Supercharge Your Innovation With Domain-Expert AI Agents!

Noise waveform removing device and method, model training device and method, generation model and wearable device

A technology for generating models and model training, which is applied in neural learning methods, biological neural network models, sound-generating devices, etc., and can solve the problem that wearable devices cannot correctly determine the user's motion state, etc.

Pending Publication Date: 2022-03-18
CASIO COMPUTER CO LTD
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In this case, the motion waveform data detected by the wearable device includes not only the waveform due to the impact of landing as expected data, but also noise, that is, the waveform due to non-landing impact, and the wearable device may not be able to obtain the waveform based on the inertial sensor. motion waveform data to correctly determine the user's motion state

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
  • Noise waveform removing device and method, model training device and method, generation model and wearable device
  • Noise waveform removing device and method, model training device and method, generation model and wearable device
  • Noise waveform removing device and method, model training device and method, generation model and wearable device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In the following embodiments, a noise waveform removing device is disclosed, which uses a trained generation model to generate noise-free motion waveform data from noisy motion waveform data including noise originating from non-ground impact; and a model training device, which utilizes the recognition model to train the generation model following a GAN (Generative Adversarial Network, Generative Adversarial Network).

[0028] [Summary of this disclosure]

[0029] If carry out outline to the embodiment described later, then as follows figure 1 As shown, the noise waveform removing device 100 inputs noisy motion waveform data including noise originating from non-ground impacts to a trained generation model, and obtains a filter contribution rate from the trained generation model. The noise waveform removing device 100 performs filtering according to the filter contribution rate, removes noise from noisy motion waveform data, and generates noise-free motion waveform data....

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 noise waveform removal device, a model training device, a noise waveform removal method, a model training method, a generative model and a wearable device. Techniques are provided for removing noise from motion waveform data containing noise. One embodiment of the present disclosure relates to a noise waveform removal device comprising: an acquisition unit that acquires noisy motion waveform data; a filter contribution rate determination unit that determines a filter contribution rate on the basis of the noisy motion waveform data by using a trained generation model; and a noise removal unit that generates noiseless motion waveform data on the basis of the determined filter contribution rate and the noisy motion waveform data.

Description

[0001] This application claims priority based on Japanese Patent Application No. 2020-157821 (filing date: September 18, 2020), the contents of which are incorporated into this specification by reference. technical field [0002] The present disclosure relates to a noise waveform removing device, a model training device, a noise waveform removing method, a model training method, a generated model, and a wearable device. Background technique [0003] In order to detect the motion state of the user during exercise such as running and walking, inertial sensors such as acceleration sensors and gyro sensors are used. A user carries a wearable device such as a smart phone, a smart watch, or a pedometer (registered trademark) incorporating such an inertial sensor, and checks the motion state analyzed based on motion waveform data representing the motion state acquired by the device. [0004] On the other hand, when carrying such a wearable device, the user sometimes puts the wearab...

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 Applications(China)
IPC IPC(8): A61B5/00
CPCA61B5/7207A61B5/7225A61B5/7267G10K15/02G10K11/16G06N3/08G06N3/045G06N3/088
Inventor 上田将司
Owner CASIO COMPUTER CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com