Artificial Intelligence (AI) and blockchain technologies in advancing sustainable healthcare development in Kenya: a critique of dependency theory
- Monethi, Tlhokomelo Brigette Rethabile
- Authors: Monethi, Tlhokomelo Brigette Rethabile
- Date: 2024-10-11
- Subjects: Artificial intelligence , Blockchains (Databases) , Dependency theory , Sustainable development , Health care reform Kenya
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/466016 , vital:76677
- Description: This thesis explores the transformative potential of artificial intelligence (AI) and blockchain technologies in advancing healthcare delivery in Kenya through a critique of Dependency Theory. It investigates how these technologies contribute to improving accessibility, efficiency, and quality of care—particularly in underserved regions, while also addressing the structural dependencies that limit Kenya’s healthcare autonomy. Using a qualitative methodology, this study examines five case studies—Sophie Bot, Ilara Health, Tambua Health, AfyaRekod, and PanaBIOS—to highlight both the opportunities and challenges AI and blockchain present in reducing external reliance. Although AI-powered diagnostics and blockchain-based patient data management systems have revolutionised healthcare in Kenya, these technologies remain dependent on foreign capital and expertise for their development and maintenance. The research finds that while AI and blockchain technologies offer a path to leapfrog traditional barriers in healthcare delivery, their implementation critiques traditional notions of dependency theory. Nonetheless, the thesis identifies significant ethical considerations—including digital inequality, data privacy, and AI biases—that must be addressed to ensure equitable, self-sufficient healthcare provision. This study concludes with recommendations for fostering technological autonomy in Kenya's healthcare system, focusing on building local capacity, addressing infrastructural challenges, and aligning AI and blockchain integration with ethical and socio-cultural contexts. By doing this, this research contributes to the broader discourse on technology and healthcare in developing nations, offering pathways for reducing dependency and achieving sustainable healthcare development in Kenya. , Thesis (MA) -- Faculty of Humanities, Political and International Studies, 2024
- Full Text:
- Authors: Monethi, Tlhokomelo Brigette Rethabile
- Date: 2024-10-11
- Subjects: Artificial intelligence , Blockchains (Databases) , Dependency theory , Sustainable development , Health care reform Kenya
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/466016 , vital:76677
- Description: This thesis explores the transformative potential of artificial intelligence (AI) and blockchain technologies in advancing healthcare delivery in Kenya through a critique of Dependency Theory. It investigates how these technologies contribute to improving accessibility, efficiency, and quality of care—particularly in underserved regions, while also addressing the structural dependencies that limit Kenya’s healthcare autonomy. Using a qualitative methodology, this study examines five case studies—Sophie Bot, Ilara Health, Tambua Health, AfyaRekod, and PanaBIOS—to highlight both the opportunities and challenges AI and blockchain present in reducing external reliance. Although AI-powered diagnostics and blockchain-based patient data management systems have revolutionised healthcare in Kenya, these technologies remain dependent on foreign capital and expertise for their development and maintenance. The research finds that while AI and blockchain technologies offer a path to leapfrog traditional barriers in healthcare delivery, their implementation critiques traditional notions of dependency theory. Nonetheless, the thesis identifies significant ethical considerations—including digital inequality, data privacy, and AI biases—that must be addressed to ensure equitable, self-sufficient healthcare provision. This study concludes with recommendations for fostering technological autonomy in Kenya's healthcare system, focusing on building local capacity, addressing infrastructural challenges, and aligning AI and blockchain integration with ethical and socio-cultural contexts. By doing this, this research contributes to the broader discourse on technology and healthcare in developing nations, offering pathways for reducing dependency and achieving sustainable healthcare development in Kenya. , Thesis (MA) -- Faculty of Humanities, Political and International Studies, 2024
- Full Text:
Comparative analysis of YOLOV5 and YOLOV8 for automated fish detection and classification in underwater environments
- Authors: Kuhlane, Luxolo
- Date: 2024-10-11
- Subjects: Artificial intelligence , Deep learning (Machine learning) , Machine learning , Neural networks (Computer science) , You Only Look Once , YOLOv5 , YOLOv8
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/464333 , vital:76502
- Description: The application of traditional manual techniques for fish detection and classification faces significant challenges, primarily stemming from their labour-intensive nature and limited scalability. Automating these kinds of processes through computer vision practices and machine learning techniques has emerged as a potential solution in recent years. With the development of and increase in ease of access to new technology in recent years, the use of a deep learning object detector known as YOLO (You Only Look Once) in the detection and classification of fish has steadily become notably popular. This thesis thus explores suitable YOLO architectures for detecting and classifying fish. The YOLOv5 and YOLOv8 models were evaluated explicitly for detecting and classifying fish in underwater environments. The selection of these models was based on a literature review highlighting their success in similar applications but remains largely understudied in underwater environments. Therefore, the effectiveness of these models was evaluated through comprehensive experimentation on collected and publicly available underwater fish datasets. In collaboration with the South African Institute of Biodiversity (SAIAB), five datasets were collected and manually annotated for labels for supervised machine learning. Moreover, two publicly available datasets were sourced for comparison to the literature. Furthermore, after determining that the smallest YOLO architectures are better suited to these imbalanced datasets, hyperparameter tuning tailored the models to the characteristics of the various underwater environments used in the research. The popular DeepFish dataset was evaluated to establish a baseline and feasibility of these models in the understudied domain. The results demonstrated high detection accuracy for both YOLOv5 and YOLOv8. However, YOLOv8 outperformed YOLOv5, achieving 97.43% accuracy compared to 94.53%. After experiments on seven datasets, trends revealed YOLOv8’s enhanced generalisation accuracy due to architectural improvements, particularly in detecting smaller fish. Overall, YOLOv8 demonstrated that it is the better fish detection and classification model on diverse data. , Thesis (MSc) -- Faculty of Science, Computer Science, 2024
- Full Text:
- Authors: Kuhlane, Luxolo
- Date: 2024-10-11
- Subjects: Artificial intelligence , Deep learning (Machine learning) , Machine learning , Neural networks (Computer science) , You Only Look Once , YOLOv5 , YOLOv8
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/464333 , vital:76502
- Description: The application of traditional manual techniques for fish detection and classification faces significant challenges, primarily stemming from their labour-intensive nature and limited scalability. Automating these kinds of processes through computer vision practices and machine learning techniques has emerged as a potential solution in recent years. With the development of and increase in ease of access to new technology in recent years, the use of a deep learning object detector known as YOLO (You Only Look Once) in the detection and classification of fish has steadily become notably popular. This thesis thus explores suitable YOLO architectures for detecting and classifying fish. The YOLOv5 and YOLOv8 models were evaluated explicitly for detecting and classifying fish in underwater environments. The selection of these models was based on a literature review highlighting their success in similar applications but remains largely understudied in underwater environments. Therefore, the effectiveness of these models was evaluated through comprehensive experimentation on collected and publicly available underwater fish datasets. In collaboration with the South African Institute of Biodiversity (SAIAB), five datasets were collected and manually annotated for labels for supervised machine learning. Moreover, two publicly available datasets were sourced for comparison to the literature. Furthermore, after determining that the smallest YOLO architectures are better suited to these imbalanced datasets, hyperparameter tuning tailored the models to the characteristics of the various underwater environments used in the research. The popular DeepFish dataset was evaluated to establish a baseline and feasibility of these models in the understudied domain. The results demonstrated high detection accuracy for both YOLOv5 and YOLOv8. However, YOLOv8 outperformed YOLOv5, achieving 97.43% accuracy compared to 94.53%. After experiments on seven datasets, trends revealed YOLOv8’s enhanced generalisation accuracy due to architectural improvements, particularly in detecting smaller fish. Overall, YOLOv8 demonstrated that it is the better fish detection and classification model on diverse data. , Thesis (MSc) -- Faculty of Science, Computer Science, 2024
- Full Text:
Towards an artificial intelligence-based agent for characterising the organisation of primes
- Authors: Oyetunji, Nicole Armlade
- Date: 2024-04-04
- Subjects: Numbers, Prime , Odd number , Machine learning , Deep learning (Machine learning) , Mathematical forecasting , Neural networks (Computer science) , Artificial intelligence
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/435389 , vital:73153
- Description: Machine learning has experienced significant growth in recent decades, driven by advancements in computational power and data storage. One of the applications of machine learning is in the field of number theory. Prime numbers hold significant importance in mathematics and its applications, for example in cryptography, owing to their distinct properties. Therefore, it is crucial to efficiently obtain the complete list of primes below a given threshold, with low relatively computational cost. This study extensively explores a deterministic scheme, proposed by Hawing and Okouma (2016), that is centered around Consecutive Composite Odd Numbers, showing the link between these numbers and prime numbers by examining their internal structure. The main objective of this dissertation is to develop two main artificial intelligence agents capable of learning and recognizing patterns within a list of consecutive composite odd numbers. To achieve this, the mathematical foundations of the deterministic scheme are used to generate a dataset of consecutive composite odd numbers. This dataset is further transformed into a dataset of differences to simplify the prediction problem. A literature review is conducted which encompasses research from the domains of machine learning and deep learning. Two main machine learning algorithms are implemented along with their variations, Long Short-Term Memory Networks and Error Correction Neural Networks. These models are trained independently on two separate but related datasets, the dataset of consecutive composite odd numbers and the dataset of differences between those numbers. The evaluation of these models includes relevant metrics, for example, Root Mean Square Error, Mean Absolute Percentage Error, Theil U coefficient, and Directional Accuracy. Through a comparative analysis, the study identifies the top-performing 3 models, with a particular emphasis on accuracy and computational efficiency. The results indicate that the LSTM model, when trained on difference data and coupled with exponential smoothing, displays superior performance as the most accurate model overall. It achieves a RMSE of 0.08, which significantly outperforms the dataset’s standard deviation of 0.42. This model exceeds the performance of basic estimator models, implying that a data-driven approach utilizing machine learning techniques can provide valuable insights in the field of number theory. The second best model, the ECNN trained on difference data combined with exponential smoothing, achieves an RMSE of 0.28. However, it is worth mentioning that this model is the most computationally efficient, being 32 times faster than the LSTM model. , Thesis (MSc) -- Faculty of Science, Mathematics, 2024
- Full Text:
- Authors: Oyetunji, Nicole Armlade
- Date: 2024-04-04
- Subjects: Numbers, Prime , Odd number , Machine learning , Deep learning (Machine learning) , Mathematical forecasting , Neural networks (Computer science) , Artificial intelligence
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/435389 , vital:73153
- Description: Machine learning has experienced significant growth in recent decades, driven by advancements in computational power and data storage. One of the applications of machine learning is in the field of number theory. Prime numbers hold significant importance in mathematics and its applications, for example in cryptography, owing to their distinct properties. Therefore, it is crucial to efficiently obtain the complete list of primes below a given threshold, with low relatively computational cost. This study extensively explores a deterministic scheme, proposed by Hawing and Okouma (2016), that is centered around Consecutive Composite Odd Numbers, showing the link between these numbers and prime numbers by examining their internal structure. The main objective of this dissertation is to develop two main artificial intelligence agents capable of learning and recognizing patterns within a list of consecutive composite odd numbers. To achieve this, the mathematical foundations of the deterministic scheme are used to generate a dataset of consecutive composite odd numbers. This dataset is further transformed into a dataset of differences to simplify the prediction problem. A literature review is conducted which encompasses research from the domains of machine learning and deep learning. Two main machine learning algorithms are implemented along with their variations, Long Short-Term Memory Networks and Error Correction Neural Networks. These models are trained independently on two separate but related datasets, the dataset of consecutive composite odd numbers and the dataset of differences between those numbers. The evaluation of these models includes relevant metrics, for example, Root Mean Square Error, Mean Absolute Percentage Error, Theil U coefficient, and Directional Accuracy. Through a comparative analysis, the study identifies the top-performing 3 models, with a particular emphasis on accuracy and computational efficiency. The results indicate that the LSTM model, when trained on difference data and coupled with exponential smoothing, displays superior performance as the most accurate model overall. It achieves a RMSE of 0.08, which significantly outperforms the dataset’s standard deviation of 0.42. This model exceeds the performance of basic estimator models, implying that a data-driven approach utilizing machine learning techniques can provide valuable insights in the field of number theory. The second best model, the ECNN trained on difference data combined with exponential smoothing, achieves an RMSE of 0.28. However, it is worth mentioning that this model is the most computationally efficient, being 32 times faster than the LSTM model. , Thesis (MSc) -- Faculty of Science, Mathematics, 2024
- Full Text:
The use of simulators and artificial intelligence in leadership feedback
- Authors: Ntombana, Sixolile
- Date: 2022-10-14
- Subjects: Artificial intelligence , Leadership , Employees Rating of , Communication in industrial relations , Qualitative reasoning Technological innovations , Chatbots
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/357685 , vital:64767
- Description: Leadership is a key factor in team success. For leadership to succeed, leaders need to possess the requisite competencies that can facilitate their performance. Team skills is identified as a leadership competency that is prioritised and most sought after by leaders. This follows studies that confirm that team skills are vital for leadership and team success. For leadership to develop team skills, feedback must be provided. Feedback is identified as information that is provided by an observer on a particular performance. The role of feedback in leadership development serves the purposes of engagement and self-reflection and evaluation of a leader’s performance. In this light, feedback cannot be separated from leadership as it is an essential part of communication in a leadership context. The nature and source of feedback can affect how the feedback is received, as shown by studies that suggest that the effectiveness of feedback goes beyond the content or nature (good/bad feedback) of the feedback. This study looks at two feedback sources: humans and artificial intelligence (AI) using students as the population. Humans have been the traditional source in feedback provision. Thus, in a team setting peers provide feedback on their peers’ performances. Unprecedented technological advancements have seen the improvement of AI capabilities to being able to give feedback. This has made AI a feedback source. Following these developments, this research assessed the way in which humans and AI provide feedback and the way in which students react to feedback provided by humans and AI. The research used chatbot AI, a Skills Simulator Assessment, launched by Kotlyar (2018). Students registered for Management One at Rhodes University in 2021 were the population for this research. The research was comprised of two phases where in phase one they were assessed by the Skill Simulator Assessment and in phase two they were assessed by their peers. This research found that students are not averse to feedback from AI, although they prefer peer feedback. It was further found that peer feedback tends to be tainted by lenience, while AI is not affected by lenience. This finding marked a significant development of AI in feedback provision. , Thesis (MCom) -- Faculty of Commerce, Management, 2022
- Full Text:
- Authors: Ntombana, Sixolile
- Date: 2022-10-14
- Subjects: Artificial intelligence , Leadership , Employees Rating of , Communication in industrial relations , Qualitative reasoning Technological innovations , Chatbots
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/357685 , vital:64767
- Description: Leadership is a key factor in team success. For leadership to succeed, leaders need to possess the requisite competencies that can facilitate their performance. Team skills is identified as a leadership competency that is prioritised and most sought after by leaders. This follows studies that confirm that team skills are vital for leadership and team success. For leadership to develop team skills, feedback must be provided. Feedback is identified as information that is provided by an observer on a particular performance. The role of feedback in leadership development serves the purposes of engagement and self-reflection and evaluation of a leader’s performance. In this light, feedback cannot be separated from leadership as it is an essential part of communication in a leadership context. The nature and source of feedback can affect how the feedback is received, as shown by studies that suggest that the effectiveness of feedback goes beyond the content or nature (good/bad feedback) of the feedback. This study looks at two feedback sources: humans and artificial intelligence (AI) using students as the population. Humans have been the traditional source in feedback provision. Thus, in a team setting peers provide feedback on their peers’ performances. Unprecedented technological advancements have seen the improvement of AI capabilities to being able to give feedback. This has made AI a feedback source. Following these developments, this research assessed the way in which humans and AI provide feedback and the way in which students react to feedback provided by humans and AI. The research used chatbot AI, a Skills Simulator Assessment, launched by Kotlyar (2018). Students registered for Management One at Rhodes University in 2021 were the population for this research. The research was comprised of two phases where in phase one they were assessed by the Skill Simulator Assessment and in phase two they were assessed by their peers. This research found that students are not averse to feedback from AI, although they prefer peer feedback. It was further found that peer feedback tends to be tainted by lenience, while AI is not affected by lenience. This finding marked a significant development of AI in feedback provision. , Thesis (MCom) -- Faculty of Commerce, Management, 2022
- Full Text:
Robot Rights, an approach appealing to Animal Rights Theory
- Authors: Millin, Murray David
- Date: 2021-10-29
- Subjects: Artificial intelligence , Singer, Peter, 1946- , Dennett, D C (Daniel Clement) , Animal rights , Ethics , Asimov, Isaac, 1920-1992 Criticism and interpretation , Asimov, Isaac, 1920-1992. Bicentennial man , Asimov, Isaac, 1920-1992. Sally , Preference utilitarianism
- Language: English
- Type: Master's theses , text
- Identifier: http://hdl.handle.net/10962/191854 , vital:45172
- Description: This thesis proposes that Peter Singer’s theory of preference utilitarianism, which is designed to be universally applicable to humans and animals, can be applied to robots of a particular kind — such as those seen in Isaac Asimov’s work. I shall do this by using Singer’s conception of interests as a framework, and appealing to Daniel Dennett’s intentional stance to deal with methodological issues about other minds. I shall then apply those theories to Isaac Asimov’s Sally and The Bicentennial Man. These two narratives show the importance of the intentional stance as an ethical tool and provide an example of how we might talk about the interests of a robot. Sally’s behaviour and ethical status is examined according to how she is perceived, and so I shall investigate how various persons engage with her and why they do so in those manners. This narrative demonstrates the value of the intentional and design stance as methods to approach other minds problems with regards to ethical status. The Bicentennial Man’s Andrew allows us to look for interests in a more concrete way. I look to see how he situates himself in his world, as well as investigate how and why he makes the demand to be morally considerable. This will be done by examining his creativity, personal development and drive for mortality throughout the narrative. , Thesis (MA) -- Faculty of Humanities, Philosophy, 2021
- Full Text:
- Authors: Millin, Murray David
- Date: 2021-10-29
- Subjects: Artificial intelligence , Singer, Peter, 1946- , Dennett, D C (Daniel Clement) , Animal rights , Ethics , Asimov, Isaac, 1920-1992 Criticism and interpretation , Asimov, Isaac, 1920-1992. Bicentennial man , Asimov, Isaac, 1920-1992. Sally , Preference utilitarianism
- Language: English
- Type: Master's theses , text
- Identifier: http://hdl.handle.net/10962/191854 , vital:45172
- Description: This thesis proposes that Peter Singer’s theory of preference utilitarianism, which is designed to be universally applicable to humans and animals, can be applied to robots of a particular kind — such as those seen in Isaac Asimov’s work. I shall do this by using Singer’s conception of interests as a framework, and appealing to Daniel Dennett’s intentional stance to deal with methodological issues about other minds. I shall then apply those theories to Isaac Asimov’s Sally and The Bicentennial Man. These two narratives show the importance of the intentional stance as an ethical tool and provide an example of how we might talk about the interests of a robot. Sally’s behaviour and ethical status is examined according to how she is perceived, and so I shall investigate how various persons engage with her and why they do so in those manners. This narrative demonstrates the value of the intentional and design stance as methods to approach other minds problems with regards to ethical status. The Bicentennial Man’s Andrew allows us to look for interests in a more concrete way. I look to see how he situates himself in his world, as well as investigate how and why he makes the demand to be morally considerable. This will be done by examining his creativity, personal development and drive for mortality throughout the narrative. , Thesis (MA) -- Faculty of Humanities, Philosophy, 2021
- Full Text:
OVR : a novel architecture for voice-based applications
- Authors: Maema, Mathe
- Date: 2011 , 2011-04-01
- Subjects: Telephone systems -- Research , User interfaces (Computer systems) -- Research , Expert systems (Computer science) , Artificial intelligence , VoiceXML (Document markup language) , Application software -- Development
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:4671 , http://hdl.handle.net/10962/d1006694 , Telephone systems -- Research , User interfaces (Computer systems) -- Research , Expert systems (Computer science) , Artificial intelligence , VoiceXML (Document markup language) , Application software -- Development
- Description: Despite the inherent limitation of accessing information serially, voice applications are increasingly growing in popularity as computing technologies advance. This is a positive development, because voice communication offers a number of benefits over other forms of communication. For example, voice may be better for delivering services to users whose eyes and hands may be engaged in other activities (e.g. driving) or to semi-literate or illiterate users. This thesis proposes a knowledge based architecture for building voice applications to help reduce the limitations of serial access to information. The proposed architecture, called OVR (Ontologies, VoiceXML and Reasoners), uses a rich backend that represents knowledge via ontologies and utilises reasoning engines to reason with it, in order to generate intelligent behaviour. Ontologies were chosen over other knowledge representation formalisms because of their expressivity and executable format, and because current trends suggest a general shift towards the use of ontologies in many systems used for information storing and sharing. For the frontend, this architecture uses VoiceXML, the emerging, and de facto standard for voice automated applications. A functional prototype was built for an initial validation of the architecture. The system is a simple voice application to help locate information about service providers that offer HIV (Human Immunodeficiency Virus) testing. We called this implementation HTLS (HIV Testing Locator System). The functional prototype was implemented using a number of technologies. OWL API, a Java interface designed to facilitate manipulation of ontologies authored in OWL was used to build a customised query interface for HTLS. Pellet reasoner was used for supporting queries to the knowledge base and Drools (JBoss rule engine) was used for processing dialog rules. VXI was used as the VoiceXML browser and an experimental softswitch called iLanga as the bridge to the telephony system. (At the heart of iLanga is Asterisk, a well known PBX-in-a-box.) HTLS behaved properly under system testing, providing the sought initial validation of OVR. , LaTeX with hyperref package
- Full Text:
- Authors: Maema, Mathe
- Date: 2011 , 2011-04-01
- Subjects: Telephone systems -- Research , User interfaces (Computer systems) -- Research , Expert systems (Computer science) , Artificial intelligence , VoiceXML (Document markup language) , Application software -- Development
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:4671 , http://hdl.handle.net/10962/d1006694 , Telephone systems -- Research , User interfaces (Computer systems) -- Research , Expert systems (Computer science) , Artificial intelligence , VoiceXML (Document markup language) , Application software -- Development
- Description: Despite the inherent limitation of accessing information serially, voice applications are increasingly growing in popularity as computing technologies advance. This is a positive development, because voice communication offers a number of benefits over other forms of communication. For example, voice may be better for delivering services to users whose eyes and hands may be engaged in other activities (e.g. driving) or to semi-literate or illiterate users. This thesis proposes a knowledge based architecture for building voice applications to help reduce the limitations of serial access to information. The proposed architecture, called OVR (Ontologies, VoiceXML and Reasoners), uses a rich backend that represents knowledge via ontologies and utilises reasoning engines to reason with it, in order to generate intelligent behaviour. Ontologies were chosen over other knowledge representation formalisms because of their expressivity and executable format, and because current trends suggest a general shift towards the use of ontologies in many systems used for information storing and sharing. For the frontend, this architecture uses VoiceXML, the emerging, and de facto standard for voice automated applications. A functional prototype was built for an initial validation of the architecture. The system is a simple voice application to help locate information about service providers that offer HIV (Human Immunodeficiency Virus) testing. We called this implementation HTLS (HIV Testing Locator System). The functional prototype was implemented using a number of technologies. OWL API, a Java interface designed to facilitate manipulation of ontologies authored in OWL was used to build a customised query interface for HTLS. Pellet reasoner was used for supporting queries to the knowledge base and Drools (JBoss rule engine) was used for processing dialog rules. VXI was used as the VoiceXML browser and an experimental softswitch called iLanga as the bridge to the telephony system. (At the heart of iLanga is Asterisk, a well known PBX-in-a-box.) HTLS behaved properly under system testing, providing the sought initial validation of OVR. , LaTeX with hyperref package
- Full Text:
Predictability of Geomagnetically Induced Currents using neural networks
- Authors: Lotz, Stefanus Ignatius
- Date: 2009
- Subjects: Advanced Composition Explorer (Artificial satellite) , Geomagnetism , Electromagnetic induction , Neural networks (Computer science) , Artificial intelligence
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:5483 , http://hdl.handle.net/10962/d1005269 , Advanced Composition Explorer (Artificial satellite) , Geomagnetism , Electromagnetic induction , Neural networks (Computer science) , Artificial intelligence
- Description: It is a well documented fact that Geomagnetically Induced Currents (GIC’s) poses a significant threat to ground-based electric conductor networks like oil pipelines, railways and powerline networks. A study is undertaken to determine the feasibility of using artificial neural network models to predict GIC occurrence in the Southern African power grid. The magnitude of an induced current at a specific location on the Earth’s surface is directly related to the temporal derivative of the geomagnetic field (specifically its horizontal components) at that point. Hence, the focus of the problem is on the prediction of the temporal variations in the horizontal geomagnetic field (@Bx/@t and @By/@t). Artificial neural networks are used to predict @Bx/@t and @By/@t measured at Hermanus, South Africa (34.27◦ S, 19.12◦ E) with a 30 minute prediction lead time. As input parameters to the neural networks, insitu solar wind measurements made by the Advanced Composition Explorer (ACE) satellite are used. The results presented here compare well with similar models developed at high-latitude locations (e.g. Sweden, Finland, Canada) where extensive GIC research has been undertaken. It is concluded that it would indeed be feasible to use a neural network model to predict GIC occurrence in the Southern African power grid, provided that GIC measurements, powerline configuration and network parameters are made available.
- Full Text:
- Authors: Lotz, Stefanus Ignatius
- Date: 2009
- Subjects: Advanced Composition Explorer (Artificial satellite) , Geomagnetism , Electromagnetic induction , Neural networks (Computer science) , Artificial intelligence
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:5483 , http://hdl.handle.net/10962/d1005269 , Advanced Composition Explorer (Artificial satellite) , Geomagnetism , Electromagnetic induction , Neural networks (Computer science) , Artificial intelligence
- Description: It is a well documented fact that Geomagnetically Induced Currents (GIC’s) poses a significant threat to ground-based electric conductor networks like oil pipelines, railways and powerline networks. A study is undertaken to determine the feasibility of using artificial neural network models to predict GIC occurrence in the Southern African power grid. The magnitude of an induced current at a specific location on the Earth’s surface is directly related to the temporal derivative of the geomagnetic field (specifically its horizontal components) at that point. Hence, the focus of the problem is on the prediction of the temporal variations in the horizontal geomagnetic field (@Bx/@t and @By/@t). Artificial neural networks are used to predict @Bx/@t and @By/@t measured at Hermanus, South Africa (34.27◦ S, 19.12◦ E) with a 30 minute prediction lead time. As input parameters to the neural networks, insitu solar wind measurements made by the Advanced Composition Explorer (ACE) satellite are used. The results presented here compare well with similar models developed at high-latitude locations (e.g. Sweden, Finland, Canada) where extensive GIC research has been undertaken. It is concluded that it would indeed be feasible to use a neural network model to predict GIC occurrence in the Southern African power grid, provided that GIC measurements, powerline configuration and network parameters are made available.
- Full Text:
An analysis of neural networks and time series techniques for demand forecasting
- Authors: Winn, David
- Date: 2007
- Subjects: Time-series analysis , Neural networks (Computer science) , Artificial intelligence , Marketing -- Management , Marketing -- Data processing , Marketing -- Statistical methods , Consumer behaviour
- Language: English
- Type: Thesis , Masters , MCom
- Identifier: vital:5572 , http://hdl.handle.net/10962/d1004362 , Time-series analysis , Neural networks (Computer science) , Artificial intelligence , Marketing -- Management , Marketing -- Data processing , Marketing -- Statistical methods , Consumer behaviour
- Description: This research examines the plausibility of developing demand forecasting techniques which are consistently and accurately able to predict demand. Time Series Techniques and Artificial Neural Networks are both investigated. Deodorant sales in South Africa are specifically studied in this thesis. Marketing techniques which are used to influence consumer buyer behaviour are considered, and these factors are integrated into the forecasting models wherever possible. The results of this research suggest that Artificial Neural Networks can be developed which consistently outperform industry forecasting targets as well as Time Series forecasts, suggesting that producers could reduce costs by adopting this more effective method.
- Full Text:
- Authors: Winn, David
- Date: 2007
- Subjects: Time-series analysis , Neural networks (Computer science) , Artificial intelligence , Marketing -- Management , Marketing -- Data processing , Marketing -- Statistical methods , Consumer behaviour
- Language: English
- Type: Thesis , Masters , MCom
- Identifier: vital:5572 , http://hdl.handle.net/10962/d1004362 , Time-series analysis , Neural networks (Computer science) , Artificial intelligence , Marketing -- Management , Marketing -- Data processing , Marketing -- Statistical methods , Consumer behaviour
- Description: This research examines the plausibility of developing demand forecasting techniques which are consistently and accurately able to predict demand. Time Series Techniques and Artificial Neural Networks are both investigated. Deodorant sales in South Africa are specifically studied in this thesis. Marketing techniques which are used to influence consumer buyer behaviour are considered, and these factors are integrated into the forecasting models wherever possible. The results of this research suggest that Artificial Neural Networks can be developed which consistently outperform industry forecasting targets as well as Time Series forecasts, suggesting that producers could reduce costs by adopting this more effective method.
- Full Text:
- «
- ‹
- 1
- ›
- »