Masters Degrees (Industrial Engineering)
Permanent URI for this collection
Browse
Recent Submissions
- ItemReinforcement learning for algorithmic day trading on the Johannesburg Stock Exchange(Stellenbosch : Stellenbosch University, 2023-02) Richards, Nicole; Eldon, Burger; Thorsten, Schmidt-Dumont; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.ENGLISH ABSTRACT: Given the rapidly advancing capabilities of modern computers, there has been a considerable increase in interest in algorithmic trading. From reducing trading latency by purchasing highly sought-after property as close to stock exchanges as possible, to conducting research on the capabilities of the most recent artificial intelligence algorithms on the stock markets, market participants and academic researchers are all looking for innovative methods to achieve maximum returns with minimum risk. In this thesis, a reinforcement learning approach is adopted to determine the capabilities of such algorithms, along with a suitable neural network architecture, to make day trading decisions. A reinforcement learning agent learns through a process of trial-and-error. The agent performs various actions in order to determine which actions yield rewards, which reinforce desirable behaviour. The capacity of reinforcement learning algorithms to improve their decision-making over time through self-learning makes them naturally suitable for algorithmic trading. During the experiments conducted for this thesis, the reinforcement learning agents were trained and tested on the Johannesburg Stock Exchange. A day trading approach is taken, which means positions are never kept overnight, in an e ort to reduce trading risk. Furthermore, the available computational power is proposed as a limiting factor to determine the capabilities of such a reinforcement learning trading approach in a personal capacity when no special computational facilities are available. Various experiments are conducted to determine the impact of di erent reward functions, neural network architectures, and reinforcement learning algorithms on the reinforcement learning agents' day trading performance in terms of pro tability and risk. Additionally, hyperparameter optimisation is performed, which yields improved performance across all reinforcement learning agents. Certain inputs and reward functions are better suited to the default reinforcement learning algorithm parameters, and hyperparameter optimisation of the reinforcement learning algorithm parameters is required to make fair comparisons between the di erent reward functions and algorithms. When the number of stocks available on the Johannesburg Stock Exchange environment is increased, the nal account value that the reinforcement learning agent achieved also increased. The computational power limited the number of stocks that could be available within the Johannesburg Stock Exchange environment, but the results of this thesis serve as a proof-of-concept of reinforcement learning for algorithmic trading on the Johannesburg Stock Exchange.
- ItemInnovation for inclusive development: an agent-based and system dynamics modelling approach to technology adoption in marginalised communities.(Stellenbosch : Stellenbosch University, 2023-03) Venter, Michal Barend; Grobbelaar, SaraENGLISH ABSTRACT: Innovation has been described as a key driver of economic growth. Traditional forms of innovation, however, generally focus on macro-level economic growth and often fail to include marginalised communities. This has been argued to exacerbate inequality within society. The concept of Innovation for Inclusive Development (I4ID) builds on the innovation systems literature and aims to address the shortcomings of traditional innovation systems towards marginalised communities. I4ID aims to improve the socio-economic status of marginalised communities by involving them in the innovation process. The literature on I4ID has matured over recent years, but formal modelling has thus far lagged the theoretical advancements. This thesis aims to address this gap by developing a formal model of a project that introduces an innovation to a marginalised community using the I4ID literature. The conceptual foundation of the formal model was formed by combining various technology adoption models to ensure the requirements of I4ID were met. Roger’s Diffusion of Innovation (DOI) theory was used as a basis for the conceptual model. A key component of the DOI is the innovation-decision process which details various stages an individual progresses through over time as they make their adoption decision. These stages are qualitatively described in the DOI. The Decomposed-Theory of Planned Behaviour (DTPB) was incorporated to quantify the innovation-decision process with thresholds of an individual's specific belief structures (as described in the DTPB). Further, the Concerns-Based Adoption Model was incorporated to focus the innovation-decision process detailed in the DOI on the local needs and demands of the marginalised community. Finally, a hybrid-model, using system dynamics and agent-based modelling, was selected as an appropriate modelling technique to capture the macro-level system processes and the micro-level analysis of actors in a marginalised community. The developed model, the Technology Adoption Model for Marginalised Communities (TAMMAC), is intended to provide a quantitative method of identifying the critical leverage points to ensure an innovation is successfully introduced to a marginalised community. The Creation of Legitimacy function was selected to indicate whether adoption occurred successfully. This decision meant that adoption was not considered as the mere use of an innovation but rather as the positive and meaningful impact of an innovation through its use and integration within a community. Adopting this legitimacy perspective aligns with the I4ID goal of improving the socio-economic status of marginalised communities. A formal model was developed to apply the TAMMAC to the ICT for Education (ICT4E) case study. The ICT4E project aimed to improve teaching and learning in rural schools by introducing tablets. The developed model indicated that the project’s initial implementation did not foster enough legitimacy in the tablets to ensure a sustainable outcome. Several scenarios were developed to identify effective interventions to ensure the legitimization of the tablets. The key interventions identified centred around ensuring technology availability and restructuring the training offered. The TAMMAC answered calls from researchers to modify existing adoption models to be more suited for an I4ID context. Integrating system dynamics and agent-based modelling allows for a macro-level analysis of larger processes in a system and a micro-level analysis of the marginalised community. Interventions that promote the legitimacy of an innovation may be determined by analysing the decomposed belief structures of the community. However, it is recommended that future research explores ways to strengthen the measure of legitimacy in the TAMMAC and incorporate the influence of an individual’s innovativeness on their adoption-decision process.
- ItemA systems engineering approach : the application of lean thinking to support sustainability transitions in healthcare.(Stellenbosch : Stellenbosch University, 2023-02) Cromhout, Bianca; De Kock, Prof Imke; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.ENGLISH ABSTRACT: Sustainable healthcare systems have become increasingly difficult to achieve because of the large amount of competition in the healthcare industry. The healthcare industry needs to move away from the current situation to deliver higher quality, full-access, affordable, and sustainable healthcare services. The status quo of sustainability transitions in healthcare is currently lacking in drivers which support the socio-technical transition to increased sustainable states. Sustainability in healthcare is a relatively novel concept, but it contributes to solving some of the increasing challenges faced in the healthcare industry. By increasing the economic-, social-, and environmental sustainability in healthcare systems, a significant amount of waste can be eliminated while achieving the sustainable development goals set out by the United Nations to be met by 2030. Lean implementations in healthcare systems have proven difficult because the improvements are not maintained, and the system tends to return to its previous unsustainable and non-lean system state. Thus, healthcare systems, as socio-technical systems, are deemed unsustainable. Socio-technical transitions in healthcare systems have increasingly been analysed to understand how they can be designed to increase sustainability and thus assist in achieving sustainable development goals. Given this global sustainability challenge in healthcare systems, it is deemed necessary to develop methods and approaches to ease the transition process to more sustainable system states. Lean thinking and sustainability are interconnected regarding their objectives and aims in system processes. Therefore, incorporating lean thinking into sustainability transitions can strengthen the value creation of system processes by efficiently allocating and consuming resources while ensuring waste elimination during system processes. Thus, this research aims to use lean thinking to support the progression of sustainability transitions in relation to healthcare systems. Literature has proven that lean implementation is a strong driver for increased sustainability. Thus, implementing lean thinking into sustainability transitions strengthens the sustainability transition. This is achieved by developing the lean thinking for sustainability transitions in healthcare (LT4STHC) framework, which uses the author’s developed methodology and LT4ST index to determine which lean thinking approaches or principles could be used to address specific aspects of sustainability transitions in relation to healthcare systems. These aspects include but are not limited to landscape tensions, regime stresses, niche pressures, transition weaknesses, and transition failures. The developed framework, methodology, and index were evaluated in three ways. The framework, methodology, and index were assessed against the requirement specifications for its development. The self-assessment demonstrated that the framework, methodology, and index met the stipulated requirement specifications for its development. Interviews were conducted with subject matter experts (SMEs) in lean, healthcare, or sustainability and sustainability transitions. SMEs verified the theoretical accuracy and tenability of the framework, methodology, and index content. The SMEs were requested to complete questionnaires. A further evaluation of the developed framework, methodology, and index was conducted through a practical application in the form of a case study. Finally, the case study application of the framework, methodology, and index demonstrated its applicability, practicability, and usability. The LT4STHC framework, methodology, and LT4ST index achieved the intended goal of implementing lean thinking approaches and principles into sustainability transitions to support its progression towards an even greater sustainable state. The overall evaluation of the framework, methodology, and index demonstrates that the developed research products achieve the stated research aim and provide assertion to using lean thinking to support sustainability transitions in healthcare.
- ItemDevelopment of a comprehensive product lifecycle based on data of smart factories and smart products.(Stellenbosch : Stellenbosch University, 2023-02) Schnabel, Benedikt; von Leipzig, Konrad; Hummel, Prof. Dr.-Ing. Vera; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.ENGLISH ABSTRACT: Trends of customisability and innovation in products influence the way companies develop products. Customers want products that meet their individual requirements through a high degree of customisation. Mass customisation was created to meet this demand. With mass customisation product diversity increases and product generations are changed more frequently. This often results in higher costs since the product engineering process is not familiar with Trends of customisability and innovation in products influence the way companies develop products. Customers want products that meet their individual requirements through a high degree of customisation. Mass customisation was created to meet this demand. With mass customisation product diversity increases and product generations are changed more frequently. This often results in higher costs since the product engineering process is not familiar with the new product types. From the companies' point of view, this situation is complicated by the trend that product development processes are being shortened, and companies need to get their products to market faster. This forces companies to develop more complex products in more complex environments and to bring them to market quicker. Also, current product lifecycles consider only one product generation and no product diversity. More- over, product engineering and the subsequent phases are often separated from each other. Due to this silo working, knowledge cannot be transferred further, mistakes are made repeatedly, and product engineering teams cannot use the feedback from smart factories and smart products. For this reason, potentials offered by the use of smart factory and smart product data for smart, customisable product families are not being exploited in current product lifecycles. To exploit the potentials, a novel prod- uct lifecycle i2PLM is created in this thesis. A mixed literature review is used to evaluate current product lifecycles and to create a reference process. Also, challenges and cause-and-effect relation- ships are identified in the overall context of the product lifecycle. The findings result in defining data streams and relevant data in a product lifecycle. The data streams and relevant data are incorporated into the reference process, creating a novel product lifecycle called i2PLM. The i2PLM consists of six components. The different components provide, among other things, an overview of the main phases of a product lifecycle and the current status of the product portfolio. One of the components represents the organisational processes and another the business processes. The core component of i2PLM is the product lifecycle database, which enables the implementation of data generation and analysis with its processes. The i2PLM is validated within the scope of an experiment. The validation takes place in an industrial research environment at the University of Reutlingen. The content of the experiment is the development of a smart product variant based on production and use data. Further research is recommended for the applicability and implementation methods of i2PLM in business practice, as well as for the automatic generation of cause-and-effect relationships. h the new product types. From the companies' point of view, this situation is complicated by the trend that product development processes are being shortened, and companies need to get their products to market faster. This forces companies to develop more complex products in more complex environments and to bring them to market quicker. Also, current product lifecycles consider only one product generation and no product diversity. More- over, product engineering and the subsequent phases are often separated from each other. Due to this silo working, knowledge cannot be transferred further, mistakes are made repeatedly, and product engineering teams cannot use the feedback from smart factories and smart products. For this reason, potentials offered by the use of smart factory and smart product data for smart, customisable product families are not being exploited in current product lifecycles. To exploit the potentials, a novel product lifecycle i2PLM is created in this thesis. A mixed literature review is used to evaluate current product lifecycles and to create a reference process. Also, challenges and cause-and-effect relation- ships are identified in the overall context of the product lifecycle. The findings result in defining data streams and relevant data in a product lifecycle. The data streams and relevant data are incorporated into the reference process, creating a novel product lifecycle called i2PLM. The i2PLM consists of six components. The different components provide, among other things, an overview of the main phases of a product lifecycle and the current status of the product portfolio. One of the components represents the organisational processes and another the business processes. The core component of i2PLM is the product lifecycle database, which enables the implementation of data generation and analysis with its processes. The i2PLM is validated within the scope of an experiment. The validation takes place in an industrial research environment at the University of Reutlingen. The content of the experiment is the development of a smart product variant based on production and use data. Further research is recommended for the applicability and implementation methods of i2PLM in business practice, as well as for the automatic generation of cause-and-effect relationships.
- ItemA business model innovation framework for establishing successful product-service systems(Stellenbosch : Stellenbosch University, 2023-03) van Zyl, Frederick Jacobus van Eeden; Schutte, Corne; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.ENGLISH ABSTRACT: It is widely agreed among scholars and practitioners that innovation is imperative for any business to obtain a sustainable competitive advantage. A business model underlies a firm’s architecture and is the rationale of how an organisation creates and delivers value for customers. Business Model Innovation (BMI), where value is created by making simultaneous changes to an organisation’s value proposition and underlying operating model, is an excellent way to remain competitive. However, attempts to apply this often fail. Implementing a new innovative business model has much uncertainty, but it needs not to be risky if the correct structure is provided. Product-Service Systems (PSS) are business models that provide cohesive delivery of tangible products and intangible services that provide value in use as it more adequately satisfies customer needs. A PSS promotes the notion of buying a hole instead of buying a drill, where satisfaction is sold rather than a product. It seems that BMI literature does not currently focus on adopting a PSS from a BMI perspective. The problem is that research lacks the merging of PSS and BMI streams. This thesis includes a thorough literature review of reputable business model frameworks, BMI frameworks, innovation frameworks, and PSS frameworks. The fundamental business model constitutional elements, design principles, paramount BMI process stages, and high-level innovation phases described within the literature were extracted to generate framework design requirements. This thesis undertook the challenge of developing a comprehensive and holistic BMI framework for establishing a PSS. The generic framework will help innovators navigate the blurry process of innovating their business model to establish a self-sustainable PSS business model.