Random Forest enhancement using improved Artificial Fish Swarm for the medial knee contact force prediction

作者：

Highlights：

• The first is to implement knee contact force prediction via Random Forest. Compared with other algorithms proposed by other papers, the algorithm has better performance.

• The study uses the improved Fish Swarm algorithm to optimize the main parameters of the Random Forest model. From the experimental results, ours improved method has better performance on the standard test function, compared with the other 5 advanced improvement methods.

• The proposed methodology was cost-effective and easy to recreate for any subject.

摘要

•The first is to implement knee contact force prediction via Random Forest. Compared with other algorithms proposed by other papers, the algorithm has better performance.•The study uses the improved Fish Swarm algorithm to optimize the main parameters of the Random Forest model. From the experimental results, ours improved method has better performance on the standard test function, compared with the other 5 advanced improvement methods.•The proposed methodology was cost-effective and easy to recreate for any subject.

论文关键词：Artificial Fish Swarm,Random Forest,Knee replacement,Contact force prediction

论文评审过程：Received 7 October 2019, Revised 6 January 2020, Accepted 28 January 2020, Available online 3 February 2020, Version of Record 6 February 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101811