| 引用本文: | 朱磊,牛绿茵,宋士吉,张玉利.基于最大熵马尔科夫模型的绩效评价方法[J].控制理论与应用,2017,34(3):337~344.[点击复制] |
| ZHU Lei,NIU Lv-yin,SONG Shi-ji,ZHANG Yu-li.Performance evaluation based on maximum entropy Markov model[J].Control Theory and Technology,2017,34(3):337~344.[点击复制] |
|
| 基于最大熵马尔科夫模型的绩效评价方法 |
| Performance evaluation based on maximum entropy Markov model |
| 摘要点击 2541 全文点击 2568 投稿时间：2016-03-13 修订日期：2016-12-23 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2017.60134 |
| 2017,34(3):337-344 |
| 中文关键词 绩效评价方法 最大熵马尔科夫模型 最大熵 隐马尔科夫模型 Viterbi算法 改进迭代算法 |
| 英文关键词 performance evaluation method maximum entropy Markov model maximum entropy methods hidden Markov models Viterbi algorithm improved iterative scaling algorithm |
| 基金项目 国家海洋局大洋专项基金项目(DYXY–125), 国家自然科学基金项目(61273233), 中国博士后科学基金特别项目(61503211), 教育部高等学校博士 |
|
| 中文摘要 |
| 本文提出了一种基于最大熵马尔科夫模型的绩效评价方法. 该方法采用马氏模型来定量化建模专家打分过程, 采用特征函数表征打分规则, 通过在训练集上最大化熵来获得符合专家经验的最优的打分模型. 与传统方法相比, 所提出的方法可以融合各种打分规则、专家经验和指标逻辑关系得到综合打分结果. 为了提高模型的训练和打分的效率, 本文提出了基于改进迭代算法的参数估计方法, 并利用Viterbi算法进行快速打分计算. 利用中国大洋协会绩效评价指标体系历史数据进行的仿真实验表明, 与BP神经网络方法和最大熵方法进行对比, 本文所提出的
方法具有更高的打分正确率. |
| 英文摘要 |
| This paper presents a new performance evaluation method based on the maximum entropy Markov model,which quantifies the process of scoring as a Markov process, represents the scoring rules by characteristic functions and
obtains the optimal model parameters by maximizing the maximum entropy over a training sample set. Compared with other traditional methods, this method has the ability to combine complex scoring rules, expert experience with logical connection
of the evaluated items to get comprehensive evaluation results. To improve the efficiency of training and scoring, this paper adopts the improved iterative scaling algorithm to obtain near-optimal model parameters and uses the Viterbi algorithm to
quickly calculate the final evaluation results. The proposed method has been applied in the history data of China Ocean Mineral Resources R&D Association’s evaluation system for simulation. The experimental results show that this method
has higher accuracy compared with BP networks and the classical maximum entropy model. |
|
|
|
|
|