Developing Software Agents for Data Mining : [AIMM] Agents for Improving Maintenance Management

This report demonstrates the development of: • Development of software agents for data mining • Link data mining to building model in virtual environments • Link knowledge development with building model in virtual environments • Demonstration of software agents for data mining • Populate with maintenance data

Using data mining to improve building life cycle

The building life cycle process is complex and prone to fragmentation as it moves through its various stages. The number of participants, and the diversity, specialisation and isolation both in space and time of their activities, have dramatically increased over time. The data generated within the construction industry has become increasingly overwhelming. Most currently available computer tools for the building industry have offered productivity improvement in the transmission of graphical drawings and textual specifications, without addressing more fundamental changes in building life cycle management. Facility managers and building owners are primarily concerned with highlighting areas of existing or potential maintenance problems in order to be able to improve the building performance, satisfying occupants and minimising turnover especially the operational cost of maintenance. In doing so, they collect large amounts of data that is stored in the building’s maintenance database. The work described in this paper is targeted at adding value to the design and maintenance of buildings by turning maintenance data into information and knowledge. Data mining technology presents an opportunity to increase significantly the rate at which the volumes of data generated through the maintenance process can be turned into useful information. This can be done using classification algorithms to discover patterns and correlations within a large volume of data. This paper presents how and what data mining techniques can be applied on maintenance data of buildings to identify the impediments to better performance of building assets. It demonstrates what sorts of knowledge can be found in maintenance records. The benefits to the construction industry lie in turning passive data in databases into knowledge that can improve the efficiency of the maintenance process and of future designs that incorporate that maintenance knowledge.

Making visible the coding process : Using qualitative data software in a post-structural study

Qualitative research methods require transparency to ensure the ‘trustworthiness’ of the data analysis. The intricate processes of organizing, coding and analyzing the data are often rendered invisible in the presentation of the research findings, which requires a ‘leap of faith’ for the reader. Computer assisted data analysis software can be used to make the research process more transparent, without sacrificing rich, interpretive analysis by the researcher. This article describes in detail how one software package was used in a poststructural study to link and code multiple forms of data to four research questions for fine-grained analysis. This description will be useful for researchers seeking to use qualitative data analysis software as an analytic tool.

Sustainable subdivisions – ventilation data analysis

This project, as part of a broader Sustainable Sub-divisions research agenda, addresses the role of natural ventilation in reducing the use of energy required to cool dwellings

Looking through the haze of discontent : smokers as a data source

In the case of industrial relations research, particularly that which sets out to examine practices within workplaces, the best way to study this real-life context is to work for the organisation. Studies conducted by researchers working within the organisation comprise some of the (broad) field’s classic research (cf. Roy, 1954; Burawoy, 1979). Participant and non-participant ethnographic research provides an opportunity to investigate workplace behaviour beyond the scope of questionnaires and interviews. However, we suggest that the data collected outside a workplace can be just as important as the data collected inside the organisation’s walls. In recent years the introduction of anti-smoking legislation in Australia has meant that people who smoke cigarettes are no longer allowed to do so inside buildings. Not only are smokers forced outside to engage in their habit, but they have to smoke prescribed distances from doorways, or in some workplaces outside the property line. This chapter considers the importance of cigarette-smoking employees in ethnographic research. Through data collected across three separate research projects, the chapter argues that smokers, as social outcasts in the workplace, can provide a wealth of important research data. We suggest that smokers also appear more likely to provide stories that contradict the ‘management’ or ‘organisational’ position. Thus, within the haze of smoke, researchers can uncover a level of discontent with the ‘corporate line’ presented inside the workplace. There are several aspects to the increased propensity of smokers to provide a contradictory or discontented story. It may be that the researcher is better able to establish a rapport with smokers, as there is a removal of the artificial wall a researcher presents as an outsider. It may also be that a research location physically outside the boundaries of the organisation provides workers with the freedom to express their discontent. The authors offer no definitive answers; rather, this chapter is intended to extend our knowledge of workplace research through highlighting the methodological value in using smokers as research subjects. We present the experience of three separate case studies where interactions with cigarette smokers have provided either important organisational data or alternatively a means of entering what Cunnison (1966) referred to as the ‘gossip circle’. The final section of the chapter draws on the evidence to demonstrate how the community of smokers, as social outcasts, are valuable in investigating workplace issues. For researchers and practitioners, these social outcasts may very well prove to be an important barometer of employee attitudes; attitudes that perhaps cannot be measured through traditional staff surveys.

Preliminary report on data mining techniques for life prediction

This project is an extension of a previous CRC project (220-059-B) which developed a program for life prediction of gutters in Queensland schools. A number of sources of information on service life of metallic building components were formed into databases linked to a Case-Based Reasoning Engine which extracted relevant cases from each source. In the initial software, no attempt was made to choose between the results offered or construct a case for retention in the casebase. In this phase of the project, alternative data mining techniques will be explored and evaluated. A process for selecting a unique service life prediction for each query will also be investigated. This report summarises the initial evaluation of several data mining techniques.

Report : school survey to collect data on material performance

A survey of a number of schools in a number of different climates was carried out to determine the condition of building components of interest in the project. Schools in Melbourne, the Victorian Surf Coast, Brisbane, Townsville and the Sunshine Coast were inspected. A rating system was devised to categorise the components and the results collated in tables. Analysis of the data (where sufficient examples permitted) resulted in formulae to predict the service of the components and a database was derived.

Report : wireless data throughput testing on a mobile device using WiFi and GPRS

This project report presents the results of a study on wireless communication data transfer rates for a mobile device running a custombuilt construction defect reporting application. The study measured the time taken to transmit data about a construction defect, which included digital imagery and text, in order to assess the feasibility of transferring various types and sizes of data and the ICT-supported construction management applications that could be developed as a consequence. Data transfer rates over GPRS through the Telstra network and WiFi over a private network were compared. Based on the data size and data transfer time, the rate of transfer was calculated to determine the actual data transmission speeds at which the information was being sent using the wireless mobile communication protocols. The report finds that the transmission speeds vary considerably when using GPRS and can be significantly slower than what is advertised by mobile network providers. While WiFi is much faster than GPRS, the limited range of WiFi limits the protocol to residential-scale construction sites.

Report : stochastic analysis of road asset data for maintenance cost prediction

Reliable budget/cost estimates for road maintenance and rehabilitation are subjected to uncertainties and variability in road asset condition and characteristics of road users. The CRC CI research project 2003-029-C ‘Maintenance Cost Prediction for Road’ developed a method for assessing variation and reliability in budget/cost estimates for road maintenance and rehabilitation. The method is based on probability-based reliable theory and statistical method. The next stage of the current project is to apply the developed method to predict maintenance/rehabilitation budgets/costs of large networks for strategic investment. The first task is to assess the variability of road data. This report presents initial results of the analysis in assessing the variability of road data. A case study of the analysis for dry non reactive soil is presented to demonstrate the concept in analysing the variability of road data for large road networks. In assessing the variability of road data, large road networks were categorised into categories with common characteristics according to soil and climatic conditions, pavement conditions, pavement types, surface types and annual average daily traffic. The probability distributions, statistical means, and standard deviation values of asset conditions and annual average daily traffic for each type were quantified. The probability distributions and the statistical information obtained in this analysis will be used to asset the variation and reliability in budget/cost estimates in later stage. Generally, we usually used mean values of asset data of each category as input values for investment analysis. The variability of asset data in each category is not taken into account. This analysis method demonstrated that it can be used for practical application taking into account the variability of road data in analysing large road networks for maintenance/rehabilitation investment analysis.

Nonfatal heroin overdoses in Queensland, Australia : an analysis of ambulance data

In the past decade, the utilization of ambulance data to inform the prevalence of nonfatal heroin overdose has increased. These data can assist public health policymakers, law enforcement agencies, and health providers in planning and allocating resources. This study examined the 672 ambulance attendances at nonfatal heroin overdoses in Queensland, Australia, in 2000. Gender distribution showed a typical 70/30 male-to-female ratio. An equal number of persons with nonfatal heroin overdose were between 15 and 24 years of age and 25 and 34 years of age. Police were present in only 1 of 6 cases, and 28.1% of patients reported using drugs alone. Ambulance data are proving to be a valuable population-based resource for describing the incidence and characteristics of nonfatal heroin overdose episodes. Future studies could focus on the differences between nonfatal heroin overdose and fatal heroin overdose samples.

Benchmarks for recycling practices in commercial office building refurbishment : data collection challenges

In recent years considerable effort has gone into quantifying the reuse and recycling potential of waste generated by residential construction. Unfortunately less information is available for the commercial refurbishment sector. It is hypothesised that significant economic and environmental benefit can be derived from closer monitoring of the commercial construction waste stream. With the aim of assessing these benefits, the authors are involved in ongoing case studies to record both current standard practice and the most effective means of improving the eco-efficiency of materials use in office building refurbishments. This paper focuses on the issues involved in developing methods for obtaining the necessary information on better waste management practices and establishing benchmark indicators. The need to create databases to establish benchmarks of waste minimisation best practice in commercial construction is stressed. Further research will monitor the delivery of case study projects and the levels of reuse and recycling achieved in directly quantifiable ways

A user driven data mining process model and learning system

This paper deals with the problem of using the data mining models in a real-world situation where the user can not provide all the inputs with which the predictive model is built. A learning system framework, Query Based Learning System (QBLS), is developed for improving the performance of the predictive models in practice where not all inputs are available for querying to the system. The automatic feature selection algorithm called Query Based Feature Selection (QBFS) is developed for selecting features to obtain a balance between the relative minimum subset of features and the relative maximum classification accuracy. Performance of the QBLS system and the QBFS algorithm is successfully demonstrated with a real-world application

Generation of a 3D proximal femur shape from a single projection 2D radiographic image.

Summary Generalized Procrustes analysis and thin plate splines were employed to create an average 3D shape template of the proximal femur that was warped to the size and shape of a single 2D radiographic image of a subject. Mean absolute depth errors are comparable with previous approaches utilising multiple 2D input projections. Introduction Several approaches have been adopted to derive volumetric density (g cm-3) from a conventional 2D representation of areal bone mineral density (BMD, g cm-2). Such approaches have generally aimed at deriving an average depth across the areal projection rather than creating a formal 3D shape of the bone. Methods Generalized Procrustes analysis and thin plate splines were employed to create an average 3D shape template of the proximal femur that was subsequently warped to suit the size and shape of a single 2D radiographic image of a subject. CT scans of excised human femora, 18 and 24 scanned at pixel resolutions of 1.08 mm and 0.674 mm, respectively, were equally split into training (created 3D shape template) and test cohorts. Results The mean absolute depth errors of 3.4 mm and 1.73 mm, respectively, for the two CT pixel sizes are comparable with previous approaches based upon multiple 2D input projections. Conclusions This technique has the potential to derive volumetric density from BMD and to facilitate 3D finite element analysis for prediction of the mechanical integrity of the proximal femur. It may further be applied to other anatomical bone sites such as the distal radius and lumbar spine.

Fusion of in-vehicle sensor data to develop Intelligent Driver Training System (IDTS)

The over represented number of novice drivers involved in crashes is alarming. Driver training is one of the interventions aimed at mitigating the number of crashes that involve young drivers. To our knowledge, Advanced Driver Assistance Systems (ADAS) have never been comprehensively used in designing an intelligent driver training system. Currently, there is a need to develop and evaluate ADAS that could assess driving competencies. The aim is to develop an unsupervised system called Intelligent Driver Training System (IDTS) that analyzes crash risks in a given driving situation. In order to design a comprehensive IDTS, data is collected from the Driver, Vehicle and Environment (DVE), synchronized and analyzed. The first implementation phase of this intelligent driver training system deals with synchronizing multiple variables acquired from DVE. RTMaps is used to collect and synchronize data like GPS, vehicle dynamics and driver head movement. After the data synchronization, maneuvers are segmented out as right turn, left turn and overtake. Each maneuver is composed of several individual tasks that are necessary to be performed in a sequential manner. This paper focuses on turn maneuvers. Some of the tasks required in the analysis of ‘turn’ maneuver are: detect the start and end of the turn, detect the indicator status change, check if the indicator was turned on within a safe distance and check the lane keeping during the turn maneuver. This paper proposes a fusion and analysis of heterogeneous data, mainly involved in driving, to determine the risk factor of particular maneuvers within the drive. It also explains the segmentation and risk analysis of the turn maneuver in a drive.