Research Article Open Access

Intelligent Identification and Sorting of Chinese Herbs Recommend a String-Level Predictive Electromechanical System

Wenyi Zhang1, Gang Wang2, Xiaofei Xu1, Junjie Zhu1, Keping Mao1, Tao Ma1 and Zixuan Li1
  • 1 School of Automation, Beijing Information Science and Technology University, Beijing, China
  • 2 School of Life Sciences, Beijing University of Chinese Medicine, Beijing, China

Abstract

Based on the analysis of a large number of Chinese medicinal materials, a mobile robot visual function research and development experimental domestic chips electromechanical arm-controller, which was constructed using a typical kernel algorithm recommended by Chinese medicinal materials visual recognition, which the cascade Electromechanical Control System was based on iterative learning electromechanical control for multi-joint manipulators. The original and improved YOLOV5 algorithm models were compared to detect and recommend targets in the color recognition and shape recognition vision scene of mobile robots in human-computer interaction. The experimental results show that, on the self-made data set, the improved system can obtain a better average accuracy score and detection speed and meet the requirements of real-time and accuracy, it provides a new reference design scheme for the experimental platform of mobile robot vision recognition

American Journal of Biochemistry and Biotechnology
Volume 20 No. 2, 2024, 159-168

DOI: https://doi.org/10.3844/ajbbsp.2024.159.168

Submitted On: 4 February 2024 Published On: 11 July 2024

How to Cite: Zhang, W., Wang, G., Xu, X., Zhu, J., Mao, K., Ma, T. & Li, Z. (2024). Intelligent Identification and Sorting of Chinese Herbs Recommend a String-Level Predictive Electromechanical System. American Journal of Biochemistry and Biotechnology, 20(2), 159-168. https://doi.org/10.3844/ajbbsp.2024.159.168

  • 216 Views
  • 71 Downloads
  • 0 Citations

Download

Keywords

  • Domestic Chips
  • Electromechanical Controller
  • Mobile Robot Vision
  • Target Recognition Recommendation
  • YOLOv5
  • Distance-IOU
  • CSPNet
  • FocalLoss