A distributed affective cognitive architecture for cooperative multi-agent learning systems
- Authors: Barnett, Tristan Darrell
- Date: 2012-11-02
- Subjects: Multiagent systems , Intelligent agents (Computer software) , Robotics , Cloud computing , Artificial intelligence , Machine learning
- Type: Thesis
- Identifier: uj:7317 , http://hdl.handle.net/10210/8055
- Description: M.Sc. (Computer Science) , General machine intelligence represents the principal ambition of artificial intelligence research: creating machines that readily adapt to their environment. Machine learning represents the driving force of adaptation in artificial intelligence. However, two pertinent dilemmas emerge from research into machine learning. Firstly, how do intelligent agents learn effectively in real-world environments, in which randomness, perceptual aliasing and dynamics complicate learning algorithms? Secondly, how can intelligent agents exchange knowledge and learn from one another without introducing mathematical anomalies that might impede on the effectiveness of the applied learning algorithms? In a robotic search and rescue scenario, for example, the control system of each robot must learn from its surroundings in a fast-changing and unpredictable environment while at the same time sharing its learned information with others. In well-understood problems, an intelligent agent that is capable of solving task-specific problems will suffice. The challenge behind complex environments comes from fact that agents must solve arbitrary problems (Kaelbling et al. 1996; Ryan 2008). General problem-solving abilities are hence necessary for intelligent agents in complex environments, such as robotic applications. Although specialized machine learning techniques and cognitive hierarchical planning and learning may be a suitable solution for general problem-solving, such techniques have not been extensively explored in the context of cooperative multi-agent learning. In particular, to the knowledge of the author, no cognitive architecture has been designed which can support knowledge-sharing or self-organisation in cooperative multi-agent learning systems. It is therefore social learning in real-world applications that forms the basis of the research presented in this dissertation. This research aims to develop a distributed cognitive architecture for cooperative multi-agent learning in complex environments. The proposed Multi-agent Learning through Distributed Adaptive Contextualization Distributed Cognitive Architecture for Multi-agent Learning (MALDAC) Architecture comprises a self-organising multi-agent system to address the communication constraints that the physical hardware imposes on the system. The individual agents of the system implement their own cognitive learning architecture. The proposed Context-based Adaptive Empathy-deliberation Agent (CAEDA) Architecture investigates the applicability of emotion, ‘consciousness’, embodiment and sociability in cognitive architecture design. Cloud computing is proposed as a method of service delivery for the learning system, in which the MALDAC Architecture governs multiple CAEDA-based agents. An implementation of the proposed architecture is applied to a simulated multi-robot system to best emulate real-world complexities. Analyses indicate favourable results for the cooperative learning capabilities of the proposed MALDAC and CAEDA architectures.
- Full Text:
- Authors: Barnett, Tristan Darrell
- Date: 2012-11-02
- Subjects: Multiagent systems , Intelligent agents (Computer software) , Robotics , Cloud computing , Artificial intelligence , Machine learning
- Type: Thesis
- Identifier: uj:7317 , http://hdl.handle.net/10210/8055
- Description: M.Sc. (Computer Science) , General machine intelligence represents the principal ambition of artificial intelligence research: creating machines that readily adapt to their environment. Machine learning represents the driving force of adaptation in artificial intelligence. However, two pertinent dilemmas emerge from research into machine learning. Firstly, how do intelligent agents learn effectively in real-world environments, in which randomness, perceptual aliasing and dynamics complicate learning algorithms? Secondly, how can intelligent agents exchange knowledge and learn from one another without introducing mathematical anomalies that might impede on the effectiveness of the applied learning algorithms? In a robotic search and rescue scenario, for example, the control system of each robot must learn from its surroundings in a fast-changing and unpredictable environment while at the same time sharing its learned information with others. In well-understood problems, an intelligent agent that is capable of solving task-specific problems will suffice. The challenge behind complex environments comes from fact that agents must solve arbitrary problems (Kaelbling et al. 1996; Ryan 2008). General problem-solving abilities are hence necessary for intelligent agents in complex environments, such as robotic applications. Although specialized machine learning techniques and cognitive hierarchical planning and learning may be a suitable solution for general problem-solving, such techniques have not been extensively explored in the context of cooperative multi-agent learning. In particular, to the knowledge of the author, no cognitive architecture has been designed which can support knowledge-sharing or self-organisation in cooperative multi-agent learning systems. It is therefore social learning in real-world applications that forms the basis of the research presented in this dissertation. This research aims to develop a distributed cognitive architecture for cooperative multi-agent learning in complex environments. The proposed Multi-agent Learning through Distributed Adaptive Contextualization Distributed Cognitive Architecture for Multi-agent Learning (MALDAC) Architecture comprises a self-organising multi-agent system to address the communication constraints that the physical hardware imposes on the system. The individual agents of the system implement their own cognitive learning architecture. The proposed Context-based Adaptive Empathy-deliberation Agent (CAEDA) Architecture investigates the applicability of emotion, ‘consciousness’, embodiment and sociability in cognitive architecture design. Cloud computing is proposed as a method of service delivery for the learning system, in which the MALDAC Architecture governs multiple CAEDA-based agents. An implementation of the proposed architecture is applied to a simulated multi-robot system to best emulate real-world complexities. Analyses indicate favourable results for the cooperative learning capabilities of the proposed MALDAC and CAEDA architectures.
- Full Text:
A hierarchy of random context grammars and automata
- Authors: Ehlers, Elizabeth Marie
- Date: 2014-04-03
- Subjects: Machine theory , Formal languages , Artificial intelligence
- Type: Thesis
- Identifier: uj:10501 , http://hdl.handle.net/10210/10004
- Description: Ph.D. (Computer Science) , Traditionally a formal language can be characterized in two ways: by a generative device (a grammar) and an acceptive device (an automaton). The characterization of two- and three-dimensional Random Context Grammars by two- and three-dimensional Random Context Automata are investigated. This thesis is an attempt to progressively extend a certain class of grammars to higher dimensions where the class of languages generated in each dimension is contained in the class of languages generated in the next higher dimension. Random Context Array Automata which characterizes Random Context Array Grammars (Von Solms [4,5]) are defined. The power of both Random Context Array Grammars and Random Context Array Automata is inherent in the fact that the replacement of symbols in figures is subject to horizontal, vertical and global context. A proof is given for the equivalence of the class of languages generated by Random Context Array Grammars and the class of languages accepted by Random Context Array Automata. The two-dimensional Random Context Array Grammars are extended to three dimensions. Random Context Structure Grammars generate three-dimensional structures. A characteristic of Random Context Structure Grammars is that the replacement of symbols in a structure is subject to seven relevant contexts. Random Context Structure Automata which characterize Random Context Structure Grammars are defined. It is shown that the class of languages generated by Random Context Structure Grammars are equivalent to the class of languages accepted by Random Context Array Automata...
- Full Text:
- Authors: Ehlers, Elizabeth Marie
- Date: 2014-04-03
- Subjects: Machine theory , Formal languages , Artificial intelligence
- Type: Thesis
- Identifier: uj:10501 , http://hdl.handle.net/10210/10004
- Description: Ph.D. (Computer Science) , Traditionally a formal language can be characterized in two ways: by a generative device (a grammar) and an acceptive device (an automaton). The characterization of two- and three-dimensional Random Context Grammars by two- and three-dimensional Random Context Automata are investigated. This thesis is an attempt to progressively extend a certain class of grammars to higher dimensions where the class of languages generated in each dimension is contained in the class of languages generated in the next higher dimension. Random Context Array Automata which characterizes Random Context Array Grammars (Von Solms [4,5]) are defined. The power of both Random Context Array Grammars and Random Context Array Automata is inherent in the fact that the replacement of symbols in figures is subject to horizontal, vertical and global context. A proof is given for the equivalence of the class of languages generated by Random Context Array Grammars and the class of languages accepted by Random Context Array Automata. The two-dimensional Random Context Array Grammars are extended to three dimensions. Random Context Structure Grammars generate three-dimensional structures. A characteristic of Random Context Structure Grammars is that the replacement of symbols in a structure is subject to seven relevant contexts. Random Context Structure Automata which characterize Random Context Structure Grammars are defined. It is shown that the class of languages generated by Random Context Structure Grammars are equivalent to the class of languages accepted by Random Context Array Automata...
- Full Text:
A modular agent-based communications framework for autonomous vehicles in a simulated urban environment
- Authors: Chhaya, Meraj Mohamed Anis
- Date: 2015
- Subjects: Autonomous vehicles , Automobiles - Automatic control , Intelligent agents (Computer software) , Multiagent systems , Artificial intelligence
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/84586 , uj:19239
- Description: Abstract: Autonomous vehicles, also known as self-driving cars, refer to vehicles that can travel on public roads to destinations with minimal to no interaction with human beings. These types of cars can respond to traffic-related incidents faster and more precisely than human beings, thus potentially reducing the number of traffic accidents, subsequent pedestrian injuries and even fatalities. Autonomous vehicles have been a major focus of artificial intelligence research over the past few years, with major developments being contributed to the industry by Google, Bosch, and leading companies in the automobile industry. The study presented in the dissertation explores the use of Intelligent Agents as a computer science abstraction that encapsulates the several components of an autonomous vehicle, in order to promote component modularity and to allow the inclusion of newer technologies that could further improve the effectiveness of autonomous vehicles. A particular recent advancement in the field of autonomous vehicles is the use of intervehicle communications, which supplements the array of sensors provided in the vehicles, in case of failure or inability to produce sufficient data that would be necessary for the vehicle to make a decision. The agent model proposed in the dissertation places a paramount importance on the communications mechanism, incorporating it in its agent architecture, in order to produce an autonomous vehicle model that is safer and more effective than current solutions. The autonomous vehicle agent model, given research constraints, was deployed in a simulated 3D urban traffic environment, where it was tested in a number of scenarios where a vehicle's sensors failed or provided insufficient data, preventing a safe journey for the vehicle's passengers, passengers of other vehicles and pedestrians in the simulated environment. The results of the tests demonstrated that an inter-vehicle communications mechanism, even with limited transmission range, effectively complements the existing modules of an autonomous vehicle, and is especially useful in case one of the modules fails. , M.Sc. (Information Technology)
- Full Text:
- Authors: Chhaya, Meraj Mohamed Anis
- Date: 2015
- Subjects: Autonomous vehicles , Automobiles - Automatic control , Intelligent agents (Computer software) , Multiagent systems , Artificial intelligence
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/84586 , uj:19239
- Description: Abstract: Autonomous vehicles, also known as self-driving cars, refer to vehicles that can travel on public roads to destinations with minimal to no interaction with human beings. These types of cars can respond to traffic-related incidents faster and more precisely than human beings, thus potentially reducing the number of traffic accidents, subsequent pedestrian injuries and even fatalities. Autonomous vehicles have been a major focus of artificial intelligence research over the past few years, with major developments being contributed to the industry by Google, Bosch, and leading companies in the automobile industry. The study presented in the dissertation explores the use of Intelligent Agents as a computer science abstraction that encapsulates the several components of an autonomous vehicle, in order to promote component modularity and to allow the inclusion of newer technologies that could further improve the effectiveness of autonomous vehicles. A particular recent advancement in the field of autonomous vehicles is the use of intervehicle communications, which supplements the array of sensors provided in the vehicles, in case of failure or inability to produce sufficient data that would be necessary for the vehicle to make a decision. The agent model proposed in the dissertation places a paramount importance on the communications mechanism, incorporating it in its agent architecture, in order to produce an autonomous vehicle model that is safer and more effective than current solutions. The autonomous vehicle agent model, given research constraints, was deployed in a simulated 3D urban traffic environment, where it was tested in a number of scenarios where a vehicle's sensors failed or provided insufficient data, preventing a safe journey for the vehicle's passengers, passengers of other vehicles and pedestrians in the simulated environment. The results of the tests demonstrated that an inter-vehicle communications mechanism, even with limited transmission range, effectively complements the existing modules of an autonomous vehicle, and is especially useful in case one of the modules fails. , M.Sc. (Information Technology)
- Full Text:
Adapting to artificial intelligence through workforce re-skilling within the banking sector in South Africa
- Mamela, Tebogo Lucky, Sukdeo, Nita, Mukwakungu, Sambil Charles
- Authors: Mamela, Tebogo Lucky , Sukdeo, Nita , Mukwakungu, Sambil Charles
- Date: 2020
- Subjects: Banking institution , Workforce , Artificial intelligence
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/450788 , uj:39640 , Citation: Mamela, T.L., Sukdeo, N. & Mukwakungu, S.C. 2020. Adapting to artificial intelligence through workforce re-skilling within the banking sector in South Africa.
- Description: Abstract: This research paper intends to inspire the banking sector to re-skill the workforces and present the opportunities in re-skilling the banking institutions workforces in South Africa to adapt to the roll out of Artificial Intelligence technologies. The research addresses the factors that will contribute to the workers re-skilling and the skills that are needed in order for the banking workforce to survive in the competitive labor market of the fourth industrial revolution which may result in the obsolete of many job skills. This research also considers the relevant skills and competencies that will be on-demand by the future banking workforces to enable them to successfully adapt to the aspects of the 4IR technological innovations inclusive of the AI toolset such as machine learning, blockchain, nanotechnology, robotics, Internet of Things, biotechnology, cloud computing and so forth, which may ultimately impact the workforce’s performance and productivity in the banking institutions. The research uses descriptive statistics and inferential statistics. The research has achieved results based on the assessment of the relationship between workforces’ capabilities and the components that make up Artificial Intelligence toolset. The findings show that the adaptation of AI strongly depends on most of the stated skills, therefore banks are required to re-skill their workforces in order to adapt to AI advanced technologies so as to make them relevant in the future. Re-skilling the banking workforce to cooperate and collaborate effectively with Artificial Intelligence will enable not only efficiency, but innovation and growth.
- Full Text:
- Authors: Mamela, Tebogo Lucky , Sukdeo, Nita , Mukwakungu, Sambil Charles
- Date: 2020
- Subjects: Banking institution , Workforce , Artificial intelligence
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/450788 , uj:39640 , Citation: Mamela, T.L., Sukdeo, N. & Mukwakungu, S.C. 2020. Adapting to artificial intelligence through workforce re-skilling within the banking sector in South Africa.
- Description: Abstract: This research paper intends to inspire the banking sector to re-skill the workforces and present the opportunities in re-skilling the banking institutions workforces in South Africa to adapt to the roll out of Artificial Intelligence technologies. The research addresses the factors that will contribute to the workers re-skilling and the skills that are needed in order for the banking workforce to survive in the competitive labor market of the fourth industrial revolution which may result in the obsolete of many job skills. This research also considers the relevant skills and competencies that will be on-demand by the future banking workforces to enable them to successfully adapt to the aspects of the 4IR technological innovations inclusive of the AI toolset such as machine learning, blockchain, nanotechnology, robotics, Internet of Things, biotechnology, cloud computing and so forth, which may ultimately impact the workforce’s performance and productivity in the banking institutions. The research uses descriptive statistics and inferential statistics. The research has achieved results based on the assessment of the relationship between workforces’ capabilities and the components that make up Artificial Intelligence toolset. The findings show that the adaptation of AI strongly depends on most of the stated skills, therefore banks are required to re-skill their workforces in order to adapt to AI advanced technologies so as to make them relevant in the future. Re-skilling the banking workforce to cooperate and collaborate effectively with Artificial Intelligence will enable not only efficiency, but innovation and growth.
- Full Text:
An integrated systems approach to risk management within a technology driven industry using the design structure matrix and fuzzy logic
- Authors: Barkhuizen, Willem Frederik
- Date: 2012-08-01
- Subjects: Value analysis (Cost control) , Risk management , Artificial intelligence , Fuzzy logic
- Type: Thesis
- Identifier: uj:8904 , http://hdl.handle.net/10210/5376
- Description: D.Ing. , “Innovation is the act of introducing something new” (Byrd & Brown, 2003). When companies are competing on the technology “playground” they need to be innovative. By analysis according to Byrd & Brown (Byrd & Brown, 2003) the “act of introducing”, relates to risk taking, and the “new” relates to creativity, and therefore these concepts, creativity and risk taking, in combination, are what innovation is all about. Risk management has become one of the greatest challenges of the 21st century, and one of the main components in innovation and the technology driven industry, intensifying the need for a systematic approach to managing uncertainties. During the development and design of complex engineering products, the input and teamwork of multiple participants from various backgrounds are required resulting in complex interactions. Risk interactions exist between the functional and physical elements within such a system and its sub-systems in various dimensions such as spatial interaction, information interaction etc. The relationships are of a multi-dimensional complexity that cannot be simplified using the standard task management tools (Yassine A. A., 2004). To find a meaningful starting point for the seemingly boundless subject of risk management the research takes a step back into the basic definition of risk management and follows an exploratory research methodology to explore each of the risk management processes (risk assessment, risk identification, risk analysis, risk evaluation, risk treatment and risk monitoring and review) and how these processes can be enhanced using the design structure matrix (DSM) and fuzzy logic thinking. The approach to risk management within an organisation should be seen as a holistic approach similar to the total quality management process, providing the ii opportunity to incorporated risk management during the design process as a concurrent task. The risk management model is then developed concurrently (during the design phase) using product development methodologies such as conceptual modeling and prototyping, and ultimately the prototype is tested using a case study. Finally resulting in a clustered DSM providing a visual representation of the system risk areas similar to the methodology used in Finite Element Analysis (FEA). The research combines alternative system representation and analysis techniques (Warfield, 2005), in particular the design structure matrix, and fuzzy logic to quantify the risk management effort neccessary to deal with uncertain and imprecise interactions between system elements.
- Full Text:
- Authors: Barkhuizen, Willem Frederik
- Date: 2012-08-01
- Subjects: Value analysis (Cost control) , Risk management , Artificial intelligence , Fuzzy logic
- Type: Thesis
- Identifier: uj:8904 , http://hdl.handle.net/10210/5376
- Description: D.Ing. , “Innovation is the act of introducing something new” (Byrd & Brown, 2003). When companies are competing on the technology “playground” they need to be innovative. By analysis according to Byrd & Brown (Byrd & Brown, 2003) the “act of introducing”, relates to risk taking, and the “new” relates to creativity, and therefore these concepts, creativity and risk taking, in combination, are what innovation is all about. Risk management has become one of the greatest challenges of the 21st century, and one of the main components in innovation and the technology driven industry, intensifying the need for a systematic approach to managing uncertainties. During the development and design of complex engineering products, the input and teamwork of multiple participants from various backgrounds are required resulting in complex interactions. Risk interactions exist between the functional and physical elements within such a system and its sub-systems in various dimensions such as spatial interaction, information interaction etc. The relationships are of a multi-dimensional complexity that cannot be simplified using the standard task management tools (Yassine A. A., 2004). To find a meaningful starting point for the seemingly boundless subject of risk management the research takes a step back into the basic definition of risk management and follows an exploratory research methodology to explore each of the risk management processes (risk assessment, risk identification, risk analysis, risk evaluation, risk treatment and risk monitoring and review) and how these processes can be enhanced using the design structure matrix (DSM) and fuzzy logic thinking. The approach to risk management within an organisation should be seen as a holistic approach similar to the total quality management process, providing the ii opportunity to incorporated risk management during the design process as a concurrent task. The risk management model is then developed concurrently (during the design phase) using product development methodologies such as conceptual modeling and prototyping, and ultimately the prototype is tested using a case study. Finally resulting in a clustered DSM providing a visual representation of the system risk areas similar to the methodology used in Finite Element Analysis (FEA). The research combines alternative system representation and analysis techniques (Warfield, 2005), in particular the design structure matrix, and fuzzy logic to quantify the risk management effort neccessary to deal with uncertain and imprecise interactions between system elements.
- Full Text:
Application of Artificial Intelligence (AI) methods for designing and analysis of Reconfigurable Cellular Manufacturing System (RCMS)
- Marwala, Tshilidzi, Xing, Bo, Nelwamondo, Fulufbelo V., Battle, Kimberly, Gao, Wenjing
- Authors: Marwala, Tshilidzi , Xing, Bo , Nelwamondo, Fulufbelo V. , Battle, Kimberly , Gao, Wenjing
- Date: 2009
- Subjects: Reconfigurable Cellular Manufacturing System , Artificial intelligence , Cellular Manufacturing System , Reconfigurable Manufacturing System
- Type: Article
- Identifier: uj:5305 , ISSN 978-1-4244-3523-4 , http://hdl.handle.net/10210/5266
- Description: This work focuses on the design and control of a novel hybrId manufacturing system: Reconfigurable Cellular Manufacturing System (RCMS) by using Artificial Intelligence (AI) approach. It is hybrid as it combines the advantages of Cellular Manufacturing System (CMS) and Reconfigurable Manufacturing System (RMS). In addition to inheriting desirable properties from CMS and RMS, RCMS provides additional benefits including flexibility and the ability to respond to changing products, product mix and market conditions during its useful life, avoiding premature obsolescence of the manufacturing system. The emphasis of this research is the formation of Reconfigurable Manufacturing Cell (RMC) which is the dynamic and logical clustering of some manufacturing resources, driven by specific customer orders, aiming at optimally fulfilling customers' orders along with other RMCs in the RCMS.
- Full Text:
- Authors: Marwala, Tshilidzi , Xing, Bo , Nelwamondo, Fulufbelo V. , Battle, Kimberly , Gao, Wenjing
- Date: 2009
- Subjects: Reconfigurable Cellular Manufacturing System , Artificial intelligence , Cellular Manufacturing System , Reconfigurable Manufacturing System
- Type: Article
- Identifier: uj:5305 , ISSN 978-1-4244-3523-4 , http://hdl.handle.net/10210/5266
- Description: This work focuses on the design and control of a novel hybrId manufacturing system: Reconfigurable Cellular Manufacturing System (RCMS) by using Artificial Intelligence (AI) approach. It is hybrid as it combines the advantages of Cellular Manufacturing System (CMS) and Reconfigurable Manufacturing System (RMS). In addition to inheriting desirable properties from CMS and RMS, RCMS provides additional benefits including flexibility and the ability to respond to changing products, product mix and market conditions during its useful life, avoiding premature obsolescence of the manufacturing system. The emphasis of this research is the formation of Reconfigurable Manufacturing Cell (RMC) which is the dynamic and logical clustering of some manufacturing resources, driven by specific customer orders, aiming at optimally fulfilling customers' orders along with other RMCs in the RCMS.
- Full Text:
Application of artificial intelligence techniques in design optimization of a parallel manipulator
- Authors: Modungwa, Dithoto
- Date: 2015-02-12
- Subjects: Parallel processing (Electronic computers) , Electronic data processing , Adaptive computing systems , Artificial intelligence
- Type: Thesis
- Identifier: uj:13311 , http://hdl.handle.net/10210/13328
- Description: D.Phil. (Electrical and Electronic Engineering) , The complexity of multi-objective functions and diverse variables involved with optimization of parallel manipulator or parallel kinematic machine design has inspired the research conducted in this thesis to investigate techniques that are suitable to tackle this problem efficiently. Further the parallel manipulator dimensional synthesis problem is multimodal and has no explicit analytical expressions. This process requires optimization techniques which offer high level of accuracy and robustness. The goal of this work is to present method(s) based on Artificial Intelligence (AI) that may be applied in addressing the challenge stated above. The performance criteria considered include; stiffness, dexterity and workspace. The case studied in this work is a 6 degrees of freedom (DOF) parallel manipulator, particularly because it is considered much more complicated than the lesser DOF mechanisms, owing to the number of independent parameters or inputs needed to specify its configuration (i.e. the higher the DOFs, the more the number of independent variables to be considered). The first contribution in this thesis is a comparative study of several hybrid Multi- Objective Optimization (MOO) AI algorithms, in application of a parallel manipulator dimensional synthesis. Artificial neural networks are utilized to approximate a multiple function for the analytical solution of the 6 DOF parallel manipulator’s performance indices, followed by implementation of Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) as search algorithms. Further two hybrid techniques are proposed which implement Simulated Annealing and Random Forest in searching for optimum solutions in the Multi-objective Optimization problem. The final contribution in this thesis is ensemble machine learning algorithms for approximation of a multiple objective function for the 6 DOF parallel manipulator analytical solution. The results from the experiments demonstrated not only neural network (NN) but also other machine learning algorithms namely K- Nearest Neighbour (k-NN), M5 Prime (M5’), Zero R (ZR) and Decision Stump (DS) can effectively be implemented for the application of function approximation.
- Full Text:
- Authors: Modungwa, Dithoto
- Date: 2015-02-12
- Subjects: Parallel processing (Electronic computers) , Electronic data processing , Adaptive computing systems , Artificial intelligence
- Type: Thesis
- Identifier: uj:13311 , http://hdl.handle.net/10210/13328
- Description: D.Phil. (Electrical and Electronic Engineering) , The complexity of multi-objective functions and diverse variables involved with optimization of parallel manipulator or parallel kinematic machine design has inspired the research conducted in this thesis to investigate techniques that are suitable to tackle this problem efficiently. Further the parallel manipulator dimensional synthesis problem is multimodal and has no explicit analytical expressions. This process requires optimization techniques which offer high level of accuracy and robustness. The goal of this work is to present method(s) based on Artificial Intelligence (AI) that may be applied in addressing the challenge stated above. The performance criteria considered include; stiffness, dexterity and workspace. The case studied in this work is a 6 degrees of freedom (DOF) parallel manipulator, particularly because it is considered much more complicated than the lesser DOF mechanisms, owing to the number of independent parameters or inputs needed to specify its configuration (i.e. the higher the DOFs, the more the number of independent variables to be considered). The first contribution in this thesis is a comparative study of several hybrid Multi- Objective Optimization (MOO) AI algorithms, in application of a parallel manipulator dimensional synthesis. Artificial neural networks are utilized to approximate a multiple function for the analytical solution of the 6 DOF parallel manipulator’s performance indices, followed by implementation of Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) as search algorithms. Further two hybrid techniques are proposed which implement Simulated Annealing and Random Forest in searching for optimum solutions in the Multi-objective Optimization problem. The final contribution in this thesis is ensemble machine learning algorithms for approximation of a multiple objective function for the 6 DOF parallel manipulator analytical solution. The results from the experiments demonstrated not only neural network (NN) but also other machine learning algorithms namely K- Nearest Neighbour (k-NN), M5 Prime (M5’), Zero R (ZR) and Decision Stump (DS) can effectively be implemented for the application of function approximation.
- Full Text:
Approach for implementing Industry 4.0 framework in the steel industry
- Authors: Govender, Esenthren
- Date: 2019
- Subjects: Steel industry and trade , Industrial revolution , Artificial intelligence
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/417192 , uj:35321
- Description: Abstract: The growth of the steel sector requires a fully integrated manufacturing system for real-time decision making. The primary challenge in the steel sector is the lack of data flow between the production operations such as Manufacturing Execution System (MES) and business systems as an example the Enterprise Resource Planning (ERP). The production operations of the steel sector require visibility of product quality, maintenance management, operational lead times, planning and scheduling, equipment health, to name but a few aspects. Legacy systems and technologies that are in the steel sector have plagued the organisation. State of the art technology implementations is defined as “brownfields” as they are deployed in silos with no standardisation across the organisation. Production data in the steel sector constitutes disparate sources as there is a multitude of processes and applications. Real-time data is collected and aggregated before being shared with other systems. The paper investigates current technologies and investments adopted by the steel sector and how to leverage off these existing expenditure to attain a smart enterprise and subsequently manage current and future steel demands efficiently. The paper defines an implementation approach and system architecture to assist the steel sector aligned to Industry 4.0. Industry 4.0 simplifies the approach to implement complex systems in a structured and logical manner in manufacturing organisations. Industry 4.0 integrates the operational equipment, people, processes, products and the supply chain. The study deliberates the Industry 4.0 framework and the approach to implement Industry 4.0 in the steel sector. The focus areas of the research include the review of Cyber-Physical Systems (CPS), Internet of Things (IoT), Industrial Internet of Things (IIoT) and Big Data at the steel entity. The Systems Development Life Cycle (SDLC) methodology is utilised in the research to gather information on the steel entity. A steel entity in South Africa is utilised in the research. Workshops and observations are employed at the steel entity to gather data and identify business processes utilised. The results based on data collated prove the viability of industry 4.0 in the steel sector. The alignment of the current system architecture of the steel entity to Industry 4.0 framework results in a reduction of thirty-four per cent in system applications utilised in the organisation which is presented in an Industry 4.0 architecture. Further benefits are defined in terms of reduction of integration interfaces, improved real-time data flow, financial savings based on a single data and reporting repository and reduction in month-end financial reporting timelines. , M.Phil. (Engineering Management)
- Full Text:
- Authors: Govender, Esenthren
- Date: 2019
- Subjects: Steel industry and trade , Industrial revolution , Artificial intelligence
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/417192 , uj:35321
- Description: Abstract: The growth of the steel sector requires a fully integrated manufacturing system for real-time decision making. The primary challenge in the steel sector is the lack of data flow between the production operations such as Manufacturing Execution System (MES) and business systems as an example the Enterprise Resource Planning (ERP). The production operations of the steel sector require visibility of product quality, maintenance management, operational lead times, planning and scheduling, equipment health, to name but a few aspects. Legacy systems and technologies that are in the steel sector have plagued the organisation. State of the art technology implementations is defined as “brownfields” as they are deployed in silos with no standardisation across the organisation. Production data in the steel sector constitutes disparate sources as there is a multitude of processes and applications. Real-time data is collected and aggregated before being shared with other systems. The paper investigates current technologies and investments adopted by the steel sector and how to leverage off these existing expenditure to attain a smart enterprise and subsequently manage current and future steel demands efficiently. The paper defines an implementation approach and system architecture to assist the steel sector aligned to Industry 4.0. Industry 4.0 simplifies the approach to implement complex systems in a structured and logical manner in manufacturing organisations. Industry 4.0 integrates the operational equipment, people, processes, products and the supply chain. The study deliberates the Industry 4.0 framework and the approach to implement Industry 4.0 in the steel sector. The focus areas of the research include the review of Cyber-Physical Systems (CPS), Internet of Things (IoT), Industrial Internet of Things (IIoT) and Big Data at the steel entity. The Systems Development Life Cycle (SDLC) methodology is utilised in the research to gather information on the steel entity. A steel entity in South Africa is utilised in the research. Workshops and observations are employed at the steel entity to gather data and identify business processes utilised. The results based on data collated prove the viability of industry 4.0 in the steel sector. The alignment of the current system architecture of the steel entity to Industry 4.0 framework results in a reduction of thirty-four per cent in system applications utilised in the organisation which is presented in an Industry 4.0 architecture. Further benefits are defined in terms of reduction of integration interfaces, improved real-time data flow, financial savings based on a single data and reporting repository and reduction in month-end financial reporting timelines. , M.Phil. (Engineering Management)
- Full Text:
Artificial intelligence and knowledge management principles in secure corporate intranets
- Authors: Barry, Christopher
- Date: 2010-02-23T10:25:43Z
- Subjects: Artificial intelligence , Knowledge management , Intranets (Computer networks) , Computer networks security measures
- Type: Thesis
- Identifier: uj:6634 , http://hdl.handle.net/10210/3035
- Description: M.Sc. (Computer Science) , Corporations throughout the world are facing numerous challenges in today’s competitive marketplace and are continuously looking for new and innovative means and methods of gaining competitive advantage. One of the means used to gain this advantage is that of information technology, and all the associated technologies and principles. These are primarily used to facilitate business processes and procedures that are designed to provide this competitive advantage. Significant attention has been given to each of the individual technologies and principles of Artificial Intelligence, Knowledge Management, Information Security, and Intranets and how they can be leveraged in order to improve efficiency and functionality within a corporation. However, in order to truly reap the benefits of these technologies and principles, it is necessary to look at them as a collaborative system, rather as individual components. This dissertation therefore investigates each of these individual technologies and principles in isolation, as well as in combination with each other to outline potential advantages, associated risks, and disadvantages when combining them within the corporate world. Based on these, the Intelligently Generated Knowledge (IGK) framework is outlined to implement such a collaborative system. Thereafter, an investigation of a theoretical situation is conducted based on this framework to examine the impact of the implementation of this type of collaborative system. The potential increase in cost savings, efficiency and functionality of corporations that would employ the IGK framework is clearly outlined in the theoretical example, and should this approach be adopted, it would be able to provide significant competitive advantage for any corporation.
- Full Text:
- Authors: Barry, Christopher
- Date: 2010-02-23T10:25:43Z
- Subjects: Artificial intelligence , Knowledge management , Intranets (Computer networks) , Computer networks security measures
- Type: Thesis
- Identifier: uj:6634 , http://hdl.handle.net/10210/3035
- Description: M.Sc. (Computer Science) , Corporations throughout the world are facing numerous challenges in today’s competitive marketplace and are continuously looking for new and innovative means and methods of gaining competitive advantage. One of the means used to gain this advantage is that of information technology, and all the associated technologies and principles. These are primarily used to facilitate business processes and procedures that are designed to provide this competitive advantage. Significant attention has been given to each of the individual technologies and principles of Artificial Intelligence, Knowledge Management, Information Security, and Intranets and how they can be leveraged in order to improve efficiency and functionality within a corporation. However, in order to truly reap the benefits of these technologies and principles, it is necessary to look at them as a collaborative system, rather as individual components. This dissertation therefore investigates each of these individual technologies and principles in isolation, as well as in combination with each other to outline potential advantages, associated risks, and disadvantages when combining them within the corporate world. Based on these, the Intelligently Generated Knowledge (IGK) framework is outlined to implement such a collaborative system. Thereafter, an investigation of a theoretical situation is conducted based on this framework to examine the impact of the implementation of this type of collaborative system. The potential increase in cost savings, efficiency and functionality of corporations that would employ the IGK framework is clearly outlined in the theoretical example, and should this approach be adopted, it would be able to provide significant competitive advantage for any corporation.
- Full Text:
Benchmarking a neural network forecaster against statistical measures
- Authors: Herman, Hilde
- Date: 2014-09-16
- Subjects: Forecasting - Data processing , Neural networks (Computer science) , Artificial intelligence , Benchmarking (Management)
- Type: Thesis
- Identifier: uj:12312 , http://hdl.handle.net/10210/12098
- Description: M.Ing. (Mechanical Engineering) , The combination of non-linear signal processing and financial market forecasting is a relatively new field of research. This dissertation concerns the forecasting of shares quoted on the Johannesburg Stock Exchange by using Artificial Neural Networks, and does so by comparing neural network results with established statistical results. The share price rise or fall are predicted as well as buy, sell and hold signals and compared to Time Series model and Moving Average Convergence Divergence results. The dissertation will show that artificial neural networks predict the share price rise or fall with less error than statistical models and yielded the highest profit when forecasting buy, sell and hold signals for a particular share.
- Full Text:
- Authors: Herman, Hilde
- Date: 2014-09-16
- Subjects: Forecasting - Data processing , Neural networks (Computer science) , Artificial intelligence , Benchmarking (Management)
- Type: Thesis
- Identifier: uj:12312 , http://hdl.handle.net/10210/12098
- Description: M.Ing. (Mechanical Engineering) , The combination of non-linear signal processing and financial market forecasting is a relatively new field of research. This dissertation concerns the forecasting of shares quoted on the Johannesburg Stock Exchange by using Artificial Neural Networks, and does so by comparing neural network results with established statistical results. The share price rise or fall are predicted as well as buy, sell and hold signals and compared to Time Series model and Moving Average Convergence Divergence results. The dissertation will show that artificial neural networks predict the share price rise or fall with less error than statistical models and yielded the highest profit when forecasting buy, sell and hold signals for a particular share.
- Full Text:
Chaotic neural network swarm optimization
- Sun, Y-X
- Authors: Sun, Y-X
- Date: 2007
- Subjects: Artificial intelligence , Chaos theory , Computer simulation , Convergence of numerical methods , Global optimization , Hopfield neural networks
- Language: Chinese
- Type: Article
- Identifier: http://hdl.handle.net/10210/18234 , uj:15975 , ISSN: 1671-5497 , Citation: Sun, Y-X. et al. 2007. Chaotic neural network swarm optimization. Engineering village, 37(9):113-116.
- Description: A single particle structure of particle swarm optimization was analyzed which is found to have some properties of a Chaos-Hopfield neural net work. A new model of particle swarm optimization is presented. The model is a deterministic Chaos-Hopfield neural network swarm which is different from the existing one with stochastic parameters. Its search orbits show an evolution process of inverse period bifurcation from chaos to periodic orbits then to sink. In this evolution process, the initial chaos-like search expands the optimal scope, and inverse period bifurcation determines the stability and convergence of the search. Moreover, the convergence is theoretically analyzed. Finally, the numerical simulation shows the basic procedure of the proposed model and verifies its efficiency.
- Full Text:
- Authors: Sun, Y-X
- Date: 2007
- Subjects: Artificial intelligence , Chaos theory , Computer simulation , Convergence of numerical methods , Global optimization , Hopfield neural networks
- Language: Chinese
- Type: Article
- Identifier: http://hdl.handle.net/10210/18234 , uj:15975 , ISSN: 1671-5497 , Citation: Sun, Y-X. et al. 2007. Chaotic neural network swarm optimization. Engineering village, 37(9):113-116.
- Description: A single particle structure of particle swarm optimization was analyzed which is found to have some properties of a Chaos-Hopfield neural net work. A new model of particle swarm optimization is presented. The model is a deterministic Chaos-Hopfield neural network swarm which is different from the existing one with stochastic parameters. Its search orbits show an evolution process of inverse period bifurcation from chaos to periodic orbits then to sink. In this evolution process, the initial chaos-like search expands the optimal scope, and inverse period bifurcation determines the stability and convergence of the search. Moreover, the convergence is theoretically analyzed. Finally, the numerical simulation shows the basic procedure of the proposed model and verifies its efficiency.
- Full Text:
Communication and complex control membrane symbiotic agents
- Authors: Cotterrell, Deon
- Date: 2019
- Subjects: Artificial intelligence , Adaptive control systems , Interactive computer systems , Computer games - Programming
- Language: English
- Type: Doctoral (Thesis)
- Identifier: http://hdl.handle.net/10210/458403 , uj:40715
- Description: Abstract: The aim of this thesis was to improve on the symbiotic agent. As highlighted in the section on future work for the symbiotic agent in the study, one goal was to increase the flexibility and adaptability of the model in “real time”. The need for improvement is further highlighted by the fact that information technology is constantly improving. Artificial intelligence algorithms and techniques in all areas need to be reviewed and adjusted if the new requirements of the environment are to be met. The thesis starts by considering which research methodology should be used to conduct the research. This is followed by an examination of artificial intelligence and agents. The section that then follows covers the field of computer games and artificial intelligence techniques and algorithms that have been used in the creation of computer games. After this, the original symbiotic agent model is examined along with all the components that make up the symbiotic agent model. The last section that is covered in the literature review is that of membranes, with a focus on biological membranes – in particular, the plasma membrane. The plasma membrane is considered in the context of the cell, where it functions to support the cell. With the literature review completed, the plasma membrane was used as the inspiration for the creation of the control membrane symbiotic agent model. Additional models were also developed and designed. These are the complex communication membranes, which are made up of the following membranes: stacked, semi-merged and unified communication membranes. Establishing the four models led to the fifth and final model, the complex control membrane symbiotic agent, which is a combination of the control membrane symbiotic agent and one of the complex communication membranes. The final step of the thesis was the implementation of the complex control membrane symbiotic agent as a proof of concept. All the variations of the complex control membrane symbiotic agent were implemented in a procedurally generated game environment. The result of the implementation provides some means to compare the various complex membranes that had been implemented inside the control membrane. The contribution of the thesis is not the implementation but the five different models of the symbiotic agents that have been developed to be flexible and adaptable in “real-time” situations. , Ph.D. (Computer Science)
- Full Text:
- Authors: Cotterrell, Deon
- Date: 2019
- Subjects: Artificial intelligence , Adaptive control systems , Interactive computer systems , Computer games - Programming
- Language: English
- Type: Doctoral (Thesis)
- Identifier: http://hdl.handle.net/10210/458403 , uj:40715
- Description: Abstract: The aim of this thesis was to improve on the symbiotic agent. As highlighted in the section on future work for the symbiotic agent in the study, one goal was to increase the flexibility and adaptability of the model in “real time”. The need for improvement is further highlighted by the fact that information technology is constantly improving. Artificial intelligence algorithms and techniques in all areas need to be reviewed and adjusted if the new requirements of the environment are to be met. The thesis starts by considering which research methodology should be used to conduct the research. This is followed by an examination of artificial intelligence and agents. The section that then follows covers the field of computer games and artificial intelligence techniques and algorithms that have been used in the creation of computer games. After this, the original symbiotic agent model is examined along with all the components that make up the symbiotic agent model. The last section that is covered in the literature review is that of membranes, with a focus on biological membranes – in particular, the plasma membrane. The plasma membrane is considered in the context of the cell, where it functions to support the cell. With the literature review completed, the plasma membrane was used as the inspiration for the creation of the control membrane symbiotic agent model. Additional models were also developed and designed. These are the complex communication membranes, which are made up of the following membranes: stacked, semi-merged and unified communication membranes. Establishing the four models led to the fifth and final model, the complex control membrane symbiotic agent, which is a combination of the control membrane symbiotic agent and one of the complex communication membranes. The final step of the thesis was the implementation of the complex control membrane symbiotic agent as a proof of concept. All the variations of the complex control membrane symbiotic agent were implemented in a procedurally generated game environment. The result of the implementation provides some means to compare the various complex membranes that had been implemented inside the control membrane. The contribution of the thesis is not the implementation but the five different models of the symbiotic agents that have been developed to be flexible and adaptable in “real-time” situations. , Ph.D. (Computer Science)
- Full Text:
Detecting emotions from speech using machine learning techniques
- Authors: Roy, Tanmoy
- Date: 2019
- Subjects: Artificial intelligence , Automatic speech perception - Technological innovations , Automatic speech recognition , Algorithms , Speech processing systems
- Language: English
- Type: Doctoral (Thesis)
- Identifier: http://hdl.handle.net/10210/437516 , uj:37992
- Description: D.Phil. (Electronic Engineering)
- Full Text:
- Authors: Roy, Tanmoy
- Date: 2019
- Subjects: Artificial intelligence , Automatic speech perception - Technological innovations , Automatic speech recognition , Algorithms , Speech processing systems
- Language: English
- Type: Doctoral (Thesis)
- Identifier: http://hdl.handle.net/10210/437516 , uj:37992
- Description: D.Phil. (Electronic Engineering)
- Full Text:
Effective use of artificial intelligence in predicting energy consumption and underground dam levels in two gold mines in South Africa
- Authors: Hasan, Ali N.
- Date: 2015-02-12
- Subjects: Artificial intelligence , Artificial intelligence - Engineering applications , Expert systems (Computer science) Electric power consumption
- Type: Thesis
- Identifier: uj:13316 , http://hdl.handle.net/10210/13332
- Description: D.Ing. (Electrical and Electronic Engineering) , The electricity shortage in South Africa has required the implementation of demand side management (DSM) projects. The DSM projects were implemented by installing energy monitoring and control systems to monitor certain mining aspects such as water pumping systems. Certain energy saving procedures and control systems followed by the mining industry are not sustainable and must be updated regularly in order to meet any changes in the water pumping system. In addition, the present water pumping, monitoring, and control system does not predict the energy consumption or the underground water dam levels. Hence, there is a need to introduce new monitoring system that could control and predict the energy consumption of the underground water pumping system and dam levels based on present and historical data. The work is undertaken to investigate the feasibility of using artificial intelligence in certain aspects of the mining industry. If successful, artificial intelligence systems could lead to improved safety and reduced electrical energy consumption, and decreased human error that could occur throughout the pump station monitoring and control process ...
- Full Text:
- Authors: Hasan, Ali N.
- Date: 2015-02-12
- Subjects: Artificial intelligence , Artificial intelligence - Engineering applications , Expert systems (Computer science) Electric power consumption
- Type: Thesis
- Identifier: uj:13316 , http://hdl.handle.net/10210/13332
- Description: D.Ing. (Electrical and Electronic Engineering) , The electricity shortage in South Africa has required the implementation of demand side management (DSM) projects. The DSM projects were implemented by installing energy monitoring and control systems to monitor certain mining aspects such as water pumping systems. Certain energy saving procedures and control systems followed by the mining industry are not sustainable and must be updated regularly in order to meet any changes in the water pumping system. In addition, the present water pumping, monitoring, and control system does not predict the energy consumption or the underground water dam levels. Hence, there is a need to introduce new monitoring system that could control and predict the energy consumption of the underground water pumping system and dam levels based on present and historical data. The work is undertaken to investigate the feasibility of using artificial intelligence in certain aspects of the mining industry. If successful, artificial intelligence systems could lead to improved safety and reduced electrical energy consumption, and decreased human error that could occur throughout the pump station monitoring and control process ...
- Full Text:
Embedding intelligence in enhanced music mapping agents
- Authors: Gray, Marnitz Cornell
- Date: 2009-05-19T06:39:53Z
- Subjects: Artificial intelligence , Intelligent agents (Computer software) , Digital jukebox software
- Type: Thesis
- Identifier: uj:8382 , http://hdl.handle.net/10210/2548
- Description: M.Sc. (Computer Science) , Artificial Intelligence has been an increasing focus of study over the past years. Agent technology has emerged as being the preferred model for simulating intelligence [Jen00a]. Focus is now turning to inter-agent communication [Jen00b] and agents that can adapt to changes in their environment. Digital music has been gaining in popularity over the past few years. Devices such as Apple’s iPod have sold millions. These devices have the capability of holding thousands of songs. Managing such a device and selecting a list of songs to play from so many can be a difficult task. This dissertation expands on agent types by creating a new agent type known as the Modifiable Agent. The Modifiable Agent type defines agents which have the ability to modify their intelligence depending on what data they need to analyse. This allows an agent to, for example, change from being a goal based to a learning based agent, or allows an agent to modify the way in which it processes data. Digital music is a growing field with devices such as the Apple iPod revolutionising the industry. These devices can store large amounts of songs and as such, make it very difficult to navigate as they usually don’t include devices such as a mouse or keyboard. Therefore, creating a play list of songs can be a tiresome process which can lead to the user playing the same songs over and over. The goal of the dissertation is to provide research into methods of automatically creating a play list from a user selected song, i.e. once a user selects a song, a list of similar music is automatically generated and added to the user’s playlist. This simplifies the task of selecting music and adds diversity to the songs which the user listens to. The dissertation introduces intelligent music selection, or selecting a play list of songs depending on music classification techniques and past human interaction.
- Full Text:
- Authors: Gray, Marnitz Cornell
- Date: 2009-05-19T06:39:53Z
- Subjects: Artificial intelligence , Intelligent agents (Computer software) , Digital jukebox software
- Type: Thesis
- Identifier: uj:8382 , http://hdl.handle.net/10210/2548
- Description: M.Sc. (Computer Science) , Artificial Intelligence has been an increasing focus of study over the past years. Agent technology has emerged as being the preferred model for simulating intelligence [Jen00a]. Focus is now turning to inter-agent communication [Jen00b] and agents that can adapt to changes in their environment. Digital music has been gaining in popularity over the past few years. Devices such as Apple’s iPod have sold millions. These devices have the capability of holding thousands of songs. Managing such a device and selecting a list of songs to play from so many can be a difficult task. This dissertation expands on agent types by creating a new agent type known as the Modifiable Agent. The Modifiable Agent type defines agents which have the ability to modify their intelligence depending on what data they need to analyse. This allows an agent to, for example, change from being a goal based to a learning based agent, or allows an agent to modify the way in which it processes data. Digital music is a growing field with devices such as the Apple iPod revolutionising the industry. These devices can store large amounts of songs and as such, make it very difficult to navigate as they usually don’t include devices such as a mouse or keyboard. Therefore, creating a play list of songs can be a tiresome process which can lead to the user playing the same songs over and over. The goal of the dissertation is to provide research into methods of automatically creating a play list from a user selected song, i.e. once a user selects a song, a list of similar music is automatically generated and added to the user’s playlist. This simplifies the task of selecting music and adds diversity to the songs which the user listens to. The dissertation introduces intelligent music selection, or selecting a play list of songs depending on music classification techniques and past human interaction.
- Full Text:
Extending labour law and social protection to waste pickers in the Fourth Industrial Age
- Authors: Koen, Louis
- Date: 2019
- Subjects: Refuse and refuse disposal - Social aspects , Informal sector (Economics) - Employees , Technological innovations - Social aspects - South Africa , Artificial intelligence
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/413489 , uj:34836
- Description: Abstract: The world of work has changed significantly and continues to undergo changes brought about by the Fourth Industrial Revolution. These changes have contributed to a significant increase in informal employment where workers face a lack of adequate labour and social protection. The majority of the world’s workforce is engaged in informal employment, and in South Africa the growth in the number of workers in the informal economy has far outpaced that in the formal economy since the 2008/9 global financial crises. This dissertation therefore considers these challenges together with new challenges brought about by the Fourth Industrial Revolution. The rise of systems such as autonomous pneumatic waste management systems demonstrates the ability of new technologies to fundamentally alter the face of the waste management industries. It is against the backdrop of these potentially significant changes that this dissertation considers the need to provide waste pickers with adequate labour and social protection. It does so by firstly considering the protection available to these workers in terms of international and regional instruments. An analysis is also undertaken of the potential for new sources of international labour law, in the form of international trade agreements, to enhance compliance with international labour standards. This dissertation also considers the existing legal framework in order to identify deficiencies in regulation for the Fourth Industrial Age. To this end an analysis is undertaken of the valuable procedural safeguards provided to waste pickers, where new technologies are implemented, within the realm of administrative law. However, the practical ability to enforce these provisions are criticised given that cases brought in terms of the Promotion of Administrative Justice Act can only be heard by the High Court of South Africa. This dissertation then considers the World Economic Forum’s “human centred approach” to the Fourth Industrial Age. It is acknowledged that this idea by the WEF does not in itself represent a legally binding obligation, however, the internationally binding right to development and the constitutional obligation on municipalities to promote the social and economic development of the community similarly place people at the centre. The WEF human centred approach could accordingly guide interpretation of these obligations in the context of regulation for the Fourth Industrial Age. , LL.M. (Mercantile Law)
- Full Text:
- Authors: Koen, Louis
- Date: 2019
- Subjects: Refuse and refuse disposal - Social aspects , Informal sector (Economics) - Employees , Technological innovations - Social aspects - South Africa , Artificial intelligence
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/413489 , uj:34836
- Description: Abstract: The world of work has changed significantly and continues to undergo changes brought about by the Fourth Industrial Revolution. These changes have contributed to a significant increase in informal employment where workers face a lack of adequate labour and social protection. The majority of the world’s workforce is engaged in informal employment, and in South Africa the growth in the number of workers in the informal economy has far outpaced that in the formal economy since the 2008/9 global financial crises. This dissertation therefore considers these challenges together with new challenges brought about by the Fourth Industrial Revolution. The rise of systems such as autonomous pneumatic waste management systems demonstrates the ability of new technologies to fundamentally alter the face of the waste management industries. It is against the backdrop of these potentially significant changes that this dissertation considers the need to provide waste pickers with adequate labour and social protection. It does so by firstly considering the protection available to these workers in terms of international and regional instruments. An analysis is also undertaken of the potential for new sources of international labour law, in the form of international trade agreements, to enhance compliance with international labour standards. This dissertation also considers the existing legal framework in order to identify deficiencies in regulation for the Fourth Industrial Age. To this end an analysis is undertaken of the valuable procedural safeguards provided to waste pickers, where new technologies are implemented, within the realm of administrative law. However, the practical ability to enforce these provisions are criticised given that cases brought in terms of the Promotion of Administrative Justice Act can only be heard by the High Court of South Africa. This dissertation then considers the World Economic Forum’s “human centred approach” to the Fourth Industrial Age. It is acknowledged that this idea by the WEF does not in itself represent a legally binding obligation, however, the internationally binding right to development and the constitutional obligation on municipalities to promote the social and economic development of the community similarly place people at the centre. The WEF human centred approach could accordingly guide interpretation of these obligations in the context of regulation for the Fourth Industrial Age. , LL.M. (Mercantile Law)
- Full Text:
Has the rise of digitalisation threatened the establishment of taxing rights? A critical analysis of threatened international income tax rules – as robotics, automation and artificial intelligence attempt to destroy the ‘brick and mortar’ principle
- Authors: Daniel, Jason
- Date: 2019
- Subjects: Taxation - Law and legislation , Conflict of laws - Commercial law , Electronic commerce - Taxation , Artificial intelligence
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/413381 , uj:34823
- Description: Abstract: Please refer to full text to view abstract. , LL.M. (Tax Law)
- Full Text:
- Authors: Daniel, Jason
- Date: 2019
- Subjects: Taxation - Law and legislation , Conflict of laws - Commercial law , Electronic commerce - Taxation , Artificial intelligence
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/413381 , uj:34823
- Description: Abstract: Please refer to full text to view abstract. , LL.M. (Tax Law)
- Full Text:
Intelligent system for automated components recognition and handling
- Authors: Findlay, Peter
- Date: 2012-02-06
- Subjects: Computer vision , Artificial intelligence , Pattern recognition systems
- Type: Thesis
- Identifier: uj:2012 , http://hdl.handle.net/10210/4365
- Description: M.Ing. , A machine vision system must, by definition, be intelligent, adaptable and reliable to satisfY the objectives of a system that is highly interactive with its dynamic environment and therefore prone to outside error factors. A machine vision system is described that utilizes a 2D captured web cam image for the purpose of intelligent object recognition, gripping and handling. The system is designed to be generic in its application and adaptable to various gripper configurations and handling configurations. This is achieved by using highly adaptable and intelligent recognition algorithms the gathers as much information as possible from a 2D colour web cam image. Numerous error-checking abilities are also built into the system to account for possible anomalies in the working environment. The entire system is designed around four separate but tightly integrated systems, namely the Recognition, Gripping and Handling structures and the Component Database which acts as the backbone of the system. The Recognition system provides all the input data that is then used for the Gripping and Handling systems. This integrated system functions as a single unit but a hierarchical structure has been used so that each of the systems can function as a stand-alone unit. The recognition system is generic in its ability to provide information such as recognized object identification, position and other orientation information that could be used by another handling system or gripper configuration. The Gripping system is based on a single custom designed gripper that provides basic gripping functionality. It is powered by a single motor and is highly functional with respect to the large range of object sizes that it can grip. The Handling Sub-system controls gripper positioning and motion. The Handling System incorporates control of the robot and the execution of both predetermined and online adaptable handling algorithms based on component data. It receives data from the Component database. The database allows the transparent ability to add and remove objects for recognition as well as other basic abilities. Experimental verification of the system is performed using a fully integrated and automated program and hardware control system developed for this purpose. The integration of the proposed system into a flexible and reconfigurable manufacturing system is explained.
- Full Text:
- Authors: Findlay, Peter
- Date: 2012-02-06
- Subjects: Computer vision , Artificial intelligence , Pattern recognition systems
- Type: Thesis
- Identifier: uj:2012 , http://hdl.handle.net/10210/4365
- Description: M.Ing. , A machine vision system must, by definition, be intelligent, adaptable and reliable to satisfY the objectives of a system that is highly interactive with its dynamic environment and therefore prone to outside error factors. A machine vision system is described that utilizes a 2D captured web cam image for the purpose of intelligent object recognition, gripping and handling. The system is designed to be generic in its application and adaptable to various gripper configurations and handling configurations. This is achieved by using highly adaptable and intelligent recognition algorithms the gathers as much information as possible from a 2D colour web cam image. Numerous error-checking abilities are also built into the system to account for possible anomalies in the working environment. The entire system is designed around four separate but tightly integrated systems, namely the Recognition, Gripping and Handling structures and the Component Database which acts as the backbone of the system. The Recognition system provides all the input data that is then used for the Gripping and Handling systems. This integrated system functions as a single unit but a hierarchical structure has been used so that each of the systems can function as a stand-alone unit. The recognition system is generic in its ability to provide information such as recognized object identification, position and other orientation information that could be used by another handling system or gripper configuration. The Gripping system is based on a single custom designed gripper that provides basic gripping functionality. It is powered by a single motor and is highly functional with respect to the large range of object sizes that it can grip. The Handling Sub-system controls gripper positioning and motion. The Handling System incorporates control of the robot and the execution of both predetermined and online adaptable handling algorithms based on component data. It receives data from the Component database. The database allows the transparent ability to add and remove objects for recognition as well as other basic abilities. Experimental verification of the system is performed using a fully integrated and automated program and hardware control system developed for this purpose. The integration of the proposed system into a flexible and reconfigurable manufacturing system is explained.
- Full Text:
Knowledge-based automation and new workforce implementation at a financial institution
- Authors: Elsworth, Catherine
- Date: 2018
- Subjects: Industrial revolution , Artificial intelligence , Banks and banking - Technological innovations , Banks and banking - Customer services , Knowledge management , Banks and banking - Information technology
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/402839 , uj:33730
- Description: Abstract : Intelligent Automation (IA) entails advanced knowledge-based technologies associated with the so-called Fourth Industrial Revolution (4IR). In this study, the phrase “IA journey” refers to the processes of knowledge-based automation and new workforce implementation. The study’s unit of analysis is not as much the IA journey itself, rather it is an analysis of what constitutes a balanced approach to IA implementation and adoption within an organisation. For example, employees’ feelings of uncertainty during an organisation’s IA journey could cause an imbalance in staff morale and resistance from employees to adapt to the changes. Therefore, the main research question of this study is: What are the components of a balanced approach to knowledge-based automation and new workforce implementation of a financial institution? The research question aligns to the world of service delivery that is changing at an alarming rate, with customers expecting fast, personalised, digital service. The landscape for financial institutions is changing, for example, traditional competitors are taking steps to meet customer demands and non-traditional competitors are entering the market place, threatening the existence of traditional financial institutions, commonly referred to as banks. The literature reveals that the evolution of Internet usage and the influence of social media and smart phones have increased the significance of technology and digital service in the financial services industry. Adoptions of these technologies is vital if traditional banks want to remain relevant in the market where financial technologies companies (Fintechs), and small, digitally nimble start-ups can provide the quick, personalised service that customers expect. Already many financial institutions have started to investigate the opportunities that technologies such as IA and chatbots provide. The potential of chatbot technology to improve customer experience and reduce operational costs make it an attractive option for organisations to consider. Literature reveals that the cost of implementation of this technology is a fraction of the cost of legacy system re-writes. The ability of this technology to integrate with existing systems and improve turnaround time and service to customers makes the IA journey a favourable choice. The IA journey of one South African Financial Institution (SAFI) formed the focus of this study. Research was conducted within the SAFI into the application of this technology across the organisation to understand the impact that the changes experienced had on the employees of the organisation. Understanding how these changes impact employees helps in determining the best ways to manage the changes in order to develop a balanced approach to implementation and adaption of IA within an organisation. The empirical study followed a qualitative research design, featuring qualitative data collection and analysis techniques. Secondary data were collected and displayed in order to show case v hoe IA project were implemented into the organisation. The philosophical paradigm that suited a study of this nature was interpretivism as the research was socially constructed in its aim to understand the adoption processes of the organisation implementing an IA programme. The research followed an inductive approach as the study’s conceptual framework was developed based on data collected and conclusions drawn through the analysis of this data. The study involved the collection of data through the use of interviews conducted across junior and senior management levels within the business units impacted by the changes associated with the IA journey. The aim of these interviews was to gain an understanding of employees’ perceptions of the IA journey across the organisation as well as understand the experiences of those involved in the IA programme. Secondary data was also collected from five SAFI use cases, which provided a rich source for quantitative data. The presentation of results regarding the outcomes of use cases implemented across the organisation is in accordance to the University of Johannesburg Code of Academic and Research Ethics. The research findings informed the development of a conceptual framework, which can be used to encourage a balanced approach towards IA implementation and adoption throughout an organisation that is experiencing major changes. This study reveals that employees’ fears of the changes need to be identified and managed early in order to avoid resistance to the changes and negative perceptions of the technology being created. The conceptual framework identifies the components that a financial institution can use in its balanced approach to increase adoption and reduce fears. Moreover, the study revealed the need for organisations to invest in technologies of the future and the benefits that this technology can have for the organisation. Customer experience and expectations form a vital part of any organisation and the lessons learnt in the value this technology can provide in creating a great customer experience are invaluable. The study revealed that there is a difference between digitisation and automation and that knowledge-based automation technology plays a key role in enabling a digital customer experience... , M.Phil. (Information Management)
- Full Text:
- Authors: Elsworth, Catherine
- Date: 2018
- Subjects: Industrial revolution , Artificial intelligence , Banks and banking - Technological innovations , Banks and banking - Customer services , Knowledge management , Banks and banking - Information technology
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/402839 , uj:33730
- Description: Abstract : Intelligent Automation (IA) entails advanced knowledge-based technologies associated with the so-called Fourth Industrial Revolution (4IR). In this study, the phrase “IA journey” refers to the processes of knowledge-based automation and new workforce implementation. The study’s unit of analysis is not as much the IA journey itself, rather it is an analysis of what constitutes a balanced approach to IA implementation and adoption within an organisation. For example, employees’ feelings of uncertainty during an organisation’s IA journey could cause an imbalance in staff morale and resistance from employees to adapt to the changes. Therefore, the main research question of this study is: What are the components of a balanced approach to knowledge-based automation and new workforce implementation of a financial institution? The research question aligns to the world of service delivery that is changing at an alarming rate, with customers expecting fast, personalised, digital service. The landscape for financial institutions is changing, for example, traditional competitors are taking steps to meet customer demands and non-traditional competitors are entering the market place, threatening the existence of traditional financial institutions, commonly referred to as banks. The literature reveals that the evolution of Internet usage and the influence of social media and smart phones have increased the significance of technology and digital service in the financial services industry. Adoptions of these technologies is vital if traditional banks want to remain relevant in the market where financial technologies companies (Fintechs), and small, digitally nimble start-ups can provide the quick, personalised service that customers expect. Already many financial institutions have started to investigate the opportunities that technologies such as IA and chatbots provide. The potential of chatbot technology to improve customer experience and reduce operational costs make it an attractive option for organisations to consider. Literature reveals that the cost of implementation of this technology is a fraction of the cost of legacy system re-writes. The ability of this technology to integrate with existing systems and improve turnaround time and service to customers makes the IA journey a favourable choice. The IA journey of one South African Financial Institution (SAFI) formed the focus of this study. Research was conducted within the SAFI into the application of this technology across the organisation to understand the impact that the changes experienced had on the employees of the organisation. Understanding how these changes impact employees helps in determining the best ways to manage the changes in order to develop a balanced approach to implementation and adaption of IA within an organisation. The empirical study followed a qualitative research design, featuring qualitative data collection and analysis techniques. Secondary data were collected and displayed in order to show case v hoe IA project were implemented into the organisation. The philosophical paradigm that suited a study of this nature was interpretivism as the research was socially constructed in its aim to understand the adoption processes of the organisation implementing an IA programme. The research followed an inductive approach as the study’s conceptual framework was developed based on data collected and conclusions drawn through the analysis of this data. The study involved the collection of data through the use of interviews conducted across junior and senior management levels within the business units impacted by the changes associated with the IA journey. The aim of these interviews was to gain an understanding of employees’ perceptions of the IA journey across the organisation as well as understand the experiences of those involved in the IA programme. Secondary data was also collected from five SAFI use cases, which provided a rich source for quantitative data. The presentation of results regarding the outcomes of use cases implemented across the organisation is in accordance to the University of Johannesburg Code of Academic and Research Ethics. The research findings informed the development of a conceptual framework, which can be used to encourage a balanced approach towards IA implementation and adoption throughout an organisation that is experiencing major changes. This study reveals that employees’ fears of the changes need to be identified and managed early in order to avoid resistance to the changes and negative perceptions of the technology being created. The conceptual framework identifies the components that a financial institution can use in its balanced approach to increase adoption and reduce fears. Moreover, the study revealed the need for organisations to invest in technologies of the future and the benefits that this technology can have for the organisation. Customer experience and expectations form a vital part of any organisation and the lessons learnt in the value this technology can provide in creating a great customer experience are invaluable. The study revealed that there is a difference between digitisation and automation and that knowledge-based automation technology plays a key role in enabling a digital customer experience... , M.Phil. (Information Management)
- Full Text:
Leadership capabilities and opportunity realisation in the Fourth Industrial Revolution
- Authors: Venter, Johannes
- Date: 2019
- Subjects: Leadership , Technological innovations - Management , Industrial revolution , Artificial intelligence , Coal mines and mining - South Africa
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/446406 , uj:39090
- Description: M.Com. (Business Management) , Abstract: The study explored the leadership capabilities required to realise opportunities brought by the fourth industrial revolution in the South African coal mining sector. A qualitative research paradigm methodology was used. During the literature review references by other researchers were used to form a basic understanding of the origins of 4IR as well as how 4IR is used to modernise the mining sector, considering the current mining industry economic condition. The governments involvement as well as other industries like manufacturing in Industry 4.0 were also explored. Leadership evolution, risks and challenges through the industrial revolutions were furthermore researched and broaden the study’s knowledge base. A total of ten leadership professionals in the coal mining industry that has expert knowledge and experience with 4IR was interviewed and provided valuable input to the study. The research data transcripts were analysed for themes and subthemes that emerged repeatedly...
- Full Text:
- Authors: Venter, Johannes
- Date: 2019
- Subjects: Leadership , Technological innovations - Management , Industrial revolution , Artificial intelligence , Coal mines and mining - South Africa
- Language: English
- Type: Masters (Thesis)
- Identifier: http://hdl.handle.net/10210/446406 , uj:39090
- Description: M.Com. (Business Management) , Abstract: The study explored the leadership capabilities required to realise opportunities brought by the fourth industrial revolution in the South African coal mining sector. A qualitative research paradigm methodology was used. During the literature review references by other researchers were used to form a basic understanding of the origins of 4IR as well as how 4IR is used to modernise the mining sector, considering the current mining industry economic condition. The governments involvement as well as other industries like manufacturing in Industry 4.0 were also explored. Leadership evolution, risks and challenges through the industrial revolutions were furthermore researched and broaden the study’s knowledge base. A total of ten leadership professionals in the coal mining industry that has expert knowledge and experience with 4IR was interviewed and provided valuable input to the study. The research data transcripts were analysed for themes and subthemes that emerged repeatedly...
- Full Text: