基于群聚智能的汉语认知隐态建模研究

项目名称： 基于群聚智能的汉语认知隐态建模研究

项目编号： No.60873054

项目类型： 面上项目

立项/批准年度： 2009

项目学科： 金属学与金属工艺

项目作者： 刘洪波

作者单位： 大连海事大学

项目金额： 33万元

中文摘要： 汉语微文广义，是稳定收敛的二维信息，生动而且高效。汉语认知研究为开启智能之门提供了机遇。本项目在神经信息学的基础上研究汉语认知隐态建模，从汉语认知实验样本数据较小的实际出发，观测到的激活特征被视为一个或多个隐性认知状态在同一时段对脑激活的反映，但观测数据与隐性认知状态并不是一一对应，而是与刺激(事件)相关并依一定概率激活不同的隐性认知状态，考虑刺激系列的时间效应，以认知实验刺激系列为依据，形成一种新的隐性动态建模方法和技术。基于双重时间序列思想，采用条件概率推理和群聚智能分析人脑汉语认知过程中脑区状态及其迁移过程，在更高分辨率的脑区上分析、统计具体认知实验任务时间序列上的激活、负激活乃至抑制信息，绘制脑区汉语认知动态回路和网络。这项研究具有中国特色和优势，将会为汉语认知脑研究提供新的手段，而且对人机汉语理解开展一些基础性研究。

中文关键词： 神经信息学；汉语认知；概率论；群聚智能

英文摘要： Chinese language could provide refined representations, which is convergent and provides stable two-dimension information. The research on language cognition would provide us the opportunities to uncover the complex relationship between mind and consciousness. This project focuses on Hidden Chinese Cognition Model (HCCM) based on Probability Theory and Swarm Intelligence, which is an advanced topic involving neuroscience and computer science. Neuroinformatics provides tools to create databases and the possibilities for interoperability between and among databases, models, networks technologies and models for the clinical and research purposes in the neuroscience community and other fields. Swarm intelligence is an innovative distributed intelligent paradigm, which is gaining momentum by several success stories. In our research on Chinese cognition, we usually have to confront that the available sample data is not enough from traditional statistical perspectives and the cognition processes are not directly visible. Our preliminary studies on Chinese language cognition experiments provide cognition observed time series according to stimulated time series. There is a probability distribution over the two types of time series. The unobserved series of hidden, overlapping cognitive processes in the brain probabilistically generates the cognition observed time series. We believe that the HCCM would help us to formulate the relationship between the time series and understand the dynamic processes of Chinese cognition, which would provide tools to draw the dynamic Chinese cognition networks. This research would be a significant step to understand the functioning of the human brain.

英文关键词： Neuroinformatics; Chinese Cognition; Probabilistic Theory; Swarm Intelligence