Rough set-based reasoning and pattern mining for information filtering

An information filtering (IF) system monitors an incoming document stream to find the documents that match the information needs specified by the user profiles. To learn to use the user profiles effectively is one of the most challenging tasks when developing an IF system. With the document selection criteria better defined based on the users’ needs, filtering large streams of information can be more efficient and effective. To learn the user profiles, term-based approaches have been widely used in the IF community because of their simplicity and directness. Term-based approaches are relatively well established. However, these approaches have problems when dealing with polysemy and synonymy, which often lead to an information overload problem. Recently, pattern-based approaches (or Pattern Taxonomy Models (PTM) [160]) have been proposed for IF by the data mining community. These approaches are better at capturing sematic information and have shown encouraging results for improving the effectiveness of the IF system. On the other hand, pattern discovery from large data streams is not computationally efficient. Also, these approaches had to deal with low frequency pattern issues. The measures used by the data mining technique (for example, “support” and “confidences”) to learn the profile have turned out to be not suitable for filtering. They can lead to a mismatch problem. This thesis uses the rough set-based reasoning (term-based) and pattern mining approach as a unified framework for information filtering to overcome the aforementioned problems. This system consists of two stages - topic filtering and pattern mining stages. The topic filtering stage is intended to minimize information overloading by filtering out the most likely irrelevant information based on the user profiles. A novel user-profiles learning method and a theoretical model of the threshold setting have been developed by using rough set decision theory. The second stage (pattern mining) aims at solving the problem of the information mismatch. This stage is precision-oriented. A new document-ranking function has been derived by exploiting the patterns in the pattern taxonomy. The most likely relevant documents were assigned higher scores by the ranking function. Because there is a relatively small amount of documents left after the first stage, the computational cost is markedly reduced; at the same time, pattern discoveries yield more accurate results. The overall performance of the system was improved significantly. The new two-stage information filtering model has been evaluated by extensive experiments. Tests were based on the well-known IR bench-marking processes, using the latest version of the Reuters dataset, namely, the Reuters Corpus Volume 1 (RCV1). The performance of the new two-stage model was compared with both the term-based and data mining-based IF models. The results demonstrate that the proposed information filtering system outperforms significantly the other IF systems, such as the traditional Rocchio IF model, the state-of-the-art term-based models, including the BM25, Support Vector Machines (SVM), and Pattern Taxonomy Model (PTM).

Application of text mining in analysing road crashes for road asset management

Traffic safety is a major concern world-wide. It is in both the sociological and economic interests of society that attempts should be made to identify the major and multiple contributory factors to those road crashes. This paper presents a text mining based method to better understand the contextual relationships inherent in road crashes. By examining and analyzing the crash report data in Queensland from year 2004 and year 2005, this paper identifies and reports the major and multiple contributory factors to those crashes. The outcome of this study will support road asset management in reducing road crashes.

Effective pattern taxonomy mining in text documents

Many data mining techniques have been proposed for mining useful patterns in databases. However, how to effectively utilize discovered patterns is still an open research issue, especially in the domain of text mining. Most existing methods adopt term-based approaches. However, they all suffer from the problems of polysemy and synonymy. This paper presents an innovative technique, pattern taxonomy mining, to improve the effectiveness of using discovered patterns for finding useful information. Substantial experiments on RCV1 demonstrate that the proposed solution achieves encouraging performance.

Mining patterns and factors contributing to crash severity on road curves

Road curves are an important feature of road infrastructure and many serious crashes occur on road curves. In Queensland, the number of fatalities is twice as many on curves as that on straight roads. Therefore, there is a need to reduce drivers’ exposure to crash risk on road curves. Road crashes in Australia and in the Organisation for Economic Co-operation and Development(OECD) have plateaued in the last five years (2004 to 2008) and the road safety community is desperately seeking innovative interventions to reduce the number of crashes. However, designing an innovative and effective intervention may prove to be difficult as it relies on providing theoretical foundation, coherence, understanding, and structure to both the design and validation of the efficiency of the new intervention. Researchers from multiple disciplines have developed various models to determine the contributing factors for crashes on road curves with a view towards reducing the crash rate. However, most of the existing methods are based on statistical analysis of contributing factors described in government crash reports. In order to further explore the contributing factors related to crashes on road curves, this thesis designs a novel method to analyse and validate these contributing factors. The use of crash claim reports from an insurance company is proposed for analysis using data mining techniques. To the best of our knowledge, this is the first attempt to use data mining techniques to analyse crashes on road curves. Text mining technique is employed as the reports consist of thousands of textual descriptions and hence, text mining is able to identify the contributing factors. Besides identifying the contributing factors, limited studies to date have investigated the relationships between these factors, especially for crashes on road curves. Thus, this study proposed the use of the rough set analysis technique to determine these relationships. The results from this analysis are used to assess the effect of these contributing factors on crash severity. The findings obtained through the use of data mining techniques presented in this thesis, have been found to be consistent with existing identified contributing factors. Furthermore, this thesis has identified new contributing factors towards crashes and the relationships between them. A significant pattern related with crash severity is the time of the day where severe road crashes occur more frequently in the evening or night time. Tree collision is another common pattern where crashes that occur in the morning and involves hitting a tree are likely to have a higher crash severity. Another factor that influences crash severity is the age of the driver. Most age groups face a high crash severity except for drivers between 60 and 100 years old, who have the lowest crash severity. The significant relationship identified between contributing factors consists of the time of the crash, the manufactured year of the vehicle, the age of the driver and hitting a tree. Having identified new contributing factors and relationships, a validation process is carried out using a traffic simulator in order to determine their accuracy. The validation process indicates that the results are accurate. This demonstrates that data mining techniques are a powerful tool in road safety research, and can be usefully applied within the Intelligent Transport System (ITS) domain. The research presented in this thesis provides an insight into the complexity of crashes on road curves. The findings of this research have important implications for both practitioners and academics. For road safety practitioners, the results from this research illustrate practical benefits for the design of interventions for road curves that will potentially help in decreasing related injuries and fatalities. For academics, this research opens up a new research methodology to assess crash severity, related to road crashes on curves.

Data-driven background dataset selection for SVM-based speaker verification

The recently proposed data-driven background dataset refinement technique provides a means of selecting an informative background for support vector machine (SVM)-based speaker verification systems. This paper investigates the characteristics of the impostor examples in such highly-informative background datasets. Data-driven dataset refinement individually evaluates the suitability of candidate impostor examples for the SVM background prior to selecting the highest-ranking examples as a refined background dataset. Further, the characteristics of the refined dataset were analysed to investigate the desired traits of an informative SVM background. The most informative examples of the refined dataset were found to consist of large amounts of active speech and distinctive language characteristics. The data-driven refinement technique was shown to filter the set of candidate impostor examples to produce a more disperse representation of the impostor population in the SVM kernel space, thereby reducing the number of redundant and less-informative examples in the background dataset. Furthermore, data-driven refinement was shown to provide performance gains when applied to the difficult task of refining a small candidate dataset that was mis-matched to the evaluation conditions.

Exploiting multiple feature sets in data-driven impostor dataset selection for speaker verification

This study assesses the recently proposed data-driven background dataset refinement technique for speaker verification using alternate SVM feature sets to the GMM supervector features for which it was originally designed. The performance improvements brought about in each trialled SVM configuration demonstrate the versatility of background dataset refinement. This work also extends on the originally proposed technique to exploit support vector coefficients as an impostor suitability metric in the data-driven selection process. Using support vector coefficients improved the performance of the refined datasets in the evaluation of unseen data. Further, attempts are made to exploit the differences in impostor example suitability measures from varying features spaces to provide added robustness.

Sequential decision fusion for controlled detection errors

Information fusion in biometrics has received considerable attention. The architecture proposed here is based on the sequential integration of multi-instance and multi-sample fusion schemes. This method is analytically shown to improve the performance and allow a controlled trade-off between false alarms and false rejects when the classifier decisions are statistically independent. Equations developed for detection error rates are experimentally evaluated by considering the proposed architecture for text dependent speaker verification using HMM based digit dependent speaker models. The tuning of parameters, n classifiers and m attempts/samples, is investigated and the resultant detection error trade-off performance is evaluated on individual digits. Results show that performance improvement can be achieved even for weaker classifiers (FRR-19.6%, FAR-16.7%). The architectures investigated apply to speaker verification from spoken digit strings such as credit card numbers in telephone or VOIP or internet based applications.

GYAN: A methodology for rule extraction from artificial neural networks

Artificial neural network (ANN) learning methods provide a robust and non-linear approach to approximating the target function for many classification, regression and clustering problems. ANNs have demonstrated good predictive performance in a wide variety of practical problems. However, there are strong arguments as to why ANNs are not sufficient for the general representation of knowledge. The arguments are the poor comprehensibility of the learned ANN, and the inability to represent explanation structures. The overall objective of this thesis is to address these issues by: (1) explanation of the decision process in ANNs in the form of symbolic rules (predicate rules with variables); and (2) provision of explanatory capability by mapping the general conceptual knowledge that is learned by the neural networks into a knowledge base to be used in a rule-based reasoning system. A multi-stage methodology GYAN is developed and evaluated for the task of extracting knowledge from the trained ANNs. The extracted knowledge is represented in the form of restricted first-order logic rules, and subsequently allows user interaction by interfacing with a knowledge based reasoner. The performance of GYAN is demonstrated using a number of real world and artificial data sets. The empirical results demonstrate that: (1) an equivalent symbolic interpretation is derived describing the overall behaviour of the ANN with high accuracy and fidelity, and (2) a concise explanation is given (in terms of rules, facts and predicates activated in a reasoning episode) as to why a particular instance is being classified into a certain category.

Using Association Rules to Solve the Cold-Start Problem in Recommender Systems

Recommender systems are widely used online to help users find other products, items etc that they may be interested in based on what is known about that user in their profile. Often however user profiles may be short on information and thus it is difficult for a recommender system to make quality recommendations. This problem is known as the cold-start problem. Here we investigate using association rules as a source of information to expand a user profile and thus avoid this problem. Our experiments show that it is possible to use association rules to noticeably improve the performance of a recommender system under the cold-start situation. Furthermore, we also show that the improvement in performance obtained can be achieved while using non-redundant rule sets. This shows that non-redundant rules do not cause a loss of information and are just as informative as a set of association rules that contain redundancy.

Overview of the INEX 2010 XML mining track : clustering and classification of XML documents

The XML Document Mining track was launched for exploring two main ideas: (1) identifying key problems and new challenges of the emerging field of mining semi-structured documents, and (2) studying and assessing the potential of Machine Learning (ML) techniques for dealing with generic ML tasks in the structured domain, i.e., classification and clustering of semi-structured documents. This track has run for six editions during INEX 2005, 2006, 2007, 2008, 2009 and 2010. The first five editions have been summarized in previous editions and we focus here on the 2010 edition. INEX 2010 included two tasks in the XML Mining track: (1) unsupervised clustering task and (2) semi-supervised classification task where documents are organized in a graph. The clustering task requires the participants to group the documents into clusters without any knowledge of category labels using an unsupervised learning algorithm. On the other hand, the classification task requires the participants to label the documents in the dataset into known categories using a supervised learning algorithm and a training set. This report gives the details of clustering and classification tasks.

Mining users’ opinions based on item folksonomy and taxonomy for personalized recommender systems

Item folksonomy or tag information is a kind of typical and prevalent web 2.0 information. Item folksonmy contains rich opinion information of users on item classifications and descriptions. It can be used as another important information source to conduct opinion mining. On the other hand, each item is associated with taxonomy information that reflects the viewpoints of experts. In this paper, we propose to mine for users’ opinions on items based on item taxonomy developed by experts and folksonomy contributed by users. In addition, we explore how to make personalized item recommendations based on users’ opinions. The experiments conducted on real word datasets collected from Amazon.com and CiteULike demonstrated the effectiveness of the proposed approaches.

Effective pattern discovery for text mining

Many data mining techniques have been proposed for mining useful patterns in text documents. However, how to effectively use and update discovered patterns is still an open research issue, especially in the domain of text mining. Since most existing text mining methods adopted term-based approaches, they all suffer from the problems of polysemy and synonymy. Over the years, people have often held the hypothesis that pattern (or phrase) based approaches should perform better than the term-based ones, but many experiments did not support this hypothesis. This paper presents an innovative technique, effective pattern discovery which includes the processes of pattern deploying and pattern evolving, to improve the effectiveness of using and updating discovered patterns for finding relevant and interesting information. Substantial experiments on RCV1 data collection and TREC topics demonstrate that the proposed solution achieves encouraging performance.