School of Computing and Information Science

Permanent URI for this communityhttps://hdl.handle.net/20.500.12504/206

Browse

Now showing 1 - 20 of 31

Adaptive object detection in dynamic road environments using YOLOv11 with continuous learning for real-time obstacle detection
(Discover Artificial Intelligence, 2026-01-13) Nkalubo, Lenard Byenkya; Nakibuule, Rose; Okila, Nixson
Real-time object detection in dynamic road environments is crucial for enhancing road safety, infrastructure monitoring, and Intelligent Transportation Systems (ITS). This study presents an adaptive object detection model based on YOLOv11 with continuous learning, designed to detect road obstacles in real-time without frequent retraining autonomously. Unlike existing YOLO-based models such as YOLOv10 and LD-YOLOv10, the proposed model integrates a continuous learning mechanism, enabling it to adapt dynamically to evolving road conditions, including potholes, vehicles, signposts, and other obstacles. The model was trained and evaluated on a dataset collected from diverse urban road environments in Uganda, achieving a mean average precision (mAP) of 0.856, precision of 0.873, and recall of 0.849. It also demonstrates high-speed performance at 78.7 Frames Per Second (FPS), making it suitable for real-time deployment on resourceconstrained edge devices. While this study primarily focuses on model development and optimization for road obstacle detection, future research will explore its potential application in assistive navigation systems for visually impaired individuals. Comparative analysis against state-of-the-art models, including YOLOv10, LD-YOLOv10, and Tiny-DSOD, demonstrates the competitive performance of the proposed model, particularly in detecting small and occluded objects.
Adaptive-size dictionary learning using information theoretic criteria for image reconstruction from undersampled k-space data in low field magnetic resonance imaging
(BMC Medical Imaging, 2020-06) Emmanuel, Ahishakiye; Martin, Bastiaan Van Gijzen; Julius, Tumwiine; Johnes, Obungoloch
Background Magnetic resonance imaging (MRI) is a safe non-invasive and nonionizing medical imaging modality that is used to visualize the structure of human anatomy. Conventional (high-field) MRI scanners are very expensive to purchase, operate and maintain, which limit their use in many developing countries. This study is part of a project that aims at addressing these challenges and is carried out by teams from Mbarara University of Science and Technology (MUST) in Uganda, Leiden University Medical Center (LUMC) in the Netherlands, Delft University of Technology (TU Delft) in the Netherlands and Pennsylvania State University (PSU) in the USA. These are working on developing affordable, portable and low-field MRI scanners to diagnose children in developing countries with hydrocephalus. The challenges faced by the teams are that the low-field MRI scanners currently under development are characterized by low Signal-to-Noise Ratio (SNR), and long scan times. Methods We propose an algorithm called adaptive-size dictionary learning algorithm (AS-DLMRI) that integrates information-theoretic criteria (ITC) and Dictionary learning approaches. The result of the integration is an adaptive-size dictionary that is optimal for any input signal. AS-DLMRI may help to reduce the scan time and improve the SNR of the generated images, thereby improving the image quality. Results We compared our proposed algorithm AS-DLMRI with adaptive patch-based algorithm known as DLMRI and non-adaptive CSMRI technique known as LDP. DLMRI and LDP have been used as the baseline algorithms in other related studies. The results of AS-DLMRI are consistently slightly better in terms of PSNR, SNR and HFEN than for DLMRI, and are significantly better than for LDP. Moreover, AS-DLMRI is faster than DLMRI. Conclusion Using a dictionary size that is appropriate to the input data could reduce the computational complexity, and also the construction quality since only dictionary atoms that are relevant to the task are included in the dictionary and are used during the reconstruction. However, AS-DLMRI did not completely remove noise during the experiments with the noisy phantom. Our next step in our research is to integrate our proposed algorithm with an image denoising function.
Advancing child-centred research methodologies in the school library context
(IGI Global Scientific Publishing, 2026-03-28) Rugambwa, Nina Olivia; Lyaka, Martha
Research involving children in the field of Library and Information Science (LIS) has mainly relied on traditional data collection methods rooted in social research paradigms. Common techniques include interviews, documentary analyses, and surveys. This chapter emphasizes the importance of child-centered research methods in LIS, especially for understanding children's information-seeking behaviors in school libraries. A study conducted in two primary schools in Kampala and Mukono involved 32 children, using storytelling and flower maps, to share their views on libraries. Children perceive good libraries as safe spaces, with children's pets, knowledge hubs, places for adventure and relaxation. Conversely, children also described negative aspects of libraries, such as noise, disorganization, dirtiness, unfriendly staff, non-functional information tools, and intimidating content, which characterized bad libraries. The chapter advocates adopting child-centered methodologies to foster a more inclusive understanding of children's informational experiences and needs.
Advancing indigenous knowledge research epistemologies and research methodologies in LIS research
(IGI Global Scientific Publishing., 2026-03-28) Rugambwa, Nina Olivia; Lyaka, Martha
This chapter explores the integration and advancement of Indigenous knowledge systems within Library and Information Science (LIS) research, emphasizing the importance of Indigenous epistemologies and research methodologies. It critically examines how traditional LIS paradigms can be expanded to incorporate Indigenous ways of knowing, valuing cultural context, oral traditions, and community-based approaches. Special attention is given to the cultural context, oral traditions, and community-centered approaches that underpin these epistemologies. The chapter advocates for the development of inclusive research frameworks that respect Indigenous epistemologies, fostering more equitable and culturally responsive LIS scholarship. By advancing these paradigms, the chapter aims to promote greater recognition, validation, and utilization of Indigenous knowledge in information practices and research through providing guidance on how researches biased towards indigenous knowledge systems can be effectively conducted in the LIS discipline.
Assistive technologies for inclusion of deaf and hard-of hearing (DHH) students and academic staff: a call to action for library and information science professionals in Uganda
(Qualitative and Quantitative Methods in Libraries, 2024-12-09) Robinah, K. Namuleme; Denis Ssebuggwawo; Caroline Ilako
Assistive technology (AT) is “any product whose primary purpose is to maintain or improve an individual’s functioning and independence and thereby promote their well-being. For people with disabilities, AT has the potential to improve functioning, reduce activity limitations, promote social inclusion, and increase participation in education. University libraries are mandated to provide assistive technologies, adequate space, resources, and services suitable to support and meet teaching, learning, and research needs for all users, including persons with disabilities. However, it was hitherto unknown how university libraries in Uganda facilitate accessibility to library facilities services to meet the unique needs of deaf or hard-of-hearing students and academic staff. The current paper aimed to generate rich insights into the digital inclusion needs of Deaf and Hard-of-Hearing (DHH) students and academic staff, and to explore how university libraries in Ugandan higher education institutions facilitate the accessibility, adoption, and application of assistive technologies for teaching, learning, and research. Employing a mixed-methods design, the study utilized two semi-structured questionnaires and two interview guides to gather data from DHH students, academic staff, and librarians at four public universities in Uganda. The recruitment of DHH participants was conducted using purposive and snowball sampling techniques. Ethical clearance was granted by the Aids Support Organisation (TASO) Research Ethics Committee on July 27, 2023 (Ethics reference number: TASO-2023-237). Quantitative data were analysed using the Statistical Package for Social Scientists (SPSS ver. 21), while qualitative data underwent thematic analysis, with selected verbatim quotations used to corroborate the quantitative findings. This paper has unearthed digital inclusion needs of DHH Students and Academic Staff, including access to high-speed internet, sufficient bandwidth, university websites with captions, software that translates a signer’s words into text, captioning software, video editing software, multimedia mobile phone applications, LCD Projectors, personal computers, mobile phones, assistive technology technical support, digital and assistive technology training, and sign language interpretation which must be met for them to taking advantage of library resources as services that are available to all other users. In addition, the paper has revealed that Libraries are inaccessible because DHH Students and Academic Staff cannot afford the hardware, software, and peripheral equipment and data required to access technology-supported resources, systems, content, and services; the majority of Libraries did not conduct staff capacity building on basic knowledge of assistive technologies, digital and assistive technology training. Furthermore, the libraries did not train DHH students and academic staff in accessing databases, using Google Suite, and Mendeley, Endnote, and Zotero to manage citations and references. Libraries also did not identify and evaluate the Digital literacy training needs and lacked a clear strategy for meeting the digital literacy needs of DHH academic staff and students. Together these hindered the DHH Students and Academic Staff from effectively adopting and applying these technologies for teaching, learning, and research. Overall, the finding revealed a great mismatch between the existing library-related assistive technology services and resources and the digital inclusion needs of students and staff with hearing impairments. Given the important role of academic libraries in promoting digital inclusion, especially for Deaf and Hard of Hearing (DHH) academic staff and students, the paper recommends that University Libraries prioritize the development of a digital inclusion policy to guide the design and implementation of initiatives that improve access to library resources and services for DHH individuals.
Blockchain technology needs for sustainable mineral supply chains: A framework for responsible sourcing of Cobalt.
(Elsevier, 2022) Godfrey, Mugurusi; Emmanuel, Ahishakiye
Blockchain technology has recently become the go-to solution for companies and industries that seek to enhance value chain traceability of their products, and transparency in their supply chains. Because of these benefits, it's been proposed for monitoring environmental, social, and governance (ESG) performance and compliance in industries that have weak regulatory and formal structures. The cobalt mining industry especially in the Democratic Republic of Congo, the world’s biggest producer of cobalt ore used in the manufacturing of lithium-ion batteries, is one such environment that’s characterized by conflict, and serious human rights abuses. The key actors in the cobalt supply chain, therefore, face the tradeoff involving maintaining long-term supply versus reducing the risks associated with cobalt sourced from locations with poor environmental and human rights records. Most of such problems emerge from Artisanal and small-scale mining. This paper presents an attempt to tightly link existing blockchain technology frameworks in the cobalt industry with ESG performance of companies to enable them to audit the chain of custody journeys for their components and ultimately sustainability performance. We present a responsible sourcing framework to connect blockchain source data needs to ESG metrics to help companies build interoperable but understandable blockchain architectures.
Burden of cumulative risk factors associated with non-communicable diseases among adults in Uganda : evidence from a national baseline survey
(International Journal for Equity in Health, 2016-12-01) Wesonga, Ronald; Guwatudde, David; Bahendeka, Silver K.; Mutungi, Gerald; Nabugoomu, Fabian; Muwonge, James
Modification of known risk factors has been the most tested strategy for dealing with noncommunicable diseases (NCDs). The cumulative number of NCD risk factors exhibited by an individual depicts a disease burden. However, understanding the risk factors associated with increased NCD burden has been constrained by scarcity of nationally representative data, especially in the developing countries and not well explored in the developed countries as well. Methods: Assessment of key risk factors for NCDs using population data drawn from 3987 participants in a nationally representative baseline survey in Uganda was made. Five key risk factors considered for the indicator variable included: high frequency of tobacco smoking, less than five servings of fruit and vegetables per day, low physical activity levels, high body mass index and raised blood pressure. We developed a composite indicator dependent variable with counts of number of risk factors associated with NCDs per participant. A statistical modeling framework was developed and a multinomial logistic regression model was fitted. The endogenous and exogenous predictors of NCD cumulative risk factors were assessed. Results: A novel model framework for cumulative number of NCD risk factors was developed. Most respondents, 38 · 6% exhibited one or two NCD risk factors each. Of the total sample, 56 · 4% had at least two risk factors whereas only 5.3% showed no risk factor at all. Body mass index, systolic blood pressure, diastolic blood pressure, consumption of fruit and vegetables, age, region, residence, type of residence and land tenure system were statistically significant predictors of number of NCD risk factors (p < 0 · 05). With exception to diastolic blood pressure, increase in age, body mass index, systolic blood pressure and reduction in daily fruit and vegetable servings were found to significantly increase the relative risks of exhibiting cumulative NCD risk factors. Compared to the urban residence status, the relative risk of living in a rural area significantly increased the risk of having 1 or 2 risk factors by a multiple of 1.55. Conclusions: The non-communicable disease burden is on the increase, with more participants reporting to have at least two risk factors. Our findings imply that, besides endogenous factors, exogenous factors such as region, residence status, land tenure system and behavioral characteristics have significant causal effects on the cumulative NCD risk factors. Subsequently, while developing interventions to combat cumulative risk factors of NCDs, the Ministry of Health needs to employ a more holistic approach to facilitate equitable health and sensitization across age, residence and regional divide.
Children and libraries: innovative library services at marko lukooya memorial community library during the Covid-19 pandemic, Uganda
(International Journal of Advanced Research, 2025-04-17) Rugambwa, Nina Olivia; Kawalya, Jane; Mutibwa, Lois Nankya
Community libraries do not receive financial support from the government, unlike public and academic libraries in Uganda. This study explored the provision of library services during the COVID-19 period by Marko Lukooya Memorial Community Library. The study investigated library services provided by the library, challenges encountered, and strategies that were used to address the challenges faced during the pandemic. A qualitative case study research design was used. Data was collected using face-to-face in-depth interviews and observation methods with library staff and patrons. Standard Operating Procedures were followed during the pandemic by both the participants and researchers to mitigate the risk of the deadly COVID-19 virus. Key findings revealed that the library adapted innovative ways to provide library services to children and the community during the COVID-19 pandemic amidst many challenges. The study recommends training of library staff in information management and more material and financial support by donors, the government, and all well-wishers to support the good work being done by Marko Lukooya Memorial Community Library in Uganda.
Classification of cassava leaf diseases using deep Gaussian transfer learning model
(Engineering Reports, 2023-03) Emmanuel, Ahishakiye; Ronald, Waweru Mwangi; Petronilla, Murithi; Fredrick, Kanobe; Danison, Taremwa
In Sub-Saharan Africa, experts visually examine the plants and look for disease symptoms on the leaves to diagnose cassava diseases, a subjective method. Machine learning algorithms have been employed to quickly identify and classify crop diseases. In this study, we propose a model that integrates a transfer learning approach with a deep Gaussian convolutional neural network model. In this study, two pre-trained transfer learning models were used, that is, Mobile Net V2 and VGG16, together with three different kernels: a hybrid kernel (a product of a squared exponential kernel and a rational quadratic kernel), a squared expo-nential kernel, and a rational quadratic kernel. In experiments using MobileNet V2 and the three kernels, the hybrid kernel performed better, with an accuracy of 90.11%, compared to 86.03% and 85.14% for the squared exponential kernel and a rational quadratic kernel, respectively. Additionally, experiments using VGG16 and the three kernels showed that the hybrid kernel performed better, with an accuracy of 88.63%, compared to the squared exponential kernel’s accuracy of 84.62% and the rational quadratic kernel’s accuracy of 83.95%, respectively. All the experiments were done using a traditional computer with no access to GPU and this was the major limitation of the study.
Comparative Performance of Machine Leaning Algorithms in Prediction of Cervical Cancer
(IEEE xplore, 2021-10) Emmanuel, Ahishakiye; Waweru, Mwangi; Petronilla, Muthoni; Lawrence, Nderu; Ruth, Wario
Cervical cancer is among the most common types of cancer affecting women around the world despite the advances in prevention, screening, diagnosis, and treatment during the past decade. Cervical cancer can be treated if diagnosed in its early stages. Machine learning algorithms like multi-layer perceptron, decision trees, random forest, K-Nearest Neighbor, and Naïve-Bayes have been used for the prediction of cervical cancer to aid in its early diagnoses. In this study, we compare the performance of ensemble methods (AdaBoost, Stochastic Gradient Boosting, Random Forests, and Extra Trees), and classification algorithms (K-Nearest Neighbor and Support Vector Machine) in the prediction of cervical cancer basin g risk factors. Ensemble methods and classification algorithms were used during this study. Ensemble methods were selected because they combine several machine learning techniques into one model to decrease variance, bias, or improve performance while the classification methods were selected because our dataset was generally categorical and therefore could work well with our problem domain. Experimental results revealed that all the algorithms did not perform well on the “imbalanced” dataset. Experiments on balanced revealed an improved performance. The performance metrics used include Fl-score, Area Under Curve (AUC), and Recall. Extra Trees performed better than the rest when using the Fl-score metric, Stochastic Gradient Boosting and Random Forest performed better than the rest when using the AUC metric, K-Nearest Neighbors outperformed the rest using the recall metric, and Extra Trees had the best accuracy 0.96. The application of machine learning methods in the prediction of cervical cancer using risk factors may lead to early detection of the disease which can be treated if diagnosed early. Six algorithms have been considered in this study. The general performance reveals that ensemble methods performed better than classification methods using both imbalanced and balanced datasets.
A comparative study of some pre-trained models on transfer learning approach in detection and classification of cassava leaf diseases
(SSRN, 2022) Emmanuel, Ahishakiye; Waweru, Mwangi; Petronilla, Muthoni; Danison, Taremwa; Fredrick, Kanobe
Cassava diseases affect cassava harvest posing the greatest danger to the food security and livelihoods of more than 200 million people. To identify cassava diseases, government professionals visit various sections of the country and visually score the plants by looking for disease indicators on the leaves. This procedure is notoriously subjective; it is not uncommon for specialists to differ on a plant's diagnosis. Automating the detection and classification of crop diseases could help professionals diagnose diseases more accurately and allow farmers in remote locations to monitor their crops without the help of specialists. Machine learning algorithms have been used in the early detection and classification of crop diseases. Motivated by the current developments and many influential studies in the field of deep learning and transfer learning models in the detection and classification of crop diseases, this study evaluates the performance of VGG16, VGG19, ResNet50, InceptionV3, DenseNet201, and MobileNetV2 in detection and classification of cassava leaf diseases. Fine-tuning of the hyperparameters was done during training to improve the accuracy of the models. Experimental results on the cassava dataset revealed that InceptionV3, DenseNet201, and MobileNetV2 models had high training accuracy but low validation accuracy with various epochs which means that they had issues with over fitting while ResNet50 had issues with underfitting. Moreso, VGG16 and VGG19 models performed well on both training and validation datasets, though VGG16 performed relatively well compared to VGG19.
Consumer segmentation and profiling using demographic data and spending habits obtained through daily mobile conversations
(American Journal of Modeling and Optimization, 2018-08) Samuel, W. Kamande; Evans, A. K. Miriti; Emmanuel, Ahishakiye
Knowledge of customer behaviour helps organizations to continuously re-evaluate their strategies with the consumers and plan to improve and expand their application of the mosteffective strategies. Using expenditure data collected through daily mobile conversations with consumers in Kenya, this study sought to compare various clustering algorithms and establish one that best segments consumers, and subsequently providing profiles that provide a basis for marketing and brand strategy based on existing demographic data – age, gender, region and primary income source. K-Means, Hierarchical and Partitioning around Medoids (PAM) clustering algorithms were compared using internal and stability validation tests. Hierarchical clustering with four clusters had the best Connectivity (0.847) and Silhouette width (0.924) measures. Stability validation compares the results by removing a column, one at a time. Average Proportion of Non-overlap (APN), Average Distance (AD), Average Distance Between Means (AND) and Figure of Merit (FOM) were used to compare the algorithms. Again, Hierarchical clustering with four clusters was found to partition the data best. The study forms a basis for the use of additional profile descriptors once available to provide a firmer understanding of the customer segments built on expenditure data in Kenya.
Designing robust sampling frameworks for mixed methods research: challenges and practical guidelines
(IGI Global Scientific Publishing, 2026-03-18) Lyaka, Martha; Mukungu, Isaac; Rugambwa, Nina Olivia; Ngulube, Patrick
In recent years, research in mixed methods has received considerable attention in a wide range of fields, including computer science and informatics. This methodology encourages the integration of both qualitative and quantitative data to provide a comprehensive picture of complex phenomena. However, one of the main problems faced by researchers participating in mixed method projects is that of sampling. Sampling, as a cornerstone of methodological rigour, has an impact on the validity and application of research findings. The aim of this chapter is to analyse the nuances of sampling in the context of mixed-method research, specifically to address the complexity involved and to provide practical suggestions for computational and informatics researchers.
Detecting the risk of customer churn in telecom sector: a comparative study
(Mathematical Problems in Engineering : Hindawi, 2022-07-18) Edwine, Nabahirwa; Wang, Wenjuan; Song, Wei; Ssebuggwawo, Denis
Churn rate describes the rate at which customers abandon a product or service. Identifying churn-risk customers is essential for telecom sectors to retain old customers and maintain a higher competitive advantage. The purpose of this paper is to explore an effective method for detecting the risk of customer churn in telecom sectors through comparing the advanced machine learning methods and their optimization algorithms. Based on two different telecom datasets, Mutual Information classifier was firstly utilized to select the most critical features relevant to customer churn. Next, the controlled-ratio undersampling strategy was employed to balance both minority and majority classes. Key hyperparameter optimization algorithms of Grid Search, Random Search, and Genetic Algorithms were then combined to fit the three promising machine learning models-Random Forest, Support Vector Machines, and K-nearest neighbors into the customer churn prediction problem. Six evaluation metrics-Accuracy, Recall, Precision, AUC, F1-score and Mean Absolute Error, were last used to evaluate the performance of the proposed models. The experimental results have revealed that the RF algorithm optimized by Grid Search based on a low-ratio undersampling strategy (RF-GS-LR) outperformed other models in extracting hidden information and understanding future churning behaviors of customers on both datasets, with the maximum accuracy of 99% and 95% on the applied dataset 1-2 respectively.
Determination of the quality parameter ranges of reinforcing bars used in Uganda's construction industry
(Kyambogo University (Unpublished work), 2024-10) Agaba, Pius
Uganda's construction industry faces a serious concern with substandard reinforcing bars (rebars), leading to building collapses, fatalities, and financial losses. A study was conducted to determine quality parameter ranges of reinforcing bars by determining mass per unit length, testing mechanical properties, analyzing chemical composition, and evaluating conformity to standards. The goal was to prevent future collapses and safeguard lives and investments. Experiments focused on 10 mm and 12 mm rebars, commonly used in various construction projects, unlike larger rebars typically made from imported billets. Samples from four hardware stores representing different manufacturers were tested, with initial measurements taken using a meter rule and weighing scale to assess length and mass. Later, the mass per unit length was calculated and it was found that the obtained results were within acceptable ranges from 0.567 kg/m to 0.667 kg/m for rebars with diameters of 10 mm and 0.838 kg/m to 0.938 kg/m for rebars with diameters of 12 mm based on US-EAS 412-2-2022. Mechanical properties like yield stress, tensile strength, elongation, and stress ratio were tested on a universal testing machine and they revealed acceptable yield stress values above 500 MPa and elongation above 14% across all samples. While all rebars exhibited yield stress above the minimum allowable limit of 500 MPa based on US EAS 412-2-2022, some did not meet the stress ratios like A10, B12, C10, C12, and 012, which were below the specified minimum 1.15 outlined in US EAS 412-2-2022. Bending tests indicated no observable cracks in the rebars. On the other hand, using a spectrometer, the chemical composition of steel rebars was analyzed, and it was revealed that some elements were slightly below allowable limits. The analysis focused on major alloying elements, including C, Mn, Si, P, S, Cr, Mo, Ni, V, and Cu. Rebar A10's manganese content was significantly below the minimum allowable limit of 1.6% (at 0.75 %).Other elements (C, Si, P, S, Cr, Mo, Ni,V, Cu) were within allowable minimum limits, aligning with US EAS 412-2-2022 standards. The carbon equivalent value (CEV) was then calculated and used to evaluate weldability, which ranged from 0.315 to 0.376, all falling within acceptable established standards. Notably, while three rebars A12, B10, and 010 met the specified quality parameters, the other five rebars A 10, B 12, C 10, C 12, and 012 did not conform, primarily due to low-stress ratios below 1.15, a critical factor affecting ductility and load absorption during seismic events. This research could improve the rebar quality and help prevent future building collapses, protect lives, and safeguard investments. The findings emphasized the need for stricter quality control in rebar production and selection to avoid structural failures.
A dictionary learning approach for joint reconstruction and denoising in low field magnetic resonance imaging
(2021 IST-Africa Conference (IST-Africa), 2021-10) Emmanuel, Ahishakiye; Martin, Bastiaan VAN Gijzen; Xiujie, Shan; Julius, Tumwiine; Johnes, Obungoloch
Currently, many children with hydrocephalus in East Africa and other resource-constrained countries do not have access to Magnetic Resonance Imaging (MRI) scanners, the preferred imaging tool during the disease administration and treatment. Conventional MRI scanners are costly to buy and manage, which limits their utilization in low-income countries. Low-field MRI scanners can offer an affordable, sustainable, and safe imaging alternative to high-field MRI. However, they are associated with a low signal-to-noise ratio (SNR), and therefore the images obtained are noisy. In this study, we propose an algorithm that may help to alleviate the drawbacks of low-field MRI by improving the quality of images obtained. The proposed algorithm combines our previous proposed algorithm known as AS-DLMRI for image reconstruction and a nonlinear diffusion filter for image denoising. The formulation is capable of removing additive zero-mean white and homogeneous Gaussian noise, as well as other noise types that could be present in the original signal. Experiments on visual quality revealed that the proposed algorithm is effective in denoising images during reconstruction. The proposed algorithm effectively denoised a noisy phantom, and a noisy MRI image, and had better performance when compared to DLMRI and AS-DLMRI in terms of Peak Signal to Noise ratio (PSNR) and High-Frequency Error Norm (HFEN). Integrating AS-DLMRI and the nonlinear diffusion filter proved to be effective in improving the quality of the images during the experiments performed. The hybrid algorithm may be of great use in imaging modalities like low-field MRI that are associated with low SNR.
Enhancing African indigenous knowledge collection management in Ugandan public university libraries: lived experiences of senior library staff
(IGI Global, 2023) Rugambwa, Nina Olivia; Akena, Francis Adyanga; Nabutto, Claire Clement Lutaaya; Bugembe, Kamulegeya Grace
Various studies in library and information science have emphasized that indigenous knowledge management is still a neglected area and a challenge in the discipline of information management. However, the rationale for this neglect and driving challenges in university libraries has not been documented from the practitioner's perspective. This chapter shares lived experiences from experienced senior staff of public University libraries in Uganda regarding the management of African Indigenous knowledge collections. The study uses the theoretical lens of Wilson's information behavior model interpolated with participants' views to gain insight into the perspectives of the practitioners. The findings revealed challenges in lack of appropriate metadata descriptors to accommodate this knowledge, biased knowledge organization tools that are incompatible with African indigenous knowledge metadata characteristics, and limited funding in university libraries for research and indigenous knowledge collection development.
Enhancing the monitoring and evaluation of road construction projects using expert opinion: A case of Uganda national roads authority
(International Journal of Industrial Management, 2026-03-26) Kamukama, Ismail; Wadembere, Ismail; Ssebuggwaawo, Denis
Road transport is among the sub-sectors that receive the highest funding in Uganda. Nevertheless, there has been a persistent public outcry on delays, low-quality deliveries, and even project failures in different parts of the country. Existing studies have attributed this to inefficient monitoring and evaluation (M&E) of road construction projects, which remains underexplored at the local scale. Therefore, the purpose of this study was to enhance the M&E of road construction projects in Uganda by establishing key factors of the exercise. Initial key M&E factors were identified through a literature review, and the Delphi technique was later employed to determine the experts’ levels of agreement towards these factors using measures of central tendency, such as mean, standard deviation, and coefficient of variation. The levels of consensus among experts were further confirmed by Kendall’s W, and the relative importance index finally revealed key M&E factors in road construction. The findings are crucial to support planning and decision-making across all stages of road construction projects in Uganda and the execution of targeted interventions in M&E exercises during project implementation. This study can be expanded in the future by focusing on the development of regression modelling, spatial modelling, and machine learning to predict the success and failure of M&E in road construction projects.
An ensemble model based on learning vector quantization algorithms for early detection of cassava diseases using spectral data
(SpringerLink, 2023-03) Emmanuel, Ahishakiye; Waweru, Mwangi; Petronilla, Murithi; Ruth, Wario; Fredrick, Kanobe; Taremwa, Danison
In Sub-Saharan Africa, cassava is the second most significant food crop after maize. Cassava brown streak disease (CBSD) and cassava mosaic virus disease (CMD) combined account for nearly 90% of productivity losses. Automating the detection and classification of crop diseases could help professionals diagnose diseases more accurately and allow farmers in remote locations to monitor their crops without the help of specialists. Machine learning algorithms have been used in the early detection and classification of crop diseases. Previous research has used plant image data captured with smartphones. However, disease symptoms must be observable to use this strategy (using image data). Unfortunately, once symptoms appear on the aerial part of the plant, the root, which is the edible part of the plant, is destroyed. In this study, we used spectral data in a three-class classification challenge for diagnosing cassava diseases. We propose an ensemble model based on Generalized Learning Vector Quantization (GLVQ), Generalized Matrix LVQ (GMLVQ), and Local Generalized Matrix LVQ (LGMLVQ). Experimental results revealed that the LGMLVQ model had the best overall performance on the precision, recall, and F1-score followed by our proposed ensemble model, the GMLVQ model performed third, and finally GLVQ model. Also, using an accuracy performance metric, LGMLVQ had overfitting issues even though it had the highest accuracy of 100%, followed by our proposed ensemble model with an accuracy of 82%, and then the third in performance was the GMLVQ model with an accuracy of 74% and the least performed model on accuracy was GLVQ model with an accuracy of 56%.
Evaluation of Information literacy training for enhanced teaching, learning, and research competence for academic staff and students at the University of Rwanda: A descriptive mixed-method study
(Qualitative and Quantitative Methods in Libraries, 2024-07-09) Namuleme, Robinah Kalemeera; Umutesi, Annonciatte
This study evaluates the effectiveness of Information Literacy Training (ILT) for academic staff and postgraduate students in the digital era. A descriptive mixed-method approach was used, with data collected from 87 postgraduate students, academic staff, and librarians from nine Campuses across the University of Rwanda. The results showed that providing ILT at the beginning of student’s study program significantly enhanced their capacity to identify, access, evaluate, and use information effectively. It also improved students’ competencies in research and scholarly publishing. The study highlights the importance of ILT evaluation in training, providing critical insights into program effectiveness, efficiency, and long-term impact. It recommends ILT as a mandatory component in the curriculum for all students. Keywords: Information Literacy, Critical thinking, Reference Management, Digital literacy, Literacy proficiency.

Browse

Browsing School of Computing and Information Science by Title