Faculty of Engineering and Technology

Permanent URI for this community

https://bdears.busitema.ac.ug/handle/123456789/2

Browse

Now showing 1 - 20 of 218

4 pupils electrocuted as concerns grow over power theft in Sironko
(Daily Monitor, 2018-05-01) Kitunzi, Yahudu
Most victims either touch live wires or attempt to tap power directly from the high voltage lines overhead.
48 irrigation schemes constructed, 30 in pipeline
(New Vision, 2018-05-18) Tenywa, Gerald; Amamukirori, Betty
The Ministry of Water and Environment is constructing 48 new small and big irrigation schemes in order to increase food security and resilience against climate change impacts.
A crusader for sustainable energy
(New Vision, 2018-04-04) Rwothungeyo, Billy
"Hydrogen obtained from water will be the dominant fuel for most of our energy needs", Dr.Masa.
A field-based recommender system for crop disease detection using machine learning
(Frontiers in Artificial Intelligence, 2023) Omara, Jonathan; Talavera, Estefania; Otim, Daniel; Turcza, Dan; Ofumbi, Emmanuel; Owomugisha, Godliver
This study investigates crop disease monitoring with real-time information feedback to smallholder farmers. Proper crop disease diagnosis tools and information about agricultural practices are key to growth and development in the agricultural sector. The research was piloted in a rural community of smallholder farmers having 100 farmers participating in a system that performs diagnosis on cassava diseases and provides advisory recommendation services with real-time information. Here, we present a field-based recommendation system that provides real-time feedback on crop disease diagnosis. Our recommender system is based on question–answer pairs, and it is built using machine learning and natural language processing techniques. We study and experiment with various algorithms that are considered state-of-the-art in the field. The best performance is achieved with the sentence BERT model (RetBERT), which obtains a BLEU score of 50.8%, which we think is limited by the limited amount of available data. The application tool integrates both online and online services since farmers come from remote areas where internet is limited. Success in this study will result in a large trial to validate its applicability for use in alleviating the food security problem in sub-Saharan Africa. KEYWORDS Crop disease monitoring, recommendation systems, natural language processing, smart farming, question-answer pairs, food security
A Hybrid Modflow-Machine Learning Approach for Groundwater Prospecting and Optimal Borehole Siting
(Busitema University, 2026) Ouma, Hassan Masinde
This report presents the role of a hybrid MODFLOW-Machine Learning (ML) approach in predicting groundwater potential and optimizing borehole siting in the Awoja Catchment in eastern Uganda. Groundwater remains the primary source of safe water for rural communities in Uganda; however, its exploration and development are often hindered by limited hydrogeological data and the use of conventional methods that inadequately capture subsurface variability. The study integrates the physically based MODFLOW groundwater flow model with data-driven ML algorithms, including Random Forest, Support Vector Machine, Artificial Neural Networks, and XGBoost to form a hybrid framework capable of enhancing groundwater prospecting accuracy. Hydrogeological, geological, soil, and climatic datasets were utilized to simulate aquifer conditions, generate hydraulic parameters, and train predictive models. Model performance was evaluated using statistical indicators such as the Coefficient of Determination (R²), Root Mean Square Error (RMSE), and Nash-Sutcliffe Efficiency (NSE). The hybrid model demonstrates superior predictive accuracy compared to standalone ML approaches, effectively delineating high-yielding aquifer zones and identifying optimal borehole locations. The findings provide a framework that supports efficient groundwater exploration, minimizes drilling failure rates, and promotes sustainable groundwater management. This study directly contributes to Sustainable Development Goal 6 (SDG 6) on clean water and sanitation and aligns with Uganda’s Third National Development Plan (NDPIII), which prioritizes reliable and sustainable groundwater utilization for socio-economic development.
A labeled spectral dataset with cassava disease occurrences using virus titre determination protocol
(Elsevier, 2023) Owomugisha, Godliver; Nakatumba-Nabende, Joyce; Dhikusooka, Joshua Jeremy; Taravera, Estefania; Nuwamanya, Ephraim; Mwebaze, Ernest
In this work, we present a novel dataset composed of spectral data and images of cassava crops with and without diseases. Together with the description of the dataset, we describe the protocol to collect such data in a controlled environment and in an open field where pests are not controlled. Crop disease diagnosis has been done in the past through the analysis of plant images taken with a smartphone camera. However, in some cases, disease symptoms are not visible. Furthermore, for some cassava diseases, once symptoms have manifested on the aerial part of the plant, the root which is the edible part of the plant has been totally destroyed. The goal of collecting this multimodality of the crop disease is early intervention, following the hypothesis that diseased crops without visible symptoms can be detected using spectral information. We collected visible and near-infrared spectra captured from leaves infected with two common cassava diseases namely; Cassava Brown Streak Disease and Cassava Mosaic Disease, as well as from healthy plants. Together, we also captured leaf imagery data that corresponds to the spectral information. In our experiments, biochemical data is collected and taken as the ground truth. Finally, agricultural experts provided a disease score per plant leaf from 1 to 5, 1 representing healthy and 5 severely diseased. The process of disease monitoring and data collection took 19 and 15 consecutive weeks for screen house and open ﬁeld, respectively, until disease symptoms were visibly seen by the human eye. Keywords: Spectral data protocol, Cassava diseases, Crop diagnosis, Smart agriculture, Early disease detection
A light spectrometer device for crop disease monitoring
(ICLR, 2023) Dhikusooka, J Joshua; Nuwamanya, Ephraim; Talavera, Estefania; Owomugisha, Godliver
Portable devices for the early detection of crop diseases are needed to support the farmers working in the field. Spectrometers showed their potential in the detection of crop diseases. However, high interpretation skills are needed to use the currently available spectrometers. In this project, we propose a portable device that obtains a spectrum wavelength of 700 nanometers describing the information of the crop. The output of this tool is integrated into a smartphone in the form of an app, making it accessible for use in the field in real applications.
A low-cost 3-D printed smartphone add-on spectrometer for diagnosis of crop diseases in field
(Association for Computing Machinery, 2020) Owomugisha, Godliver; Mugagga, K. B. Pius; Melchert, Friedrich; Mwebaze, Ernest; Quinn, A. John; Biehl, Michael
We present our initial proof of concept study towards the development of a low-cost 3-D printed smartphone add-on spectrometer. The study aimed at developing a cheap technology (less than 5USD) to be used for detection of crop diseases in the field using spectrometry. Previously, we experimented with the problem of disease diagnosis using an off-the-shelf and expensive spectrometer (approximately 1000 USD). However, in real world practice, this off-the-shelf device cannot be used by typical users (smallholder farmers). Therefore, the study presents a tool that is cheap and user friendly. We present preliminary results and identify requirements for a future version aiming at an accurate diagnostic technology to be used in the field before disease symptoms are visibly seen by the naked eye. Evaluation shows performance of the tool is better than random however below performance of an industry grade spectrometer. CCS CONCEPTS • Applied computing → Physical sciences and engineering; • Computing methodologies → Machine learning. KEYWORDS Low-cost, Spectrometery, Crop disease, Diagnosis, 3-D printed, Smartphone
Adaptive Thresholding of CNN Features for Maize Leaf Disease Classification and Severity Estimation
(MDPI, 2022) Mafukidze, Dzingai Harry; Owomugisha, Godliver; Otim, Daniel; Nechibvute, Action; Nyamhere, Cloud; Mazunga, Felix
Convolutional neural networks (CNNs) are the gold standard in the machine learning (ML) community. As a result, most of the recent studies have relied on CNNs, which have achieved higher accuracies compared with traditional machine learning approaches. From prior research, we learned that multi-class image classification models can solve leaf disease identification problems, and multi-label image classification models can solve leaf disease quantification problems (severity analysis). Historically, maize leaf disease severity analysis or quantification has always relied on domain knowledge—that is, experts evaluate the images and train the CNN models based on their knowledge. Here, we propose a unique system that achieves the same objective while excluding input from specialists. This avoids bias and does not rely on a “human in the loop model” for disease quantification. The advantages of the proposed system are many. Notably, the conventional system of maize leaf disease quantification is labor intensive, time-consuming and prone to errors since it lacks standardized diagnosis guidelines. In this work, we present an approach to quantify maize leaf disease based on adaptive thresholding. The experimental work of our study is in three parts. First, we train a wide variety of well-known deep learning models for maize leaf disease classification, then we compare the performance of the deep learning models and finally extract the class activation heatmaps from the prediction layers of the CNN models. Second, we develop an adaptive thresholding technique that automatically extracts the regions of interest from the class activation maps without any prior knowledge. Lastly, we use these regions of interest to estimate image leaf disease severity. Experimental results show that transfer learning approaches can classify maize leaf diseases with up to 99% accuracy. With a high quantification accuracy, our proposed adaptive thresholding method for CNN class activation maps can be a valuable contribution to quantifying maize leaf diseases without relying on domain knowledge. Keywords: CNN; transfer learning; class activation heatmap; adaptive thresholding
AfDB launches programme to grow Africa's textile industry
(Daily Monitor, 2017-10-18) Agencies
The African Development Bank ( AFDB) and its partners have launched a specialised training programme for entrepreneurs and startups in the textile, apparel and accessories (TA&A) sector in Africa.
American, Italian firm get refinery deal
(New Vision, 2018-04-04) Odyek, John; Mubiru, Apollo
The Government has signed an initial project framework agreement with a consortium of American and Italian firms to finance and construct the $4b (sh14.4 trillion) refinery in Hoima district. The first oil barrel is expected in 2020 and the refinery is a key element in the production of oil.
An Iot-driven patient vital monitoring and doctor alerting system for early health intervention.
(Busitema University, 2026) Turinawe, Richard; Nabirye, Barbra Bayuule
Access to timely health monitoring is limited in rural areas like Busia District, where patients with chronic conditions often face delays in diagnosis and treatment due to limited medical personnel, lack of diagnostic equipment, and unreliable internet connectivity. This project aims to develop a low-cost, IoT-driven wearable device capable of continuously monitoring essential vital signs, including heart rate, oxygen saturation (SpO₂), blood pressure and the body temperature. The system incorporates a real-time alert mechanism that notifies doctors or caregivers when abnormal readings occur, ensuring prompt intervention. Requirements for the system were identified through stakeholder consultations and literature review. A prototype wearable device was designed and integrated with Wi-Fi connectivity to support both online and offline operation, addressing rural infrastructure challenges. Field validation was conducted in local healthcare settings to evaluate accuracy, usability, and reliability. Results indicate that the device can effectively monitor patient vitals, provide timely alerts, and operate sustainably in low-resource environments. This system offers a practical solution to improve patient care, reduce preventable complications, and enhance health outcomes in rural communities.
Antimicrobial hand wipes from banana fibres.
(Busitema University, 2023) Kanene, Levi Brian
At the onset of the COVID-19 pandemic, one of the measures for combating the spread was the use of personal decontamination. Whereas sanitizing wipes are among the strategies for combatting COVID-19, there are growing concerns regarding their disposal, due to majority of them being made of non-biodegradable fibres. Additionally, some of the sanitizing solutions used have been found irritant, while some are carcinogenic. In this study, banana fibre wipes, impregnated with an organic antimicrobial formulation were developed as a sustainable alternative to synthetic fibre wipes and synthetic antimicrobial formulations. Banana fibres were extracted from banana pseudostem sheaths and alkali-treated at varying sodium hydroxide concentrations of 5 g/l – 20 g/l, varying temperatures of 85 0C to 105 0C under different immersion times of 60 min to 180 min. Other factors that were varied include the fibre length (20 mm – 40 mm) and the concentration of hydrogen peroxide (5 % v/v – 20 % v/v). Functional group analysis of the alkalitreated samples was done using the Fourier transform infrared (FTIR) spectroscopy. It was observed that during alkali treatment, the banana fibres undergo a loss of lignin and hemicellulose. Hydro-distillation was used to extract essential oils from the sap of Pinus caribaea var. hondurensis as a specie cited to possess antimicrobial activity. Phytochemical screening indicated that P. caribaea sap contains flavonoids and alkaloids. Extracts from lemon essential oil and cedar oil were equally studied and compared with oil from P. caribaea sap for antimicrobial efficacy. Assessment of the agar plates revealed that the P. caribaea extract did not show inhibitory activity to Escherichia coli (wild), E. coli (ATCC 25922), Staphylococcus aureus (wild), S. aureus (ATCC 25923), Pseudomonas aeruginosa (wild) and P. aeruginosa (ATCC 27853). However, essential oils from cedar and lemon showed inhibitory activity. From the Gas chromatography–mass spectrometry (GC-MS) analysis, oil obtained from P. caribaea sap was found to contain 23 bioactive compounds, with sabinene having the highest concentration of 34.24 % followed by βPinene (24.82%). A spunlaced non-woven fabric made from 100% banana fibres was impregnated with a commercial formulation containing essential oils from lemon, eucalyptus, cedar and orange. The antimicrobial efficacy test done on the impregnated wipe showed inhibitory activity against all the bacterial strains. Furthermore, the mechanical properties of the fabric showed that the tensile strength in the wet state increased by 4.29% and 20.414% in both the machine and cross directions respectively. Given that synthetic fibres are used in wipes to achieve a high wet tensile strength since most cellulosic fibres become weaker and disintegrate when wet, it can be concluded that banana fibres can be effectively used in wipes functionality given that they are biodegradable and are stronger when wet. From this study, there is need to carry out more studies on the dispersibility behaviour of the wet banana wipes and their rate of degradation during storage. Keywords: Sanitizing wipes, banana pseudostem, COVID-19, antimicrobial formulation, biodegradability, bio-based, nonwoven, plant extract
Antimicrobial potential of essential oil from Pinus caribaea var. hondurensis (P. caribaea) sap.
(Nature portfolios, 2025) Musinguzi, Alex; Kanene, Levi Brian; Kamalha, Edwin
The majority of hand sanitizers now in use include synthetic fragrances and chemical additives that pose substantial risks to human health and the environment. Ingredients like triclosan are linked to carcinogenesis, endocrine disruption, allergies, and antimicrobial resistance. This study aims to determine the constituents in pine (Pinus caribaea (P. caribaea) var. hondurensis sap and extract essential oil to be assessed for its bioactive components and antibacterial potential. Phytochemical screening of the sap was done using a qualitative method and the sap was found to contain flavonoids and alkaloids while tannins, anthraquinones and saponins were absent. Essential oil was obtained from the P. caribaea sap using the hydro-distillation process. In the GC–MS analysis that was carried out on the essential oil, it was found that the oil contained 23 bioactive compounds with the highest concentration being Sabinen (34.24%), β-Pinene (24.82%) and α-Thujene (11.5%). Other compounds such as Anethole, Linalool, Isolongifolol acetate, Camphene, Cyclopentene, γ-Terpinen, Fenchol, allo-Ocimene, Isopulegol, Levomenthol, Borneol, Citronellol, α-Longipinene and Caryophyllene were present in relatively small amounts. Assessment of the agar plates revealed that the essential oil did not show inhibitory activity to Escherichia coli (wild), E. coli (ATCC 25,922), Staphylococcus aureus (wild), S. aureus (ATCC 25,923), Pseudomonas aeruginosa (wild) and P. aeruginosa (ATCC 27,853). Whereas the essential oil did not show inhibitory activity, more studies should be carried out to evaluate the potential of essential oil from Pinus sap in the cosmetic and pharmaceutical sectors. Keywords: Antimicrobial formulation, Pnus caribaea sap
Application of data driven modelling in prediction of future climate change on the solar powered water pumping production.
(Busitema University, 2026) Mukasa, Robert
This study investigated the impact of climate change on the performance of photovoltaic (PV) solar powered water pumping systems (SPWPS) and future prediction of their performance, with the aim of: (i) identifying the key meteorological and technological parameters governing water yield; (ii) developing a validated predictive model linking meteorological variables to daily water yield; and (iii) simulating future water yield under Intergovernmental Panel on Climate Change (IPCC) climate projections. Historical meteorological data including solar irradiance, ambient temperature, relative humidity, wind speed, rainfall, and dust deposition index were analyzed alongside ten years of system performance data (2014–2023) using descriptive statistics, Principal Component Analysis (PCA), and Pearson correlation analysis to identify dominant influencing variables. Three data driven predictive models were developed and evaluated: Multiple Linear Regression (MLR), an Artificial Neural Network (ANN), and a Hybrid GRU-LSTM Recurrent Neural Network. The Hybrid GRU-LSTM model achieved the highest predictive accuracy (R² = 0.95, NSE = 0.94, RMSE = 0.31 m³/day), significantly outperforming MLR (R² = 0.71, NSE = 0.68) and the ANN (R² = 0.83, NSE = 0.81). PCA revealed that solar irradiance and ambient temperature together account for approximately 67% of total system performance variance. Sensitivity analysis confirmed solar irradiance (34.1%) and ambient temperature (21.3%) as the most influential model inputs. Future climate scenario simulations using IPCC SSP2-4.5 (moderate emissions) and SSP5-8.5 (high emissions) projections indicated projected declines in mean daily water yield of 6.7% and 13.6% respectively by 2050–2060, with reductions reaching 9.1% (SSP2-4.5) and 21.4% (SSP5-8.5) by 2070–2080. The largest losses are projected during the hot dry season (June–August), precisely when domestic water demand is highest, presenting a critical water security risk. The study recommends incorporating a 10–20% climate adjustment factor in future SPWPS design standards and establishing structured monitoring and maintenance frameworks aligned with projected climate trajectories
Application of Machine Learning to optimize Gold recovery during Cyanide Leaching at Wagagai gold mine
(Busitema University, 2026) Ayebale, Reyes
The cyanide leach process, also known as gold cyanidation, is a hydrometallurgical technique used to extract gold from low-grade ore, yet its efficiency is often compromised by the complex, non-linear interactions among various operational parameters (e.g., cyanide concentration, pH, leaching time, pulp density, and dissolved oxygen). Traditional optimization methods heavily rely on subjective operator experience, leading to suboptimal and inconsistent gold recovery rates.This study addressed this challenge by applying machine learning techniques to predict and optimize gold recovery during cyanide leaching at Wagagai Mining (U) Limited. A dataset of 2801 historical plant records was developed using key process variables, including cyanide concentration, pH, leaching time, pulp density, and dissolved oxygen. Three models including Multiple Linear Regression (MLR), Random Forest (RF), and Artificial Neural Network (ANN) were developed and evaluated using statistical performance metrics including the coefficient of determination (R²), Root Mean Square Error (RMSE), and Mean Squared Error (MSE). The results showed that the ANN model outperformed the others, achieving the highest predictive accuracy with an R² of 0.9444 and RMSE of 1.0209, compared to RF (R² = 0.9133) and MLR (R² = 0.8509). Hyperparameter optimization further improved ANN performance and confirmed that a single hidden layer with 10 neurons was optimal. The optimized ANN predicted a maximum gold recovery of 96.42% at a cyanide concentration of 800 mg/L, pH of 10.67, leaching time of 48 hours, pulp density of 35%, and dissolved oxygen of 12 mg/L. Partial Dependence Plots (PDPs) and sensitivity analysis were used to interpret the model, revealing that pulp density and cyanide concentration are the most influential variables affecting recovery, while pH and dissolved oxygen play significant but moderate roles. Sensitivity analysis revealed that pulp density (10.53) and cyanide concentration (8.004) were the most influential variables. The findings demonstrate that ANN-based models are effective tools for optimizing cyanide leaching and improving operational efficiency in gold mining.
Assessing required upgrades on electricity distribution network in Tororo to adopt e-mobility charging infrastructure : case study Town Ring 11Kv feeder.
(Busitema University, 2026-06-29) Opio, Paul; Okello, Oscar
Uganda's growing adoption of electric vehicles (EVs), driven by the National E-Mobility Strategy, presents both opportunities and challenges for the existing electricity distribution infrastructure. This study assesses the required upgrades on the electricity distribution network in Tororo to support e-mobility charging infrastructure, using the Town Ring 11 kV feeder supplied from Tororo Rock Substation as a case study. Primary data was collected through field visits, interviews with electric motorcycle operators from Spiro and Gogo, and site visits to battery swapping stations. Secondary data was obtained from the Uganda E-Mobility Report and MEMD publications. Energy demand was estimated using the formula E = N × S × Es, and EV growth was projected from a baseline of 300 electric motorcycles in 2025 to 4,000 by 2030, with electric cars growing from 0 to 50 over the same period. Network simulation was carried out under three scenarios: baseline with no EVs, 10% EV penetration, and 30% EV penetration. Results show that the feeder's peak demand of 1,820 kW already exceeds its thermal limit of 1,800 kW before any EV load is added. At 30% EV penetration, five out of eleven transformers enter overload conditions. The integration of EV charging infrastructure significantly reshapes the load profile, with the evening peak increasing from 1,820 kW to a projected total of 6,010 kW by 2030. The study recommends upgrading overloaded transformers, increasing cable capacity, and deploying smart charging strategies to shift EV demand to off-peak hours, ensuring reliable and stable grid operation as e-mobility adoption accelerates in Tororo.
Assisted evolution and geo-engineering.
(New Vision, 2018-01-01) Gwynne, Dyer
Whenever I get the chance, I go driving. The whole family are drivers, right down to the grand-children: it's one of the pretexts we use to get together. And we all know the coral reefs are drying. There are still healthy reefs, and even after they have been bleached they can recover- but only until the next time that sea temperatures rise beyond their tolerance range.
Automated hydroponic fodder growth chamber with live monitoring and AI mold detection.
(Busitema University, 2026-07) Kabwangu, Muhamed; Talemwa, Dickson
Livestock production heavily depends on the consistent availability of high quality fodder and hydroponic fodder systems have become a sustainable solution for efficient animal feed production. However, these systems are often affected by challenges such as mold contamination and the lack of continuous monitoring, which can reduce fodder quality and result in losses. Traditional manual inspection methods are time consuming, inconsistent and unable to provide real-time monitoring of system conditions. [1] This project presents the design and implementation of an Automated Hydroponic Fodder Grow Chamber with AI-Based Mold Detection and Real-Time Web Monitoring System to address these challenges. The system automates the monitoring of key environmental parameters such as temperature, humidity and pH level using sensors connected to a microcontroller. A camera-based Artificial Intelligence model was integrated to detect mold growth on hydroponically produced rice fodder. The AI model processes images frames using computer vision techniques and classifies the fodder as either healthy or mold-infected. The results are displayed in real time on a web-based dashboard together with sensor data for easy monitoring. The integration of automation, artificial intelligence and web technologies enables continuous monitoring, reduces manual inspection efforts and improves the accuracy and speed of detecting mold contamination. This leads to improved fodder quality, reduced losses and more efficient livestock feed production.
Biotechnology law a welcome devt.
(Daily Monitor, 2017-10-30) Nyanzi, Timothy Joseph
After several years of activism, consultative meetings and nationwide sensitisation of both policy makers and the public, the National Biotechnology and Biosafety Bill 2012 has finally been passed into law- the National Biosafety Act 2017. This is a great milestone for Uganda as a nation,

Browse

Browsing Faculty of Engineering and Technology by Title

Results Per Page

Sort Options