Electronic Theses and Dissertations (Masters)
Permanent URI for this collectionhttps://hdl.handle.net/10539/37972
Browse
12 results
Search Results
Item Prediction of Water Hyacinth Coverage on Hartbeespoort Dam(University of the Witwatersrand, Johannesburg, 2024) de Gouveia, Claudia D. Camacho; Bührmann, Doctor JokeWater hyacinth is an invasive weed contributing to Hartbeespoort Dam’s poor water quality. Although biological control is the most effective and sustainable method of controlling water hyacinth, the dam has unfavourable conditions for agents that the weed thrives in. Literature uses mathematical models and remote sensing to theorise growth rates or estimate coverage. However, prediction could prove beneficial as planning biological control is essential to its success. Hence, a model to predict water hyacinth coverage was developed. This research simplified the complex relationships involved in water hyacinth growth to focus on the most influential factors: temperature and nutrients. Missing data were imputed using multiple k-nearest neighbours. Nutrient datasets had limited data, thus five scenarios were developed to extrapolate datasets, using Monte Carlo simulation and seasonal patterns. The features were used to build ensemble, decision tree, artificial neural network and support vector machine models. Ensemble using the bagging method was the best model resulting in a root mean square error of 4.01 for water hyacinth coverage predictions from 1 June 2018 to 1 May 2019.Item e-Commerce adoption in South African SMMEs(University of the Witwatersrand, Johannesburg, 2024) Mathe, Barney; Sunjka, BernadetteIn this research study e-Commerce adoption in Small, Medium and Micro enterprises (SMMEs) in South Africa was studied. The purpose of this study was to determine the factors that constitute for a successful implementation of the e-Commerce strategy and compare this to the adoption of e- Commerce in SMMEs. The study evaluated frameworks/standards for successful e-Commerce implementation and with this evaluation a consolidated conceptual framework for the successful implementation of e-Commerce was developed. Through samples of both SMME and successful/most visited platforms, functionality and performance assessments of the platforms were conducted using the Jaccard similarity method, and time and method study. T-tests and ANOVA were conducted for performance assessments, to assess if there was a significant difference in performance between SMME and successful e-Commerce sites. Through these assessments it was found that there is a clear gap in adoption from both a functionality and performance perspective, 6 out of 7 of the successful sites had advanced to the last stage of adoption while only one SMME platform reached the last stage which is an external integration stage of the developed framework.Item Inventory Management using Artificial Intelligence(University of the Witwatersrand, Johannesburg, 2024) Garg, Arnav; Smith, Bevan; Rich, WilliamPoor inventory management negatively affects a company’s profits. Too little stock limits potential sales and customer satisfaction while too much stock increases storage costs and potential damage. Company X distributes butter in a multi-echelon supply chain consisting of multiple entities such as a manufacturing plant, distribution centre and retailers before reaching the customer. For every 1% of the demand that is not met, revenue in excess of R18 million is lost per year. This study aims to use machine learning methods (supervised and reinforcement learning) for optimal decision making that maximizes profits. Supervised learning methods (random forest, recurrent neural network and support vector machines) were used to forecast the demand based on historical data. Thereafter, deep reinforcement learning (DRL) was used to train an agent to decide when and how much to order over a period of a year. Various algorithms (PPO and DDPG) and unique reward functions were tested and the performance was compared to a benchmark heuristic that stocks inventory based on a sum of the forecasted demand. The random forest algorithm performed the best at predicting the forecasted demand. The DRL model using a continuous action and state space together with the DDPG algorithm and a reward function based on a combination of the current profit, order fulfilment rate, units available and units unsatisfied performed the best. The DDPG algorithm outperformed the PPO algorithm with the DDPG model being able to provide a 21% increase in net profit over the benchmark heuristic when the production and warehouse facilities of the supply chain were merged. The DRL models were not able to provide a higher order fulfilment rate compared to the benchmark heuristic but they were able to provide better asset utilization by sending full trucks and minimizing the inventory held to maximize the profitability in the supply chain. The results suggest that RL has potential of better handling the stochastic constraints (demand and lead times) in real supply chains to automate the ordering process. It was found that increasing the order fulfilment rate does not necessarily lead to higher profits and the reward function has a significant effect on the net profit which can be further optimized in the future.Item Systems approach to improve utilisation of autonomous drilling at an open pit mine in South Africa(University of the Witwatersrand, Johannesburg, 2024) Talane, Tabotabo; Botha, AndriesMining companies have opportunities to feed the continuously growing global economy. However, these opportunities come with challenges. Technologies like drilling automation can help combat these challenges while improving operational efficiency. Although the importance of investing in technology is well appreciated, mining houses still struggle with the sustainable and effective use of introduced technologies. This study looks at the challenges faced by one of the open pit mines in South Africa. The case study mine has introduced ADS (autonomous drilling system) to aid in improving both health and safety, and operational efficiency, but utilisation of the system remains low. The aim of this study is to investigate potential causes of the problem and to come up with an actionable solution to tackle the challenges faced and improve the use of ADS. Six semi-structured interviews were conducted where experts in the field of autonomous drilling shared their insights into factors affecting the adoption of ADS. The interview data were recorded, transcribed and analysed using thematic content analysis. The analysis of the interview data yields seven themes: stakeholder engagement and buy-in; management support and trust; process management and KPIs (key performance indicators); ownership, accountability and influence; site capability; culture and attitude shift; and implementation approach. Using the systems approach and soft systems methodologies (SSM), the study found that effective stakeholder engagement and communication with workers early in the project can lead to a positive attitude towards the introduced system, improving its adoption. Further, management support becomes vital to build trust and team resilience, especially during challenging times. Additionally, the way of managing processes must evolve and adapt to accommodate the technology system introduced, and this requires a mindset shift from a leadership perspective. Operating standards and procedures of the entire drilling process, from planning to execution, also need to evolve with the introduction of technology to ensure that upstream processes become enablers of the effective use of the technology. Like standards and procedures, key performance indicators are those metrics that managers track, and they also need to be updated to allow accountability and ownership around the use of technologies like ADS. With commitment and drive from operational leaders, technology implementation can succeed. The correct implementation approach will increase the chances of success. The approach must be guided by an effective stakeholder engagement and requirements analysis. A proper approach in tandem with both management support and team commitment can result in the sustainable adoption of new technologies, including ADS.Item An Investigation Into The Propulsive Force Generation Of Multiple Flapping Surfaces(University of the Witwatersrand, Johannesburg, 2024) Mabvuu, Never; Ho, WeihuaThe aerodynamic performance of flapping NACA0012 airfoils was analyzed through numerical simulation, focusing on the effects of stagger, gap, phase difference, and the number of airfoils. The simulation was conducted under specific conditions: 𝑈∞ = 0.2𝑚/𝑠, f=2Hz, 𝛼0=200, C=0.04m, St=0.2 and Re= 8000). The problem was modeled in ANSYS Fluent using a transient viscous approach with absolute velocity formulation, employing the pressure-based coupled solver (PBCS). PRESTO! interpolation and second-order upwind discretization were applied for pressure, momentum, intermittency, turbulent kinetic energy, and specific dissipation rate. Mesh validation and independence studies confirmed that the results were driven by the physics setup, independent of mesh configuration. It was discovered that small stagger and gap at φ=1800 is not good for thrust production as the airfoils produced thrust less than a single airfoil with ∆Ctav = -0.94. However, lift production is increased and ∆Clav =1.2. At larger spacing ∆Ct, ∆Cl and η generally become constant. One of the worst performing cases (X=1.0C;Y=0.5C; ϕ= 1800 ) was improved by making the aft airfoil lead ( φ= -450 ). This explains why insects alter φ or frequency depending on the situation and flight requirements. The most effective X-Y- ϕ were found to be the ones at which flow separation is suppressed. For the 4 airfoils cases the fore pair performed better than the aft pair for the small spacing case. When spacing was increased the aft pair performed better than the aft pair.Item Factors influencing innovation in public healthcare in South Africa: A critical analysis(University of the Witwatersrand, Johannesburg, 2024) Nkosi, Mbali Rosemary; Siriram, RajenlallHealthcare innovation has proven to reduce morbidity and mortality rates by enhancing healthcare delivery. Most of the South African population depends on the public healthcare system for health needs. The morbidity and mortality rates in South Africa are much higher compared to other middle-income countries in the world. To enhance healthcare delivery in South Africa, understanding the factors that influence innovation in public healthcare is important. Therefore, this research aims to provide a comprehensive understanding of the factors influencing innovation in public healthcare in South Africa and the potential impact of innovation on the country's healthcare system. The main objectives of this study are to determine the level of successfully implemented innovation in public healthcare and the factors influencing it. Existing literature identifies several factors that influence innovation in public healthcare, including design empathy, technological infrastructure, decision-makers, human capital, and organisational culture. This study also investigates the readiness of the public health sector to embrace innovation and the strategies in place for implementing innovation in public healthcare. A gap was identified in the existing literature. There is evidence in literature is that healthcare innovation centres in South Africa and their impact on the adoption of innovation in public healthcare were only covered marginally by existing literature. To bridge this gap, this study provides results on the status of suitable research and development hubs for testing healthcare innovation prototypes in South Africa and their impact on the adoption of innovation in public healthcare. Currently, there are limited health innovation centres in South Africa. This study posits that an increase in the number of healthcare innovation centres would increase evidence-based innovation which would increase the uptake of innovation in public healthcare. A qualitative research approach was used to acquire descriptive information on the factors that influence innovation in healthcare through interviewing participants. Semi-structured interviews were used as the primary instruments of data collection. The interviews were then subjected to a thematic analysis. One of the significant findings of this research is that the lack of funding in public healthcare hinders innovation in the public healthcare system. Also, the rigorous regulatory requirements pertaining to healthcare innovation tend to cause uncertainty and delays, which in turn reduces the funding available for innovative projeItem An investigation of factors contributing to long waiting of patients collecting repeat medication in a tertiary hospital pharmacy(University of the Witwatersrand, Johannesburg, 2022) Oladipupo, Rekgopetse Victoria; Sunjka, B.According to the World Health Organization (WHO) patient waiting time is identified as a key measurement to a responsive healthcare service and is an important indicator of quality of services offered by hospitals (NDoH, 2011) as it affects the patient’s responsiveness to the services received (NDoH, 2011; SA FAM PRACTICE, 2008; Tegabu, 2008; Pandit et, al. 2016). Long waiting times at healthcare facilities undermines the services rendered resulting in compromised or unfulfilled patient care (Afolabi & Erhun, 2003). This research studies the processes associated with the collection of repeat medication in a tertiary hospital pharmacy in order to identify value adding activities and non-value adding activities that could be impacting patient waiting time using the Lean thinking concept of driving out waste. A qualitative observational method was therefore employed to observe all the steps involved during the journey of the patient collecting repeat medication from the registration point until medication was issued at the pharmacy. Value stream mapping (one of Lean Thinking principle) was employed to analyze the processes that took place. Patient waiting time was also measured from the registration point to the pharmacy. On average patients had to wait a total 159 minutes before they could access services both at the registration point (67 minutes) and at pharmacy (92 minutes). The service time was 29 minutes at both registration point (11 minutes) and pharmacy (18 minutes). Of the 18 minutes pharmacy service time; eight minutes were found to be value-adding while 10 minutes were non-value-adding mainly due to prescriptions waiting on queue to be picked, waiting to be signed by the pharmacist and waiting to be issued out to the patient. Lack of a dedicated pharmacy service points exclusively for chronic repeat patients, manual dispensing, illegible doctor’s prescriptions, were found to prolong the time it takes the Pharmacist to complete a prescription. Post Basic Pharmacist Assistants performing duties that could be performed by a less qualified staff (e.g., Learner Basic Pharmacist Assistants) during peak hours was not value adding and thus decreasing productivity. The level of staff commitment in addressing issues of quality such as long waiting time was questionable. The demand / workload and capacity during the early hours of business at the registration point did not seem to match, thus resulting in bottlenecks at the patient registration point and throughout the system.Item The Development and Application of a Hybrid Metaheuristic Clustering Algorithm to the Capacitated Vehicle Routing Problem(University of the Witwatersrand, Johannesburg, 2023-11) de Sousa, Andrea Vaz; Bührmann, JokeThe Vehicle Routing Problem (VRP) is an important combinatorial optimization problem in the field of operations research that remains a significant challenge for distribution and logistics operations globally. This research is concerned with a relatively simple variation of the VRP referred to as the Capacitated Vehicle Routing Problem (CVRP), and it focuses on the integration of metaheuristics into its solution. A Genetic Algorithm (GA) was selected and integrated into several CVRP solutions with various configurations of the algorithm. Additionally, a hybrid implementation was proposed, which augments the GA by incorporating conventional heuristics to seed the initial population with “good” solutions. The proposed hybrid solution was the best performing solution evaluated and yielded results comparable to the best-known solution for the smaller datasets. However, the solution quality with respect to the best known solutions decreased with an increase in the size of the problem. This may be attributed to premature termination of the algorithm. Overall, the solutions evaluated were not able to match the best-known solution for each dataset, however successive improvements in the results suggest that GAs are effective at solving the CVRP. Moreover, combining metaheuristics with other methods is also an effective strategy for improving the efficiency of the solution space exploration.Item An Investigation of Factors Contributing to Long Waiting of Patients Collecting Repeat Medication in a Tertiary Hospital Pharmacy(University of the Witwatersrand, Johannesburg, 2023-02) Oladipupo, Rekgopetse Victoria; Hattingh, Teresa; Sunjka, BernadetteAccording to the World Health Organization (WHO) patient waiting time is identified as a key measurement to a responsive healthcare service and is an important indicator of quality of services offered by hospitals (NDoH, 2011) as it affects the patient’s responsiveness to the services received (NDoH, 2011; SA FAM PRACTICE, 2008; Tegabu, 2008; Pandit et, al. 2016). Long waiting times at healthcare facilities undermines the services rendered resulting in compromised or unfulfilled patient care (Afolabi & Erhun, 2003). This research studies the processes associated with the collection of repeat medication in a tertiary hospital pharmacy in order to identify value adding activities and non-value adding activities that could be impacting patient waiting time using the Lean thinking concept of driving out waste. A qualitative observational method was therefore employed to observe all the steps involved during the journey of the patient collecting repeat medication from the registration point until medication was issued at the pharmacy. Value stream mapping (one of Lean Thinking principle) was employed to analyze the processes that took place. Patient waiting time was also measured from the registration point to the pharmacy. On average patients had to wait a total 159 minutes before they could access services both at the registration point (67 minutes) and at pharmacy (92 minutes). The service time was 29 minutes at both registration point (11 minutes) and pharmacy (18 minutes). Of the 18 minutes pharmacy service time; eight minutes were found to be value-adding while 10 minutes were non-value-adding mainly due to prescriptions waiting on queue to be picked, waiting to be signed by the pharmacist and waiting to be issued out to the patient. Lack of a dedicated pharmacy service points exclusively for chronic repeat patients, manual dispensing, illegible doctor’s prescriptions, were found to prolong the time it takes the Pharmacist to complete a prescription. Post Basic Pharmacist Assistants performing duties that could be performed by a less qualified staff (e.g., Learner Basic Pharmacist Assistants) during peak hours was not value adding and thus decreasing productivity. The level of staff commitment in addressing issues of quality such as long waiting time was questionable. The demand / workload and capacity during the early hours of business at the registration point did not seem to match, thus resulting in bottlenecks at the patient registration point and throughout the system.Item Provision of personal protective equipment and sanitary facilities to female construction site workers(University of the Witwatersrand, Johannesburg, 2023-09) Nene, Simphiwe; Ozumba, Obinna; Sunjika, BernadetteThe study was based on an aspect of social justice, namely gender equality in the workplace for the female workers who work on construction sites. The area covered in this study was the health and safety of women in construction in the form of the provision of personal protective equipment (PPE) and sanitary facilities to female workers. This specific focus is largely overlooked. The study explored, female workers’ (end-user) perceptions and experiences on the provisions of sanitary and personal protective equipment through a qualitative approach. The main source of data collection was through semi-structured interviews and further supported with site observations in order to triangulate the interview responses. The results of the study found that the availability of PPE for females in the construction industry has improved as women are provided with female size PPE. However, quality and advanced gender sensitive PPE still needs attention. Sanitary facilities at established sites are generally up to standard. However, female workers still share these facilities with their male counter parts. Sanitary facilities at unestablished sites still need attention.