Application of Convolution Neural Network (CNN) Model Combined with Pyramid Algorithm in Aerobics Action Recognition

Area of Science:

• Computer Science
• Artificial Intelligence
• Biomedical Engineering

Background:

• High-accuracy recognition of aerobics actions is crucial but challenging.
• Existing methods often lack efficiency and applicability for complex movements.
• Deep learning models offer potential but require optimization for this domain.

Purpose of the Study:

• To develop and evaluate a deep learning model for precise aerobics action recognition.
• To investigate the combined application of convolution neural networks (CNNs) and the pyramid algorithm.
• To improve the efficiency and accuracy of aerobics action recognition systems.

Main Methods:

• Proposed a novel architecture integrating CNNs with a pyramid algorithm for aerobics action recognition.
• Processed traditional aerobics action capture data using the proposed model.
• Optimized the CNN model using deep learning techniques and the pyramid algorithm to address recognition function limitations.

Main Results:

• The proposed CNN model based on the pyramid algorithm demonstrated superior performance in recognizing different aerobics actions.
• The model achieved higher accuracy and efficiency compared to conventional recognition methods.
• Error evaluation confirmed the effectiveness of the developed recognition model.

Conclusions:

• The integration of CNNs with the pyramid algorithm provides a highly applicable and efficient solution for aerobics action recognition.
• This deep learning approach significantly enhances the accuracy of identifying complex aerobics movements.
• The study validates the effectiveness of the proposed model over traditional techniques.