatives fail, especially in developing countries. Despite the alanning failure rate of e-government initiatives, the governments of developing countries are allocating a huge budget out of their limited resources to support and improve e-government services.Prior research suggested that maturity is a prerequisite for egovernment sustainability, but the relationship between e-government maturity and sustainability has not been investigated. Hence, this research is aimed at developing a conceptual framework that maps e-government maturity to a sustainable e-government service. Qualitative case study was employed in selected government organizations in Ethiopia that provide e-service through the e-government portal of Ethiopia. The detenninants of e-government maturity and sustainability were derived from extant literature and the relationship between them were conceptualized. The conceptual framework was evaluated through document analysis and interview with experts. A six-step qualitative data analysis framework by Kiger and Varpio (2020) has been used to identify, analyze, organize, describe, and report patterns within the collected data. The study results show that availability of an ICT department with an independent annual budget for the e-government development, human resource capability/ human and intellectual capability, staff retention, manager's commitment to prioritize e-government projects, degree and frequency of customer contacts, customer satisfaction, ICT infrastructure development, integration, Website age, legal and political strategies, institutional instability, organizational e-government operational plan, political environment and e-payments were identified to be the detenninants of egovernment maturity. These detenninants are found as the key factors that affect e-govemment service maturity. Some of the detenninants identified from the literature review were excluded after the case study investigation and some other detenninants are newly identified. The study contributes to e-govemment literature by providing a better understanding on the detenninants of e-government service maturity and sustainability. Identifying the detenninants of maturity and sustainability and exploring the link between the two constructs improve our understanding of sustainable e-government services. The outcome of the research could also be of value for practitioners as a quality tool to assess the maturity and sustainability of e-govemment initiatives. keywords: Maturity, Sustainability, E-government maturity, E-government sustainaoility, Egovernment SuccessItem Factors Affecting Information Systems Security Investment in Selected Public Organizations in Ethiopia(Addis Ababa University, 2023-06) Eden Zewdie; Lemma Lessa (PhD)Ethiopian public institutions are investing in various IT infrastructure and systems to improve the effectiveness and efficiency of their operations. Organizations are highly dependent on network connection and information systems which make them to become hot point of cyber-security. With respect to this, the government of Ethiopia adopts a digitization strategy that strength security capacity as a key element. However, most Organizations have hesitated to make security investments due to several reasons. Most organizations do not consider how cyber-attacks affect the costs and benefits, which results in underinvestment in cyber-security. Due to the dearth of information determining the benefit on information security investment (ROSI) is always challenging. Decision-makers are frequently confused by the abundance of competing solutions and unsure of whether their investments in security are appropriate or even effective. The goal of this study is to identify the factors that affect investment in information security based on TOE framework. In addition, the study determines the significance of those factors that affect information system security investment and provide suggestion on how information system security could be guided. Identifying the factors that influence security investment decisions will assist decision-makers to drive better cyber-security investment decision-making in a proper manner. The study used a quantitative research method using questionnaires as a data collection tool. A total of 105 questionnaire sets were distributed, and 86 were returned, which accounts for 81.9% of the total response rate. Descriptive and explanatory analyses were used to examine the data. The result revealed that among organizational factors: management support, economy, awareness, decision support process, risk assessment, future Growth, and organization culture have significant impact on information security investment. Similarly, environmental factors, namely; legal and regulatory framework, have an impact on security investment. Based on the results, information system security investment could be guided by the support and commitment of management. Raising the information system security awareness among management and key decision makers can increase investment in information system security. The greater awareness and support on security among the decision makers, the greater the security investment. Furthermore, Organizations must take risk assessment; create security controls, policies, and frameworks in order to maintain their spending in information security. Key words: Information system security, Information system security investment, Technology, Organization, EnvironmentItem Predicting Quality of Service of ethiotelecom GSM Mobile Network using Machine Learning algorithms(Addis Ababa University, 2023-01) Dereje Yihalem; Solomon Teferra (PhD)Global System for Mobile Communication (GSM) is globally accepted stand ard for di gital mobile communications. Ethiotel ecom is one of the oldest telecom serv ice providers in Africa, which offer telecommunication services in Ethiopia. GSM ce llular mobile ervice is one of the various telecom services, which has millions of customers in Ethiopia. However, ethiotelecom has done many remarkable works in deve loping information and communications technology network, customers still have been complaining about the poor quality in GSM ce llul ar mobile service. The prime objective of this study is building a pred ictive model using machine-l ea rning techniques to determine the quality of service of GSM network for ethiotelecom Addis Ababa region, which helps to optimize quali ty of service in the area. The data used in this study was obtained from Ethiopian Communications Authority qua lity of service department. For the aim of constructing the machine learning model , a total of 2294 data sets with 6 attributes are employed before preprocessing. After co mpil ati on of the primary dataset preprocessing task is undertaken to make su itab le for the ML task li ke cleaning and attribute selection. Strictl y, following the experimental resea rch process, various experiments are conducted using python as a tool. This is done to find out the best model that clas i fies the KP I data by applyi ng the best classification models by comparing the performance of the models developed using KNN, SVM, as well as the Logistic regress ion learning methods. According to experimental results, logistic regressio n classification algo rithm outperfo rms the I other two classification algorithms with an accuracy of 99.854%. The fi nding indicates Call Setup Success Rate, Handover success rate, Dropped call rate and call attempt are the major determinant factors of QoS of GSM Network. The study also indicates that a GSM mobile network located in Addis Ababa and its surrounding are susceptible to fa ilure in network quality. Finall y, the study is limited to build a predictive machine-learning model for class ificati on of the dataset into the right level of QoS data. Through the res ults found in this study, we recommend ethiotelecom to implement such mobile network quality prediction techniques and avoid inegularities throughout the network that will improve customer satisfaction. Key words: Quality of service, Machine learning, Mobile network, GSM, Key Peljorman ce Indicators.Item Designing Readiness Assessment Guideline towards Adopting loT: The Case of Ethio telecom(Addis Ababa University, 2021-09) Amanuel Zewdu; Million Meshesha (PhD)Internet of Thing (loT) is a comprehensive and open network of intelligent objects which have the capacity to share in formation, data and resources, auto -organize, act and react when any situation or change in the environment is faced. Organizations believe that loT can improve their performance and transform how they made business . However, as with any innovation and adoption and since organizations place a huge amount of in vestment, readiness of a company to adopt loT should be strictly assessed before its widespread adoption. This study assesses the challenges in vo lved in loT adoption and proposes the guideline to be fo llowed for adopting loT. A design science research methodology is employed to in vest igate the readiness of Ethio te lecom to adopt foT, to des ign the gu ideline and to conduct evaluatio n to prove potential appl icabil ity of the proposed guideline. The outcome of this study requires a de ign and des ign science is suitable for thi s. A guideline is a model artifact or a statement that shows a course of action to follow in doing something. In our context, it is a statement that shows the procedures to be follower re loT implementation. Furthermore, a quantitative approach was used to assess the readiness of Telecommute as well as to evaluate the applicability of the guideline. The study used the TOE and 0 0 1 framework to design the guideline. This research used survey questionnaire to collect data for the assessment. The data was analyzed using quantitative data analysis too l, SPSS. The main finding of the study identifies a gap that serves as a requirement to the proposed artifact. After the gap was identified the strategic guideline is designed by incorporating components from the above mentioned framework and carefully choosing the components that are inline with the identified artifact requirement. The artifact designed is a strategic guideline that could be used by the company for the successful adoption of loT. The researcher also gets the artifact evaluated by different experts that works in different position in Telecommute. The result of the evaluation indicated that the guideline fulfilled the requirements of goal, environment, structure, activity and evolution. The organization can use the strategic guideline developed in this study to determine the direction, strategy, and resource allocation in their decision to migrate from the traditional to loT based environment. This study doesn't include assessing the post fact um effect of the strategic guideline after it is being appl ied to the real situation. Therefore, further studies that attempt to expand our understand ing of the postpartum effect of the proposed strategic guideline in supporting the loT adoption need to be conducted by extending or refining the proposed strategic guideline. Keywords: loT; Ethiote lecom; Readiness Assessment Guideline; loT adoptionItem A Study of Employees’ Information Security Policy Violation and Rational Choice Theory: The Case of Ethiopia(Addis Ababa Unversity, 2017-02-01) Tilahun Muluneh; France BelangerNowadays, it becomes clear that information systems security (ISS) is one of the most important issues that organizations need to focus on. Despite huge investments made by companies to keep their information systems (IS) safe, there are many ISS breaches that infiltrate companies’ systems and consequently, these cost their reputation, affect customers’ confidence, and bring huge financial losses. Ethiopian companies are not immune to the ISS problem and there are some signs of ISS breaches. The ISS literature suggests that almost all investments in ISS related issues are for technological solutions. However, this type of solutions alone does not work well, and according to some researchers, there is one significant element that has been given very little attention, the human factor. Most of the ISS breaches are caused by employees who are the legitimate users of organizations’ IS. So “how can we counter the illegal action of our own employees?” is the main agenda this research tries to address. Many researchers advocate the use of deterrence mechanisms to decrease the employees’ noncompliance problem. Despite these findings, there is a lot of research output that reported the inability of the deterrent countermeasures alone to protect IS from security breaches. And more importantly, some researchers point out that different cultures require different ISS interventions. Interestingly, in the last decade, some researchers have studied how culture can influence people’s intention towards ISSP (information systems security policy) compliance. However, most of the current ISS (information systems security) studies assume that deterrent countermeasures’ effect is uniform across countries and culture. This situation identifies a gap that needs to be bridged, and this study address the issue by raising the question “To what extent, if any, national culture moderates the influence of formal iv sanctions, perceived benefits, moral beliefs, and shame on employees’ intention to violate ISSP?” We use survey method to collect data and SPSS Amos to conduct SEM (Structural Equation Modeling) based data analysis. Finally, we get results that show the moderating impact of national culture on the influence of formal sanctions, perceived benefits, moral beliefs, and shame on employees’ intention to violate ISSP.Item Designing Business - Information Technology Alignment Continuity Management Framework for Ethio-Telecom(Addis Ababa University, 2022-06) Habtamu Abune; Million Meshsha (PhD)Achieving and maintaining continual busine s-information technology alignment (BfTA) is a crucial enabler of corporate success in today 's changing business environment, technological innovation, and competitive business world. However, maintaining and managing continuou BfTA remains the main challenge in ethio telecom. Therefore, the main purpose of this study is to design a BITA continuity management framework that gUide the company on how to maintain and manage continuous BIT A within a changing business and technology environment. The study follows a design science research methodology to design the proposed framework. The re earch entry pointfollowed is problem-centered approach. A qualitative research approach wasfollowed to collect and analyze the data. Primary data was collected u 'ing interviews and observation. Also, secondary data was collected using document analysis. Two chief officers, seven directors, and twelve managers were selected using purposive sampling techniques from ethio telecoms business and information system divisions management. Thematic analy is techniques were used to analyze the collected data. The result of the study shows that there are challenges at ethio telecom towards maintaining and managing BfTA continuity due to a lack of mutual leadership and shared understanding between business and fS, in addition to minimal executive leadership support and shared domain knowledge, as well a change in a telecom environment. Moreover, based on the thematic analysis four main themes were generated, the 'e are continuous assessment, continuous alignment, change management, and organizational culture. These themes are used to formulate design requirements and define the objective of the solution. fn this study, the researcher proposes the BITA Continuity management ji-amework with .five core component ·: executive leadership support, change management; continuous BfTA as 'essment in a regular time interval, continuous alignment (plan, implement; and monitor), and creation of shared domain knowledge through building a strong organizational culture. All the core activities are critical to maintaining and managing BIT A continuity at ethio telecom. The proposedji-amework is demonstrated through an illustrative case study with an example by taking a real telecom industry scenario and evaluating it using a question-based method that consists of survey evaluation questioners and expert interviews for user 's acceptance by selected experts Fom ethio telecom business and IS division management. The evaluation result shows 93. 72% of the proposed framework was accepted by the ethio telecom Management. The proposedFamework has a great contribution to the ethio telecom industry by guiding them towards maintaining and managing BfTA continuity within a changing business and technology environment as well as a competitive business world. The evaluation result shows that 6.28% of the proposedframework was not accepted because it is not in operation yet. Future research needs to consider applying the BITA continuity management framework in other organizations or the telecom sector to jilrther evaluate the acceptance of the framework. Keywords: ethio telecom; Business IT Alignment; Continuous Business-IT Alignment; Alignment Continuity Management; BIT A Continuity Management Framework