Nonlinear discrimination using support vector machine

Appropriate training data always play an important role in constructing an efficient classifier to solve the data mining classification problem. Support Vector Machine (SVM) is a comparatively new approach in constructing a model/classifier for data analysis, based on Statistical Learning Theory (SLT). SVM utilizes a transformation of the basic constrained optimization problem compared to that of a quadratic programming method, which can be solved parsimoniously through standard methods. Our research focuses on SVM to classify a number of different sizes of data sets. We found SVM to perform well in the case of discrimination compared to some other existing popular classifiers.

Press shop machine analysis and trending

Historically downtime data collection and reporting systems in many automotive body panel press shops has been somewhat adhoc. The impetus for this study stems from frustration in respect of how this data is collected, assessed for trends and presented. Ideally this data should be used to identify costly repetitious faults for actioning of maintenance work and for feedback to tool design for consideration when designing new parts.

Presently this data is stored largely in the form of tacit knowledge by press shop operators; the encumbrance of transferring such information being that there is very often only limited channels to quantify it into something more tangible. Findings show that there tend to be two related obstacles to plant data recording. The first is that automation of down time data collection alone cannot determine fault causes as the majority of press shop events are initiated primarily from operator observation. The second is that excessive subjective operator input can often result in confusion and end up taking greater time in recording than remedying the actual fault.

This Paper presents the development of a system that through press mounted touchscreens encourages basic subjective operator input and relates this with basic objective data such as timekeeping. In this way all responses for a given press line become valuable and can be trended and placed in a hierarchy based on their percentage contribution to downtime or statistical importance. This then is capable of statistically alerting maintenance, line flow and/or toolbuild areas as to what issues require their most urgent attention.

Design of minimal-order stabilisers for multi-machine unstable power systems

A reduced dynamics stabiliser for multi-machine power systems is presented in this paper. The design of the stabiliser is based on the theory of linear functional observers and the solution of a simple parameter optimisation problem. The order of the stabiliser could be as low as the number of machines in the system. The design is applied to an open-loop unstable multi-machine power system.

The reality of quality systems software : working for the machine, or smart people around the machine?

This case study-based research examines the outcomes of using quality system software (QSS) in terms of the support it provides to, and the constraints it imposes on, its users. The results indicate that QSS can help facilitate knowledge access and sharing, and to a lesser extent, facilitate communication. It can be an effective mechanism for initiating and managing changes to work processes. Although some writers have opined that information technology (IT) is another way of controlling workers, this was not evidenced in this study. Technical shortcomings did hamper performance of some tasks, and for some managers, extra work was involved.

Machine to die for: the quest for free energy

This is about the search for 'perpetual motion' and 'free energy'. Conventional science claims that it is impossible, yet generations of inventors have been mesmerised by the promise of an engine that powers itself. The world's reliance on diminishing fossil fuel resources and the associated problems of pollution serve to spur them on. It showcases a number of dedicated, sometimes eccentric, and always obsessive individuals who have devoted their lives to this quest.

Dehairing Australian alpaca fibres with a cashmere dehairing machine

Many classes of alpaca fibres contain a certain amount of coarse fibres, which are strong and stiff, and cause discomfort to the end users of the alpaca fibre products. It is therefore desirable to separate the coarse fibres from the fine alpaca fibres. This paper reports trial results on alpaca dehairing using a cashmere dehairing machine. The diameters of alpaca fleece, dehaired alpaca fibres and removed alpaca fibres were analysed, and the fibre lengths before and after dehairing have been compared. The results indicate that it is feasible to dehair alpaca fibres using a cashmere dehairing facility. The dehaired alpaca fibres are cleaner, bulkier and softer, with around 1.5 μm reduction in average fibre diameter, but the dehairing process shortens the dehaired fibre length considerably. The dehairing effectiveness of coarse fibre removal using the cashmere dehairing technology has also been discussed in this paper.

Ghosts in the machine : student participation and grade attainment in a web-assisted social work course

For many social work educators, the debate about whether social work education should be delivered using online technology has, as a result of institutional imperatives, moved on to how best this can be done. In this article, the process of designing and delivering part of a social work course using asynchronous online discussion is described and reflected upon. Student participation in the online environment is also compared with final course grades and the findings discussed in relation to existing literature. Recommendations for the future delivery of social work courses using online technology emerging from this discussion are offered.

The effect of smokefree policies on electronic gaming machine expenditure in Victoria, Australia

Objective: To examine the impact of smoke-free policies in Victorian gambling venues on electronic gaming machine (EGM) expenditure.

Method: Monthly EGM expenditure from July 1998 to December 2005, provided by the Victorian Commission for Gambling Regulation and the Office of the Liquor and Gambling Commissioner in South Australia, was analysed. The outcome measure was the ratio of monthly expenditure for Victoria to monthly expenditure in South Australia. Intervention analysis and autoregressive integrated moving average modelling were used to assess the impact of the smoke-free policy on expenditure.

Results: The smoke-free policy resulted in an abrupt, long-term decrease in the level of EGM expenditure. The mean level of monthly expenditure decreased by approximately 14%.

Conclusion: The smoke-free policy not only protects hospitality workers and patrons from exposure to secondhand smoke but has also had an impact on slowing gambling losses.

The effect of smoke-free policies on electronic gaming machine expenditure in Victoria, Australia

Objective: To examine the impact of smoke-free policies in Victorian gambling venues on electronic gaming machine (EGM) expenditure.

Method: Monthly EGM expenditure from July 1998 to December 2005, provided by the Victorian Commission for Gambling Regulation and the Office of the Liquor and Gambling Commissioner in South Australia, was analysed. The outcome measure was the ratio of monthly expenditure for Victoria to monthly expenditure in South Australia. Intervention analysis and autoregressive integrated moving average modelling were used to assess the impact of the smoke-free policy on expenditure.

Results: The smoke-free policy resulted in an abrupt, long-term decrease in the level of EGM expenditure. The mean level of monthly expenditure decreased by approximately 14%.

Conclusion: The smoke-free policy not only protects hospitality workers and patrons from exposure to secondhand smoke but has also had an impact on slowing gambling losses.

Choreographer-mathematician collaboration: developing machine segmentation techniques for motion capture analysis of dance

This paper/presentation focuses on the science of human movement, motion capture and cognition in action, and examines the necessity of choreographer-mathematician collaboration in developing appropriate analysis techniques.

Linear-motor based five-axis parallel machine for effective material processing

The aim of the work was to reduce the cost and improve the performance of five-axis machines. The main performance criteria were motion cycle-time and positioning accuracy/precision. A novel machine that utilizes the concept of parallel-kinematics and linear motor technology is proposed, designed, built and controlled for this sake.