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
An investigation of Raymond Mhlaba municipality indigent policy on water service delivery: a case study of free basic water policy (FBWP) in selected areas of Golf Course and Bhofolo.
- Authors: Ncube, Mary Silibaziso
- Date: 2019
- Subjects: Community development
- Language: English
- Type: Thesis , Masters , MCom (Development Studies)
- Identifier: http://hdl.handle.net/10353/16974 , vital:40799
- Description: The study was looking at the Free Basic Water policy (FBWP) in the Eastern Cape which was introduced in July 2001 in South Africa. FBWP was introduced to all provinces, however people living in rural areas, poor areas and villages are still suffering from lack of clean and safe drinking water. People lack adequate supplies of water and this creates conditions under which the diseases thrive. The researcher used mixed research methodology which comprises of qualitative (interview) and quantitative (questionnaire) approaches. The reason for the use of mixed methodology was to get adequate information both from the municipality (the provider of water) and the residents (the receivers of the services provided by the municipality) in order to assess how the unreliable water provision affect residents and the challenges being faced by the municipality in providing water. The findings of the study are that both people under Golf course and Bhofolo have little knowledge about FBW and most of the residents are unable to pay their water bills. Residents in the two research areas suffer from medical problems due to unreliable water provision. The study is therefore, of view that South Africa needs to prioritise improvement of access to water in rural areas, poor areas and villages. There is a need to educate people about FBW and on how to save water.
- Full Text:
- Date Issued: 2019
- Authors: Ncube, Mary Silibaziso
- Date: 2019
- Subjects: Community development
- Language: English
- Type: Thesis , Masters , MCom (Development Studies)
- Identifier: http://hdl.handle.net/10353/16974 , vital:40799
- Description: The study was looking at the Free Basic Water policy (FBWP) in the Eastern Cape which was introduced in July 2001 in South Africa. FBWP was introduced to all provinces, however people living in rural areas, poor areas and villages are still suffering from lack of clean and safe drinking water. People lack adequate supplies of water and this creates conditions under which the diseases thrive. The researcher used mixed research methodology which comprises of qualitative (interview) and quantitative (questionnaire) approaches. The reason for the use of mixed methodology was to get adequate information both from the municipality (the provider of water) and the residents (the receivers of the services provided by the municipality) in order to assess how the unreliable water provision affect residents and the challenges being faced by the municipality in providing water. The findings of the study are that both people under Golf course and Bhofolo have little knowledge about FBW and most of the residents are unable to pay their water bills. Residents in the two research areas suffer from medical problems due to unreliable water provision. The study is therefore, of view that South Africa needs to prioritise improvement of access to water in rural areas, poor areas and villages. There is a need to educate people about FBW and on how to save water.
- Full Text:
- Date Issued: 2019
The state and local government joint account system and performance of local government councils in Nigeria: a case study of Awgu local council of Enugu state (1999-2016)
- Authors: Okafor, Chukwuemeka
- Date: 2019
- Subjects: Local finance --Nigeria Local government-- Nigeria Intergovernmental fiscal relations|
- Language: English
- Type: Thesis , Masters , M.Admin
- Identifier: http://hdl.handle.net/10353/13917 , vital:39727
- Description: The State and Local Government Joint Account system was introduced in the 1999 Constitution of the Federal Republic of Nigeria with the basic aim of pooling all the financial allocations due to the various local government councils from the Federation Account for onward distribution by the states to the local councils. This is to ensure that the state governments effectively control and monitor expenditure by the executives of the local government councils and also to ensure that the funds are properly allocated to various areas of need. This provision is contained in Section 162 (5) of the Constitution which states that “the amount standing to the credit of local government councils in the Federation Account shall also be allocated to the states for the benefit of their local government councils on such terms and in such manner as may be prescribed by the National Assembly”. Section 162 (7) also states that “each state shall pay to local government councils in its area of jurisdiction such proportion of its total revenue on such terms and in such manner as may be prescribed by the National Assembly”. However, this arrangement has not worked well as state governments continue to manipulate the joint account through illegal deductions, misappropriations, deliberate delays in disbursement and in failure to remit their 10% of internally generated revenue as stipulated in the Constitution. This study examines the State and Local Government Joint Account system in relation to the fiscal autonomy of local government councils and the impact of the joint account system on public service delivery at Awgu Local Government Council. The study used the qualitative methodology design with focus on case-study approach. Data was collected from both primary and secondary sources. Primary data was collected through interviews from stakeholders in the joint account system and secondary data collected from relevant textual sources. The study findings show that this relationship affects the fiscal autonomy of local councils and result in cases of illegal deductions, withholding of funds, refusal to remit statutory 10% of total revenue of states to local councils. In Awgu Local Government from 1999-2016, more than N3billion was withheld and this amounts to a deficit of about 22.5%. This has negatively affected the volume of service delivery to the various communities. Based on these findings, the study recommends for a constitutional review to strengthen the local government system to effectively function as the third tier of government in line with the “Guidelines for1976 Local Government Reforms”. The study also recommends the abolishing of the joint account system and granting local councils full fiscal autonomy. This is the desideratum for enhanced service delivery at Awgu Local Government and other local council areas of Enugu State.
- Full Text:
- Date Issued: 2019
- Authors: Okafor, Chukwuemeka
- Date: 2019
- Subjects: Local finance --Nigeria Local government-- Nigeria Intergovernmental fiscal relations|
- Language: English
- Type: Thesis , Masters , M.Admin
- Identifier: http://hdl.handle.net/10353/13917 , vital:39727
- Description: The State and Local Government Joint Account system was introduced in the 1999 Constitution of the Federal Republic of Nigeria with the basic aim of pooling all the financial allocations due to the various local government councils from the Federation Account for onward distribution by the states to the local councils. This is to ensure that the state governments effectively control and monitor expenditure by the executives of the local government councils and also to ensure that the funds are properly allocated to various areas of need. This provision is contained in Section 162 (5) of the Constitution which states that “the amount standing to the credit of local government councils in the Federation Account shall also be allocated to the states for the benefit of their local government councils on such terms and in such manner as may be prescribed by the National Assembly”. Section 162 (7) also states that “each state shall pay to local government councils in its area of jurisdiction such proportion of its total revenue on such terms and in such manner as may be prescribed by the National Assembly”. However, this arrangement has not worked well as state governments continue to manipulate the joint account through illegal deductions, misappropriations, deliberate delays in disbursement and in failure to remit their 10% of internally generated revenue as stipulated in the Constitution. This study examines the State and Local Government Joint Account system in relation to the fiscal autonomy of local government councils and the impact of the joint account system on public service delivery at Awgu Local Government Council. The study used the qualitative methodology design with focus on case-study approach. Data was collected from both primary and secondary sources. Primary data was collected through interviews from stakeholders in the joint account system and secondary data collected from relevant textual sources. The study findings show that this relationship affects the fiscal autonomy of local councils and result in cases of illegal deductions, withholding of funds, refusal to remit statutory 10% of total revenue of states to local councils. In Awgu Local Government from 1999-2016, more than N3billion was withheld and this amounts to a deficit of about 22.5%. This has negatively affected the volume of service delivery to the various communities. Based on these findings, the study recommends for a constitutional review to strengthen the local government system to effectively function as the third tier of government in line with the “Guidelines for1976 Local Government Reforms”. The study also recommends the abolishing of the joint account system and granting local councils full fiscal autonomy. This is the desideratum for enhanced service delivery at Awgu Local Government and other local council areas of Enugu State.
- Full Text:
- Date Issued: 2019
- «
- ‹
- 1
- ›
- »