“软件人”感知系统的协同分类模型研究  

Research on the Cooperative Classification Model in the Perception System of SoftMan

作　　者：米爱中[1] 徐国章[1] 曾广平[1] 涂序彦[1] 

机构地区：[1]北京科技大学信息工程学院

出　　处：《计算机科学》2007年第11期140-143,共4页Computer Science

基　　金：国家自然科学基金(60375038;60503024)

摘　　要："软件人"是计算机网络世界中的一类软件人工生命,是一种网络中的"虚拟机器人",它具有拟人结构。作为对人的模拟,其感知系统应该像人的感知系统一样,具有区分感知对象的能力。基于人体感知系统的启发,运用大系统分析的"分解-集结"方法,本文提出了一种"软件人"感知系统的协同分类模型。该模型通过多分类器系统模拟人的不同感觉,从而实现"软件人"对感知对象的多感觉协同分类。仿真实验结果初步验证了本文提出模型的可行性。今后的工作是研究如何构造实际系统并将其应用于数字气田建设的数据处理工作中。SoftMan, the virtual robot in network environment, is a kind of software Artificial Life living in computer networks. It has a humanoid structure, and simulating human, its perception system should be able to recognize the perceptive object. Enlightened by human perception system and the ＂disassemble-integration＂ method in analyzing large systems, a cooperative classification model in SoftMan＇s perception system is proposed. In the model, different humanized senses are simulated by multiple classifier systems. Consequently, SoftMan can perform multi-sense cooperative classification on its perceptive objects. A simulated experiment validates the basic feasibility of the model. The future work is how to construct a practical system and apply it to the data processing work in building digital gas fields.

关 键 词：“软件人” 感知系统 协同分类 多分类器系统 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]