Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Faculty of Engineering, Faculty of Engineering, Computing and Mathematics Computing and Mathematics Big Data Research Processing and Mining Advanced Sensing Technologies Advancing big data technology for remote engineering Introducing the Big Data Processing and Mining research group The group’s goal is to develop new techniques and systems to manage and make sense of big data. Big data from engineering projects and research is transforming our world. The opportunities are vast. So are the challenges, generated by the sheer volume and complexity of this data. Engineering projects linked to remote operations typically generate unstructured data sets of hundreds of gigabytes – a size beyond the capabilities of commonly used software tools. From equipment and safety monitoring, to movement sensors and cameras, to satellites and mobile communications, remote engineering data trails are massive. Big data sets contain invaluable knowledge. For example, in marine environments data sets are collected from sensors deployed in floating buoys, underwater remote vehicles and offshore oil and gas platforms. In mining operations, data sets are collected on process control, operating, transportation and maintenance operations. Successful and reliable use of these information channels depends on understanding the patterns within this data. Every remote operations engineering activity has projects that demand new techniques and systems for the management of big data. The team brings together a multidisciplinary group of expert researchers. Problems that we solve Our work will focus on two main areas: Data Mining for engineering intelligence - the process of knowledge extraction is known as data mining. • Extracting knowledge from • • large volumes of data using high performance computers and accelerators Domain specific techniques are used to mine the data to discover the underlying patters and structure Development of new ways to automate the discovery of parameters for pattern discovery and changes of context. Processing engineering for remote operations data - the collection, cleaning and efficient processing of big data is essential for its usability. Our research contributes to the following areas: • • • • • ‘Real-time’ streaming Data representation Unstructured data Integration Cleaning of data Projects Key contacts • Analytics for discovering regular For further information about the group’s research capabilities: • • • • • • patterns in metered water use Sensor networks for monitoring the performance of rammed earth buildings have now collected 1 year of 2-minute to 1-hour sensor data from a network of 160 sensors in remote WA Anomaly detection in smart meter data to help users understand their highest water use behaviours Addressing the US$14 million dollar per year problem of leaks in water distribution pipeline systems, by researching machine learning methods for leak detection Occupancy detection sensor using a low-pixel count thermal imaging sensor Clinical text processing and mining methods were developed for mobile health applications from web resources Scalability of Relational Database Technologies for Exascale Data: Big data storage Opportunities for researchers Big data techniques are valuable in many knowledge areas. In addition to engineering for remote operations, there are opportunities in areas such as ocean engineering, asset management, geology, radio astronomy, genomics and medical research. Example project areas include: • Real-time online analytical • • • processing on a hybrid high performance computing platform Fast parallel subspace clustering to explore large, unknown data sets Cleaning and using unstructured data for large scale asset management tasks Intelligent urban water systems: smart water meters data analysis and mining environmental sensor networks. • Professor Rachel Cardell-Oliver Group Director, Specialises in data mining, sensor networks Email: [email protected] • Professor Amitava Datta Specialises in high performance computing, data mining Email: [email protected] • Professor Wei Liu Specialises in data mining, text mining Email: [email protected] To meet the challenges of ERO, a number of large-scale multidisciplinary research groups exist within the overall ERO theme, including: • • • • • • • • • • Advanced Sensing Technologies Big Data Processing and Mining Complex Data Modelling Engineering, Communities and Environment Engineering System Health Fluid Science and Resources Offshore Facilities and Ocean Systems Real-time Optimisation, Scheduling and Logistics Robotics and Automation Structural Mechanics, Geomechanics and Computation Global impact and industry support Located in Perth, the University of Western Australia is a world-top 100 university in the World University rankings and a member of the ‘Group of Eight’ - a coalition of the best researchintensive universities in Australia. Engineering for Remote Operations (ERO) is the Faculty of Engineering, Computing and Mathematics single strategic research initiative to find novel solutions to the challenges provided by remote operations. We are continuing to grow and develop our innovative research capabilities. The interdisciplinary, integrated approach and solutions within ERO are relevant internationally, nationally and in Western Australia. The ERO initiative encompasses: • Mining exploration, development • and operations • Coastal and offshore infrastructure • • • for the oil and gas industry Agriculture and aquaculture Transport, energy, communication and water supply networks Remote community development Faculty of Engineering, Computing and Mathematics The University of Western Australia M017, Perth WA 6009 Australia Tel: +61 8 6488 3061 Email: [email protected] ecm.uwa.edu.au Engineering for Remote Operations Professor Greg Ivey Deputy Dean (Research) Email: [email protected] ecm.uwa.edu.au/research