该项目负责人是新葡的京集团35222vip的左路路。项目组成员：左路路、杨学森、刘佳、蚁文洁。本项目的主要研究内容是整理和总结了国内外关于卷积神经网络的发展历程和最新的研究成果，将卷积神经网络算法进行了改进并应用于医学图像识别问题，分别在理论和应用层面对卷积神经网络的架构和性能进行研究分析。

本项目创新点：在医疗影像特征选择方面，采用了强化学习机制、轮盘赌机制等构建适应于提取医学影像特征的方法模型；小波分析等方法对于医学数据进行结构化处理，有效提高医疗辅助诊断的准确率和稳定性，减少误诊和漏诊。这不仅在人工智能、深度学习领域具有领先影响，在临床诊断、病理分析及治疗方案的选取方面也有重大意义。

本项目经结项验收，符合结项要求。其最终成果为：

论文：

1.Hong Wang, Lulu Zuo（左路路）, Jia Liu（刘佳）, Wenjie Yi（蚁文洁）, Ben Niu*. Ensemble Particle Swarm Optimization and Differential Evolution with Alternative Mutation Method. 2018，Natural Computing Online.

2.Lulu Zuo（左路路）, Lei Liu, Hong Wang*, and Lijing Tan*. A Hybrid Differential Evolution Algorithm and Particle Swarm Optimization with Alternative Replication Strategy. Advances in Swarm Intelligence. 9th International Conference, ICSI 2018, Shanghai, China, 17-22 June 2018.

3.Lu Xiao, Jinsong Chen, Lulu Zuo*（左路路）, Huan Wang, and Lijing Tan. Differential Structure-Redesigned-Based Bacterial Foraging Optimization. 9th International Conference, ICSI 2018, Shanghai, China, 17-22 June 2018.

4.Ben Niu, Xuesen Yang（杨学森）, Hong Wang*, Kaishan Huang, and Sung-Shun Weng. Feature Subset Selection Using a Self-adaptive Strategy Based Differential Evolution Method. Advances in Swarm Intelligence. 9th International Conference, ICSI 2018, Shanghai, China, 17-22 June 2018.

5.Hong Wang, Lulu Zuo（左路路）, Xuesen Yang（杨学森）. A Novel PSOEDE Algorithm for Vehicle Scheduling Problem in Public Transportation. 10th International Conference, ICSI 2019已录用.

6.Ben Niu, Xuesen Yang（杨学森）, Hong Wang*.Feature Selection using a Reinforcement-Behaved Brain Storm Optimization. IEEE CEC 2019. 2019已录用.