Selected medicinal plants leaves identification: a computer vision approach
- Authors: Deyi, Avuya
- Date: 2023-10-13
- Subjects: Deep learning (Machine learning) , Machine learning , Convolutional neural network , Computer vision in medicine , Medicinal plants
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/424552 , vital:72163
- Description: Identifying and classifying medicinal plants are valuable and essential skills during drug manufacturing because several active pharmaceutical ingredients (API) are sourced from medicinal plants. For many years, identifying and classifying medicinal plants have been exclusively done by experts in the domain, such as botanists, and herbarium curators. Recently, powerful computer vision technologies, using machine learning and deep convolutional neural networks, have been developed for classifying or identifying objects on images. A convolutional neural network is a deep learning architecture that outperforms previous advanced approaches in image classification and object detection based on its efficient features extraction on images. In this thesis, we investigate different convolutional neural networks and machine learning algorithms for identifying and classifying leaves of three species of the genus Brachylaena. The three species considered are Brachylaena discolor, Brachylaena ilicifolia and Brachylaena elliptica. All three species are used medicinally by people in South Africa to treat diseases like diabetes. From 1259 labelled images of those plants species (at least 400 for each species) split into training, evaluation and test sets, we trained and evaluated different deep convolutional neural networks and machine learning models. The VGG model achieved the best results with 98.26% accuracy from cross-validation. , Thesis (MSc) -- Faculty of Science, Mathematics, 2023
- Full Text:
- Date Issued: 2023-10-13
- Authors: Deyi, Avuya
- Date: 2023-10-13
- Subjects: Deep learning (Machine learning) , Machine learning , Convolutional neural network , Computer vision in medicine , Medicinal plants
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/424552 , vital:72163
- Description: Identifying and classifying medicinal plants are valuable and essential skills during drug manufacturing because several active pharmaceutical ingredients (API) are sourced from medicinal plants. For many years, identifying and classifying medicinal plants have been exclusively done by experts in the domain, such as botanists, and herbarium curators. Recently, powerful computer vision technologies, using machine learning and deep convolutional neural networks, have been developed for classifying or identifying objects on images. A convolutional neural network is a deep learning architecture that outperforms previous advanced approaches in image classification and object detection based on its efficient features extraction on images. In this thesis, we investigate different convolutional neural networks and machine learning algorithms for identifying and classifying leaves of three species of the genus Brachylaena. The three species considered are Brachylaena discolor, Brachylaena ilicifolia and Brachylaena elliptica. All three species are used medicinally by people in South Africa to treat diseases like diabetes. From 1259 labelled images of those plants species (at least 400 for each species) split into training, evaluation and test sets, we trained and evaluated different deep convolutional neural networks and machine learning models. The VGG model achieved the best results with 98.26% accuracy from cross-validation. , Thesis (MSc) -- Faculty of Science, Mathematics, 2023
- Full Text:
- Date Issued: 2023-10-13
Health and activity monitoring to support the self-management of chronic diseases of lifestyle using smart devices
- Authors: Mujuru, George Tungamirai
- Date: 2018
- Subjects: Computer vision in medicine , Self-care, Health Chronic diseases
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: http://hdl.handle.net/10948/33076 , vital:32516
- Description: Chronic diseases of lifestyle (CDLs) are non-infectious medical conditions, such as diabetes, cardiovascular disease and cancer. These conditions are the second leading cause of death and disease in Africa. Failure to modify primary risk factors, such as an unhealthy diet, lack of physical activity and tobacco use, can give rise to intermediate risk factors such as hypertension and obesity, which predispose individuals to CDLs. The aim of the research was to investigate the use of smart devices to facilitate the self-management of health and health behaviours. The Health Action Process Approach (HAPA) model of health behaviour change was adopted, which focuses on the correction of modifiable risk factors. Two smart devices were selected, namely the Fitbit Charge 2 and Fitbit Aria, which monitor specific physiological information. The Fitbit Charge 2 can determine health activity, and the Fitbit Aria can determine the weight, body mass index (BMI) and body fat percentage of an individual. A field study was conducted with 22 participants (11 males and 11 females) to evaluate and determine the effectiveness of the smart devices. The participants were sampled from Nelson Mandela University staff and were aged between 30 and 60 years of age. The field study was conducted over two weeks in two one-week long phases. The first phase was used to obtain subjective data (using a lifestyle questionnaire), and objective health data (collected by the smart devices) from the participants. The purpose of the first phase was to form intentions. The second phase was the goal setting phase, where each participant was assisted in setting manageable personal goals. The results show that the smart devices used in the research could be used to provide motivation and monitor health data to support self-management of CDLs. The use of these smart devices was included in an updated HAPA model.
- Full Text:
- Date Issued: 2018
- Authors: Mujuru, George Tungamirai
- Date: 2018
- Subjects: Computer vision in medicine , Self-care, Health Chronic diseases
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: http://hdl.handle.net/10948/33076 , vital:32516
- Description: Chronic diseases of lifestyle (CDLs) are non-infectious medical conditions, such as diabetes, cardiovascular disease and cancer. These conditions are the second leading cause of death and disease in Africa. Failure to modify primary risk factors, such as an unhealthy diet, lack of physical activity and tobacco use, can give rise to intermediate risk factors such as hypertension and obesity, which predispose individuals to CDLs. The aim of the research was to investigate the use of smart devices to facilitate the self-management of health and health behaviours. The Health Action Process Approach (HAPA) model of health behaviour change was adopted, which focuses on the correction of modifiable risk factors. Two smart devices were selected, namely the Fitbit Charge 2 and Fitbit Aria, which monitor specific physiological information. The Fitbit Charge 2 can determine health activity, and the Fitbit Aria can determine the weight, body mass index (BMI) and body fat percentage of an individual. A field study was conducted with 22 participants (11 males and 11 females) to evaluate and determine the effectiveness of the smart devices. The participants were sampled from Nelson Mandela University staff and were aged between 30 and 60 years of age. The field study was conducted over two weeks in two one-week long phases. The first phase was used to obtain subjective data (using a lifestyle questionnaire), and objective health data (collected by the smart devices) from the participants. The purpose of the first phase was to form intentions. The second phase was the goal setting phase, where each participant was assisted in setting manageable personal goals. The results show that the smart devices used in the research could be used to provide motivation and monitor health data to support self-management of CDLs. The use of these smart devices was included in an updated HAPA model.
- Full Text:
- Date Issued: 2018
- «
- ‹
- 1
- ›
- »