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:
- 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:
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:
- 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:
- «
- ‹
- 1
- ›
- »