Description:
A method of truncated codifferential descent for minimizing continuously codifferentiable functions is suggested. The convergence of the method is studied. Results of numerical experiments are presented. Application of the suggested method for the solution of some problems of cluster analysis are discussed. In numerical experiments Wisconsin Diagnostic Breast Cancer database was used.
Description:
"The purpose of this thesis is to develop and test new methods for data classification based on mathematical programming and nonsmooth optimization."
Description:
"The purpose of this thesis is to develop and test new methods for data classification based on mathematical programming and nonsmooth optimization."
Description:
The problem of cluster analysis is formulated as a problem of nonsmooth, nonconvex optimization. An algorithm for solving the latter optimization problem is developed which allows one to significantly reduce the computational efforts. This algorithm is based on the so-called discrete gradient method. Results of numerical experiments are presented which demonstrate the effectiveness of the proposed algorithm.
Description:
The problem of cluster analysis is formulated as a problem of nonsmooth, nonconvex optimization. An algorithm for solving the latter optimization problem is developed which allows one to significantly reduce the computational efforts. This algorithm is based on the so-called discrete gradient method. Results of numerical experiments are presented which demonstrate the effectiveness of the proposed algorithm.
Description:
This article reports research conducted on students’ perceptions of assessment in science classes in Queensland and Western Australia. A specially developed instrument, the Student Perceptions of Assessment Questionnaire (SPAQ) which assesses Congruence with Planned Learning, Authenticity, Student Consultation, Transparency, and Diversity was used to collect data from 3,055 students. Hierarchical cluster analysis resulted in a four cluster solution being accepted. While one cluster of 799 students held positive perceptions of assessment, another cluster of 640 students held negative views. The SPAQ allows for a greater focus on classroom-based perceptions of assessment rather than crude external accountability measures that decontextualise classroom assessment.
Description:
This thesis is devoted to the development of algorithms for solving nonsmooth nonconvex problems. Some of these algorithms are derivative free methods.
Description:
This thesis is devoted to the development of algorithms for solving nonsmooth nonconvex problems. Some of these algorithms are derivative free methods.
Description:
The purpose of this thesis is to develop some new algorithms based on optimization techniques for solving some problems in some areas of telecommunications and the Internet. There are two main parts to this thesis. In the first part we discuss optimization based stochastic and queueing models in telecommunications network corrective maintenance. In the second part we develop optimization based clustering (OBC) algorithms for network evolution and multicast routing. The most typical scenario encountered during mathematical optimization modelling in telecommunications, for example, is to minimize the cost of establishment and maintenance of the networks subject to the performance constraints of the networks and the reliability constraints of the networks as well. Most of these optimization problems are global optimization, that is, they have many local minima and most of these local minima do not provide any useful information for solving these problems. Therefore, the development of effective methods for solving such global optimization problems is important. To run the telecommunications networks with cost-effective network maintenance,we need to establish a practical maintenance model and optimize it. In the first part of the thesis, we solve a known stochastic programming maintenance optimization model with a direct method and then develop some new models. After that we introduce queue programming models in telecommunications network maintenance optimization. The ideas of profit, loss, and penalty will help telecommunications companies have a good view of their maintenance policies and help them improve their service. In the second part of this thesis we propose the use of optimization based clustering (OBC) algorithms to determine level-constrained hierarchical trees for network evolution and multicast routing. This problem is formulated as an optimization problem with a non-smooth, non-convex objective function. Different algorithms are examined for solving this problem. Results of numerical experiments using some artifiicial and real-world databases are reported.
Description:
The purpose of this thesis is to develop some new algorithms based on optimization techniques for solving some problems in some areas of telecommunications and the Internet. There are two main parts to this thesis. In the first part we discuss optimization based stochastic and queueing models in telecommunications network corrective maintenance. In the second part we develop optimization based clustering (OBC) algorithms for network evolution and multicast routing. The most typical scenario encountered during mathematical optimization modelling in telecommunications, for example, is to minimize the cost of establishment and maintenance of the networks subject to the performance constraints of the networks and the reliability constraints of the networks as well. Most of these optimization problems are global optimization, that is, they have many local minima and most of these local minima do not provide any useful information for solving these problems. Therefore, the development of effective methods for solving such global optimization problems is important. To run the telecommunications networks with cost-effective network maintenance,we need to establish a practical maintenance model and optimize it. In the first part of the thesis, we solve a known stochastic programming maintenance optimization model with a direct method and then develop some new models. After that we introduce queue programming models in telecommunications network maintenance optimization. The ideas of profit, loss, and penalty will help telecommunications companies have a good view of their maintenance policies and help them improve their service. In the second part of this thesis we propose the use of optimization based clustering (OBC) algorithms to determine level-constrained hierarchical trees for network evolution and multicast routing. This problem is formulated as an optimization problem with a non-smooth, non-convex objective function. Different algorithms are examined for solving this problem. Results of numerical experiments using some artifiicial and real-world databases are reported.
Description:
Background: Cholera continues to be a devastating disease in many developing countries where inadequate safe water supply and poor sanitation facilitate spread. From July 2009 until late 2011 Papua New Guinea experienced the first outbreak of cholera recorded in the country, resulting in > 15,500 cases and > 500 deaths. Methods: Using the national cholera database, we analysed the spatio-temporal distribution and clustering of the Papua New Guinea cholera outbreak. The Kulldorff space-time permutation scan statistic, contained in the software package SatScan v9.2 was used to describe the first 8 weeks of the outbreak in Morobe Province before cholera cases spread throughout other regions of the country. Data were aggregated at the provincial level to describe the spread of the disease to other affected provinces. Results: Spatio-temporal and cluster analyses revealed that the outbreak was characterized by three distinct phases punctuated by explosive propagation of cases when the outbreak spread to a new region. The lack of road networks across most of Papua New Guinea is likely to have had a major influence on the slow spread of the disease during this outbreak. Conclusions: Identification of high risk areas and the likely mode of spread can guide government health authorities to formulate public health strategies to mitigate the spread of the disease through education campaigns, vaccination, increased surveillance in targeted areas and interventions to improve water, sanitation and hygiene.
Description:
Background: Cholera continues to be a devastating disease in many developing countries where inadequate safe water supply and poor sanitation facilitate spread. From July 2009 until late 2011 Papua New Guinea experienced the first outbreak of cholera recorded in the country, resulting in > 15,500 cases and > 500 deaths. Methods: Using the national cholera database, we analysed the spatio-temporal distribution and clustering of the Papua New Guinea cholera outbreak. The Kulldorff space-time permutation scan statistic, contained in the software package SatScan v9.2 was used to describe the first 8 weeks of the outbreak in Morobe Province before cholera cases spread throughout other regions of the country. Data were aggregated at the provincial level to describe the spread of the disease to other affected provinces. Results: Spatio-temporal and cluster analyses revealed that the outbreak was characterized by three distinct phases punctuated by explosive propagation of cases when the outbreak spread to a new region. The lack of road networks across most of Papua New Guinea is likely to have had a major influence on the slow spread of the disease during this outbreak. Conclusions: Identification of high risk areas and the likely mode of spread can guide government health authorities to formulate public health strategies to mitigate the spread of the disease through education campaigns, vaccination, increased surveillance in targeted areas and interventions to improve water, sanitation and hygiene.
Description:
The aim of this paper is to design an algorithm based on nonsmooth optimization techniques to solve the minimum sum-of-squares clustering problems in very large data sets. First, the clustering problem is formulated as a nonsmooth optimization problem. Then the limited memory bundle method [Haarala et al., 2007] is modified and combined with an incremental approach to design a new clustering algorithm. The algorithm is evaluated using real world data sets with both the large number of attributes and the large number of data points. It is also compared with some other optimization based clustering algorithms. The numerical results demonstrate the efficiency of the proposed algorithm for clustering in very large data sets.
Description:
This research was conducted in Internet Commerce Security Laboratory (ICSL) funded by Westpac Banking Corporation Australia. In addition, the research by Dr. Sona Taheri and A/Prof. Adil Bagirov was supported by the Australian Government through the Australian Research Council’s Discovery Projects funding scheme (DP190100580).
Description:
This research was conducted in Internet Commerce Security Laboratory (ICSL) funded by Westpac Banking Corporation Australia. In addition, the research by Dr. Sona Taheri and A/Prof. Adil Bagirov was supported by the Australian Government through the Australian Research Council’s Discovery Projects funding scheme (DP190100580).
Description:
Phishing is a form of online fraud with drastic consequences for the victims and institutions being defrauded. A phishing attack tries to create a believable environment for the intended victim to enter their confidential data such that the attacker can use or sell this information later. In order to apprehend phishers, law enforcement agencies need automated systems capable of tracking the size and scope of phishing attacks, in order to more wisely use their resources shutting down the major players, rather then wasting resources stopping smaller operations. In order to develop these systems, phishing attacks need to be clustered by provenance in a way that adequately profiles these evolving attackers. The research presented in this paper looks at the viability of using automated conceptual analysis through cluster analysis techniques on phishing websites, with the aim of determining provenance of these phishing attacks. Conceptual analysis is performed on the source code of the websites, rather than the final text that is displayed to the user, eliminating problems with rendering obfuscation and increasing the distinctiveness brought about by differences in coding styles of the phishers. By using cluster analysis algorithms, distinguishing factors between groups of phishing websites can be obtained. The results indicate that it is difficult to separate websites by provenance without also separating by intent, by looking at the phishing websites alone. Instead, the methods discussed in this paper should form part of a larger system that uses more information about the phishing attacks.
Description:
Phishing is a form of online fraud with drastic consequences for the victims and institutions being defrauded. A phishing attack tries to create a believable environment for the intended victim to enter their confidential data such that the attacker can use or sell this information later. In order to apprehend phishers, law enforcement agencies need automated systems capable of tracking the size and scope of phishing attacks, in order to more wisely use their resources shutting down the major players, rather then wasting resources stopping smaller operations. In order to develop these systems, phishing attacks need to be clustered by provenance in a way that adequately profiles these evolving attackers. The research presented in this paper looks at the viability of using automated conceptual analysis through cluster analysis techniques on phishing websites, with the aim of determining provenance of these phishing attacks. Conceptual analysis is performed on the source code of the websites, rather than the final text that is displayed to the user, eliminating problems with rendering obfuscation and increasing the distinctiveness brought about by differences in coding styles of the phishers. By using cluster analysis algorithms, distinguishing factors between groups of phishing websites can be obtained. The results indicate that it is difficult to separate websites by provenance without also separating by intent, by looking at the phishing websites alone. Instead, the methods discussed in this paper should form part of a larger system that uses more information about the phishing attacks.
Description:
Unsupervised Authorship Analysis (UAA) aims to cluster documents by authorship without knowing the authorship of any documents. An important factor in UAA is the method for calculating the distance between documents. This choice of the authorship distance method is considered more critical to the end result than the choice of cluster analysis algorithm. One method for measuring the correlation between a distance metric and a labelling (such as class values or clusters) is the Silhouette Coefficient (SC). The SC can be leveraged by measuring the correlation between the authorship distance method and the true authorship, evaluating the quality of the distance method. However, we show that the SC can be severely affected by outliers. To address this issue, we introduce the Positive Silhouette Coefficient, given as the proportion of instances with a positive SC value. This metric is not easily altered by outliers and produces a more robust metric. A large number of authorship distance methods are then compared using the PSC, and the findings are presented. This research provides an insight into the efficacy of methods for UAA and presents a framework for testing authorship distance methods.
Description:
Unsupervised Authorship Analysis (UAA) aims to cluster documents by authorship without knowing the authorship of any documents. An important factor in UAA is the method for calculating the distance between documents. This choice of the authorship distance method is considered more critical to the end result than the choice of cluster analysis algorithm. One method for measuring the correlation between a distance metric and a labelling (such as class values or clusters) is the Silhouette Coefficient (SC). The SC can be leveraged by measuring the correlation between the authorship distance method and the true authorship, evaluating the quality of the distance method. However, we show that the SC can be severely affected by outliers. To address this issue, we introduce the Positive Silhouette Coefficient, given as the proportion of instances with a positive SC value. This metric is not easily altered by outliers and produces a more robust metric. A large number of authorship distance methods are then compared using the PSC, and the findings are presented. This research provides an insight into the efficacy of methods for UAA and presents a framework for testing authorship distance methods.
Description:
The problem of cluster analysis is formulated as a problem of non-smooth, non-convex optimization, and an algorithm for solving the cluster analysis problem based on non-smooth optimization techniques is developed. We discuss applications of this algorithm in large databases. Results of numerical experiments are presented to demonstrate the effectiveness of this algorithm.
Description:
Objectives: To describe patterns of time use among regional and rural adolescent girls and compare identified clusters with respect to correlates of physical activity (PA) and health-related quality of life (HRQoL). Methods: Data were from Year 7-9 adolescent girls (aged 12-15 years) from 16 schools involved in a cluster-randomised trial in regional and rural Victoria, Australia (n = 494). Time use data were collected using 24-h Previous Day Physical Activity Recall (PDPAR-24) questionnaire, collapsed into 17 categories of time use. Differences between time use clusters with regard to demographics, correlates of PA and HRQoL measured using PedsQL 4.0 Generic Core Scales, were investigated. Results: Two time use clusters were identified and were associated with correlates of PA and HRQoL. Girls who spent significantly more time in teams sports, non-team sports, school classes, watching TV and sleeping had higher levels of positively aligned PA correlates (e.g. self-efficacy, perceived sports competence) and HRQoL than girls characterised with high levels of computer use and video gaming. Conclusions: These findings highlight how different activity patterns of regional and rural girls affect HRQoL and can inform future intervention strategies to improve PA levels and HRQoL. Clusters characterised by low levels of PA and high computer use and video gaming require targeted interventions to address barriers to their participation. (C) 2016 Published by Elsevier Ltd on behalf of Sports Medicine Australia.