Mpho Muloiwa

Dr. Mpho Muloiwa


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 December 2024 in CivilEng
Verified
Journal Article
Open access
PDF file
ADAdekunle Olorunlowo David
Adekunle Olorunlowo David
JNJULIUS MUSYOKA NDAMBUKI
JULIUS MUSYOKA NDAMBUKI
MMMpho Muloiwa
Mpho Muloiwa
WKWilliams Kehinde Kupolati
Williams Kehinde Kupolati
JSJacques Snyman
Jacques Snyman
A fresh paradigm for classifying current studies on flood management systems is proposed in this review. The literature has examined methods for managing different flood management activities from a variety of fields, such as machine learning, image processing, data analysis, and remote sensing. Prediction, detection, mapping, evacuation, and relief efforts are all part of flood management. This can be improved by adopting state-of-the-art tools and technology. Preventing floods and ensuring a prompt response after floods is crucial to ensuring the lowest number of fatalities as well as minimizing environmental and financial damages. The following noteworthy research questions are addressed by the framework: (1) What are the main methods used in flood control? (2) Which stages of flood management are the majority of research currently in existence focused on? (3) Which systems are being suggested to address issues with flood control? (4) In the literature, what are the research gaps regarding the use of technology for flood management? To classify the many technologies that have been studied, a framework for classification has been provided for flood management. It was found that there were few hybrid models for flood control that combined machine learning and image processing. Furthermore, it was discovered that there was little use of machine learning-based techniques in the aftermath of a disaster. To provide efficient and comprehensive disaster management, future efforts must concentrate on integrating image processing methods, machine learning technologies, and the understanding of disaster management across all phases. The study has proposed the use of Generative Artificial Intelligence.

29 August 2025 in E3S Web of Conferences
Verified
Conference Paper
Open access
PDF file
MMMpho Muloiwa
Mpho Muloiwa
JNJulius Musyoka Ndambuki
Julius Musyoka Ndambuki
LMLusiwe Zamokuhle Maduna
Lusiwe Zamokuhle Maduna
DCDumisani Thomas Chabalala
Dumisani Thomas Chabalala
Municipalities’ most commonly applied wastewater treatment technology is the conventional activated sludge process (ASP). The challenge is that the ASP consumes high levels of electric power, which results in high electric energy consumption. The power consumption can be attributed to the air blowers/pumps that function non-stop to supply oxygen for the survival of microorganisms in the ASP. This study proposes optimizing electric pump power consumption in the ASP. Multilayer perceptron (MLP) Artificial Neural Network (ANN) algorithm was used to develop the pump power consumption optimization model. Particle Swarm Optimization (PSO) algorithm was applied to optimize the electric pump power consumption. The PSO algorithm output an optimal solution of 0.057396 kW after performing 1000 iterations. The percentage difference between the measured electric pump power consumption (0.087 kW) in the ASP and the optimized electric pump power consumption (0.057396 kW) was 34.03%. This significant difference implies that the PSO algorithm performance was satisfactory in optimizing the electric pump power consumption.

4 October 2021 in African Journal of Science, Technology, Innovation and Development
Verified
Journal Article
Closed access
MMMpho Muloiwa
Mpho Muloiwa
MDM. O. Dinka
M. O. Dinka
Stephen Nyende-ByakikaStephen Nyende-Byakika
Stephen Nyende-Byakika
The aim of the paper was to analyze factors affecting domestic water consumption in Thohoyandou, Limpopo province, South Africa. A structured questionnaire was used to collect qualitative and quantitative data in the study area. A total sample of 100 households participated in answering the questionnaire. The results of the analysis found that average bath water consumption was 122 l/c/d, toilet flushing was 26 l/c/d, drinking and food preparation was 20 l/c/d, washing clothes was 5 l/c/d, washing cars was 2.5 l/c/d and home gardening was 6 l/c/d. The average water consumption of one household in the area was 190 l/c/d. Factors influencing water consumption in Thohoyandou were: education level of household head, age of household head, occupation of household head, gender of household head, family size, and tariff. SPSS performed correlation matrix and it was used to analyze factors affecting water consumption. Correlation matrix results showed that education level of household head was −0.627**, family size was 0.947**, tariff was 0.533**, female household heads was 0.647**, male household heads was (−0.634**), and age of household heads was (0.372**). Education level of household head results showed a negative correlation in all sub areas. The consequences of having more household heads with a low level of education was high water consumption, which is not in line with the Water Conservation Act. The contribution of the research was that household heads who have a high level of education typically consume less water than household heads who have a low level of education.

26 May 2026 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
AOAyodeji Okubanjo
Ayodeji Okubanjo
IOIgnatius Kema Okakwu
Ignatius Kema Okakwu
ADAdekunle Olorunlowo David
Adekunle Olorunlowo David
JNJULIUS MUSYOKA NDAMBUKI
JULIUS MUSYOKA NDAMBUKI
JSJacques Snyman
Jacques Snyman
MMMpho Muloiwa
Mpho Muloiwa
The electrification of public transport, particularly Bus Rapid Transits (BRT), is a significant step toward achieving sustainable urban mobility and reducing dependency on fossil fuels. However, rapid adoption of Electric Vehicles Smart Charging (EVSC) infrastructure presents grid stability, economic and environmental concerns. The rising demand for electric cars, particularly in developing nations such as Nigeria, highlights the urgent need for a sustainable hybrid renewable energy charging infrastructure for BRT systems. This study presents a techno-economic assessment of an off-grid hybrid systems that use photovoltaic (PV), wind turbines (WTs), hydrogen (H2), fuel cell (FC) and battery technologies to power Electric Vehicles Smart Charging within Bus Rapid Transits networks. The Lagos BRT charging system at City Mall Station (CMS) serves as a case study, with hourly renewable resources obtained from National Aeronautics and Space Administration database (NASA). Using the HOMER pro-optimization tool, a multi-criteria analysis is performed to evaluate system viability, with special focus on key metrics such as levelized cost of energy (LCOE), net present cost (NPC), renewable energy fraction (REF), and greenhouse gas (GHG) emissions. The simulation results demonstrate that the hybrid PV/wind/FC/battery configuration is exceptionally economical, with an LCOE as low as $0.222/kWh, $2.03M NPC, 51.3% REF, and 159,209 kg of carbon dioxide emissions per year compared to grid-dependent charging. The study shows that integrated renewable-hydrogen systems are not only financially feasible, but also provide significant insights for policymakers, transportation authorities, and energy planners seeking to accelerate the transition to green public transportation infrastructure through innovative hybrid energy schemes.