Final year projects (Baccalaureus Theses) (Industrial Engineering)

Permanent URI for this collection

https://scholar.sun.ac.za/handle/10019.1/17402

Browse

Browsing Final year projects (Baccalaureus Theses) (Industrial Engineering) by browse.metadata.advisor "Visser, T."

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Estimating the threat of water scarcity in the Breede River Valley : a forecast-based analysis
    (Stellenbosch : Stellenbosch University, 2011-11) Bester, Stephanie Elizabeth; Visser, T.; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Water is a scarce resource in South Africa and especially in the Western Cape. It is, therefore, vital to manage it properly. There are a number of factors that make the task of managing water difficult. Climate change is one of these factors. It cannot be controlled and holds much uncertainty. In order to provide information for managers to plan water supply and demand in the in the Breede Water Management Area (WMA) effectively, the objective of this study is to forecast possible high, normal and low water demand and supply scenarios (Chapter 4). Furthermore this study will inform managers on the extent of the threat of the expected water scarcity occurring in the Breede River Valley through the scenarios. It was seen that all scenarios indicate shortfalls within the forecasting period of 20 years. In the best case scenario, which is already severe, water shortages will occur 12 years from now. In the worst case scenario water shortages will occur within 6 years from now. These results show that planners and developers are afforded a lead time of approximately 6 years to affect the required interventions. One possible solution involves building dams in the mountain ranges to exploit the catchment areas. The idea is that gravity fed water will be supplied to farmers from these dams – nullifying the necessity to draw irrigation water from the Breede River. It is recommended that further studies must be done to determine the feasibility and the environmental impact of interventions to reduce the expected water scarcity in the Breede River Valley.
  • Thumbnail Image
    Item
    Evaluating railway safety by observing the current condition of level crossings in the Western Cape
    (Stellenbosch : Stellenbosch University, 2011-12) Malan, Ilse; Visser, T.; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Annually a number of fatal accidents occur at level crossings in South Africa. It is assumed that these kinds of accidents could be avoided if the road and rail systems and intersections are managed properly. This final year project evaluates railway safety by observing the current condition of level crossings in the Western Cape. The goal of this study is to identify contributing factors that increase the likelihood of an injury occurring in a collision between a vehicle and a train. Once the factors have been identified plans of action can be developed to strive to decrease level crossing collisions from occurring. This could save numerous lives and lots of money. The research problem at hand is to try and determine why this class of accidents occur and to indicate how management can be improved to reduce the number of incidents annually. Accident data was collected from the Western Cape area between the period 1999 and 2010. A correlation study was performed on the different contributing variables. Logistical regression was used with the occurrence of an injury set as dependent variable. Variables that influence the occurrence of an injury was identified as day of the week, time of the day, good visibility, type of road and type of vehicle. Stellenbosch’s biggest level crossing was evaluated against the South African Traffic Road Signs Manual (Brain, 1999). It was found that the level crossing met the standards that were set by the South African Department of Transport. Then a case study of one accident was done to determine the reason for the accident. Driver error was found to be the main cause of the accident. A survey study was done to determine whether people are making errors due to lack of knowledge. The study indicated that people do not know what to do at level crossings. Furthermore it was found that the South African driving test is out-dated and failing at educating drivers. The recommendation at hand is to restructure South Africa’s driver tests. A new more advanced test should be developed. Proper driver education is necessary to increase safety at level crossings. The interim solution would be to put up traffic lights at level crossings.
  • Thumbnail Image
    Item
    Managerial support for an optometry practice : a business analytics study
    (Stellenbosch : Stellenbosch University, 2011-12) Kotze, Melandi; Visser, T.; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: The South African optometry industry has limited literature available regarding the ideal management of optometry practices. This makes it difficult for optometry practices to evaluate their performance in order to make better informed decisions for the future of their practice. According to other studies done on the South African optometry industry, optometry practice management is not initially included in the optometry post graduate or undergraduate programs. Therefore managerial skills and knowledge in most optometry practices is very limited. This report studied a specific optometry practice that strives for better business management in order to breakeven as soon as possible and to become profitable. The approach to the project was to evaluate the practice’s performance in comparison with the industry benchmarks that is available. The industry benchmarks are United States based, but can be used as a good approximation of the South African industry, seeing as literature was found to support this assumption. It was found that the practice is performing well in terms of the industry benchmarks, but certain areas were identified where there is improvement potential. These areas were analysed in more detail in order to generate possible solutions that could possibly improve the management procedures and processes used in the optometry practice. It was found that the major setback for the practice is the lack of clients in general and specifically contact lens clients. When the client base expands the revenue will increase. This report provides recommendations to aid the management procedures in the practice in order to attract more clients and to ultimately become profitable.
  • Thumbnail Image
    Item
    Paving the way for the use of prediction modelling in a health care environment
    (Stellenbosch : Stellenbosch University, 2011-10) Van Zyl, Ilse; Van Dyk, L.; Visser, T.; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: The high cost of hospitalisation is a challenge for many health insurance companies, governments and individuals alike. In 2006, studies concluded that well over $30 billion was spent on unnecessary hospitalisations in the United States of America, where unnecessary hospitalisations are those that could have been prevented through early patient diagnosis and treatment. Undoubtedly, there is room for improvement in this regard and it can be agreed that where lives are at stake, prevention is always better than cure; successful hospitalisation prediction may make hospitalisation prevention a realistic possibility. The Heritage Provider Network, a health insurance and health care provider and sponsor of the Heritage Health Prize (HHP) Competition, have come to realise the potential benefits that a hospitalisation prediction model could effect (Heritage Provider Network Health Prize, 2011). The competition is aimed at producing an effective hospitalisation prediction patient admissions algorithm (PPAA) to predict the amount of days a member will be hospitalised in the next period using health insurance claims data of the current period. The goal is to ultimately prevent the unnecessary hospitalisation of identified members in their network. If successful this could have many benefits to the wider society including fewer critical medical cases, fewer claims and consequently lower expenses for all stakeholders in the affected system. The competition serves as inspiration for this study which aims to pave the way for the research team who will be developing such a PPAA. This was accomplished by providing insights and identifying possible pitfalls in the development of a Predictive Patient Admission Algorithm (PPAA) using the Heritage Health Prize case study as a reference. Typically available hospitalisation data that serves as input for the PPAA are briefly described, together with recommendations on methods and technologies with which to extract, transform and load (ETL) data within this context. A list of contender techniques was assembled based on the given data, the algorithm’s expected input requirements and the techniques’ ability to meet these needs. The prediction modelling techniques reviewed include classification and regression trees (CART), multivariate adaptive regression splines (MARS), neural networks and ensemble methods. Techniques were compared in terms of a set of criteria needed to use the available data and give the desired outputs. Page iv The data mining technologies considered to model with the preferred technique include Statistica data miner, SPSS Clementine, SAS Enterprise Miner, Matlab, Excel with VBA and R. These technologies were also compared on how well they can model available data with the contender techniques. The research team’s compatibility with technologies was also considered. Recommendations concerning the prediction modelling technique was using ensemble methods and the choice of technology for ETL was SQL Server and for prediction model building recommendations are Statistica, R or Matlab. Experimentation was conducted with selected CART, MARS and the Random Forests techniques in the available technologies in order to support future prediction modelling decisions of the research team. It was concluded that the included predictor variables do not have sufficient predictive power for the use of CART, MARS and Neural Networks and that Random Forests deliver more favourable results and it was recommended that this modelling should be explored further for the use of the HHP application.