抑郁症智能诊断专家系统的设计  

Intelligent Diagnosis Expert System of Depression

作　　者：吉艳平[1] 危韧勇[1] 刘洋君[1] 

机构地区：[1]中南大学信息科学与工程学院,湖南长沙410075

出　　处：《计算机测量与控制》2007年第3期291-293,共3页Computer Measurement &Control

基　　金：国家"十五"科技攻关资助项目(2001BA701A22)

摘　　要：随着生活节奏加快,竞争压力增大,抑郁症已成为一种常见的心理障碍,其发病机理目前尚不是十分清楚,医学界没有严格统一的诊断标准;基于具有动态结构的BP神经网络,利用VC++设计开发了一套抑郁症智能诊断系统;该系统具有良好的灵活性和开放性,用户可以根据实际需要自行调整网络层数、节点数以及学习收敛误差等参数;采用批量BP算法,提高了学习效率和逼近能力;测试结果表明,该系统具有良好的分类效果,可以用于抑郁症的辅助诊断和治疗。Depression has become a kind of common psychological diseases with quicker life rhythm and stronger competition . Since the nosogenesis is still unclear , there is still no effective diagnostic routine for it . Based on the BP neural network with dynamic architecture , a depression intelligent diagnosis system is developed by using VC＋＋ techniques under the Windows environment. It is flexible and open for the parameters such as the numbers of the hidden layers and nodes in each layer, and the training convergent error can he configured by users easily . Adopting batch BP training algorithm , the learning efficiency and approach ability have been improved . In addition , test results show that this system has a strong ability for classif cation, and potential for the diagnosis and cure of depression.

关 键 词：抑郁症 神经网络 诊断系统 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]