ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

CIDASD 2012 - Computational Intelligent Data Analysis for Sustainable Development

Date2012-03-01

Deadline2011-08-15

VenueCALL FOR C, Online Online

Keywords

Website

Topics/Call fo Papers

Chapter Proposals Deadline: August 15, 2011
"Computational Intelligent Data Analysis for Sustainable Development", as a part of “Data Mining and Knowledge Discovery Series” published by Taylor & Francis: http://www.physics.usyd.edu.au/~tingyu/CIDASD.htm
A book edited by Ting Yu, University of Sydney, Australia, Nitesh Chawla, University of Notre Dame, USA and Simeon Simoff, University of Western Sydney, Australia

Introduction:
The characteristic of economic, environmental and social data gives many unique challenges to the data mining and machine learning researchers. First of all, economic and environmental data are often spatial and temporal. Major characteristics of spatial data are its structural complexity and the level of uncertainty, being inherited from natural system and human society which generate these datasets. For example, the uncertainty of the boundary introduces the modifiable areal unit problem (MAUP). Secondly, large databases and long periods of environmental observation, monitoring of pollution, rare and extreme events and recent remote sensing technologies entail the use of new analytical and processing tools. Observation only provides the necessary data sets, but a correct interpretation of the monitored phenomena requires a process of knowledge extraction from data aimed to the detection of spatial patterns and underlying relations among the measured variables. This is possible only through a careful machine learning and data mining process. Thirdly, in most cases, economic and environmental data manifolds are subject to strong noise and nonlinear and the relations among the involved variables are often not very clear or even distorted by the noise. Low signal-noise ratio causes the high variance of resultant models. In the classical machine learning application, variance can be decreased by including more training data. In many cases, disregarding the abundant supply of data, many economic and environmental phenomenons are time-evolving, which shortens the time span of the data and limits their relevance with the present decision making. More real-time and coverage data analysis is required to collect data cross a large area promptly.

Audience for the Book
The primary audience for the edited book will be university professors, graduate students, researchers and professionals in both data analysis and sustainable development fields. Another audience would be government officials and policy makers interested in sustainability analysis.

Recommended Topics by Domain
In order to handle and manage the complex nature of economic and environmental information, special data analysis technologies, methods and systems must be developed. The objective of this book is to present the recent work or research in the field of computational intelligent data analysis for economic, environmental and social sustainable development. The book includes, but is not limited to the following techniques for sustainable development and real case studies from three main domains of sustainable development application:
Domain 1: Environmental Sustainability
This domain focuses on sustainability on natural resources, energy resources and environment impact assessment. The sub-domains include renewable energy, smart grid, material discovery for fuel cell technology, climate change, atmosphere, water, oceans, forest, land, soil, biodiversity, species etc.
Domain 2: Economic Sustainability
This domain focuses on sustainability on economics and human behavior, for example, human well-being, risks and risk management, global flows: finance, trade, technology transfer and debt, the dynamics of production and consumption.
Domain 3: Social Sustainability
This domain focuses on sustainability on human-built social systems, including transportation systems, cities, buildings, agriculture, health Information and health in its environmental, cultural, economic and social contexts, tax Information, levels of governance: sustainability at local, regional, national, and international levels, planning for sustainability, population growth and its consequences, theories of complexity and uncertainty, and knowledge sources, information resources and data collection processes.

Intelligent Data Analysis Technology Includes:
Mathematical Optimization
Statistical Analysis
Machine Learning, Data Mining and Knowledge Discovery
Artificial Neural Networks
Spatial and Temporal Data Mining and Spatial Statistical Models
Network Modeling and Prediction
Geographic Information Systems
Data Visualization

Important Dates
Chapter Proposals Due: August 15, 2011
Notification of Accepted Chapter Proposals: September 15, 2011
Full Chapters Due: November 15, 2011
Peer Review Results: January 15, 2012
Final Revised Chapters Due: March 1, 2012

Contact person: Ting Yu, t.yu-AT-physics.usyd.edu.au

Last modified: 2011-07-20 07:37:52