摘要
项目评估在市场机遇获得、成本控制和竞争力判别等方面决定着企业的成功与否.通过对影响项目价值的属性、因素、显性指标以及它们之间关系的研究,采用模拟生物神经元基本功能的神经网络技术建立项目价值模型,改进了传统的BP算法,对样本进行监督训练的反向传播算法得到权重因子,从而确定指定项目的价值,辅助决策者进行项目评估决策.实际应用证明了算法的有效性和模型的实用性.
Project evaluation is an imlortant strategy for enterprises. Because of the significantly increasing cost and keen market competition, project evaluation will decide whether a firm succeeds or not in business, including oplortunity seizing, cost control and competitive lower. Studies the project＇s attributes influencing factors and explicit indexes, which affect the project value, and the relationship between them. The artificial neural network is used to develop a project value model, and the conventional BP algorithm is improved to get weighting factors for sample monitoring and training, thus determining the project value and assisting the decision-maker to evaluate the project. A real application example is given to prove the efficiency of the algorithm and practicality of the model.
出处
《东北大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2007年第2期169-171,共3页
Journal of Northeastern University(Natural Science)
基金
国家自然科学基金重点资助项目(70431003)
关键词
项目评估
项目价值模型
神经元网络
反向传播算法
项目评估决策
project evaluation
project value model
artificial neural network
BP （back propagation） algorithm
decision by project evaluation
