Spectral–texture feature extraction using statistical moments with application to object-based vegetation species classification

The use of appropriate features to characterise an output class or object is critical for all classification problems. In order to find optimal feature descriptors for vegetation species classification in a power line corridor monitoring application, this article evaluates the capability of several spectral and texture features. A new idea of spectral–texture feature descriptor is proposed by incorporating spectral vegetation indices in statistical moment features. The proposed method is evaluated against several classic texture feature descriptors. Object-based classification method is used and a support vector machine is employed as the benchmark classifier. Individual tree crowns are first detected and segmented from aerial images and different feature vectors are extracted to represent each tree crown. The experimental results showed that the proposed spectral moment features outperform or can at least compare with the state-of-the-art texture descriptors in terms of classification accuracy. A comprehensive quantitative evaluation using receiver operating characteristic space analysis further demonstrates the strength of the proposed feature descriptors.

Bayesian methodology for genetics of complex diseases

Genetic research of complex diseases is a challenging, but exciting, area of research. The early development of the research was limited, however, until the completion of the Human Genome and HapMap projects, along with the reduction in the cost of genotyping, which paves the way for understanding the genetic composition of complex diseases. In this thesis, we focus on the statistical methods for two aspects of genetic research: phenotype definition for diseases with complex etiology and methods for identifying potentially associated Single Nucleotide Polymorphisms (SNPs) and SNP-SNP interactions. With regard to phenotype definition for diseases with complex etiology, we firstly investigated the effects of different statistical phenotyping approaches on the subsequent analysis. In light of the findings, and the difficulties in validating the estimated phenotype, we proposed two different methods for reconciling phenotypes of different models using Bayesian model averaging as a coherent mechanism for accounting for model uncertainty. In the second part of the thesis, the focus is turned to the methods for identifying associated SNPs and SNP interactions. We review the use of Bayesian logistic regression with variable selection for SNP identification and extended the model for detecting the interaction effects for population based case-control studies. In this part of study, we also develop a machine learning algorithm to cope with the large scale data analysis, namely modified Logic Regression with Genetic Program (MLR-GEP), which is then compared with the Bayesian model, Random Forests and other variants of logic regression.

Critical gap estimation by numerical and statistical highest likelihood search

Many traffic situations require drivers to cross or merge into a stream having higher priority. Gap acceptance theory enables us to model such processes to analyse traffic operation. This discussion demonstrated that numerical search fine tuned by statistical analysis can be used to determine the most likely critical gap for a sample of drivers, based on their largest rejected gap and accepted gap. This method shares some common features with the Maximum Likelihood Estimation technique (Troutbeck 1992) but lends itself well to contemporary analysis tools such as spreadsheet and is particularly analytically transparent. This method is considered not to bias estimation of critical gap due to very small rejected gaps or very large rejected gaps. However, it requires a sufficiently large sample that there is reasonable representation of largest rejected gap/accepted gap pairs within a fairly narrow highest likelihood search band.

Consumers’ intentions to adopt 3G in regional cities in China : a comparative study

Rapid mobile technological evolution and the large economic stake in commercial development of mobile technological innovation make it necessary to understand consumers' motivations towards the latest advanced and updated technologies and services. 3G (the third generation of mobile communication technology) recently started its commercial development in the world‘s largest mobile communication market, China, after being delayed for a few years. Although China fell behind in commercially developing 3G, it is difficult to ignore studying this area, given the size of the market and promising future developments. This market deserves focused research attention, especially in terms of consumer behaviour towards the adoption of mobile technological innovation. Thus, the program of research in this thesis was designed to investigate how Chinese consumers respond to the use of this newly launched mobile technological innovation, with a focus on what factors affect their 3G adoption intentions. It aimed to yield important insights into Chinese consumers‘ innovation adoption behaviours and to contribute to marketing and innovation adoption research. Furthermore, it has been documented that Chinese consumers vary widely between regions in dialect, lifestyle, culture, purchasing power and consumption attitudes. Based on economic development and local culture, China can be divided geographically into distinctive regional consumer markets. Consequently, the results of consumer behaviour research in one region may not necessarily be extrapolated to other regions. In order to better understand Chinese consumers, the disparities between regions should not be overlooked. Therefore, another objective of this program of research was to examine regional variances in consumers' innovation adoption, specifically to identify the similarities and differences in factors influencing 3G adoption, contributing to intra-cultural studies. An extensive literature review identified two gaps: current China-based innovation adoption research studies are limited in providing adequate prediction and explanation of Chinese consumers' intentions to adopt 3G; and there was limited knowledge about the differences between regional Chinese consumers in innovation adoption. Two research questions therefore were developed to address these gaps: 1) What factors influence Chinese consumers' intentions to adopt 3G? 2) How do Chinese consumers differ between regional markets in the relative influence of the factors in determining their intentions to adopt 3G? In accordance with postpositivist research philosophy, two studies were designed to answer the research questions, using mixed methods. To meet the research objectives, the two studies were both conducted in three regional cities, namely Beijing, Shanghai and Wuhan, centred in the three regions of North China, East China and Central China respectively, with sufficient cultural and economical regional variances. Study One was an exploratory study with qualitative research methods. It involved 45 in-depth interviews in the three research cities to gain rich insights into the research context from natural settings. Eight important concepts related to 3G adoption were generated from analysis of the interview data, namely utilitarian expectation, hedonic expectation, status gains, status loss avoidance, normative influence, external influence, cost and quality concern. The concepts of social loss avoidance and quality concern were two unique findings, whereas the other concepts were similar to the findings in Western innovation adoption studies. Moreover, variances in 3G adoption between three groups of regional consumers were also identified, focusing on the perceptions of two concepts, namely status gains and normative influence. The conceptual research model was then developed incorporating the eight concepts plus the dependent variable of adoption intention. The hypothesized relationships between the nine constructs and hypotheses about the differences between regional consumers in 3G adoption were informed by the findings of Study One and the literature reviewed. Study Two was a quantitative study involving a web-based survey and statistical analysis procedure. The web-based survey attracted 800 residents from the three research cities, 270 from Beijing, 265 from Shanghai and 265 from Wuhan. They comprised three research samples for this study and consequently three sets of data were obtained. The data was analysed by Structural Equation Modelling together with Multi-group Analysis. The analysis confirmed that the concepts generated in Study One were influential factors affecting Chinese consumers' 3G adoption intention, with the exception of the concept external influence. Differences were found between the samples in the three research cities in the effect of hedonic expectation, status gains, status loss avoidance and normative influence on 3G adoption intention. The two Studies undertaken in this thesis contributed a better understanding of Chinese consumers' intentions to adopt advanced mobile technological innovation, namely 3G, in three regional markets. This knowledge contributes to innovation adoption and intra-cultural research, as well as consumer behaviour theory. It is also able to inform international and domestic telecommunication companies to develop and deliver more effective marketing strategies across Chinese regional markets. Limitations in the research were identified in terms of the sampling techniques used and the design of the two Studies. Future research was suggested in other Chinese regional markets and into consumer adoption of other types of mobile technological innovations.

Convexity, Classification, and Risk Bounds

Many of the classification algorithms developed in the machine learning literature, including the support vector machine and boosting, can be viewed as minimum contrast methods that minimize a convex surrogate of the 0–1 loss function. The convexity makes these algorithms computationally efficient. The use of a surrogate, however, has statistical consequences that must be balanced against the computational virtues of convexity. To study these issues, we provide a general quantitative relationship between the risk as assessed using the 0–1 loss and the risk as assessed using any nonnegative surrogate loss function. We show that this relationship gives nontrivial upper bounds on excess risk under the weakest possible condition on the loss function—that it satisfies a pointwise form of Fisher consistency for classification. The relationship is based on a simple variational transformation of the loss function that is easy to compute in many applications. We also present a refined version of this result in the case of low noise, and show that in this case, strictly convex loss functions lead to faster rates of convergence of the risk than would be implied by standard uniform convergence arguments. Finally, we present applications of our results to the estimation of convergence rates in function classes that are scaled convex hulls of a finite-dimensional base class, with a variety of commonly used loss functions.

Boosting the margin: A new explanation for the effectiveness of voting methods

One of the surprising recurring phenomena observed in experiments with boosting is that the test error of the generated classifier usually does not increase as its size becomes very large, and often is observed to decrease even after the training error reaches zero. In this paper, we show that this phenomenon is related to the distribution of margins of the training examples with respect to the generated voting classification rule, where the margin of an example is simply the difference between the number of correct votes and the maximum number of votes received by any incorrect label. We show that techniques used in the analysis of Vapnik's support vector classifiers and of neural networks with small weights can be applied to voting methods to relate the margin distribution to the test error. We also show theoretically and experimentally that boosting is especially effective at increasing the margins of the training examples. Finally, we compare our explanation to those based on the bias-variance decomposition.

On the consistency of multiclass classification methods

Binary classification methods can be generalized in many ways to handle multiple classes. It turns out that not all generalizations preserve the nice property of Bayes consistency. We provide a necessary and sufficient condition for consistency which applies to a large class of multiclass classification methods. The approach is illustrated by applying it to some multiclass methods proposed in the literature.

Identification of area-level influences on regions of high cancer incidence in Queensland, Australia : a classification tree approach

Background: Strategies for cancer reduction and management are targeted at both individual and area levels. Area-level strategies require careful understanding of geographic differences in cancer incidence, in particular the association with factors such as socioeconomic status, ethnicity and accessibility. This study aimed to identify the complex interplay of area-level factors associated with high area-specific incidence of Australian priority cancers using a classification and regression tree (CART) approach. Methods: Area-specific smoothed standardised incidence ratios were estimated for priority-area cancers across 478 statistical local areas in Queensland, Australia (1998-2007, n=186,075). For those cancers with significant spatial variation, CART models were used to identify whether area-level accessibility, socioeconomic status and ethnicity were associated with high area-specific incidence. Results: The accessibility of a person’s residence had the most consistent association with the risk of cancer diagnosis across the specific cancers. Many cancers were likely to have high incidence in more urban areas, although male lung cancer and cervical cancer tended to have high incidence in more remote areas. The impact of socioeconomic status and ethnicity on these associations differed by type of cancer. Conclusions: These results highlight the complex interactions between accessibility, socioeconomic status and ethnicity in determining cancer incidence risk.

Numerical methods for second-order stochastic differential equations

We seek numerical methods for second‐order stochastic differential equations that reproduce the stationary density accurately for all values of damping. A complete analysis is possible for scalar linear second‐order equations (damped harmonic oscillators with additive noise), where the statistics are Gaussian and can be calculated exactly in the continuous‐time and discrete‐time cases. A matrix equation is given for the stationary variances and correlation for methods using one Gaussian random variable per timestep. The only Runge–Kutta method with a nonsingular tableau matrix that gives the exact steady state density for all values of damping is the implicit midpoint rule. Numerical experiments, comparing the implicit midpoint rule with Heun and leapfrog methods on nonlinear equations with additive or multiplicative noise, produce behavior similar to the linear case.