School of Computing and Information Science
Permanent URI for this communityhttp://localhost:4000/handle/20.500.12504/206
Browse
Browsing School of Computing and Information Science by Issue Date
Now showing 1 - 20 of 29
- Results Per Page
- Sort Options
Item 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, JamesModification 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.Item A secure web based records management system for prisons: a case of Kisoro prison in Uganda(International journal of computer, 2017) Emmanuel, Ahishakiye; Danison, Taremwa; Elisha, Opiyo OmuloMost Prisons in the developing countries are still using the traditional system – pen and papers, to keep track of their records. This system takes long to finish a single transaction; this has led to loss of information of some cases (crimes files), insecurity and data redundancy. Similarly, some cases have been reported where some prison staff connives with clients (victims) to change and hide some information or files hence leading to compromising the evidence of the matter. This has consequently resulted in time wastage to handle cases, increased corruption and insecurity of important files hence making the whole process costly. Also when reports are needed especially about prisoners, it takes a long time and therefore makes it hard for Prison Management to take urgent decisions. This has created a lot of loopholes in the system because there is no tracking and/or monitoring of the information available in the different Departments and there are no security measures in place to safe guard the available information. This necessitated automating the system to make it more efficient and effective. There was close study of the existing manual file based system that was in use, it was compared to the proposed system. A prototype of a proposed system was developed to ease data access, security and retrieval for instant report production by the prison management. The prototype was developed using MySql database, PHP, CSS, JavaScript and HTML.Item Perspectives on university library automation and national development in Uganda(IFLA Journal, 2017-06-05) Buwule, Robert S.; Ponelis, Shana R.Academic libraries in universities store large volumes of research that can be used for development purposes to support teaching, learning, research, innovation, community outreach and partnerships. Library automation incorporates the adoption of integrated library systems. Effective adoption of an integrated library system enables broad-based access to global and local knowledge sources to solve local, regional and national development challenges. Using a sequential mixed methods approach in a case study of a Ugandan public university, Kyambogo University, this study investigated the perceptions of librarians, information workers and other university stakeholders with respect to library automation and the contribution thereof to national development. The results confirmed that the integrated library system improved library operations and played an important role in supporting national development. This study also highlights the continued challenges of adopting an integrated library system in developing countries such as Uganda, which, if addressed, could further improve information service delivery for a nation’s socio-economic transformation.Item 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, AhishakiyeKnowledge 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.Item Evaluation of requirements for the design of water resource management ICT model for integrated water resources management: the case of management of lake Victoria basin(IEEE, 2020-05-18) Odongtoo, Godfrey; Lating, Peter O.; Ssebugwawo, DenisThe paper addresses the use of partial least square-structural equation modelling (PLS- SEM) technique to evaluate the requirements for a design of a water resource management (ICT) model for an integrated water resource management. Researchers employed a quantitative approach using smart-PLS version 3. The sample size of 152 was computed from a population size of 245 across some districts within LVB. This study revealed the perceptions of different experts based on their experiences in water resource sectors. The findings of the study discovered that distribution and management, efficient use, pollution reduction, water conservation & storage factors had a significantly positive effect on the design of an effective water resource management ICT model. Pollution reduction had the highest path coefficient (beta=0.536) thus having the highest influence on the design of water resource management ICT model. The four exogenous latent constructs wholesomely explained 65.2% of the variance in the design of an effective water resource management ICT model that was also confirmed by the value of R 2 being 0.652. The study recommends putting a special attention on a pollution reduction related requirement to achieve an effective design of water resource management ICT model. These findings can support practitioners and decision makers engaged in the management of LVB and other water bodies in designing an effective water resource management ICT model.Item Prediction of cervical cancer basing on risk factors using ensemble learning(IEEE, 2020-05-22) Ahishakiye, Emmanuel; Wario, Ruth; Mwangi, Waweru; Taremwa, DanisonCervical 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 used an ensemble learning technique in the prediction of cervical cancer using risk factors. This technique was selected because it combines several machine learning techniques into one model to decrease variance, bias, and improvement in performance. K-Nearest Neighbor, Classification and Regression Trees, Naïve Bayes Classifier, and Support Vector Machine. Classification methods were selected because the interest of this study was to solve a classification problem. Therefore these algorithms could work well within our problem domain. The final prediction model was trained and validated, and our experimental results revealed that our model had an accuracy of 87.21%.Item 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, ObungolochBackground 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.Item A survey on deep learning in medical image reconstruction(Elsevier, 2021-03) Emmanuel, Ahishakiye; Martin, Bastiaan Van Gijzen; Julius, Tumwiine; Ruth, Wario; Johnes, ObungolochMedical image reconstruction aims to acquire high-quality medical images for clinical usage at minimal cost and risk to the patients. Deep learning and its applications in medical imaging, especially in image reconstruction have received considerable attention in the literature in recent years. This study reviews records obtained elec- tronically through the leading scientific databases (Magnetic Resonance Imaging journal, Google Scholar, Scopus, Science Direct, Elsevier, and from other journal publications) searched using three sets of keywords: (1) Deep learning, image reconstruction, medical imaging; (2) Medical imaging, Deep learning, Image reconstruction; (3) Open science, Open imaging data, Open software. The articles reviewed revealed that deep learning-based re- construction methods improve the quality of reconstructed images qualitatively and quantitatively. However, deep learning techniques are generally computationally expensive, require large amounts of training datasets, lack decent theory to explain why the algorithms work, and have issues of generalization and robustness. The challenge of lack of enough training datasets is currently being addressed by using transfer learning techniques.Item Misinformation, indigenous health information and HIV prevention among in- school adolescents, Uganda(DigitalCommons@University of Nebraska - Lincoln Library Philosophy and Practice (e-journal), 2021-06) Olivia, Rugambwa Nina; Ruth, Nalumaga; Ikoja-Odongo, J.R; Otim, Onapa MaxwellHIV/AIDS is still a major killer disease among adolescents in sub- Saharan Africa and Uganda in particular. There are many factors attributed to high HIV infections among young people in Uganda such as, multiple sexual partners, low condom use, those born with HIV and poverty. High level misinformation in the indigenous knowledge related to sexuality and HIV prevention remains an under investigated and under documented factor escalating the disease. Yet, the indigenous knowledge health information system is a major critical information source adolescents depend on for health information on HIV prevention in Uganda. Indigenous knowledge informs health interventions for HIV prevention among young people in many African communities and is relied on for decision making on health choices. This paper documents indigenous knowledge on practices for HIV prevention among secondary school adolescents in an urban context in Kampala District. A qualitative case study research design was employed. The findings revealed use of witchcraft, local herbs, male circumcision, elongation of labia menorah, abstinence, sexual taboos like not having sex with women in their menstrual periods and avoiding homosexuality as the key indigenous management practices for HIV prevention. Some of the findings were in agreement with existing biomedical information on prevention strategies while others were in contradiction. The findings also revealed that adolescents have a lot of misinformation on HIV prevention; such information may not support right healthy choices. The study contributes to the body of existing knowledge on HIV prevention using indigenous knowledge practices. The findings appeal to information science professionals to participate in ensuring that communities they serve have access to accurate and timely information to curb health emergencies and improve on health of societies they serve.Item 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, ObungolochCurrently, 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.Item Comparative Performance of Machine Leaning Algorithms in Prediction of Cervical Cancer(IEEE xplore, 2021-10) Emmanuel, Ahishakiye; Waweru, Mwangi; Petronilla, Muthoni; Lawrence, Nderu; Ruth, WarioCervical 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.Item Blockchain technology needs for sustainable mineral supply chains: A framework for responsible sourcing of Cobalt.(Elsevier, 2022) Godfrey, Mugurusi; Emmanuel, AhishakiyeBlockchain 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.Item 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, KanobeCassava 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.Item A system dynamics approach to support strategic planning for sustainable paved-road infrastructure management in Uganda(International Journal of Construction Engineering and Management, 2022) Godfrey, Luyimbazi; Christopher, NtwatwaSustainable transport infrastructure and services contribute significantly to the rate of economic growth and improvement of a country's standard of living; and also critical to a country’s competitiveness and ability to harness its regional and globalization potential. However, unlike in the developed economies where a holistic approach is applied for strategic planning and management for sustainable construction and maintenance of the paved-road network, a good number of developing economies where this approach is not applied are challenged on sustainable transport infrastructure development and management. This study aimed at providing a system dynamics model to support holistic strategic planning for sustainable paved-road infrastructure construction and maintenance management with Uganda as a case study. Using secondary data, the study developed a model capable of predicting the behaviour of such a system. The study suggested a number of recommendations most importantly the need to experiment the envisaged system beforehand and base on lessons learnt to make informed decisions and formulate appropriate policies and legislation before actual strategy implemItem Tacit knowledge management system practices in higher education institutions (HEIs) in developing economies: a systematic literature review(London journal of research in humanities and social sciences, 2022) Godfrey, Luyimbazi; Annabella, Habinka EjiriThis study sought to investigate the factors that influenced tacit knowledge retention and management in higher education institutions in developing economies as well as the extant tacit knowledge management systems applied/used in higher education institutions in developing economies. The penultimate aim of this research was to serve as an affirmative study whose findings shall serve as input to developing a model for tacit knowledge management in HEIs. Papers were searched from Elsevier, Emerald Insight, and ProQuest databases. The systematic protocol combined ideas presented by Jesson, Matheson and Lacey; as well as ideas by Nunes, McPherson, Annansingh, Bashir and Patterson. The latter suggested the following steps: 1. Identification of keywords; 2. Production of search queries; 3. Definition of inclusion and exclusion criteria 4. Identification of relevant databases; 5. Query of databases and selection of relevant documents; 6. Analysis of the dataset selected. The term ‘tacit knowledge’ generated 41,810 articles. 23 articles fitted the inclusion criteria. Causes for tacit knowledge loss from HEIs in low-developed economies included: death, burnout, uncertainty, mistrust in the institution, early retirement, and flaws in extant tacit knowledge management systems and processes. Various TKM frameworks in various contexts have been tried. Few were found to specifically address TKM in HEIs. Essential factors were: individual/personal factors, institutional environment factors, institutional management practice factors; and factors relating to institutional culture. Systems that were employed to manage tacit knowledge in HEIs were found to be piecemeal. The study thus highlights the status of TKM in HEIs in developing economies.Item 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, DenisChurn 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.Item 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 GraceVarious 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.Item Research data management readiness at Uganda cancer institute(Library Philosophy and Practice (e-journal)., 2023) Mukiibi, Edward; Bukirwa, JoyceThe study explored research data management readiness at the Uganda Cancer Institute. Its objectives were to; establish the state of research data and the institutional readiness for research data management practices. The case study applied a survey method using a questionnaire modified from the Data Asset Framework and the Community Capability Model Framework. The respondents were 60 staff members at different professional levels purposively selected. The findings show massive data generated from clinical trials, and routine cancer clinics at the institute. The business processes are mainly manual except for the funded research projects which are hybrid. The existing data sets could not be quantified, but all patient-related physical data are permanently archived in the institute’s registry. The electronic research data from funded projects is under the responsibility of the System Administrator and the Data Officers of respective projects. Research data management readiness assessed through collaborations was taking place and beneficial to the institute, and the technical infrastructure was robust. Findings indicate the absence of an institute-wide legal/policy framework and a substantive skills training program for staff research data management competence development. Research data management practices were intuitively executed in funded projects, the ethical requirements were embedded in the research cycle and adhered to. The study recommended emphasizing a written localised Data Management Plan for all projects submitted for approval; initiating a tailor-made RDM training program; a comprehensive RDM policy, and creating RDM awareness and interest among staff at the institute.Item 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, DanisonIn 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%.Item 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, TaremwaIn 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.