Ensemble parameter estimation for graphical models

Parameter Estimation is one of the key issues involved in the discovery of graphical models from data. Current state of the art methods have demonstrated their abilities in different kind of graphical models. In this paper, we introduce ensemble learning into the process of parameter estimation, and examine ensemble parameter estimation methods for different kind of graphical models under complete data set and incomplete data set. We provide experimental results which show that ensemble method can achieve an improved result over the base parameter estimation method in terms of accuracy. In addition, the method is amenable to parallel or distributed processing, which is an important characteristic for data mining in large data sets.

Conceptual framework of the precautionary principle approach in the decision-making process

This article reviews the precautionary principle as an approach in addressing decisions with far reaching environmental consequences under scientific uncertainty. The precautionary principle is intended to assist with structuring environmentally risky decisions toward sustainable development. It responds to the lack of scientific evidence of a potential environmental problem. There is currently no framework to assist with the process indicating the areas of importance and stages of decisionmaking. This paper suggests a framework to assist with the process of decision-making for complex environmental problems. The main areas of concern are the issues relating to the costs, risks, and benefits assessments. The main stages of the framework includes; definition of the problem, analysis of the potential environmental risks, assessments of specific anticipated legal, social, economic, political, and technological impacts, review of the key players (social, organisation and government) obligations, comparison of alternatives available, determination of accountability, implementation, decision making, monitoring and control processes.

On-line tool condition monitoring and control system in forging processes

Cold bulk metal forming has made large-scale production of small complex solid parts economically feasible. Tooling used in metal forming poses many uncertainties in the preliminary cost estimation and production process and continual tool replacement and maintenance dramatically reduces productivity and raises manufacturing cost. In order to tackle this, an on-line tool condition monitoring system using artificial neural network (ANN) to integrate information from multiple sensors for forging process has been developed. Together with the force, acoustic emission signals and process conditions, information developed from theoretical models is integrated into the ANN tool monitoring system to predict tool life and provide the maintenance schedule.

Knowledge enhancement in the change process : social marketing and attitude change leading to improved environmental behaviour

The complexity of relationships between social change and natural resource management has generated interest in the identification of indicators that might provide more streamlined means of monitoring and planning control programmes. This case study highlights the marketing paradigms of benchmarking and social marketing in a not-for-profit governmental environment. Publicly funded programs that require individual and community participation need to be marketed with a view to optimising involvement and commitment of the various stakeholders. A mail survey with a representative sample of 608 respondents was conducted to evaluate the effectiveness of a social marketing program. This study highlights the use of social marketing in a program to overcome an environmental issue by a governmental agency. Changing attitudes and beliefs takes time and often the target audience may not even know they have a problem that needs fixing. This process influences the focus of the social marketing effort which might be organised into three phases: • Raise awareness and knowledge.   •Change attitudes.  • Encourage action. The research conducted in this study illustrates how the various stages in the social marketing process were achieved through knowledge enhancement in an environmental management case study.

The mental health Risk Assessment and Management Process (RAMP) for schools: II. Process evaluation

The Risk Assessment and Management Process (RAMP) is a whole-school process for the assessment and management of student’s mental health and wellbeing in primary and secondary schools. A process evaluation revealed that RAMP was implemented as intended across six primary and three secondary schools in Melbourne, Australia. Using the RAMP risk and protective factors monitoring form and screening processes, each school identified ‘at-risk’ students who had not previously been identified or received assistance from welfare staff at the school. School staff and mental health workers from local agencies reported improvements in their knowledge of risk and protective factors, and their ability to identify at-risk students following RAMP. They also reported satisfaction in outcomes for at-risk students managed within the school using RAMP. All the primary schools and one of the
secondary schools continued to use some RAMP processes in their school up to 6 months after the initial implementation of the program.

Dynamic characteristics and efficiency of a fluidized bed heat treatment process

The dynamic characteristics of gas bubbles in fluidized beds are important to determine the heat and mass transfer rates at component surfaces and the treated profiles of components. They also have great impact on the components’ structural, mechanical and physical properties. However, it has been very difficult to monitor those characteristics dynamically. In this paper, a specifically designed fluidized bed was introduced to facilitate the capturing of its dynamic characteristics and a new video image processing and analysis algorithm was developed. The algorithm is robust and adaptive in terms of locating both bubbles and components in beds with a single or multiple components. It has many advantages in dynamic characterization of gas bubbles and monitoring component treatment. By using this algorithm, the properties of gas bubbles over any period of time can be accurately obtained. This technology will provide a potential on-line dynamic monitoring and quality control system for the chemical heat treatment processes with fluidized beds.

The process evaluation of it's your move!, an Australian adolescent community-based obesity prevention project

Background
Evidence on interventions for preventing unhealthy weight gain in adolescents is urgently needed. The aim of this paper is to describe the process evaluation for a three-year (2005-2008) project conducted in five secondary schools in the East Geelong/Bellarine region of Victoria, Australia. The project, 'It's Your Move!' aimed to reduce unhealthy weight gain by promoting healthy eating patterns, regular physical activity, healthy body weight, and body size perception amongst youth; and improve the capacity of families, schools, and community organisations to sustain the promotion of healthy eating and physical activity in the region.

Methods
The project was supported by Deakin University (training and evaluation), a Reference Committee (strategic direction, budgetary approval and monitoring) and a Project Management Committee (project delivery). A workshop of students, teachers and other stakeholders formulated a 10-point action plan, which was then translated into strategies and initiatives specific to each school by the School Project Officers (staff members released from teaching duties one day per week) and trained Student Ambassadors. Baseline surveys informed intervention development. Process data were collected on all intervention activities and these were collated and enumerated, where possible, into a set of mutually exclusive tables to demonstrate the types of strategies and the dose, frequency and reach of intervention activities.

Results
The action plan included three guiding objectives, four on nutrition, two on physical activity and one on body image. The process evaluation data showed that a mix of intervention strategies were implemented, including social marketing, one-off events, lunch time and curriculum programs, improvements in infrastructure, and healthy school food policies. The majority of the interventions were implemented in schools and focused on capacity building and healthy eating strategies as physical activity practices were seen by the teachers as already meeting students' needs.

Conclusions
While substantial health-promoting activities were conducted (especially related to healthy eating), there remain further opportunities for secondary schools to use a whole-of-school approach through the school curriculum, environment, policies and ethos to improve healthy eating, physical activity and healthy body perceptions in youth. To achieve this, significant, sustained leadership will be required within the education sector generally and within schools specifically.

Parameter sensitivity analysis of surface plasmon resonance biosensor through numerical simulation

Surface based analytical tools have gained more importance for rapid, sensitive and label-free monitoring of molecular recognition events. Surface plasmon resonance (SPR) has played a prominent role in real time monitoring of surface binding events. SPR is increasing its significance especially for the study of ultrathin dielectric layer. This paper investigates the role of thin films of gold, silver and aluminium for protein detection in SPR biosensors. It is shown that the sensitivity, which is indicated by the shift of plasmon dip, is not linearly related to the thickness of protein but quadratic over a specific range. The approach involves a plot of a reflectivity curve as a function of the angle of incidence.

Characterisation of an out-of-autoclave resin film infusion process for textile composites

A new method to manufacture damage tolerant textile composites, which combines Resin Film Infusion with a fast and cost·efficient curing technology QuickstepTM, was investigated. The effect of process parameters on resin flow through carbon fibre preforms was analysed and model-based parameter optimisation resulted in considerable improvement of resin flow properties.

Condition monitoring and fault prediction via an adaptive neural network

This paper describes the application of an adaptive neural network, called Fuzzy ARTMAP (FAM), to handle fault prediction and condition monitoring problems in a power generation station. The FAM network, which is supplemented with a pruning algorithm, is used as a classifier to predict different machine conditions, in an off-line learning mode. The process under scrutiny in the power plant is the Circulating Water (CW) system, with prime attention to monitoring the heat transfer efficiency of the condensers. Several phases of experiments were conducted to investigate the `optimum' setting of a set of parameters of the FAM classifier for monitoring heat transfer conditions in the power plant.

Processing multiple image streams for real-time monitoring of parking lots

We present a system to detect parked vehicles in a typical parking complex using multiple streams of images captured through IP connected devices. Compared to traditional object detection techniques and machine learning methods, our approach is significantly faster in detection speed in the presence of multiple image streams. It is also capable of comparable accuracy when put to test against existing methods. And this is achieved without the need to train the system that machine learning methods require. Our approach uses a combination of psychological insights obtained from human detection and an algorithm replicating the outcomes of a SVM learner but without the noise that compromises accuracy in the normal learning process. Performance enhancements are made on the algorithm so that it operates well in the context of multiple image streams. The result is faster detection with comparable accuracy. Our experiments on images captured from a local test site shows very promising results for an implementation that is not only effective and low cost but also opens doors to new parking applications when combined with other technologies.

Monitoring the early stage self-assembly of enzyme-assisted peptide hydrogels

The early stages of the self-assembly of peptide hydrogels largely determine their final material properties. Here we discuss experimental methodologies for monitoring the self-assembly kinetics which underpin peptide hydrogel formation. The early stage assembly of an enzyme-catalysed Fmoc-trileucine based self-assembled hydrogel was examined using spectroscopic techniques (circular dichroism, CD, and solution NMR) as well as chromatographic (HPLC) and mechanical (rheology) techniques. Optimal conditions for enzyme-assisted hydrogel formation were identified and the kinetics examined. A lag time associated with the formation and accumulation of the self-assembling peptide monomer was observed and a minimum hydrogelator concentration required for gelation was identified. Subsequent formation of well defined nano-and microscale structures lead to self-supporting hydrogels at a range of substrate and enzyme concentrations. 1H NMR monitoring of the early self-assembly process revealed trends that were well in agreement with those identified using traditional methods (i.e. HPLC, CD, rheology) demonstrating 1H NMR spectroscopy can be used to non-invasively monitor the self-assembly of peptide hydrogels without damaging or perturbing the system.

Computer simulation based parameter selection for resistance exercise

In contrast to most scientific disciplines, sports science research has been characterized by comparatively little effort investment in the development of relevant phenomenologi-cal models. Scarcer yet is the application of said models in practice. We present a framework which allows resistance training practitioners to employ a recently proposed neu-romuscular model in actual training program design. The first novelty concerns the monitoring aspect of coaching. A method for extracting training performance characteristics from loosely constrained video sequences, effortlessly and with minimal human input, using computer vision is described. The extracted data is subsequently used to fit the underlying neuromuscular model. This is achieved by solving an inverse dynamics problem corresponding to a particular exercise. Lastly, a computer simulation of hypothetical training bouts, using athlete-specific capability parameters, is used to predict the effected adaptation and changes in performance. The software described here allows the practitioner to manipulate hypothetical training parameters and immediately see their effect on predicted adaptation for a specific athlete. Thus, this work presents a holistic view of the monitoring-assessment-adjustment loop.

2Loud? Monitoring traffic noise with mobile phones

The World Health Organization has recently focused attention on guidelines for night noise in urban areas, based on significant medical evidence of the adverse impacts of exposure to excessive traffic noise on health, especially caused by sleep disturbance. This includes serious illnesses, such as hypertension, arteriosclerosis and myocardial infarction. 2Loud? is a research project with the aim of developing and testing a mobile phone application to allow a community to monitor traffic noise in their environment, with focus on the night period and indoor measurement. Individuals, using mobile phones, provide data on characteristics of their dwellings and systematically record the level of noise inside their homes overnight. The records from multiple individuals are sent to a server, integrated into indicators and shared through mapping. The 2Loud? application is not designed to replace existing scientific measurements, but to add information which is currently not available. Noise measurements to assist the planning and management of traffic noise are normally carried out by designated technicians, using sophisticated equipment, and following specific guidelines for outdoors locations. This process provides very accurate records, however, for being a time consuming and expensive system, it results in a limited number of locations being surveyed and long time between updates. Moreover, scientific noise measurements do not survey inside dwellings. In this paper we present and discuss the participatory process proposed, and currently under implementation and test, to characterize the levels of exposure to traffic noise of residents living in the vicinity of highways in the City of Boroondara (Victoria, Australia) using the 2Loud? application.