基于多标签k近邻方法实现元启发式算法的排名推荐

Ranking recommendation to implement meta-heuristic algorithm based on multi-label k-nearest neighbor method

设计并研究一种基于多标签k近邻方法(multi-label k-nearest neighbor,ML-k NN)推荐元启发式算法的实现框架.应用多标签k近邻分类学习技术,实现最佳元启发式算法的排名推荐.为了验证效果,以多模式资源约束项目调度问题(MRCPSP)为优化对象,选取不同规模的数百个算例分别提取问题基本特征和地标特征;选用遗传、粒子群、禁忌搜索、蜂群和蚁群5种元启发式算法,使用ML-k NN建立元推荐模型;利用海明损失、单错误率、覆盖率、排位损失和平均准确率5个指标对推荐效果做出分析和评价.实验结果表明,基于ML-k NN方法推荐元启发式算法效果突出,其中基于地标特征的单错误率指标为18.4%,平均准确率达到88.9%.相对于k NN方法,MLk NN取得了更好的推荐结果.此外,ML-k NN方法可以实现对所有备选算法的排名推荐,该研究结论有望推广应用于其他组合优化问题的优化算法推荐.

This paper designs and studies the implementation framework of a recommendation meta-heuristic algorithm based on the multi-label k-nearest neighbor(ML-k NN).The multi-label k-nearest neighbor classification learning technology is applied to implement the best meta-heuristic algorithm ranking recommendation.In order to verify the effect,the multi-modal resource-constrained project scheduling problem(MRCPSP)is taken as the optimization object,and hundreds of examples of different scales are selected to extract landmarking features and problem basic features respectively;five meta-heuristic algorithms(genetics,particle swarm,tabu search,bee colony and ant colonies)are selected;the ML-k NN is applied to establish a meta-recommendation model;and the Hamming loss,single error rate,coverage rate,ranking loss and average accuracy rate are used to analyze and evaluate the recommendation effect.The experimental results show that the meta-heuristic algorithm based on ML-kNN recommendation is effective,among which,the single error rate of the ML-k NN based on landmarking features is 18.4%,and the average precision is88.9%.The ML-k NN had been acquired the better recommendation effect in relative with the single label k NN.In addition,the ML-k NN method is able to achieve the ranking recommendations for all alternative algorithms.The research conclusions are expected to be extended to other combinatorial optimization algorithms.