Improved tree species discrimination at leaf level with hyperspectral data combining binary classifiers
- Authors: Dastile, Xolani Collen
- Date: 2011
- Subjects: Mathematical statistics , Analysis of variance , Nearest neighbor analysis (Statistics) , Trees--Classification
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:5567 , http://hdl.handle.net/10962/d1002807 , Mathematical statistics , Analysis of variance , Nearest neighbor analysis (Statistics) , Trees--Classification
- Description: The purpose of the present thesis is to show that hyperspectral data can be used for discrimination between different tree species. The data set used in this study contains the hyperspectral measurements of leaves of seven savannah tree species. The data is high-dimensional and shows large within-class variability combined with small between-class variability which makes discrimination between the classes challenging. We employ two classification methods: G-nearest neighbour and feed-forward neural networks. For both methods, direct 7-class prediction results in high misclassification rates. However, binary classification works better. We constructed binary classifiers for all possible binary classification problems and combine them with Error Correcting Output Codes. We show especially that the use of 1-nearest neighbour binary classifiers results in no improvement compared to a direct 1-nearest neighbour 7-class predictor. In contrast to this negative result, the use of neural networks binary classifiers improves accuracy by 10% compared to a direct neural networks 7-class predictor, and error rates become acceptable. This can be further improved by choosing only suitable binary classifiers for combination.
- Full Text:
- Date Issued: 2011
- Authors: Dastile, Xolani Collen
- Date: 2011
- Subjects: Mathematical statistics , Analysis of variance , Nearest neighbor analysis (Statistics) , Trees--Classification
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:5567 , http://hdl.handle.net/10962/d1002807 , Mathematical statistics , Analysis of variance , Nearest neighbor analysis (Statistics) , Trees--Classification
- Description: The purpose of the present thesis is to show that hyperspectral data can be used for discrimination between different tree species. The data set used in this study contains the hyperspectral measurements of leaves of seven savannah tree species. The data is high-dimensional and shows large within-class variability combined with small between-class variability which makes discrimination between the classes challenging. We employ two classification methods: G-nearest neighbour and feed-forward neural networks. For both methods, direct 7-class prediction results in high misclassification rates. However, binary classification works better. We constructed binary classifiers for all possible binary classification problems and combine them with Error Correcting Output Codes. We show especially that the use of 1-nearest neighbour binary classifiers results in no improvement compared to a direct 1-nearest neighbour 7-class predictor. In contrast to this negative result, the use of neural networks binary classifiers improves accuracy by 10% compared to a direct neural networks 7-class predictor, and error rates become acceptable. This can be further improved by choosing only suitable binary classifiers for combination.
- Full Text:
- Date Issued: 2011
Development of an antiretroviral solid dosage form using multivariate analysis
- Authors: Nqabeni, Luxolo
- Date: 2007
- Subjects: Analysis of variance , Experimental design , Multivariate analysis , Antiretroviral agents -- South Africa
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:10145 , http://hdl.handle.net/10948/705 , Analysis of variance , Experimental design , Multivariate analysis , Antiretroviral agents -- South Africa
- Description: The aim of pharmaceutical development is to design a quality product and the manufacturing process to deliver the product in a reproducible manner. The development of a new and generic formulation is based on a large number of experiments. Statistics provides many tools for studying the conditions of formulations and processes and enables us to optimize the same while being able to minimize our experimentation. The purpose of this study was to apply experimental design methodology (DOE) and multivariate analysis to the development and optimization of tablet formulations containing 150 mg lamivudine manufactured by direct compression.
- Full Text:
- Date Issued: 2007
- Authors: Nqabeni, Luxolo
- Date: 2007
- Subjects: Analysis of variance , Experimental design , Multivariate analysis , Antiretroviral agents -- South Africa
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:10145 , http://hdl.handle.net/10948/705 , Analysis of variance , Experimental design , Multivariate analysis , Antiretroviral agents -- South Africa
- Description: The aim of pharmaceutical development is to design a quality product and the manufacturing process to deliver the product in a reproducible manner. The development of a new and generic formulation is based on a large number of experiments. Statistics provides many tools for studying the conditions of formulations and processes and enables us to optimize the same while being able to minimize our experimentation. The purpose of this study was to apply experimental design methodology (DOE) and multivariate analysis to the development and optimization of tablet formulations containing 150 mg lamivudine manufactured by direct compression.
- Full Text:
- Date Issued: 2007
The comparative bioavailability and in vitro assessment of solid oral dosage forms of paracetamol
- Authors: Braae, Karen
- Date: 1981 , 2013-04-02
- Subjects: Acetaminophen , Bioavailability , Drugs -- Bioavailability , Drugs -- Dosage forms , Analysis of variance
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:3827 , http://hdl.handle.net/10962/d1006288 , Acetaminophen , Bioavailability , Drugs -- Bioavailability , Drugs -- Dosage forms , Analysis of variance
- Description: The dissolution profiles of eight lots of paracetamol tablets representing seven different tablet brands are determined in a USP rotating basket assembly and a stationary basket-rotating paddle apparatus. The in vitro data are expressed in terms of dissolution parameters and inter-tablet differences are assessed statistically using analysis of variance (ANOVA) and the Scheffe test. Highly significant differences are observed between a number of the tablets at the 95% confidence level. Representative tablets from the dissolution rate study and a control dose of paracetamol dissolved in water are subsequently investigated in a 4 x 4 latin square design bioavailability trial. Serum and urine samples are collected and assayed for paracetamol alone (serum) and together with its metabolites (urine) by means of high pressure liquid chromatography. The in vivo data are expressed in terms of bioavailability parameters and differences between the test doses are assessed by means of ANOVA. No significant differences are observed between the dosage forms at the 95% confidence level.
- Full Text:
- Date Issued: 1981
- Authors: Braae, Karen
- Date: 1981 , 2013-04-02
- Subjects: Acetaminophen , Bioavailability , Drugs -- Bioavailability , Drugs -- Dosage forms , Analysis of variance
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:3827 , http://hdl.handle.net/10962/d1006288 , Acetaminophen , Bioavailability , Drugs -- Bioavailability , Drugs -- Dosage forms , Analysis of variance
- Description: The dissolution profiles of eight lots of paracetamol tablets representing seven different tablet brands are determined in a USP rotating basket assembly and a stationary basket-rotating paddle apparatus. The in vitro data are expressed in terms of dissolution parameters and inter-tablet differences are assessed statistically using analysis of variance (ANOVA) and the Scheffe test. Highly significant differences are observed between a number of the tablets at the 95% confidence level. Representative tablets from the dissolution rate study and a control dose of paracetamol dissolved in water are subsequently investigated in a 4 x 4 latin square design bioavailability trial. Serum and urine samples are collected and assayed for paracetamol alone (serum) and together with its metabolites (urine) by means of high pressure liquid chromatography. The in vivo data are expressed in terms of bioavailability parameters and differences between the test doses are assessed by means of ANOVA. No significant differences are observed between the dosage forms at the 95% confidence level.
- Full Text:
- Date Issued: 1981
- «
- ‹
- 1
- ›
- »