Research on the Cooperative Classification Model in the Perception System of SoftMan
“软件人”感知系统的协同分类模型研究

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 hu- manized senses are simulated by multiple classifier systems. Consequently, SoftMan can perform multi-sense coopera- tive classification on its perceptive objects. A simulated experiment validates the basic feasibility of the model The fu- ture work is how to construct a practical system and apply it to the data processing work in building digital gas fields.