Development of effective cuckoo search algorithms for optimisation purposes
- Authors: Mareli, Mahlaku
- Date: 2018
- Subjects: Computational intelligence , Computer algorithms , Mathematical optimization - Data processing , Computer networks
- Language: English
- Type: Doctoral (Thesis)
- Identifier: http://hdl.handle.net/10210/295009 , uj:32110
- Description: Abstract: Optimisation, the process of finding either a maximum of a minimum of the problem at hand plays a key role in several disciplines including engineering and science. In this thesis, different Cuckoo Search algorithms are developed for effective optimisation purposes. These algorithms are tested on ten mathematical test functions and then used to optimise a Back-Propagation Neural Network used for short-term electricity load forecasting for South African data, with the focus on the City of Johannesburg. The original Cuckoo Search algorithm is based on random walk step sizes derived from Lévy probability distribution and the switching parameter between local and global random walks is constant. However, other probability distributions like Cauchy, Gaussian and Gamma have also been used and the switching parameter can be changed dynamically. The first contribution of the thesis is the development a new Cuckoo Search algorithm whose random step sizes are derived from Pareto probability distribution function. This new Pareto-based Cuckoo Search algorithm is tested on ten benchmark test functions together with other Cuckoo Search algorithms using step sizes derived from Gaussian, Cauchy, Gamma and Lévy probability density functions. When using the confidence interval analysis, the Lévy-based Cuckoo Search algorithm outperforms the Pareto based Cuckoo. However, confidence interval results are only superior due to only one test function whereby Lévy-based Cuckoo Search performed well. Moreover, the Pareto-based Cuckoo shows superior performance in comparison to the other algorithms, leading in seven test functions out of ten when tested for convergence. The second contribution is the implementation of Cuckoo Search algorithms with dynamically increasing switching parameters between local and random walks. The first improvement done on Cuckoo Search algorithm is the implementation of linear increasing switching parameter, the second is the implementation of power increasing switching parameter and the third improvement is the implementation of exponential increasing switching parameter. When tested on benchmark test functions, the exponentially increasing Cuckoo Search algorithm outperforms the other algorithms by obtaining the longest confidence interval of 4.50566 while the next algorithm (original Cuckoo Search) obtains an interval of 3.9699. Moreover, using convergence plots, both... , D.Ing. (Electrical and Electronic Engineering)
- Full Text:
- Authors: Mareli, Mahlaku
- Date: 2018
- Subjects: Computational intelligence , Computer algorithms , Mathematical optimization - Data processing , Computer networks
- Language: English
- Type: Doctoral (Thesis)
- Identifier: http://hdl.handle.net/10210/295009 , uj:32110
- Description: Abstract: Optimisation, the process of finding either a maximum of a minimum of the problem at hand plays a key role in several disciplines including engineering and science. In this thesis, different Cuckoo Search algorithms are developed for effective optimisation purposes. These algorithms are tested on ten mathematical test functions and then used to optimise a Back-Propagation Neural Network used for short-term electricity load forecasting for South African data, with the focus on the City of Johannesburg. The original Cuckoo Search algorithm is based on random walk step sizes derived from Lévy probability distribution and the switching parameter between local and global random walks is constant. However, other probability distributions like Cauchy, Gaussian and Gamma have also been used and the switching parameter can be changed dynamically. The first contribution of the thesis is the development a new Cuckoo Search algorithm whose random step sizes are derived from Pareto probability distribution function. This new Pareto-based Cuckoo Search algorithm is tested on ten benchmark test functions together with other Cuckoo Search algorithms using step sizes derived from Gaussian, Cauchy, Gamma and Lévy probability density functions. When using the confidence interval analysis, the Lévy-based Cuckoo Search algorithm outperforms the Pareto based Cuckoo. However, confidence interval results are only superior due to only one test function whereby Lévy-based Cuckoo Search performed well. Moreover, the Pareto-based Cuckoo shows superior performance in comparison to the other algorithms, leading in seven test functions out of ten when tested for convergence. The second contribution is the implementation of Cuckoo Search algorithms with dynamically increasing switching parameters between local and random walks. The first improvement done on Cuckoo Search algorithm is the implementation of linear increasing switching parameter, the second is the implementation of power increasing switching parameter and the third improvement is the implementation of exponential increasing switching parameter. When tested on benchmark test functions, the exponentially increasing Cuckoo Search algorithm outperforms the other algorithms by obtaining the longest confidence interval of 4.50566 while the next algorithm (original Cuckoo Search) obtains an interval of 3.9699. Moreover, using convergence plots, both... , D.Ing. (Electrical and Electronic Engineering)
- Full Text:
Medicines identification for African illiterate patients using near field communication
- Mareli, Mahlaku, Rimer, Suvendi, Paul, Babu Sean, Ouhada, Khmaies
- Authors: Mareli, Mahlaku , Rimer, Suvendi , Paul, Babu Sean , Ouhada, Khmaies
- Date: 2013
- Subjects: mutual inductance and Electronic Health Records , Near field communication , Electronic health records
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/17335 , uj:15873 , Mareli, M. et al. 2013. Medicines identification for African illiterate patients using near field communication. IEEE AFRICOMM, 2013, Malawi.
- Description: Abstract: This paper presents the application of Near Field Communication (NFC) to the healthcare sector. Although a number of papers have been written to discuss different NFC applications in the healthcare sector, none of them address the potential challenges facing illiterate patients worldwide. According to UNESCO institute for statistics, the Sub-Saharan African region has the highest percentage of illiterate people compared to other regions in the world. NFC can be used in conjunction with other technologies, especially mobile communications which provide high data speeds at cheap rates. The proposed NFC application consists of a NFC sticker placed on the medicine container, the NFC phone with an Android application that reads the sticker ID, connects to a Medicine Information Server and retrieves relevant instructions for medicine in audio form. Some of the advantages for this solution are that the NFC stickers can be recycled.
- Full Text:
- Authors: Mareli, Mahlaku , Rimer, Suvendi , Paul, Babu Sean , Ouhada, Khmaies
- Date: 2013
- Subjects: mutual inductance and Electronic Health Records , Near field communication , Electronic health records
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/17335 , uj:15873 , Mareli, M. et al. 2013. Medicines identification for African illiterate patients using near field communication. IEEE AFRICOMM, 2013, Malawi.
- Description: Abstract: This paper presents the application of Near Field Communication (NFC) to the healthcare sector. Although a number of papers have been written to discuss different NFC applications in the healthcare sector, none of them address the potential challenges facing illiterate patients worldwide. According to UNESCO institute for statistics, the Sub-Saharan African region has the highest percentage of illiterate people compared to other regions in the world. NFC can be used in conjunction with other technologies, especially mobile communications which provide high data speeds at cheap rates. The proposed NFC application consists of a NFC sticker placed on the medicine container, the NFC phone with an Android application that reads the sticker ID, connects to a Medicine Information Server and retrieves relevant instructions for medicine in audio form. Some of the advantages for this solution are that the NFC stickers can be recycled.
- Full Text:
Medicines identification for African illiterate patients using near field communication
- Mareli, Mahlaku, Rimer, Suvendi, Paul, Babu Sean, Ouahada, Khmaies
- Authors: Mareli, Mahlaku , Rimer, Suvendi , Paul, Babu Sean , Ouahada, Khmaies
- Date: 2014
- Subjects: Near field communication , Medicines - Identification - Technological innovations , Illiteracy
- Type: Book chapter
- Identifier: uj:5040 , ISBN 978-3-319-08368-1 , http://hdl.handle.net/10210/13560
- Description: This paper presents the application of Near Field Communication (NFC) to the healthcare sector. Although a number of papers have been written to discuss different NFC applications in the healthcare sector, none of them address the potential challenges facing illiterate patients worldwide. According to UNESCO institute for statistics, the Sub-Saharan African region has the highest percentage of illiterate people compared to other regions in the world. NFC can be used in conjunction with other technologies, especially mobile communications which provide high data speeds at cheap rates. The proposed NFC application consists of a NFC sticker placed on the medicine container, the NFC phone with an Android application that reads the sticker ID, connects to a Medicine Information Server and retrieves relevant instructions for medicine in audio form. Some of the advantages for this solution are that the NFC stickers can be recycled.
- Full Text:
- Authors: Mareli, Mahlaku , Rimer, Suvendi , Paul, Babu Sean , Ouahada, Khmaies
- Date: 2014
- Subjects: Near field communication , Medicines - Identification - Technological innovations , Illiteracy
- Type: Book chapter
- Identifier: uj:5040 , ISBN 978-3-319-08368-1 , http://hdl.handle.net/10210/13560
- Description: This paper presents the application of Near Field Communication (NFC) to the healthcare sector. Although a number of papers have been written to discuss different NFC applications in the healthcare sector, none of them address the potential challenges facing illiterate patients worldwide. According to UNESCO institute for statistics, the Sub-Saharan African region has the highest percentage of illiterate people compared to other regions in the world. NFC can be used in conjunction with other technologies, especially mobile communications which provide high data speeds at cheap rates. The proposed NFC application consists of a NFC sticker placed on the medicine container, the NFC phone with an Android application that reads the sticker ID, connects to a Medicine Information Server and retrieves relevant instructions for medicine in audio form. Some of the advantages for this solution are that the NFC stickers can be recycled.
- Full Text:
Near field communication in smart phones using MIFARE standards for illiterate patients
- Authors: Mareli, Mahlaku
- Date: 2014-09-17
- Subjects: Mobile communication systems , Near field communication , Mobile computing
- Type: Thesis
- Identifier: uj:12328 , http://hdl.handle.net/10210/12115
- Description: M.Ing. (Electrical And Electronic Engineering) , Patient safety in healthcare is sometimes compromised due to medical and clerical errors. These errors can increase the operational cost of healthcare if not identified and rectified speedily. They can also result in misdiagnosis, wrong treatment options being provided to patients and in the worst case may result in fatalities. Healthcare errors in medication documentation, administration, and prescription can cause incorrect medicine administration and dosage instructions for patients. Sub-Saharan Africa has the lowest percentage (adults is 59% and youth is 70%) of literacy compared to other regions of the world sitting at (adults is 84% and youth is 89%). The challenge facing illiterate patients is that they can easily make the same mistakes and may not take their medication correctly. The application of Near Field Communication (NFC) technology in healthcare has demonstrated some advantages of security, accuracy and effectiveness over other technologies. The availability of NFC in some smartphones has also encouraged the development of more applications. The main objective of this thesis is to present a solution using an Android based NFC application that enables a NFC enabled smartphone to read NFC tags placed on medication containers and be able to play the audio instructions to illiterate patients. Based on a comprehensive review of the literature on NFC applications in healthcare, this solution is the first of its kind. A set of experiments were done in an effort to understand the operation of NFC phones under different environments. The proposed application reads the NFC tag placed on the medicine container. The data read from the NFC tag is used to identify the audio file corresponding to the particular patient’s medicine instructions. If the audio instructions are not available, on the phone, it is fetched from a remote server database using an Internet connection. The application automatically plays the audio file to the patient. Three research hypotheses were tested and it was confirmed that (H1), modified NFC antenna can reduce the level of induced power in it; (H2), the NFC technology is faster and more accurate in reading tag code that Barcode technology reading the barcode; (H3), the NFC reading process of NFC tag code is not negatively affected by the amount of light in the environment it is operated in. The Barcode reading accuracy was 10% errors when operating in the environment with light brightness of 128000 lumens. When the light brightness was reduced to 8900 lumens, the Barcode accuracy errors increased to 45%.
- Full Text:
- Authors: Mareli, Mahlaku
- Date: 2014-09-17
- Subjects: Mobile communication systems , Near field communication , Mobile computing
- Type: Thesis
- Identifier: uj:12328 , http://hdl.handle.net/10210/12115
- Description: M.Ing. (Electrical And Electronic Engineering) , Patient safety in healthcare is sometimes compromised due to medical and clerical errors. These errors can increase the operational cost of healthcare if not identified and rectified speedily. They can also result in misdiagnosis, wrong treatment options being provided to patients and in the worst case may result in fatalities. Healthcare errors in medication documentation, administration, and prescription can cause incorrect medicine administration and dosage instructions for patients. Sub-Saharan Africa has the lowest percentage (adults is 59% and youth is 70%) of literacy compared to other regions of the world sitting at (adults is 84% and youth is 89%). The challenge facing illiterate patients is that they can easily make the same mistakes and may not take their medication correctly. The application of Near Field Communication (NFC) technology in healthcare has demonstrated some advantages of security, accuracy and effectiveness over other technologies. The availability of NFC in some smartphones has also encouraged the development of more applications. The main objective of this thesis is to present a solution using an Android based NFC application that enables a NFC enabled smartphone to read NFC tags placed on medication containers and be able to play the audio instructions to illiterate patients. Based on a comprehensive review of the literature on NFC applications in healthcare, this solution is the first of its kind. A set of experiments were done in an effort to understand the operation of NFC phones under different environments. The proposed application reads the NFC tag placed on the medicine container. The data read from the NFC tag is used to identify the audio file corresponding to the particular patient’s medicine instructions. If the audio instructions are not available, on the phone, it is fetched from a remote server database using an Internet connection. The application automatically plays the audio file to the patient. Three research hypotheses were tested and it was confirmed that (H1), modified NFC antenna can reduce the level of induced power in it; (H2), the NFC technology is faster and more accurate in reading tag code that Barcode technology reading the barcode; (H3), the NFC reading process of NFC tag code is not negatively affected by the amount of light in the environment it is operated in. The Barcode reading accuracy was 10% errors when operating in the environment with light brightness of 128000 lumens. When the light brightness was reduced to 8900 lumens, the Barcode accuracy errors increased to 45%.
- Full Text:
- «
- ‹
- 1
- ›
- »