Elizabeth Chang, Daniel Prior and Steve Cannon
UNSW Canberra at the Australian Defence Force Academy, Australia
Australian Defense Force, Australia
Posters & Accepted Abstracts: Int J Sens Netw Data Commun
The increasing uncertainty of the business environment and complexity of high operational tempo has increased the demand for timely, accurate and ease of use information. However, a range of challenges are currently present. a) Each enterprise relies on several desperate IT systems which have limited interoperability. b) Relevant information could emerge from thousands of data sources (particularly in wireless and mobile environment), making data capture, storage and analysis difficult. c) Too much data and information makes decision making difficult, even for Data Expert. This keynote presents emerging technologies for just-in-time human-centred recommender system and its application to logistics network situation awareness powered by Internet of Things ?? where simplified data-set and decision support are given through automated data usage and decision mining processes and in real time. This keynote introduces the framework for real time massive data mining and predictive analytics. We demonstrate this through predictive situation context and situation aspect analytics and the intelligent situation awareness platform. We also present the comparison of 40 years of data mining technologies, and an overview of the state-of-the-art recommender systems, viability of ??plug n play? functions for any enterprise systems. Finally, we present our statistics of end-users stresses with guided analytics and self-service BI. This is followed by the illustration on the need for moving forward from data visualization to recommender systems, to reduce temporal and cognitive load of the human users, decision makers or data expert.
E-mail: E.Chang@adfa.edu.au
Spanish 
Chinese 
Russian 
German 
French 
Japanese 
Portuguese 
Hindi 