A non-contact fitness monitoring method using smart speakers

A smart speaker and non-contact technology, which is applied in the field of fitness behavior monitoring and fitness behavior monitoring using smart speakers, can solve the problem that Wi-Fi signals are easily interfered by environmental factors such as other people's movement, so that there is no leakage of privacy Problems, good user experience, high accuracy effect

Active Publication Date: 2022-07-22
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the disadvantage of the Wi-Fi-based approach is that a pair of antennas is usually required, and the user needs to exercise between the antennas
In addition, Wi-Fi signals are easily interfered by environmental factors such as the movement of others

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A non-contact fitness monitoring method using smart speakers
  • A non-contact fitness monitoring method using smart speakers
  • A non-contact fitness monitoring method using smart speakers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0073] The performance of this method is tested by using a Raspberry Pi 4B, a circular array of 6 microphones, and an omnidirectional speaker to build a smart speaker prototype. Eight fitness users of different levels (5 males and 3 females) were recruited for the experiment. A total of 4 different indoor environments, a bedroom, a living room, a study and an office, were selected as experimental sites.

[0074] First, test the overall accuracy of the method in various situations. 8 volunteers performed 10 fitness actions in 4 different environments, and the smart speakers classified the user's fitness activities. image 3 Average precision, recall, and F1 scores for all classifications are shown. It can be seen from the figure that the accuracy rate in all cases is not lower than 93.24%, the recall rate is not lower than 93.80%, and the average F1 score is 96.61%, which fully shows that this method has high accuracy.

[0075] Then, test the performance of this method under...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a non-contact fitness monitoring method using a smart speaker, and belongs to the technical field of mobile computing applications. The invention can realize the recognition of fitness actions only by relying on the loudspeaker in the smart speaker to emit high-frequency sound beyond the range of human hearing, and the microphone to receive the reflected signal, and to provide fine-grained fitness statistics and evaluation for users who exercise indoors. The method of the invention has low cost, strong anti-interference, no privacy leakage problem and good user experience, and is suitable for indoor monitoring environments such as homes and offices. The high-frequency sound adopted in the present invention exceeds the frequency of most noises in life, is not easily disturbed by environmental noise, and greatly enhances the environmental robustness of the non-contact fitness monitoring method. The present invention can monitor and evaluate typical fitness actions, and by combining deep learning technology and incremental learning technology, accurate action information can be obtained on a smart speaker with limited perception ability, and it has high accuracy.

Description

technical field [0001] The invention relates to a fitness behavior monitoring method, in particular to a fitness behavior monitoring method using a smart speaker, which is used for monitoring a user's fitness type and evaluating the user's fitness quality, and belongs to the technical field of mobile computing applications. Background technique [0002] Today, more and more people are beginning to pay attention to their health and body shape, and fitness is widely popular. Effective fitness can bring many benefits, such as increased muscle strength, improved body shape, and reduced risk of cardiovascular disease. However, due to the fast pace of life, going to a dedicated gym is inconvenient for many people. And getting a gym membership and hiring a personal trainer is often expensive. Therefore, many people start exercising at home / office, which is more beneficial to save time and money. However, due to the lack of effective supervision and professional effect evaluation...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08G08C23/02
CPCG06N3/08G08C23/02G06N3/044G06F2218/12G06F18/2415
Inventor 李凡解亚东付乐萌吴玥
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap