Submission Guidelines
    Prospective authors are invited to submit full-length papers by the submission deadline. The submission of a paper implies that the paper is original and has not been submitted under review or copyright protected by the author if accepted.
    Besides papers in regular sessions, papers in special sessions are also invited to provide forums for focused discussions on new topics and innovative applications of established approaches. A special session consists of at least four related papers. Proposals for special sessions including the session organizers, author names, paper titles, abstracts, and brief statements on the purposes of the sessions must be submitted to the Special Sessions Chairs Si Wu at siwu@ion.ac.cn, Qing Ma at qma@math.ryukoku.ac.jp, or Paul S. Pang at shaoning.pang@aut.ac.nz by November 1, 2009.
    All papers should be submitted electronically via Online Paper Submission System. The format of the initial submissions must be PDF. The files of the final accepted papers should be in either Word or Latex. Enquiries on paper submissions can be addressed to the secretariat via email isnn2010@sjtu.edu.cn or phone.
    All submitted papers will be refereed by experts in the respective fields according to the criteria of originality, significance, quality, and clarity. The authors of accepted papers will have an opportunity to revise their papers and take consideration of the referees' comments and suggestions, before submitting the final papers.
    All accepted papers with paid registration will be included in the Proceedings of ISNN 2010, to be published by Springer as multiple volumes of Lecture Notes in Computer Science.

Paper Format
Papers must be single-spaced in one column format within an area of 122 mm x 193 mm with 10-point Times-Roman font. Each paper must not exceed 10 pages including figures and references (papers beyond six pages are subject to page surcharge). All papers must be written in English using the Springer LNCS (Lecture Notes in Computer Science) style, including all tables, figures, and references. It is required that the authors use the style file of Springer Lecture Notes in Computer Science (template files for MS Word or LaTeX2e) when preparing the manuscripts to ensure the uniformity of papers.

Special Sessions

Design of an Intelligent, Smart and Safe Vehicle

Tsu-Tian Lee, Chun-Fei Hsu

In the 21st century, the mainstream of technology development is the interdisciplinary integration, together with the Human Technology (HT) that emphasizes on friendly service for human rather than the forced adaptation by human. Intelligent Transportation Systems (ITS), an integrated discipline of sensing, controls, information technology, electronics and communications, represents a typical highly complex dynamic system. It is aimed to provide the traveler information to increase safety, efficiency, and reduce traffic jam, therefore a more humanistic transportation system.

In the past seven years, we focus our research efforts on the HT-ITS, which is integrated with advanced computers, electronics, communication, controls, and sensing technologies, aims to provide more “intelligent” transportation systems in terms of improved connections among users/travelers, vehicles and transportation facilities, better safety, efficiency, and reduced traffic jam, pollution and energy consumption: therefore, a more humanistic transportation system. Now, we plan to at organizing a special session titled “Design of an Intelligent, Smart and Safe Vehicle” in 7th International Symposium on Neural Networks (ISNN2010) to publish the fruits of our academic research achievements “HT-ITS”. This special session discusses some achievements of HT-ITS in Taiwan, including intelligent control technologies applied to next generation smart vehicles, driving safety assistance systems, and ITS information and communication platform.

Feature Selection for High Dimensional and Complex Data

Li Jun

Variable and feature selection has been a research topic with practical significance in many areas such as statistics, pattern recognition, machine learning, and data mining. During the past years, more and more high-dimensional datasets with small number of samples and complex data (e.g. graphs, strings, documents,..) are emerging, which have posed unprecedented challenges to data mining and pattern recognition. In order to construct simpler and more comprehensible models, improve data mining performance, and help to prepare, clean, and understand these high dimensional and complex data, the existed feature selection methodologies need to be adapted or new methodologies should be developed.

The session aims to further the cross-discipline, collaborative effort in feature selection research and share the methods. The topics include, but not limited to: Feature ranking, Feature extraction/construction, Selection in small samples with high dimensionality, Selection in extremely high-dimensional domains, Kernel feature selection, Semi-supervised feature selection, Ensemble feature selection, Combination of feature selection and feature extraction, Novel evaluation criterion for feature selection, Real-world case studies and application, such as gene selection, web mining, text processing, bioinformatics, social networks, etc.

Neural information processing and neural coding

Pei-Ji Liang

This special session proposal in ISNN2010 addresses problems related to the information representation and processing in the biological nervous system, which is fundamental and important for develop atificial neural networks and AI. It brings together researchers working across this field to share their experience and discuss advanced thinking. The introduction and discussion of neural information processing and neural coding will conduce to development of artificial neural networks and AI. The special session will be of great value to ISNN2010 participants.

Computational Intelligence for Robot Brain

Tetsuto Nishino, Haruhisa Takahashi, Shigeyoshi Watanabe

The theme reflects the growing development of robot intelligence in all aspects of human behavior and their increasing diversity. This session is motivated by that view and is centered around the study of various aspects of human actions since these are intimately linked with many higher cognitive abilities.

Natural language processing and machine learning

Qing Ma

Natural language processing (NLP) is a key technology in the information processing area and has a wide range of applications from word processor to information access including information retrieval, machine translation, text categorization, text mining, and so forth. Studies on NLP based on neural networks as a machine learning method began in the early 1980s with studies on implementing semantic networks, word-sense disambiguation, anaphora resolution, and parsing. Since then, with the increase in NLP research based on very large corpora, machine learning has attracted a great deal more attention from both the NLP and machine learning researchers. The special session provides a forum for researchers interested in further advancing the state of the art in developing NLP techniques that use machine learning.

Presentation Modes
The presentation mode of a paper can be oral or poster depending on the preference of the authors and arrangement of the organizers. The authors can indicate their preferences on oral or poster presentation when submitting papers.

Final Paper Submission
  All accepted papers, accompanied by valid registrations, must be received by February 1, 2010, in order for the papers to be included in the Proceedings. Please submit the followings
(a) Printable file of single-sided final (camera-ready) version of the paper which strictly follows the format requirements of the Springer LNCS.
(b) Source (input) files:
    For LaTeX and TeX users:
    (i) For example, LaTeX2e files for the text and PS or EPS files for figures.
    (ii) Final DVI file (for papers prepared using LaTeX/TeX).
    (iii) Final PS file (please avoid using the option "reverse order").
    (iv) Final PDF file (if possible).
    For Microsoft Word users:
    (i) RTF files (for word-processing systems other than LaTeX/TeX). Zip all files on the paper into     a single file with the paper number as the file name.
(c) Completed copyright form in scanned copy.
    The information in the copyright form:
    1. Conference/Book: Advances in Neural Networks -ISNN2010
    2. Volume Editor(s): Jun Wang, et al.
    3. Title of the contribution:
    4. Name and address of corresponding author (please print).
    5. Author's signature: