A Model for Intrusion Detection in IoT using Machine Learning
- Authors: Nkala, Junior Ruddy
- Date: 2019
- Subjects: Internet of things
- Language: English
- Type: Thesis , Masters , MSc (Computer Science )
- Identifier: http://hdl.handle.net/10353/17180 , vital:40863
- Description: The Internet of Things is an open and comprehensive global network of intelligent objects that have the capacity to auto-organize, share information, data and resources. There are currently over a billion devices connected to the Internet, and this number increases by the day. While these devices make our life easier, safer and healthier, they are expanding the number of attack targets vulnerable to cyber-attacks from potential hackers and malicious software. Therefore, protecting these devices from adversaries and unauthorized access and modification is very important. The purpose of this study is to develop a secure lightweight intrusion and anomaly detection model for IoT to help detect threats in the environment. We propose the use of data mining and machine learning algorithms as a classification technique for detecting abnormal or malicious traffic transmitted between devices due to potential attacks such as DoS, Man-In-Middle and Flooding attacks at the application level. This study makes use of two robust machine learning algorithms, namely the C4.5 Decision Trees and K-means clustering to develop an anomaly detection model. MATLAB Math Simulator was used for implementation. The study conducts a series of experiments in detecting abnormal data and normal data in a dataset that contains gas concentration readings from a number of sensors deployed in an Italian city over a year. Thereafter we examined the classification performance in terms of accuracy of our proposed anomaly detection model. Results drawn from the experiments conducted indicate that the size of the training sample improves classification ability of the proposed model. Our findings noted that the choice of discretization algorithm does matter in the quest for optimal classification performance. The proposed model proved accurate in detecting anomalies in IoT, and classifying between normal and abnormal data. The proposed model has a classification accuracy of 96.51% which proved to be higher compared to other algorithms such as the Naïve Bayes. The model proved to be lightweight and efficient in-terms of being faster at training and testing as compared to Artificial Neural Networks. The conclusions drawn from this research are a perspective from a novice machine learning researcher with valuable recommendations that ensure optimal classification of normal and abnormal IoT data.
- Full Text:
- Date Issued: 2019
- Authors: Nkala, Junior Ruddy
- Date: 2019
- Subjects: Internet of things
- Language: English
- Type: Thesis , Masters , MSc (Computer Science )
- Identifier: http://hdl.handle.net/10353/17180 , vital:40863
- Description: The Internet of Things is an open and comprehensive global network of intelligent objects that have the capacity to auto-organize, share information, data and resources. There are currently over a billion devices connected to the Internet, and this number increases by the day. While these devices make our life easier, safer and healthier, they are expanding the number of attack targets vulnerable to cyber-attacks from potential hackers and malicious software. Therefore, protecting these devices from adversaries and unauthorized access and modification is very important. The purpose of this study is to develop a secure lightweight intrusion and anomaly detection model for IoT to help detect threats in the environment. We propose the use of data mining and machine learning algorithms as a classification technique for detecting abnormal or malicious traffic transmitted between devices due to potential attacks such as DoS, Man-In-Middle and Flooding attacks at the application level. This study makes use of two robust machine learning algorithms, namely the C4.5 Decision Trees and K-means clustering to develop an anomaly detection model. MATLAB Math Simulator was used for implementation. The study conducts a series of experiments in detecting abnormal data and normal data in a dataset that contains gas concentration readings from a number of sensors deployed in an Italian city over a year. Thereafter we examined the classification performance in terms of accuracy of our proposed anomaly detection model. Results drawn from the experiments conducted indicate that the size of the training sample improves classification ability of the proposed model. Our findings noted that the choice of discretization algorithm does matter in the quest for optimal classification performance. The proposed model proved accurate in detecting anomalies in IoT, and classifying between normal and abnormal data. The proposed model has a classification accuracy of 96.51% which proved to be higher compared to other algorithms such as the Naïve Bayes. The model proved to be lightweight and efficient in-terms of being faster at training and testing as compared to Artificial Neural Networks. The conclusions drawn from this research are a perspective from a novice machine learning researcher with valuable recommendations that ensure optimal classification of normal and abnormal IoT data.
- Full Text:
- Date Issued: 2019
A model for smart factories in the pharmaceutical manufacturing sector
- Authors: Mugwagwa, Basil
- Date: 2019
- Subjects: Internet of things , Manufacturing processes -- Automation Drug factories Pharmaceutical technology
- Language: English
- Type: Thesis , Masters , MBA
- Identifier: http://hdl.handle.net/10948/41897 , vital:36607
- Description: Since the turn of the century, the manufacturing industry has metamorphosed from manually driven systems to digitalisation. Product life cycles have shortened and customer demands have become more intense. Globalisation has brought about challenges that drive the need for smart manufacturing. Industry 4.0 has emerged as a response to these demands. The integration of various processes, facilities and systems throughout the value chain and digitalisation of physical systems is promoted in Industry 4.0. Due to increased competitive pressures, organisations are strategically looking at automation to deliver competitive advantage in delivering products at the right cost, quality, time and volumes to the customers. Organisations are therefore looking for manufacturing solutions that are technology driven, such as cyber-physical systems, big data, collaborative robots and the Internet of Things. This allows autonomous communication throughout the value chain between machine-to-machine and human-to-machine. The smart factory, a component of Industry 4.0, is a self-organised, modular, highly flexible and reconfigurable factory that enables the production of customised products at low cost, therefore maximising profitability. Smart manufacturing can bring about competitive advantages for an organisation. Labour concerns have been raised against automation and smart manufacturing, citing potential job losses, workforce redundancy and potential employee lay-offs. This unease, in turn, influences the employees’ attitude towards technology, which could lead either to its acceptance or refusal. The purpose of this research is to enhance the understanding of smart factories in the pharmaceutical industry by conducting a systematic analysis of the factors which influence the attitude of those involved towards a smart factory implementation. This study focuses on the perceptions among employees and management. The research is a quantitative study consisting of a literature review of the key concepts related to Industry 4.0, smart factories and technology-acceptance theories. The empirical study consisted of surveys completed by management and employees of one of the pharmaceutical manufacturers in South Africa. The questionnaire used in this research consists of questions regarding demographic data and questions regarding the perception of change and factors influencing attitudes towards the acceptance of technology, within the pharmaceutical manufacturing company. Descriptive statistics were used to summarise the data into a more condensed form, which could simplify the identification of patterns in the data. Inferential statistics were used to validate if the conclusions made from the sample data could be inferred to a larger population. Various factors influence perceptions about ease of use and usefulness, which then, in turn, influence attitudes and the intention to use technology. These factors have been examined by numerous authors in the technology acceptance literature. Recommended factors based on the statistical analysis of the questionnaire results were identified. A model, supported by Exploratory Factor Analysis, Correlations and ANOVA Testing identified the following factors as having an influence on the Attitude towards the Positive Impact of Smart Factories, within the pharmaceutical manufacturing company: Training and Development, Individual Characteristics, Trust, Organisational Culture, Resources and Costs and Job Security. The importance of each factor was identified to understand its function how to improve the implementation of smart factories. The research results indicated that the perception of management and employees is different on factors like such as Training, Individual Characteristics, Trust, Resources and Costs, Automation and Support and Parent Company in relation to technology acceptance. There was however no difference in perception between managers and employees on Security, Government Laws and Regulations, Organisational Culture, Peer Support and Organisational Support in relation to technology acceptance. The research study contributed to the identification and understanding of the factors influencing the implementation of smart factories in the pharmaceutical industry.
- Full Text:
- Date Issued: 2019
- Authors: Mugwagwa, Basil
- Date: 2019
- Subjects: Internet of things , Manufacturing processes -- Automation Drug factories Pharmaceutical technology
- Language: English
- Type: Thesis , Masters , MBA
- Identifier: http://hdl.handle.net/10948/41897 , vital:36607
- Description: Since the turn of the century, the manufacturing industry has metamorphosed from manually driven systems to digitalisation. Product life cycles have shortened and customer demands have become more intense. Globalisation has brought about challenges that drive the need for smart manufacturing. Industry 4.0 has emerged as a response to these demands. The integration of various processes, facilities and systems throughout the value chain and digitalisation of physical systems is promoted in Industry 4.0. Due to increased competitive pressures, organisations are strategically looking at automation to deliver competitive advantage in delivering products at the right cost, quality, time and volumes to the customers. Organisations are therefore looking for manufacturing solutions that are technology driven, such as cyber-physical systems, big data, collaborative robots and the Internet of Things. This allows autonomous communication throughout the value chain between machine-to-machine and human-to-machine. The smart factory, a component of Industry 4.0, is a self-organised, modular, highly flexible and reconfigurable factory that enables the production of customised products at low cost, therefore maximising profitability. Smart manufacturing can bring about competitive advantages for an organisation. Labour concerns have been raised against automation and smart manufacturing, citing potential job losses, workforce redundancy and potential employee lay-offs. This unease, in turn, influences the employees’ attitude towards technology, which could lead either to its acceptance or refusal. The purpose of this research is to enhance the understanding of smart factories in the pharmaceutical industry by conducting a systematic analysis of the factors which influence the attitude of those involved towards a smart factory implementation. This study focuses on the perceptions among employees and management. The research is a quantitative study consisting of a literature review of the key concepts related to Industry 4.0, smart factories and technology-acceptance theories. The empirical study consisted of surveys completed by management and employees of one of the pharmaceutical manufacturers in South Africa. The questionnaire used in this research consists of questions regarding demographic data and questions regarding the perception of change and factors influencing attitudes towards the acceptance of technology, within the pharmaceutical manufacturing company. Descriptive statistics were used to summarise the data into a more condensed form, which could simplify the identification of patterns in the data. Inferential statistics were used to validate if the conclusions made from the sample data could be inferred to a larger population. Various factors influence perceptions about ease of use and usefulness, which then, in turn, influence attitudes and the intention to use technology. These factors have been examined by numerous authors in the technology acceptance literature. Recommended factors based on the statistical analysis of the questionnaire results were identified. A model, supported by Exploratory Factor Analysis, Correlations and ANOVA Testing identified the following factors as having an influence on the Attitude towards the Positive Impact of Smart Factories, within the pharmaceutical manufacturing company: Training and Development, Individual Characteristics, Trust, Organisational Culture, Resources and Costs and Job Security. The importance of each factor was identified to understand its function how to improve the implementation of smart factories. The research results indicated that the perception of management and employees is different on factors like such as Training, Individual Characteristics, Trust, Resources and Costs, Automation and Support and Parent Company in relation to technology acceptance. There was however no difference in perception between managers and employees on Security, Government Laws and Regulations, Organisational Culture, Peer Support and Organisational Support in relation to technology acceptance. The research study contributed to the identification and understanding of the factors influencing the implementation of smart factories in the pharmaceutical industry.
- Full Text:
- Date Issued: 2019
South Africa’s readiness of the smart built environment towards 2035
- Authors: Holmes, Clinton Keith
- Date: 2019
- Subjects: Internet of things , City planning Technology -- Social aspects
- Language: English
- Type: Thesis , Masters , MBA
- Identifier: http://hdl.handle.net/10948/40128 , vital:35758
- Description: It is imperative that society works together with government and industry to find solutions in solving the problem of the high utilisation of natural resources in the built environment. Natural resources are not infinite, and the increasing population are compounding the problem. The high level of unemployment in South Africa could be increased dramatically if the old skills in the industry become redundant due to new technology and there are not enough skills to apply to these technologies. This study set out to investigate the extent of the readiness of South Africa for the Smart built environment towards 2035 with an aim to provide valuable information for decision making to the government, policy makers, academic and training institutions and business leaders. South Africa boasts about the achievements of the four major municipalities namely, Cape Town, Johannesburg, Tshwane and eThekwini in terms of their commitment towards the aim for net zero carbon emissions of newly built buildings by 2050. The commitment for sustainable solutions in all sectors is echoed by the Minister of Environmental affairs, as part of the Paris agreement. South Africa does not lack the ability to plan for eventualities. This is evident by the myriad of strategies and policies that can be found all over the government information sharing outlets. The South African government is failing in implementing these policies and strategies that have been around for more than a decade. A lack of execution, lack of transparency as well as a lack of accountability is a hindrance to South Africa’s general growth path. The realisation of the preferred future rest on the acceptance, by all South Africans, that technological advancement is inevitable, and that a joint and inclusive effort should be made to prepare for such a future. South Africa has the ability and appetite to change the future for the better. Two fundamental areas of improvement are to create a united South Africa where people are held accountable for their actions. The unisons should transcend across the various South African government departments but must also include industry, entrepreneurs and the public to create a future where technology is embraced, and innovation encouraged, instead of waiting for technology to dictate a specific future.
- Full Text:
- Date Issued: 2019
- Authors: Holmes, Clinton Keith
- Date: 2019
- Subjects: Internet of things , City planning Technology -- Social aspects
- Language: English
- Type: Thesis , Masters , MBA
- Identifier: http://hdl.handle.net/10948/40128 , vital:35758
- Description: It is imperative that society works together with government and industry to find solutions in solving the problem of the high utilisation of natural resources in the built environment. Natural resources are not infinite, and the increasing population are compounding the problem. The high level of unemployment in South Africa could be increased dramatically if the old skills in the industry become redundant due to new technology and there are not enough skills to apply to these technologies. This study set out to investigate the extent of the readiness of South Africa for the Smart built environment towards 2035 with an aim to provide valuable information for decision making to the government, policy makers, academic and training institutions and business leaders. South Africa boasts about the achievements of the four major municipalities namely, Cape Town, Johannesburg, Tshwane and eThekwini in terms of their commitment towards the aim for net zero carbon emissions of newly built buildings by 2050. The commitment for sustainable solutions in all sectors is echoed by the Minister of Environmental affairs, as part of the Paris agreement. South Africa does not lack the ability to plan for eventualities. This is evident by the myriad of strategies and policies that can be found all over the government information sharing outlets. The South African government is failing in implementing these policies and strategies that have been around for more than a decade. A lack of execution, lack of transparency as well as a lack of accountability is a hindrance to South Africa’s general growth path. The realisation of the preferred future rest on the acceptance, by all South Africans, that technological advancement is inevitable, and that a joint and inclusive effort should be made to prepare for such a future. South Africa has the ability and appetite to change the future for the better. Two fundamental areas of improvement are to create a united South Africa where people are held accountable for their actions. The unisons should transcend across the various South African government departments but must also include industry, entrepreneurs and the public to create a future where technology is embraced, and innovation encouraged, instead of waiting for technology to dictate a specific future.
- Full Text:
- Date Issued: 2019
- «
- ‹
- 1
- ›
- »