Service dogs for Autism Spectrum Disorder: the experiences of caregivers in South Africa
- Authors: Martin, Emma Jeanne
- Date: 2022-04-07
- Subjects: Autism spectrum disorders South Africa , Service dogs South Africa , Animals Therapeutic use South Africa , Caregivers South Africa , Animals Therapeutic use Public opinion , Animal welfare South Africa , Children with autism spectrum disorders South Africa
- Language: English
- Type: Master's thesis , text
- Identifier: http://hdl.handle.net/10962/232855 , vital:50032
- Description: Autism spectrum disorder (ASD) is a neurodevelopmental disorder, most frequently diagnosed in childhood, with symptoms including deficits in social communication and interaction as well as restricted, repetitive patterns of behaviours, interests and activities. There is no known cure for ASD, with current treatment methods focussing upon reducing symptom severity. One such treatment method is the use of autism service dogs. Internationally, autism service dogs have been available for over two decades, while in South Africa they have only been available since 2015. A fair amount of internationally published data is available on autism service dogs, however, at the time of this research study, no data was available within South Africa. This study aimed to provide a baseline for research on autism service dogs within South Africa, by documenting the experiences of caregivers whose ASD children had been supplied with autism service dogs, with regard to the uses, effects, accessibility and public perception of the autism service dogs, as well as recommendations for future improvements of autism service dogs within South Africa. Lastly, inquiry into the welfare of the autism service dogs was sought. This study was qualitative in nature, with eight families who had been supplied with autism service dogs having chosen to participate. Data collection was achieved through one semi-structured interview with each family, which was then transcribed and thematically analysed using a hermeneutic phenomenological approach. Results indicated that autism service dogs were perceived as generally accessible, useful and beneficial for ASD children and their caregivers in a variety of ways, however, they were not without their challenges, with lifestyle adjustments and public perception being especially problematic. Participants also noted recommendations for possible future improvements. Lastly, welfare concerns for the autism service dogs relating to violent behaviour exhibited by ASD children was identified, raising the question of the suitability of service dogs for the ASD population. , Thesis (MA) -- Humanities, Psychology, 2022
- Full Text:
- Date Issued: 2022-04-07
- Authors: Martin, Emma Jeanne
- Date: 2022-04-07
- Subjects: Autism spectrum disorders South Africa , Service dogs South Africa , Animals Therapeutic use South Africa , Caregivers South Africa , Animals Therapeutic use Public opinion , Animal welfare South Africa , Children with autism spectrum disorders South Africa
- Language: English
- Type: Master's thesis , text
- Identifier: http://hdl.handle.net/10962/232855 , vital:50032
- Description: Autism spectrum disorder (ASD) is a neurodevelopmental disorder, most frequently diagnosed in childhood, with symptoms including deficits in social communication and interaction as well as restricted, repetitive patterns of behaviours, interests and activities. There is no known cure for ASD, with current treatment methods focussing upon reducing symptom severity. One such treatment method is the use of autism service dogs. Internationally, autism service dogs have been available for over two decades, while in South Africa they have only been available since 2015. A fair amount of internationally published data is available on autism service dogs, however, at the time of this research study, no data was available within South Africa. This study aimed to provide a baseline for research on autism service dogs within South Africa, by documenting the experiences of caregivers whose ASD children had been supplied with autism service dogs, with regard to the uses, effects, accessibility and public perception of the autism service dogs, as well as recommendations for future improvements of autism service dogs within South Africa. Lastly, inquiry into the welfare of the autism service dogs was sought. This study was qualitative in nature, with eight families who had been supplied with autism service dogs having chosen to participate. Data collection was achieved through one semi-structured interview with each family, which was then transcribed and thematically analysed using a hermeneutic phenomenological approach. Results indicated that autism service dogs were perceived as generally accessible, useful and beneficial for ASD children and their caregivers in a variety of ways, however, they were not without their challenges, with lifestyle adjustments and public perception being especially problematic. Participants also noted recommendations for possible future improvements. Lastly, welfare concerns for the autism service dogs relating to violent behaviour exhibited by ASD children was identified, raising the question of the suitability of service dogs for the ASD population. , Thesis (MA) -- Humanities, Psychology, 2022
- Full Text:
- Date Issued: 2022-04-07
Statistical and Mathematical Learning: an application to fraud detection and prevention
- Authors: Hamlomo, Sisipho
- Date: 2022-04-06
- Subjects: Credit card fraud , Bootstrap (Statistics) , Support vector machines , Neural networks (Computer science) , Decision trees , Machine learning , Cross-validation , Imbalanced data
- Language: English
- Type: Master's thesis , text
- Identifier: http://hdl.handle.net/10962/233795 , vital:50128
- Description: Credit card fraud is an ever-growing problem. There has been a rapid increase in the rate of fraudulent activities in recent years resulting in a considerable loss to several organizations, companies, and government agencies. Many researchers have focused on detecting fraudulent behaviours early using advanced machine learning techniques. However, credit card fraud detection is not a straightforward task since fraudulent behaviours usually differ for each attempt and the dataset is highly imbalanced, that is, the frequency of non-fraudulent cases outnumbers the frequency of fraudulent cases. In the case of the European credit card dataset, we have a ratio of approximately one fraudulent case to five hundred and seventy-eight non-fraudulent cases. Different methods were implemented to overcome this problem, namely random undersampling, one-sided sampling, SMOTE combined with Tomek links and parameter tuning. Predictive classifiers, namely logistic regression, decision trees, k-nearest neighbour, support vector machine and multilayer perceptrons, are applied to predict if a transaction is fraudulent or non-fraudulent. The model's performance is evaluated based on recall, precision, F1-score, the area under receiver operating characteristics curve, geometric mean and Matthew correlation coefficient. The results showed that the logistic regression classifier performed better than other classifiers except when the dataset was oversampled. , Thesis (MSc) -- Faculty of Science, Statistics, 2022
- Full Text:
- Date Issued: 2022-04-06
- Authors: Hamlomo, Sisipho
- Date: 2022-04-06
- Subjects: Credit card fraud , Bootstrap (Statistics) , Support vector machines , Neural networks (Computer science) , Decision trees , Machine learning , Cross-validation , Imbalanced data
- Language: English
- Type: Master's thesis , text
- Identifier: http://hdl.handle.net/10962/233795 , vital:50128
- Description: Credit card fraud is an ever-growing problem. There has been a rapid increase in the rate of fraudulent activities in recent years resulting in a considerable loss to several organizations, companies, and government agencies. Many researchers have focused on detecting fraudulent behaviours early using advanced machine learning techniques. However, credit card fraud detection is not a straightforward task since fraudulent behaviours usually differ for each attempt and the dataset is highly imbalanced, that is, the frequency of non-fraudulent cases outnumbers the frequency of fraudulent cases. In the case of the European credit card dataset, we have a ratio of approximately one fraudulent case to five hundred and seventy-eight non-fraudulent cases. Different methods were implemented to overcome this problem, namely random undersampling, one-sided sampling, SMOTE combined with Tomek links and parameter tuning. Predictive classifiers, namely logistic regression, decision trees, k-nearest neighbour, support vector machine and multilayer perceptrons, are applied to predict if a transaction is fraudulent or non-fraudulent. The model's performance is evaluated based on recall, precision, F1-score, the area under receiver operating characteristics curve, geometric mean and Matthew correlation coefficient. The results showed that the logistic regression classifier performed better than other classifiers except when the dataset was oversampled. , Thesis (MSc) -- Faculty of Science, Statistics, 2022
- Full Text:
- Date Issued: 2022-04-06
- «
- ‹
- 1
- ›
- »