Kabale University Interdisciplinary Research Journal

Application of artificial intelligence in e-governance: a comparative study of supervised machine learning and ensemble learning algorithms on crime prediction

Ivan Niyonzima, Hussein Muhaise, Aureri Akankwasa — Mon, 23 Sep 2024 00:00:00 +0000

In the developing world, the daily activities of humans’ social, political and economic life make it vital and easy to encounter the phenomenon of crime. Crime is an unnecessary evil in society and for any economic, social and political activities to run smoothly, criminal offenses must be completely eliminated from society. Advancement in information and communications technology enables law enforcement agencies to collect a huge amount of crime data, and the data collected by these organizaions have been doubling every two years. It has been found out that only 17% of the collected crime data is used in their operations today and several studies have noted that Law Enforcement Agencies are data rich but information poor. Machine learning, a subfield of artificial intelligence, has been used by government agencies in developed countries in different operations like face recognition, computer forensics, image and video analysis to identify criminals and crime predictions. It is therefore time for developing countries to leverage such technologies in order to reduce crimes. Therefore, this study proposes the application of supervised machine learning techniques in the prediction of crimes basing on the past crime data. During this study, we used open-source crime data from the UCI Machine learning repository to train and validate our algorithms. The performance of supervised machine learning and ensemble learning algorithms was done using crime data. The supervised machine learning algorithms used include K-Nearest Neighbour (KNN), decision tree classifier (CART), Naïve Bayes (NB) and Support vector machine (SVM). The ensemble learning algorithms used include AdaBoost (AD), Gradient Boosting Classifier (GBM), Random Forest (RF) and Extra Trees (ET). We used an accuracy metric to measure the performance of the algorithms. Python 3 was used in all the experiments using windows 10 laptop with 8GB RAM and 2.0GHZ processor. The performance of the supervised machine learning algorithms using the original datasets includes 60.33%, 56.24%, 57.01% and 59.06% for KNN, CART, NB, and SVM respectively. The performance of ensemble learning algorithms using the original datasets includes 58.58%, 59.81%, 55.23% and 55.74% for AD, GBM, RF and ET respectively. Experimental results revealed that KNN generally performed better when compared to the rest of the algorithms. we then developed a crime prediction model based on KNN and its prediction accuracy was 66% on our test dataset. The use of Artificial Intelligence has the potential to ameliorate several existing structural inefficiencies in the discharge of governmental functions. Machine learning, a subfield of artificial intelligence, has been used by government agencies in developed countries in crime analysis and predictions. It is therefore time for developing countries to leverage such technologies in order to reduce crimes.

The effects of tax administration on revenue collection in Uganda: the role of self-assessment system

Paul Turyaheebwa, Siraje Kaaya, Abanis Turyahebwa, Arthur Sunday — Fri, 20 Sep 2024 00:00:00 +0000

This research examines the impact of tax administration, with a focus on the self-assessment system (SAS), on revenue collection in Uganda. Utilizing data collected from 350 commercial enterprises through questionnaires, the study employs AMOS PLS-SEM for data analysis. The findings reveal that the SAS significantly enhances revenue collection by empowering taxpayers to self-report and calculate their tax liabilities, contingent upon adequate tax knowledge and awareness. The study also identifies government spending and tax collection methods as positive moderators in the relationship between SAS and revenue collection, highlighting the importance of government efficiency and transparency in fostering tax compliance. Despite the positive impact of compliance audits on revenue performance, the effectiveness of tax audits varies across different contexts, necessitating tailored approaches. The research concludes that a comprehensive strategy integrating tax education, transparent government spending, and strategic compliance audits is essential for optimizing revenue collection and supporting sustainable economic development in Uganda. Future research should explore the long-term effects of these interventions and consider the role of digitalization and socio-cultural factors in shaping tax compliance behavior.

Assessing the effectiveness of tools used for lecturer and course evaluation in institutions of higher learning: a case study from Ugandan universities

Fri, 20 Sep 2024 00:00:00 +0000

Blended learning, a pedagogical method integrating face-to-face and online instructions methodologies, has been identified as a strategic educational approach since its inception in the late 1990s. Moreover, its adoption especially in developing countries such as Uganda was widely recognized during the COVID-19 pandemic’s acceleration of digital learning adoption. However, this adoption has paused many challenges in evaluating learning content, teaching methodologies, and their impact on student progress. This study therefore, explores the critical role of quality assurance in higher education, focusing on the assessment of lecturer performance and course content. Apparently, paper-based mode of evaluation is the commonly used method in Ugandan universities, posing issues of privacy, delayed analytics, and ever-increasing operational costs. To address these challenges, this research proposes the development of an automated assessment system, informed by a benchmarking study across four universities. By adopting insights from existing evaluation practices, the proposed system aims to enhance the efficiency, accuracy, and students’ privacy during lecturer and course assessment. The implementation of this automated system at Kabale University promises to streamline evaluation process, ultimately enhancing teaching quality and academic outcomes.

Perspectives of curriculum regulatory authorities on adopting a decolonized curriculum in Uganda: a case of National Curriculum Development Center (NCDC)

Florence Kirabo Nampijja — Fri, 20 Sep 2024 00:00:00 +0000

The ongoing African renaissance and the decolonization imperatives are inviting Africans to reconsider the role of Africa ways of knowing as a way of decolonizing curriculum. Like other countries in Africa, Uganda needs an education that uses local experiences, realities, values and languages to create a lifelong impact on the masses. The ongoing colonial education was aimed at training low and middle level workers for government and missionary service and therefore the skills and competences promoted by such an education do not match with those required by contemporary demands. This explains why despite the increasing number of universities and tertiary institutions, and having many graduates (at least 400,000 per annum) Kamuhanda J(2022), the productivity of the nation in many sectors is still low. It is not clear if Uganda’s education regulatory authorities like NCDC, NCHE, ESA support and therefore consider a move towards a home grown / endogenous / decolonized curriculum. Hence, the study aimed at finding the perspectives of NCDC’s technical staff on curriculum transformation with in a decolonized framework. The study used questionnaires and review of NCDC’s literature to find views of technical staff (curriculum specialists) at NCDC.

Electronic marketing and service quality of on-line merchandisers: a case study of Jumia Uganda

Paul Ssemaluulu Mukasa, Fenehansi Isingoma, George Mugavu — Fri, 20 Sep 2024 00:00:00 +0000

The study examined electronic marketing and service quality of on-line merchandisers, a case study of Jumia Uganda. The specific objective was to find out the relationship between cart abandonment rate and service quality in Jumia Uganda. The research employed a cross-sectional survey design to investigate the association between electronic marketing efforts and service quality. A mixed-methods research approach, incorporating both quantitative and qualitative methodologies, was deemed highly relevant for this study. In addition, from the 255 target respondents, a definite sample size of 101 was determined using William G. Cochran (1997) formula. The study revealed significant correlations between various factors in the context of Jumia Uganda's electronic marketing. The study revealed that a moderate positive correlation (r = 0.422**) was identified between cart abandonment rate and service quality, emphasizing the critical role of service quality in customer retention and reducing cart abandonment. It was recommended that: Jumia should launch remarketing campaigns to re-engage customers who abandoned their carts. Personalized messages and incentives should be used to encourage them to return and finalize their transactions.

Development of a fuzzy-based predictive model for the risk of postpartum hypertension in nursing mothers

Lawrence O. Omotosho, Peter A. Idowu, Kudirat O. Jimoh, Ibrahim K. Ogundoyin — Fri, 20 Sep 2024 00:00:00 +0000

Fuzzy Logic has grown in prominence in recent years as its capacity to address a variety of problems in the field of medicine has been demonstrated to be exceptional. This study developed a model to predict risk of postpartum hypertension among nursing mothers. In this study, the variables associated with the risk of postpartum hypertension were identified, formulated a fuzzy-logic model and simulated the predictive model. The variables that were common symptoms associated with the risk of postpartum hypertension were elicited by review of related works on the body of knowledge of postpartum hypertension following which the variables were validated by mental health experts at a Nigerian hospital using the interview method. The variables identified were classified into their respective linguistic labels based on the crisp values assigned to them within the interval of acceptable values while the risk of postpartum hypertension was classified as low, moderate and high risk. Fuzzy-based related functions were used to formulate the fuzzy model for the input variables and the risk of postpartum hypertension. It was also observed that the number of triangular membership function formulated for each variable is a function of the number of classified labels for each variable. The results also showed that a total number of 288 rules were defined by the IF-THEN statements created from the variables identified by the experts. The predictive model developed and simulated can be utilized to aid expert obstetricians in the early detection and treatment of postpartum hypertension in the future.

Unlocking human potential for institutional excellence: an examination of talent management practices and employee productivity in Ogun State universities, Nigeria

Fri, 20 Sep 2024 00:00:00 +0000

This study examines the relationship between talent management practices and employee productivity in Ogun State universities, Nigeria. The study aimed to investigate the influence of talent management on employee productivity and identify strategies for unlocking human potential and driving institutional excellence. A survey research design was used, and data were collected with a self-structured questionnaire from 586 academic and non-academic employees of four selected universities in Ogun State and simple random sampling technique was employed, the research instrument was validated by the average variance (0.831). Cronbach’s alpha of the scale for the variable was greater than 0.70, which suggest that instrument was reliable and data gathered was analyzed using descriptive and inferential statistics (simple linear regression analysis). The result showed there was a positive influence talent management on employee productivity in universities in Ogun State at the value of (β= .517, t = 14.791, p< 0.05), supporting previous research that effective talent management practices improve employee productivity. The study also showed a significant relationship between talent management and organizational performance, emphasizing the importance of talent management in achieving organizational objectives. The study recommends that universities in Ogun State should develop and implement effective talent management programs, invest in training and development programs, and conduct regular assessments to evaluate the effectiveness of their talent management practices.

Christian doctrines and the death of Osinachi: social work intervention with women in intimate partner violence in Nigeria

Kelly Alfred Imafidon — Fri, 20 Sep 2024 00:00:00 +0000

This paper x-rayed the spate of Christian doctrines as a resistance for Christian women to stay in violent intimate relationship using Mrs. Osinachi as our case study. It espoused the counsels and teaching of the Christian doctrines and how these are employed to manipulate women to accept and continue to endure the harsh and intimidating relationships with their partner. The paper also established that the custodians of the Christian doctrines who are mainly men amplify the verses of the Bible that focus primarily on women to be submissive while they are silent about the areas that command men not to abuse their wives. The paper adopted literature scoping research method alongside reflexive research method togather the required data. Content analysis was use to analyzed secondary data which were comprehensively reviewed and important themes isolated and analyzed based on the aim of the study. The paper recommends social work profession that is capable of providing effective intervention to empower and liberate to women from abuse and all forms of religious and cultural oppression which has in the past rendered them voiceless and helpless.

Social administration and societal transformation in Uganda today

George Mugavu — Fri, 20 Sep 2024 00:00:00 +0000

Any attempt to divorce Social Administrators from mainstream societal arrangements aimed at causing societal transformation and development is a futile one. This is due to the fact that social administrators have historically been instrumental in working with governments around the world to ensure that societal needs at different levels are addressed to propel development. Societal transformation requires concerted efforts and this is exactly why governments have to embrace the role played Social Administrators in societal development. The researcher employed a purely critical qualitative approach in which desk research methodology was relied upon. As such secondary data was used and this data was obtained mainly from scholarly and published research articles surrounding Social administration, Social welfare, and other crucial published reports, with matters of the role of social administrators in societal transformation in Uganda today under scrutiny in which even the challenges incapacitating the social administrators from playing their roles well were also analyzed. Critical content analysis was employed in examining the roles of social administrators in Uganda and also the challenges that they face. Validity and reliability were guaranteed by paying much attention to critical conceptual clarity and interpretative rigor. In this paper I reviewed the genesis, the roles of Social Administrators, the challenges that hamper the activities the discipline of Social Administration drawing substantiations from the Ugandan experience. Connectedly, based on literature review, I further concluded that transforming the society is a holistic process which should be done involving all the relevant stakeholders at different levels especially in the community as this would be in position cause for ownership of all projects that could be set up to help the people improve their conditions of living. I also came up with some recommendations which included; the central government should strengthen the monitoring and evaluation department, integrating technology into mainstream societal development projects, continuously empowering local people and embracing the sustainable development strategies.