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.

Do board contacts matter? : an analysis of the relationship between boards of directors’ ties and the performance of Australia’s largest companies.

Boards of directors are thought to provide access to a wealth of knowledge and resources for the companies they serve, and are considered important to corporate governance. Under the Resource Based View (RBV) of the firm (Wernerfelt, 1984) boards are viewed as a strategic resource available to firms. As a consequence there has been a significant research effort aimed at establishing a link between board attributes and company performance. In this thesis I explore and extend the study of interlocking directorships (Mizruchi, 1996; Scott 1991a) by examining the links between directors’ opportunity networks and firm performance. Specifically, I use resource dependence theory (Pfeffer & Salancik, 1978) and social capital theory (Burt, 1980b; Coleman, 1988) as the basis for a new measure of a board’s opportunity network. I contend that both directors’ formal company ties and their social ties determine a director’s opportunity network through which they are able to access and mobilise resources for their firms. This approach is based on recent studies that suggest the measurement of interlocks at the director level, rather than at the firm level, may be a more reliable indicator of this phenomenon. This research uses publicly available data drawn from Australia’s top-105 listed companies and their directors in 1999. I employ Social Network Analysis (SNA) (Scott, 1991b) using the UCINET software to analyse the individual director’s formal and social networks. SNA is used to measure a the number of ties a director has to other directors in the top-105 company director network at both one and two degrees of separation, that is, direct ties and indirect (or ‘friend of a friend’) ties. These individual measures of director connectedness are aggregated to produce a board-level network metric for comparison with measures of a firm’s performance using multiple regression analysis. Performance is measured with accounting-based and market-based measures. Findings indicate that better-connected boards are associated with higher market-based company performance (measured by Tobin’s q). However, weaker and mostly unreliable associations were found for accounting-based performance measure ROA. Furthermore, formal (or corporate) network ties are a stronger predictor of market performance than total network ties (comprising social and corporate ties). Similarly, strong ties (connectedness at degree-1) are better predictors of performance than weak ties (connectedness at degree-2). My research makes four contributions to the literature on director interlocks. First, it extends a new way of measuring a board’s opportunity network based on the director rather than the company as the unit of interlock. Second, it establishes evidence of a relationship between market-based measures of firm performance and the connectedness of that firm’s board. Third, it establishes that director’s formal corporate ties matter more to market-based firm performance than their social ties. Fourth, it establishes that director’s strong direct ties are more important to market-based performance than weak ties. The thesis concludes with implications for research and practice, including a more speculative interpretation of these results. In particular, I raise the possibility of reverse causality – that is networked directors seek to join high-performing companies. Thus, the relationship may be a result of symbolic action by companies seeking to increase the legitimacy of their firms rather than a reflection of the social capital available to the companies. This is an important consideration worthy of future investigation.

Analysis and detection of cognitive load and frustration in drivers' speech

Non-driving related cognitive load and variations of emotional state may impact a driver’s capability to control a vehicle and introduces driving errors. Availability of reliable cognitive load and emotion detection in drivers would benefit the design of active safety systems and other intelligent in-vehicle interfaces. In this study, speech produced by 68 subjects while driving in urban areas is analyzed. A particular focus is on speech production differences in two secondary cognitive tasks, interactions with a co-driver and calls to automated spoken dialog systems (SDS), and two emotional states during the SDS interactions - neutral/negative. A number of speech parameters are found to vary across the cognitive/emotion classes. Suitability of selected cepstral- and production-based features for automatic cognitive task/emotion classification is investigated. A fusion of GMM/SVM classifiers yields an accuracy of 94.3% in cognitive task and 81.3% in emotion classification.

Technical report : acoustic analysis of the natural environment

This technical report is concerned with one aspect of environmental monitoring—the detection and analysis of acoustic events in sound recordings of the environment. Sound recordings offer ecologists the potential advantages of cheaper and increased sampling. An acoustic event detection algorithm is introduced that outputs a compact rectangular marquee description of each event. It can disentangle superimposed events, which are a common occurrence during morning and evening choruses. Next, three uses to which acoustic event detection can be put are illustrated. These tasks have been selected because they illustrate quite different modes of analysis: (1) the detection of diffuse events caused by wind and rain, which are a frequent contaminant of recordings of the terrestrial environment; (2) the detection of bird calls using the spatial distribution of their component events; and (3) the preparation of acoustic maps for whole ecosystem analysis. This last task utilises the temporal distribution of events over a daily, monthly or yearly cycle.

Technical report : acoustic analysis of the natural environment

This technical report is concerned with one aspect of environmental monitoring—the detection and analysis of acoustic events in sound recordings of the environment. Sound recordings offer ecologists the potential advantages of cheaper and increased sampling. An acoustic event detection algorithm is introduced that outputs a compact rectangular marquee description of each event. It can disentangle superimposed events, which are a common occurrence during morning and evening choruses. Next, three uses to which acoustic event detection can be put are illustrated. These tasks have been selected because they illustrate quite different modes of analysis: (1) the detection of diffuse events caused by wind and rain, which are a frequent contaminant of recordings of the terrestrial environment; (2) the detection of bird calls using the spatial distribution of their component events; and (3) the preparation of acoustic maps for whole ecosystem analysis. This last task utilises the temporal distribution of events over a daily, monthly or yearly cycle.

Technical report : acoustic analysis of the natural environment

This technical report is concerned with one aspect of environmental monitoring—the detection and analysis of acoustic events in sound recordings of the environment. Sound recordings offer ecologists the advantage of cheaper and increased sampling but make available so much data that automated analysis becomes essential. The report describes a number of tools for automated analysis of recordings, including noise removal from spectrograms, acoustic event detection, event pattern recognition, spectral peak tracking, syntactic pattern recognition applied to call syllables, and oscillation detection. These algorithms are applied to a number of animal call recognition tasks, chosen because they illustrate quite different modes of analysis: (1) the detection of diffuse events caused by wind and rain, which are frequent contaminants of recordings of the terrestrial environment; (2) the detection of bird and calls; and (3) the preparation of acoustic maps for whole ecosystem analysis. This last task utilises the temporal distribution of events over a daily, monthly or yearly cycle.

Automatic domain ontology extraction for context-sensitive opinion mining

Automated analysis of the sentiments presented in online consumer feedbacks can facilitate both organizations’ business strategy development and individual consumers’ comparison shopping. Nevertheless, existing opinion mining methods either adopt a context-free sentiment classification approach or rely on a large number of manually annotated training examples to perform context sensitive sentiment classification. Guided by the design science research methodology, we illustrate the design, development, and evaluation of a novel fuzzy domain ontology based contextsensitive opinion mining system. Our novel ontology extraction mechanism underpinned by a variant of Kullback-Leibler divergence can automatically acquire contextual sentiment knowledge across various product domains to improve the sentiment analysis processes. Evaluated based on a benchmark dataset and real consumer reviews collected from Amazon.com, our system shows remarkable performance improvement over the context-free baseline.

Security analysis and enhancement of one-way hash based low-cost authentication protocol (OHLCAP)

Choi et al. recently proposed an efficient RFID authentication protocol for a ubiquitous computing environment, OHLCAP(One-Way Hash based Low-Cost Authentication Protocol). However, this paper reveals that the protocol has several security weaknesses : 1) traceability based on the leakage of counter information, 2) vulnerability to an impersonation attack by maliciously updating a random number, and 3) traceability based on a physically-attacked tag. Finally, a security enhanced group-based authentication protocol is presented.

Leveraging Web 2.0 data for scalable semi-supervised learning of domain-specific sentiment lexicons

Since manually constructing domain-specific sentiment lexicons is extremely time consuming and it may not even be feasible for domains where linguistic expertise is not available. Research on the automatic construction of domain-specific sentiment lexicons has become a hot topic in recent years. The main contribution of this paper is the illustration of a novel semi-supervised learning method which exploits both term-to-term and document-to-term relations hidden in a corpus for the construction of domain specific sentiment lexicons. More specifically, the proposed two-pass pseudo labeling method combines shallow linguistic parsing and corpusbase statistical learning to make domain-specific sentiment extraction scalable with respect to the sheer volume of opinionated documents archived on the Internet these days. Another novelty of the proposed method is that it can utilize the readily available user-contributed labels of opinionated documents (e.g., the user ratings of product reviews) to bootstrap the performance of sentiment lexicon construction. Our experiments show that the proposed method can generate high quality domain-specific sentiment lexicons as directly assessed by human experts. Moreover, the system generated domain-specific sentiment lexicons can improve polarity prediction tasks at the document level by 2:18% when compared to other well-known baseline methods. Our research opens the door to the development of practical and scalable methods for domain-specific sentiment analysis.

An exploration of the technical, social and macro-societal pressures influencing the adoption of online social networking services by organisations

Measuring the business value that Internet technologies deliver for organisations has proven to be a difficult and elusive task, given their complexity and increased embeddedness within the value chain. Yet, despite the lack of empirical evidence that links the adoption of Information Technology (IT) with increased financial performance, many organisations continue to adopt new technologies at a rapid rate. This is evident in the widespread adoption of Web 2.0 online Social Networking Services (SNSs) such as Facebook, Twitter and YouTube. These new Internet based technologies, widely used for social purposes, are being employed by organisations to enhance their business communication processes. However, their use is yet to be correlated with an increase in business performance. Owing to the conflicting empirical evidence that links prior IT applications with increased business performance, IT, Information Systems (IS), and E-Business Model (EBM) research has increasingly looked to broader social and environmental factors as a means for examining and understanding the broader influences shaping IT, IS and E-Business (EB) adoption behaviour. Findings from these studies suggest that organisations adopt new technologies as a result of strong external pressures, rather than a clear measure of enhanced business value. In order to ascertain if this is the case with the adoption of SNSs, this study explores how organisations are creating value (and measuring that value) with the use of SNSs for business purposes, and the external pressures influencing their adoption. In doing so, it seeks to address two research questions: 1. What are the external pressures influencing organisations to adopt SNSs for business communication purposes? 2. Are SNSs providing increased business value for organisations, and if so, how is that value being captured and measured? Informed by the background literature fields of IT, IS, EBM, and Web 2.0, a three-tiered theoretical framework is developed that combines macro-societal, social and technological perspectives as possible causal mechanisms influencing the SNS adoption event. The macro societal view draws on the concept of Castells. (1996) network society and the behaviour of crowds, herds and swarms, to formulate a new explanatory concept of the network vortex. The social perspective draws on key components of institutional theory (DiMaggio & Powell, 1983, 1991), and the technical view draws from the organising vision concept developed by Swanson and Ramiller (1997). The study takes a critical realist approach, and conducts four stages of data collection and one stage of data coding and analysis. Stage 1 consisted of content analysis of websites and SNSs of many organisations, to identify the types of business purposes SNSs are being used for. Stage 2 also involved content analysis of organisational websites, in order to identify suitable sample organisations in which to conduct telephone interviews. Stage 3 consisted of conducting 18 in-depth, semi-structured telephone interviews within eight Australian organisations from the Media/Publishing and Galleries, Libraries, Archives and Museum (GLAM) industries. These sample organisations were considered leaders in the use of SNSs technologies. Stage 4 involved an SNS activity count of the organisations interviewed in Stage 3, in order to rate them as either Advanced Innovator (AI) organisations, or Learning Focussed (LF) organisations. A fifth stage of data coding and analysis of all four data collection stages was conducted, based on the theoretical framework developed for the study, and using QSR NVivo 8 software. The findings from this study reveal that SNSs have been adopted by organisations for the purpose of increasing business value, and as a result of strong social and macro-societal pressures. SNSs offer organisations a wide range of value enhancing opportunities that have broader benefits for customers and society. However, measuring the increased business value is difficult with traditional Return On Investment (ROI) mechanisms, ascertaining the need for new value capture and measurement rationales, to support the accountability of SNS adoption practices. The study also identified the presence of technical, social and macro-societal pressures, all of which influenced SNS adoption by organisations. These findings contribute important theoretical insight into the increased complexity of pressures influencing technology adoption rationales by organisations, and have important practical implications for practice, by reflecting the expanded global online networks in which organisations now operate. The limitations of the study include the small number of sample organisations in which interviews were conducted, its limited generalisability, and the small range of SNSs selected for the study. However, these were compensated in part by the expertise of the interviewees, and the global significance of the SNSs that were chosen. Future research could replicate the study to a larger sample from different industries, sectors and countries. It could also explore the life cycle of SNSs in a longitudinal study, and map how the technical, social and macro-societal pressures are emphasised through stages of the life cycle. The theoretical framework could also be applied to other social fad technology adoption studies.

Dashboards adoption in the business controller’s decision making process

There has been discussion whether corporate decision-making can be helped by decision support systems regarding qualitative aspects of decision making (e.g. trouble shooting)(Löf and Möller, 2003). Intelligent decision support systems have been developed to help business controllers to perform their business analysis. However, few papers investigated the user’s point of view regarding such systems. How do decision-makers perceive the use of decision support systems, in general, and dashboards in particular? Are dashboards useful tools for business controllers? Based on the technology acceptance model and on the positive mood theory, we suggest a series of antecedent factors that influence the perceived usefulness and perceived ease of use of dashboards. A survey is used to collect data regarding the measurement constructs. The managerial implications of this paper consist in showing the degree of penetration of dashboards in the decision making in organizations and some of the factors that explain this respective penetration rate.

Relevance feature discovery for text analysis

It is a big challenge to guarantee the quality of discovered relevance features in text documents for describing user preferences because of the large number of terms, patterns, and noise. Most existing popular text mining and classification methods have adopted term-based approaches. However, they have all suffered from the problems of polysemy and synonymy. Over the years, people have often held the hypothesis that pattern-based methods should perform better than term- based ones in describing user preferences, but many experiments do not support this hypothesis. This research presents a promising method, Relevance Feature Discovery (RFD), for solving this challenging issue. It discovers both positive and negative patterns in text documents as high-level features in order to accurately weight low-level features (terms) based on their specificity and their distributions in the high-level features. The thesis also introduces an adaptive model (called ARFD) to enhance the exibility of using RFD in adaptive environment. ARFD automatically updates the system's knowledge based on a sliding window over new incoming feedback documents. It can efficiently decide which incoming documents can bring in new knowledge into the system. Substantial experiments using the proposed models on Reuters Corpus Volume 1 and TREC topics show that the proposed models significantly outperform both the state-of-the-art term-based methods underpinned by Okapi BM25, Rocchio or Support Vector Machine and other pattern-based methods.

Mining a data reasoning model for personalized text classification

It is a big challenge to acquire correct user profiles for personalized text classification since users may be unsure in providing their interests. Traditional approaches to user profiling adopt machine learning (ML) to automatically discover classification knowledge from explicit user feedback in describing personal interests. However, the accuracy of ML-based methods cannot be significantly improved in many cases due to the term independence assumption and uncertainties associated with them. This paper presents a novel relevance feedback approach for personalized text classification. It basically applies data mining to discover knowledge from relevant and non-relevant text and constraints specific knowledge by reasoning rules to eliminate some conflicting information. We also developed a Dempster-Shafer (DS) approach as the means to utilise the specific knowledge to build high-quality data models for classification. The experimental results conducted on Reuters Corpus Volume 1 and TREC topics support that the proposed technique achieves encouraging performance in comparing with the state-of-the-art relevance feedback models.