A survey of machine learning methods applied to anomaly detection on drinking-water quality data
- Dogo, Eustace M., Nwulu, Nnamdi I., Twala, Bhekisipho, Aigbavboa, Clinton
- Authors: Dogo, Eustace M. , Nwulu, Nnamdi I. , Twala, Bhekisipho , Aigbavboa, Clinton
- Date: 2019
- Subjects: Machine learning , Anomaly detection , Deep learning
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/406768 , uj:34213 , Citation: Dogo, E.M. et al. 2019. A survey of machine learning methods applied to anomaly detection on drinking-water quality data.
- Description: Abstract: Traditional machine learning (ML) techniques such as support vector machine, logistic regression, and artificial neural network have been applied most frequently in water quality anomaly detection tasks. This paper presents a review of progress and advances made in detecting anomalies in water quality data using ML techniques. The review encompasses both traditional ML and deep learning (DL) approaches. Our findings indicate that: 1) Generally, DL approaches outperform traditional ML techniques in terms of feature learning accuracy and fewer false positive rates. However, is difficult to make a fair comparison between studies because of different datasets, models and parameters employed. 2) We notice that despite advances made and the advantages of the extreme learning machine (ELM), application of ELM is sparsely exploited in this domain. This study also proposes a hybrid DL-ELM framework as a possible solution that could be investigated further and used to detect anomalies in water quality data.
- Full Text:
- Authors: Dogo, Eustace M. , Nwulu, Nnamdi I. , Twala, Bhekisipho , Aigbavboa, Clinton
- Date: 2019
- Subjects: Machine learning , Anomaly detection , Deep learning
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/406768 , uj:34213 , Citation: Dogo, E.M. et al. 2019. A survey of machine learning methods applied to anomaly detection on drinking-water quality data.
- Description: Abstract: Traditional machine learning (ML) techniques such as support vector machine, logistic regression, and artificial neural network have been applied most frequently in water quality anomaly detection tasks. This paper presents a review of progress and advances made in detecting anomalies in water quality data using ML techniques. The review encompasses both traditional ML and deep learning (DL) approaches. Our findings indicate that: 1) Generally, DL approaches outperform traditional ML techniques in terms of feature learning accuracy and fewer false positive rates. However, is difficult to make a fair comparison between studies because of different datasets, models and parameters employed. 2) We notice that despite advances made and the advantages of the extreme learning machine (ELM), application of ELM is sparsely exploited in this domain. This study also proposes a hybrid DL-ELM framework as a possible solution that could be investigated further and used to detect anomalies in water quality data.
- Full Text:
An access optimization approach for FFH-OCDMA system’s fiber bragg gratings encoder
- Nlend, Samuel, Swart, Theo G., Twala, Bhekisipho
- Authors: Nlend, Samuel , Swart, Theo G. , Twala, Bhekisipho
- Date: 2017
- Subjects: Bragg gratings , FFH-OCDMA , Multiaccess communication
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/243869 , uj:25211 , Citation: Nlend, S., Swart, T.G. & Twala, B. 2017. An access optimization approach for FFH-OCDMA system’s fiber bragg gratings encoder.
- Description: Abstract: This paper suggests an adaptive 2-D Optical CDMA coding system based on one-coincidence frequency hopping (OCFH) code combined with an optical orthogonal code (OOC) in the format OCFH/OOC, suitable for the fast frequency hopping optical code division multiple access (FFH-OCDMA) channel, encoded by the Bragg gratings encoder with an aim to optimize the access network in terms of number of users and transmitted power. As wavelength hopping (WH) code, the OCFH code is herein adapted to the constraints of the encoder: the Bragg gratings chain put on the optical fiber...
- Full Text:
- Authors: Nlend, Samuel , Swart, Theo G. , Twala, Bhekisipho
- Date: 2017
- Subjects: Bragg gratings , FFH-OCDMA , Multiaccess communication
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/243869 , uj:25211 , Citation: Nlend, S., Swart, T.G. & Twala, B. 2017. An access optimization approach for FFH-OCDMA system’s fiber bragg gratings encoder.
- Description: Abstract: This paper suggests an adaptive 2-D Optical CDMA coding system based on one-coincidence frequency hopping (OCFH) code combined with an optical orthogonal code (OOC) in the format OCFH/OOC, suitable for the fast frequency hopping optical code division multiple access (FFH-OCDMA) channel, encoded by the Bragg gratings encoder with an aim to optimize the access network in terms of number of users and transmitted power. As wavelength hopping (WH) code, the OCFH code is herein adapted to the constraints of the encoder: the Bragg gratings chain put on the optical fiber...
- Full Text:
Constitutive modelling of INCONEL 718 using artificial neural network
- Abiri, Olufunminiyi, Twala, Bhekisipho
- Authors: Abiri, Olufunminiyi , Twala, Bhekisipho
- Date: 2017
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/250881 , uj:26155 , Citation: Abiri, O. & Twala, B. 2017. Constitutive modelling of INCONEL 718 using artificial neural network.
- Description: Abstract: Artificial neural network is used to model INCONEL 718 in this paper. The model accounts for precipitate hardening in the alloy. The input variables for the neural network model are strain, strain rate, temperature and microstructure state. The output variable is the flow stress. The early stopping technique is combined with Bayesian regularization process in training the network. Sample and non-sample measurement data were taken from the literature. The model predictions of flow stress of the alloy are in good agreement with experimental measurements.
- Full Text:
- Authors: Abiri, Olufunminiyi , Twala, Bhekisipho
- Date: 2017
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/250881 , uj:26155 , Citation: Abiri, O. & Twala, B. 2017. Constitutive modelling of INCONEL 718 using artificial neural network.
- Description: Abstract: Artificial neural network is used to model INCONEL 718 in this paper. The model accounts for precipitate hardening in the alloy. The input variables for the neural network model are strain, strain rate, temperature and microstructure state. The output variable is the flow stress. The early stopping technique is combined with Bayesian regularization process in training the network. Sample and non-sample measurement data were taken from the literature. The model predictions of flow stress of the alloy are in good agreement with experimental measurements.
- Full Text:
Creating social learning spaces to enhance the learning experience
- Madhav, Natasha, Joseph, Meera K., Twala, Bhekisipho
- Authors: Madhav, Natasha , Joseph, Meera K. , Twala, Bhekisipho
- Date: 2015-06-04
- Subjects: Social media , Educational technology
- Type: Article
- Identifier: uj:5145 , http://hdl.handle.net/10210/14187
- Description: Social media has been used effectively for teaching and learning for many years in developed countries. It seems there needs to be an understanding of the affordances that social media could bring to the learning space in the African context. We use qualitative research and content analysis to see how and why the learners used social media in a private Higher Educational (HE) institution in South Africa to enhance their learning experience. The course was split into face-to-face lectures and social media use by the learners and facilitators. The learners were required to engage with various social media tools to collaborate and share skills with their classmates and facilitators. We also explore the affordance of social media. Content analysis was done to see the participation of the learners in the course’s Facebook page. Data was also collected from the focus groups that led to findings that indicate that WEB 2.0 tools had the potential to support learner collaboration that is self-directed and engaging. Learners adopted social media with confidence and used it to learn beyond the borders of the physical classroom. Daily interactions and the sharing of artefacts resulted in an informal and vibrant learning ecology that became self-sustainable ...
- Full Text:
- Authors: Madhav, Natasha , Joseph, Meera K. , Twala, Bhekisipho
- Date: 2015-06-04
- Subjects: Social media , Educational technology
- Type: Article
- Identifier: uj:5145 , http://hdl.handle.net/10210/14187
- Description: Social media has been used effectively for teaching and learning for many years in developed countries. It seems there needs to be an understanding of the affordances that social media could bring to the learning space in the African context. We use qualitative research and content analysis to see how and why the learners used social media in a private Higher Educational (HE) institution in South Africa to enhance their learning experience. The course was split into face-to-face lectures and social media use by the learners and facilitators. The learners were required to engage with various social media tools to collaborate and share skills with their classmates and facilitators. We also explore the affordance of social media. Content analysis was done to see the participation of the learners in the course’s Facebook page. Data was also collected from the focus groups that led to findings that indicate that WEB 2.0 tools had the potential to support learner collaboration that is self-directed and engaging. Learners adopted social media with confidence and used it to learn beyond the borders of the physical classroom. Daily interactions and the sharing of artefacts resulted in an informal and vibrant learning ecology that became self-sustainable ...
- Full Text:
Effect of rotor barrier pitch angle on torque ripple production in synchronous reluctance machines
- Muteba, Mbika, Twala, Bhekisipho, Nicolae, Dan-Valentin
- Authors: Muteba, Mbika , Twala, Bhekisipho , Nicolae, Dan-Valentin
- Date: 2016
- Subjects: Barrier pitch angle , Synchronous reluctance machines , Torque density
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/123832 , uj:20841 , Citation: Muteba, M., Twala, B & Nicolae, D.V. 2016. Effect of rotor barrier pitch angle on torque ripple production in synchronous reluctance machines.
- Description: Abstract: This paper analyses the effect of rotor barrier pitch angles on torque ripple production in Synchronous Reluctance Machines (SynRMs), with the objective to reduce torque ripple contents in medium size ground Electric Vehicles (EVs). While keeping major-design parameters constant, the barrier pitch angle is varied by a quarter of the stator slot pitch. Three SynRMs having different rotor barrier pitch angles are designed and modeled using 2D Finite Element Method (FEM). The specifications of a traditional 5.5 kW, three-phase, 50 Hz, induction machine are used to design and model the SynRMs. Torque ripple reduction of ± 48 % is achieved for barrier pitch angles of 15o and 17.5o mech, when the machines operate at current space phasor angle of 45o electric.
- Full Text:
- Authors: Muteba, Mbika , Twala, Bhekisipho , Nicolae, Dan-Valentin
- Date: 2016
- Subjects: Barrier pitch angle , Synchronous reluctance machines , Torque density
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/123832 , uj:20841 , Citation: Muteba, M., Twala, B & Nicolae, D.V. 2016. Effect of rotor barrier pitch angle on torque ripple production in synchronous reluctance machines.
- Description: Abstract: This paper analyses the effect of rotor barrier pitch angles on torque ripple production in Synchronous Reluctance Machines (SynRMs), with the objective to reduce torque ripple contents in medium size ground Electric Vehicles (EVs). While keeping major-design parameters constant, the barrier pitch angle is varied by a quarter of the stator slot pitch. Three SynRMs having different rotor barrier pitch angles are designed and modeled using 2D Finite Element Method (FEM). The specifications of a traditional 5.5 kW, three-phase, 50 Hz, induction machine are used to design and model the SynRMs. Torque ripple reduction of ± 48 % is achieved for barrier pitch angles of 15o and 17.5o mech, when the machines operate at current space phasor angle of 45o electric.
- Full Text:
Electric power grids distribution generation system for optimal location and sizing — a case study investigation by various optimization algorithms
- Ali, Ahmed, Padmanaban, Sanjeevikumar, Twala, Bhekisipho, Marwala, Tshilidzi
- Authors: Ali, Ahmed , Padmanaban, Sanjeevikumar , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2017
- Subjects: Optimization , Simulated annealing , Genetic algorithm
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/278669 , uj:29908 , Citation: Ali, A., Padmanaban, S., Twala, B. & Marwala, T. 2017. Electric power grids distribution generation system for optimal location and sizing — a case study investigation by various optimization algorithms. Energies 2017, 10, 960; doi:10.3390/en10070960
- Description: Abstract: Abstract: In this paper, the approach focused on the variables involved in assessing the quality of a distributed generation system are reviewed in detail, for its investigation and research contribution. The aim to minimize the electric power losses (unused power consumption) and optimize the voltage profile for the power system under investigation. To provide this assessment, several experiments have been made to the IEEE 34-bus test case and various actual test cases with the respect of multiple Distribution Generation DG units. The possibility and effectiveness of the proposed algorithm for optimal placement and sizing of DG in distribution systems have been verified. Finally, four algorithms were trailed: simulated annealing (SA), hybrid genetic algorithm (HGA), genetic algorithm (GA), and variable neighbourhood search. The HGA algorithm was found to produce the best solution at a cost of a longer processing time.
- Full Text:
- Authors: Ali, Ahmed , Padmanaban, Sanjeevikumar , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2017
- Subjects: Optimization , Simulated annealing , Genetic algorithm
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/278669 , uj:29908 , Citation: Ali, A., Padmanaban, S., Twala, B. & Marwala, T. 2017. Electric power grids distribution generation system for optimal location and sizing — a case study investigation by various optimization algorithms. Energies 2017, 10, 960; doi:10.3390/en10070960
- Description: Abstract: Abstract: In this paper, the approach focused on the variables involved in assessing the quality of a distributed generation system are reviewed in detail, for its investigation and research contribution. The aim to minimize the electric power losses (unused power consumption) and optimize the voltage profile for the power system under investigation. To provide this assessment, several experiments have been made to the IEEE 34-bus test case and various actual test cases with the respect of multiple Distribution Generation DG units. The possibility and effectiveness of the proposed algorithm for optimal placement and sizing of DG in distribution systems have been verified. Finally, four algorithms were trailed: simulated annealing (SA), hybrid genetic algorithm (HGA), genetic algorithm (GA), and variable neighbourhood search. The HGA algorithm was found to produce the best solution at a cost of a longer processing time.
- Full Text:
Ensemble missing data techniques for software effort prediction
- Twala, Bhekisipho, Cartwright, Michelle
- Authors: Twala, Bhekisipho , Cartwright, Michelle
- Date: 2010
- Subjects: Software engineering - Forecasting
- Type: Article
- Identifier: uj:4670 , ISSN 1088-467X , http://hdl.handle.net/10210/10428
- Description: Constructing an accurate effort prediction model is a challenge in software engineering. The development and validation of models that are used for prediction tasks require good quality data. Unfortunately, software engineering datasets tend to suffer from the incompleteness which could result to inaccurate decision making and project management and implementation. Recently, the use of machine learning algorithms has proven to be of great practical value in solving a variety of software engineering problems including software prediction, including the use of ensemble (combining) classifiers. Research indicates that ensemble individual classifiers lead to a significant improvement in classification performance by having them vote for the most popular class. This paper proposes a method for improving software effort prediction accuracy produced by a decision tree learning algorithm and by generating the ensemble using two imputation methods as elements. Benchmarking results on ten industrial datasets show that the proposed ensemble strategy has the potential to improve prediction accuracy compared to an individual imputation method, especially if multiple imputation is a component of the ensemble.
- Full Text:
- Authors: Twala, Bhekisipho , Cartwright, Michelle
- Date: 2010
- Subjects: Software engineering - Forecasting
- Type: Article
- Identifier: uj:4670 , ISSN 1088-467X , http://hdl.handle.net/10210/10428
- Description: Constructing an accurate effort prediction model is a challenge in software engineering. The development and validation of models that are used for prediction tasks require good quality data. Unfortunately, software engineering datasets tend to suffer from the incompleteness which could result to inaccurate decision making and project management and implementation. Recently, the use of machine learning algorithms has proven to be of great practical value in solving a variety of software engineering problems including software prediction, including the use of ensemble (combining) classifiers. Research indicates that ensemble individual classifiers lead to a significant improvement in classification performance by having them vote for the most popular class. This paper proposes a method for improving software effort prediction accuracy produced by a decision tree learning algorithm and by generating the ensemble using two imputation methods as elements. Benchmarking results on ten industrial datasets show that the proposed ensemble strategy has the potential to improve prediction accuracy compared to an individual imputation method, especially if multiple imputation is a component of the ensemble.
- Full Text:
First principle leakage current reduction technique for CMOS devices
- Tsague, Hippolyte Djonon, Twala, Bhekisipho
- Authors: Tsague, Hippolyte Djonon , Twala, Bhekisipho
- Date: 2015
- Subjects: Differential power analysis , High-K dielectric gate , Smart card
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/18233 , uj:15974 , Citation: Tsague, H.D. & Twala, B. 2015. First principle leakage current reduction technique for CMOS devices. International Conference on Computing Communication and Security, December 4-6, 2015, Le Meridien, Pointes aux piments, Pamplemouses, Mauritius. 6p.
- Description: Abstract: This paper presents a comprehensive study of leakage reduction techniques applicable to CMOS based devices. In the process, mathematical equations that model the powerperformance trade-offs in CMOS logic circuits are presented. From those equations, suitable techniques for leakage reduction as pertaining to CMOS devices are deduced. Throughout this research it became evident that designing CMOS devices with high-κ dielectrics is a viable method for reducing leakages in cryptographic devices. To support our claim, a 22nm NMOS device was built and simulated in Athena software from Silvaco. The electrical characteristics of the fabricated device were extracted using the Atlas component of the simulator. From this research, it became evident that high-κ dielectric metal gate are capable of providing a reliable resistance to DPA and other form of attacks on cryptographic platforms such as smart card.The fabricated device showed a marked improvement on the I on/I off ratio, where the higher ratio means that the device is suitable for low power applications. Physical models used for simulation included Si3N4 and HfO2 as gate dielectric with TiSix as metal gate. From the simulation result, it was shown that HfO2 was the best dielectric material when TiSix is used as the metal gate.
- Full Text:
- Authors: Tsague, Hippolyte Djonon , Twala, Bhekisipho
- Date: 2015
- Subjects: Differential power analysis , High-K dielectric gate , Smart card
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/18233 , uj:15974 , Citation: Tsague, H.D. & Twala, B. 2015. First principle leakage current reduction technique for CMOS devices. International Conference on Computing Communication and Security, December 4-6, 2015, Le Meridien, Pointes aux piments, Pamplemouses, Mauritius. 6p.
- Description: Abstract: This paper presents a comprehensive study of leakage reduction techniques applicable to CMOS based devices. In the process, mathematical equations that model the powerperformance trade-offs in CMOS logic circuits are presented. From those equations, suitable techniques for leakage reduction as pertaining to CMOS devices are deduced. Throughout this research it became evident that designing CMOS devices with high-κ dielectrics is a viable method for reducing leakages in cryptographic devices. To support our claim, a 22nm NMOS device was built and simulated in Athena software from Silvaco. The electrical characteristics of the fabricated device were extracted using the Atlas component of the simulator. From this research, it became evident that high-κ dielectric metal gate are capable of providing a reliable resistance to DPA and other form of attacks on cryptographic platforms such as smart card.The fabricated device showed a marked improvement on the I on/I off ratio, where the higher ratio means that the device is suitable for low power applications. Physical models used for simulation included Si3N4 and HfO2 as gate dielectric with TiSix as metal gate. From the simulation result, it was shown that HfO2 was the best dielectric material when TiSix is used as the metal gate.
- Full Text:
Forecasting electricity consumption in South Africa : ARMA, neural networks and neuro-fuzzy systems
- Marwala, Lufuno, Twala, Bhekisipho
- Authors: Marwala, Lufuno , Twala, Bhekisipho
- Date: 2014
- Subjects: Neural networks , Electric power consumption , Fuzzy systems , ARMA models
- Type: Article
- Identifier: uj:5090 , http://hdl.handle.net/10210/13678
- Description: This paper presents an experiment that consists of constructing auto-regressive moving average (ARMA), neural networks and neuro-fuzzy models with historical electricity consumptiontime series data to create models that can be used to forecastconsumption inthe future. The data was sampled on a monthly basis from January 1985 to December 2011. An ARMA,multilayer perceptron neural network with back propagation and neuro-fuzzy modelling technique which combines Takagi-Sugeno fuzzy models and neural networks were used to create the models for one step ahead forecasting. The results of the three techniques were compared and the results show that neurofuzzy models outperformed the neural network and ARMA models in terms of accuracy.
- Full Text:
- Authors: Marwala, Lufuno , Twala, Bhekisipho
- Date: 2014
- Subjects: Neural networks , Electric power consumption , Fuzzy systems , ARMA models
- Type: Article
- Identifier: uj:5090 , http://hdl.handle.net/10210/13678
- Description: This paper presents an experiment that consists of constructing auto-regressive moving average (ARMA), neural networks and neuro-fuzzy models with historical electricity consumptiontime series data to create models that can be used to forecastconsumption inthe future. The data was sampled on a monthly basis from January 1985 to December 2011. An ARMA,multilayer perceptron neural network with back propagation and neuro-fuzzy modelling technique which combines Takagi-Sugeno fuzzy models and neural networks were used to create the models for one step ahead forecasting. The results of the three techniques were compared and the results show that neurofuzzy models outperformed the neural network and ARMA models in terms of accuracy.
- Full Text:
Gold mine dam levels and energy consumption classification using artificial intelligence methods
- Hasan, Ali N., Twala, Bhekisipho, Marwala, Tshilidzi
- Authors: Hasan, Ali N. , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2013
- Subjects: Support vector machines , Energy monitoring , Ensembles
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16619 , uj:15789 , Citation: Hasan, A.N., Twala, B. & Marwala, T. 2013. Gold mine dam levels and energy consumption classification using artificial intelligence methods. IEEE Business Engineering and Industrial Applications Colloquium (BEIAC):623–628. , ISBN: 978-1-4673-5968-9
- Description: Abstract: In this paper a comparison between two single classifier methods (support vector machine, artificial neural network) and two ensemble methods (bagging, and boosting) is applied to a real-world mining problem. The four methods are used to classify, thus monitoring underground dam levels and underground pumps energy consumption on a doublepump station deep gold in South Africa. In terms of misclassification error, the results show support vector machines (SVM) to be more efficient for classification of underground pumps energy consumption compared to artificial neural network (ANN),...
- Full Text:
- Authors: Hasan, Ali N. , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2013
- Subjects: Support vector machines , Energy monitoring , Ensembles
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16619 , uj:15789 , Citation: Hasan, A.N., Twala, B. & Marwala, T. 2013. Gold mine dam levels and energy consumption classification using artificial intelligence methods. IEEE Business Engineering and Industrial Applications Colloquium (BEIAC):623–628. , ISBN: 978-1-4673-5968-9
- Description: Abstract: In this paper a comparison between two single classifier methods (support vector machine, artificial neural network) and two ensemble methods (bagging, and boosting) is applied to a real-world mining problem. The four methods are used to classify, thus monitoring underground dam levels and underground pumps energy consumption on a doublepump station deep gold in South Africa. In terms of misclassification error, the results show support vector machines (SVM) to be more efficient for classification of underground pumps energy consumption compared to artificial neural network (ANN),...
- Full Text:
Improving single classifiers prediction accuracy for underground water pump station in a gold mine using ensemble techniques
- Hasan, Ali N, Twala, Bhekisipho
- Authors: Hasan, Ali N , Twala, Bhekisipho
- Date: 2015
- Subjects: Mutual information , Support vector machines , Prediction
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/85649 , uj:19373 , Citation: Hasan,, A.N. & Twala, B. 2015. Improving single classifiers prediction accuracy for underground water pump station in a gold mine using ensemble techniques.
- Description: Abstract: In this paper six single classifiers (support vector machine, artificial neural network, naïve Bayesian classifier, decision trees, radial basis function and k nearest neighbors) were utilized to predict water dam levels in a deep gold mine underground pump station. Also, Bagging and Boosting ensemble techniques were used to increase the prediction accuracy of the single classifiers. In order to enhance the prediction accuracy even more a mutual information ensemble approach is introduced to improve the single classifiers and the Bagging and Boosting prediction results. This ensemble is used to classify, thus monitoring and predicting the underground water dam levels on a single-pump station deep gold mine in South Africa, Mutual information theory is used in order to determine the classifiers optimum number to build the most accurate ensemble. In terms of prediction accuracy, the results show that the mutual information ensemble over performed the other used ensembles and single classifiers and is more efficient for classification of underground water dam levels. However the ensemble construction is more complicated than the Bagging and Boosting techniques.
- Full Text:
- Authors: Hasan, Ali N , Twala, Bhekisipho
- Date: 2015
- Subjects: Mutual information , Support vector machines , Prediction
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/85649 , uj:19373 , Citation: Hasan,, A.N. & Twala, B. 2015. Improving single classifiers prediction accuracy for underground water pump station in a gold mine using ensemble techniques.
- Description: Abstract: In this paper six single classifiers (support vector machine, artificial neural network, naïve Bayesian classifier, decision trees, radial basis function and k nearest neighbors) were utilized to predict water dam levels in a deep gold mine underground pump station. Also, Bagging and Boosting ensemble techniques were used to increase the prediction accuracy of the single classifiers. In order to enhance the prediction accuracy even more a mutual information ensemble approach is introduced to improve the single classifiers and the Bagging and Boosting prediction results. This ensemble is used to classify, thus monitoring and predicting the underground water dam levels on a single-pump station deep gold mine in South Africa, Mutual information theory is used in order to determine the classifiers optimum number to build the most accurate ensemble. In terms of prediction accuracy, the results show that the mutual information ensemble over performed the other used ensembles and single classifiers and is more efficient for classification of underground water dam levels. However the ensemble construction is more complicated than the Bagging and Boosting techniques.
- Full Text:
Improving the performance of the Rpper in insurance risk classification : a comparative study using feature selection
- Duma, Mlungisi, Twala, Bhekisipho, Marwala, Tshilidzi
- Authors: Duma, Mlungisi , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2011
- Subjects: Automatic relevance determination , Ripper algorithm , Artificial neural networks
- Type: Article
- Identifier: uj:4709 , http://hdl.handle.net/10210/10954
- Description: The Ripper algorithm is designed to generate rule sets for large datasets with many features. However, it was shown that the algorithm struggles with classification performance in the presence of missing data. The algorithm struggles to classify instances when the quality of the data deteriorates as a result of increasing missing data. In this paper, a feature selection technique is used to help improve the classification performance of the Ripper model. Principal component analysis and evidence automatic relevance determination techniques are used to improve the performance. A comparison is done to see which technique helps the algorithm improve the most. Training datasets with completely observable data were used to construct the model and testing datasets with missing values were used for measuring accuracy. The results showed that principal component analysis is a better feature selection for the Ripper in improving the classification performance.
- Full Text:
- Authors: Duma, Mlungisi , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2011
- Subjects: Automatic relevance determination , Ripper algorithm , Artificial neural networks
- Type: Article
- Identifier: uj:4709 , http://hdl.handle.net/10210/10954
- Description: The Ripper algorithm is designed to generate rule sets for large datasets with many features. However, it was shown that the algorithm struggles with classification performance in the presence of missing data. The algorithm struggles to classify instances when the quality of the data deteriorates as a result of increasing missing data. In this paper, a feature selection technique is used to help improve the classification performance of the Ripper model. Principal component analysis and evidence automatic relevance determination techniques are used to improve the performance. A comparison is done to see which technique helps the algorithm improve the most. Training datasets with completely observable data were used to construct the model and testing datasets with missing values were used for measuring accuracy. The results showed that principal component analysis is a better feature selection for the Ripper in improving the classification performance.
- Full Text:
Leakage current minimisation and power reduction techniques using sub-threshold design
- Tsague, Hippolyte Djonon, Twala, Bhekisipho
- Authors: Tsague, Hippolyte Djonon , Twala, Bhekisipho
- Date: 2015
- Subjects: Power dissipation , Weak inversion , Ultra-low-power , Leakage currents , Power analysis
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/18211 , uj:15971 , Citation: Tsague, H.D. & Twala, B. 2015. Leakage current minimisation and power reduction techniques using sub-threshold design. International Conference on Information Society (i-Society 2015), 9-11 November 2015, London UK. p. 146-150.
- Description: Abstract: Low power IC solutions are in great demand with the rapid advancement of handheld devices, wearables, smart cards and radio frequency identification bringing a massive amount of new products to market that all have the same primary need: Powering the device as long as possible between the need to re- charge the batteries while at the same time dramatically decreasing the device leakage currents. The use of sub-threshold techniques can be a powerful way to create circuits that consume dramatically less energy than those built using standard design practices. In this research, a SOI device was built to compare their electrical characteristics using Silvaco software. The comparisons were focus! ed on three main electrical characteristics that are threshold voltage, sub-threshold voltage and leakage current. It was found that SOI devices are ideal candidates for low power operation.
- Full Text:
- Authors: Tsague, Hippolyte Djonon , Twala, Bhekisipho
- Date: 2015
- Subjects: Power dissipation , Weak inversion , Ultra-low-power , Leakage currents , Power analysis
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/18211 , uj:15971 , Citation: Tsague, H.D. & Twala, B. 2015. Leakage current minimisation and power reduction techniques using sub-threshold design. International Conference on Information Society (i-Society 2015), 9-11 November 2015, London UK. p. 146-150.
- Description: Abstract: Low power IC solutions are in great demand with the rapid advancement of handheld devices, wearables, smart cards and radio frequency identification bringing a massive amount of new products to market that all have the same primary need: Powering the device as long as possible between the need to re- charge the batteries while at the same time dramatically decreasing the device leakage currents. The use of sub-threshold techniques can be a powerful way to create circuits that consume dramatically less energy than those built using standard design practices. In this research, a SOI device was built to compare their electrical characteristics using Silvaco software. The comparisons were focus! ed on three main electrical characteristics that are threshold voltage, sub-threshold voltage and leakage current. It was found that SOI devices are ideal candidates for low power operation.
- Full Text:
Modelling the flow stress of alloy 316L using a multi-layered feedforward neural network with Bayesian regularization
- Abiri, Olufunminiyi, Twala, Bhekisipho
- Authors: Abiri, Olufunminiyi , Twala, Bhekisipho
- Date: 2017
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/250824 , uj:26146 , Citation: Abiri, O. & Twala, B. 2017. Modelling the flow stress of alloy 316L using a multi-layered feedforward neural network with Bayesian regularization.
- Description: Abstract: In this paper, a multilayer feedforward neural network with Bayesian regularization constitutive model is developed for alloy 316L during high strain rate and high temperature plastic deformation. The input variables are strain rate, temperature and strain while the output value is the flow stress of the material. The results show that the use of Bayesian regularized technique reduces the potential of overfitting and overtraining. The prediction quality of the model is thereby improved. The model predictions are in good agreement with experimental measurements. The measurement data used for the network training and model comparison were taken from relevant literature. The developed model is robust as it can be generalized to deformation conditions slightly below or above the training dataset.
- Full Text:
- Authors: Abiri, Olufunminiyi , Twala, Bhekisipho
- Date: 2017
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/250824 , uj:26146 , Citation: Abiri, O. & Twala, B. 2017. Modelling the flow stress of alloy 316L using a multi-layered feedforward neural network with Bayesian regularization.
- Description: Abstract: In this paper, a multilayer feedforward neural network with Bayesian regularization constitutive model is developed for alloy 316L during high strain rate and high temperature plastic deformation. The input variables are strain rate, temperature and strain while the output value is the flow stress of the material. The results show that the use of Bayesian regularized technique reduces the potential of overfitting and overtraining. The prediction quality of the model is thereby improved. The model predictions are in good agreement with experimental measurements. The measurement data used for the network training and model comparison were taken from relevant literature. The developed model is robust as it can be generalized to deformation conditions slightly below or above the training dataset.
- Full Text:
Optimal placement model of TCSC in power system network considering the budget available
- Malatji, Esrom Mahlatsi, Twala, Bhekisipho, Mbuli, Nhlanhla
- Authors: Malatji, Esrom Mahlatsi , Twala, Bhekisipho , Mbuli, Nhlanhla
- Date: 2017
- Subjects: TCSC , Budget , Genetic algorithm
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/247472 , uj:25696 , Citation: Malatji, E.M., Twala, B. & Mbuli, N. 2017. Optimal placement model of TCSC in power system network considering the budget available.
- Description: Abstract: This paper presents an optimal placement of TCSC which is a FACTS (Flexible Alternative Current transmission Systems) controller in order to increase the loadbility of the system. The optimization problem is solved using the genetic algorithm. In this study the availablity of the budget is taken in consideration. The result show that the increase in loadability can be restricted by the availability of budget and also that beyond a certain budget there will not be any further increase in loadability. Also beyond a certain number of TCSC there will be no further increase in system loadability.
- Full Text:
- Authors: Malatji, Esrom Mahlatsi , Twala, Bhekisipho , Mbuli, Nhlanhla
- Date: 2017
- Subjects: TCSC , Budget , Genetic algorithm
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/247472 , uj:25696 , Citation: Malatji, E.M., Twala, B. & Mbuli, N. 2017. Optimal placement model of TCSC in power system network considering the budget available.
- Description: Abstract: This paper presents an optimal placement of TCSC which is a FACTS (Flexible Alternative Current transmission Systems) controller in order to increase the loadbility of the system. The optimization problem is solved using the genetic algorithm. In this study the availablity of the budget is taken in consideration. The result show that the increase in loadability can be restricted by the availability of budget and also that beyond a certain budget there will not be any further increase in loadability. Also beyond a certain number of TCSC there will be no further increase in system loadability.
- Full Text:
Optimization of the compressed air-usage in South African mines
- Hassan, Ali, Ouahada, Khmaies, Marwala, Tshilidzi, Twala, Bhekisipho
- Authors: Hassan, Ali , Ouahada, Khmaies , Marwala, Tshilidzi , Twala, Bhekisipho
- Date: 2011
- Subjects: Demand side management , Energy efficiency , Mines , Compressed air
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16393 , uj:15768 , Citation: Hassan, A. et al. 2011. Optimization of the compressed air-usage in South African mines. IEEE Africon, 13-15 September, 2011, Zambia.
- Description: Abstract: The critical electricity supply in South Africa has necessitated the implementation of demand-side management (DSM) projects. Load shifting and energy efficiency projects were introduced on mining sectors to reduce the electricity usage during day peak time...
- Full Text:
- Authors: Hassan, Ali , Ouahada, Khmaies , Marwala, Tshilidzi , Twala, Bhekisipho
- Date: 2011
- Subjects: Demand side management , Energy efficiency , Mines , Compressed air
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16393 , uj:15768 , Citation: Hassan, A. et al. 2011. Optimization of the compressed air-usage in South African mines. IEEE Africon, 13-15 September, 2011, Zambia.
- Description: Abstract: The critical electricity supply in South Africa has necessitated the implementation of demand-side management (DSM) projects. Load shifting and energy efficiency projects were introduced on mining sectors to reduce the electricity usage during day peak time...
- Full Text:
Predicting engineering student success using machine learning
- Taodzera, Tatenda, Twala, Bhekisipho, Carroll, Johnson
- Authors: Taodzera, Tatenda , Twala, Bhekisipho , Carroll, Johnson
- Date: 2017
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/236143 , uj:24160 , Citation: Taodzera, T., Twala, B. & Carroll, J. 2017. Predicting engineering student success using machine learning.
- Description: Abstract: Recent years have seen an increase in the number of students from diverse backgrounds enrolling into South African universities, presenting many challenges. Some students struggle with their academic choices, and universities struggle to understand and address the individual needs of such a diverse student base. Fortunately, vast amounts of student information have been collected and stored, giving an opportunity for researchers in educational data mining to derive some useful insights from this data to help both the universities and students. This research aims to identify factors that contribute to the success and or failure of a student, then predict the future performance of the student at enrolment. By using data pre-processing techniques, the experiments identify the most significant success factors from the data at enrolment time. The most significant factors can then be used to identify students who may need extra support, and the nature of those factors can help determine the manner of support needed. This study implemented and evaluated the effectiveness of the most commonly used and new machine learning algorithms in predicting student performance on a sample of 1366 engineering students. The results show various degrees of success in predicting student performance, and it is hoped that these findings will guide the selection of machine learning algorithms for future studies.
- Full Text:
- Authors: Taodzera, Tatenda , Twala, Bhekisipho , Carroll, Johnson
- Date: 2017
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/236143 , uj:24160 , Citation: Taodzera, T., Twala, B. & Carroll, J. 2017. Predicting engineering student success using machine learning.
- Description: Abstract: Recent years have seen an increase in the number of students from diverse backgrounds enrolling into South African universities, presenting many challenges. Some students struggle with their academic choices, and universities struggle to understand and address the individual needs of such a diverse student base. Fortunately, vast amounts of student information have been collected and stored, giving an opportunity for researchers in educational data mining to derive some useful insights from this data to help both the universities and students. This research aims to identify factors that contribute to the success and or failure of a student, then predict the future performance of the student at enrolment. By using data pre-processing techniques, the experiments identify the most significant success factors from the data at enrolment time. The most significant factors can then be used to identify students who may need extra support, and the nature of those factors can help determine the manner of support needed. This study implemented and evaluated the effectiveness of the most commonly used and new machine learning algorithms in predicting student performance on a sample of 1366 engineering students. The results show various degrees of success in predicting student performance, and it is hoped that these findings will guide the selection of machine learning algorithms for future studies.
- Full Text:
Predicting mine dam levels and energy consumption using artificial intelligence methods
- Hasan, Ali N., Twala, Bhekisipho, Marwala, Tshilidzi
- Authors: Hasan, Ali N. , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2013
- Subjects: Machine learning algorithms , De-watering system , Energy consumption
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16857 , uj:15816 , Citation: Hasan, A.N., Twala, B. & T Marwala. 2013. Predicting mine dam levels and energy consumption using artificial intelligence methods. IEEE Computational Intelligence for Engineering Solutions (CIES), Singapore:171-175. DOI: 10.1109/cies.2013.6611745
- Description: Abstract: Four machine learning algorithms (artificial neural networks, a naive Bayes' classifier, a support vector machines and decision trees) wwere applied for a single pump station mine to monitor and predict the dam levels and energy consumption.
- Full Text:
- Authors: Hasan, Ali N. , Twala, Bhekisipho , Marwala, Tshilidzi
- Date: 2013
- Subjects: Machine learning algorithms , De-watering system , Energy consumption
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16857 , uj:15816 , Citation: Hasan, A.N., Twala, B. & T Marwala. 2013. Predicting mine dam levels and energy consumption using artificial intelligence methods. IEEE Computational Intelligence for Engineering Solutions (CIES), Singapore:171-175. DOI: 10.1109/cies.2013.6611745
- Description: Abstract: Four machine learning algorithms (artificial neural networks, a naive Bayes' classifier, a support vector machines and decision trees) wwere applied for a single pump station mine to monitor and predict the dam levels and energy consumption.
- Full Text:
Predicting software faults in large space systems using machine learning techniques
- Authors: Twala, Bhekisipho
- Date: 2011-07-04
- Subjects: Software metrics , Machine learning , Fault-proneness prediction , Ensemble classifiers
- Type: Article
- Identifier: uj:5314 , ISSN 0011-748X , http://hdl.handle.net/10210/7754
- Description: Recently, the use of machine learning (ML) algorithms has proven to be of great practical value in solving a variety of engineering problems including the prediction of failure, fault, and defect-proneness as the space system software becomes complex. One of the most active areas of recent research in ML has been the use of ensemble classifiers. How ML techniques (or classifiers) could be used to predict software faults in space systems, including many aerospace systems is shown, and further use ensemble individual classifiers by having them vote for the most popular class to improve system software fault-proneness prediction. Benchmarking results on four NASA public datasets show the Naive Bayes classifier as more robust software fault prediction while most ensembles with a decision tree classifier as one of its components achieve higher accuracy rates.
- Full Text:
- Authors: Twala, Bhekisipho
- Date: 2011-07-04
- Subjects: Software metrics , Machine learning , Fault-proneness prediction , Ensemble classifiers
- Type: Article
- Identifier: uj:5314 , ISSN 0011-748X , http://hdl.handle.net/10210/7754
- Description: Recently, the use of machine learning (ML) algorithms has proven to be of great practical value in solving a variety of engineering problems including the prediction of failure, fault, and defect-proneness as the space system software becomes complex. One of the most active areas of recent research in ML has been the use of ensemble classifiers. How ML techniques (or classifiers) could be used to predict software faults in space systems, including many aerospace systems is shown, and further use ensemble individual classifiers by having them vote for the most popular class to improve system software fault-proneness prediction. Benchmarking results on four NASA public datasets show the Naive Bayes classifier as more robust software fault prediction while most ensembles with a decision tree classifier as one of its components achieve higher accuracy rates.
- Full Text:
Simulation and parameter optimization of polysilicon gate biaxial strained silicon MOSFETs
- Tsague, Hippolyte Djonon, Twala, Bhekisipho
- Authors: Tsague, Hippolyte Djonon , Twala, Bhekisipho
- Date: 2015
- Subjects: Cryptographic keys , Side channel , MOSFET , Biaxial , Strained , Silicon , Leakage currents , Sub-threshold voltage , Encryption
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/18137 , uj:15963 , Citation: Tsague, H.D. & Twala, B. 2015. Simulation and parameter optimization of polysilicon gate biaxial strained silicon MOSFETs. Fifth International Conference on Digital Information, Processing and Communications (ICDIPC2015), October 7-9, 2015, Sierre, Switzerland. p.38-43. ISBN: 978-1-4673-6832-2
- Description: Abstract: Although cryptography constitutes a considerable part of the overall security architecture for several use cases in embedded systems, cryptographic devices are still vulnerable to the diversity types of side channel attacks. Improvement in performance of Strained Silicon MOSFETs utilizing conventional device scaling has become more complex, because of the amount of physical limitations associated with the device miniaturization. Therefore, a great deal of attention has recently been paid to the mobility improvement technology through applying strain to CMOS channels. This paper reviews the characteristics of strained-Si CMOS with an emphasis on the mechanism of mobility enhancement due to strain. The device physics for improving the performance of MOSFETs is studied from the viewpoint of electronic states of carriers in inversion layers and, in particular, the sub-band structures. In addition, design and simulation of biaxial strained silicon NMOSFET (n-channel) is done using Silvaco’s Athena/Atlas simulator. From the results obtained, it became clear that biaxial strained silicon NMOS is one of the best alternatives to the current conventional MOSFET.
- Full Text:
- Authors: Tsague, Hippolyte Djonon , Twala, Bhekisipho
- Date: 2015
- Subjects: Cryptographic keys , Side channel , MOSFET , Biaxial , Strained , Silicon , Leakage currents , Sub-threshold voltage , Encryption
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/18137 , uj:15963 , Citation: Tsague, H.D. & Twala, B. 2015. Simulation and parameter optimization of polysilicon gate biaxial strained silicon MOSFETs. Fifth International Conference on Digital Information, Processing and Communications (ICDIPC2015), October 7-9, 2015, Sierre, Switzerland. p.38-43. ISBN: 978-1-4673-6832-2
- Description: Abstract: Although cryptography constitutes a considerable part of the overall security architecture for several use cases in embedded systems, cryptographic devices are still vulnerable to the diversity types of side channel attacks. Improvement in performance of Strained Silicon MOSFETs utilizing conventional device scaling has become more complex, because of the amount of physical limitations associated with the device miniaturization. Therefore, a great deal of attention has recently been paid to the mobility improvement technology through applying strain to CMOS channels. This paper reviews the characteristics of strained-Si CMOS with an emphasis on the mechanism of mobility enhancement due to strain. The device physics for improving the performance of MOSFETs is studied from the viewpoint of electronic states of carriers in inversion layers and, in particular, the sub-band structures. In addition, design and simulation of biaxial strained silicon NMOSFET (n-channel) is done using Silvaco’s Athena/Atlas simulator. From the results obtained, it became clear that biaxial strained silicon NMOS is one of the best alternatives to the current conventional MOSFET.
- Full Text: