CN113280832A - Step counting method and system based on accelerometer - Google Patents
Step counting method and system based on accelerometer Download PDFInfo
- Publication number
- CN113280832A CN113280832A CN202110791326.0A CN202110791326A CN113280832A CN 113280832 A CN113280832 A CN 113280832A CN 202110791326 A CN202110791326 A CN 202110791326A CN 113280832 A CN113280832 A CN 113280832A
- Authority
- CN
- China
- Prior art keywords
- signals
- acceleration
- sub
- accelerometer
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000001133 acceleration Effects 0.000 claims abstract description 111
- 210000003141 lower extremity Anatomy 0.000 claims abstract description 43
- 210000001364 upper extremity Anatomy 0.000 claims abstract description 34
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 26
- 210000000707 wrist Anatomy 0.000 claims abstract description 9
- 238000003672 processing method Methods 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 8
- 238000005311 autocorrelation function Methods 0.000 claims description 7
- 238000010183 spectrum analysis Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000001914 filtration Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C22/00—Measuring distance traversed on the ground by vehicles, persons, animals or other moving solid bodies, e.g. using odometers, using pedometers
- G01C22/006—Pedometers
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a step counting method and system based on an accelerometer, which comprises the steps of collecting acceleration signals in real time by using the accelerometer at the position where a wrist of a wearer wears a watch; carrying out signal decomposition on the collected acceleration signals to obtain sub-signals; reconstructing the sub-signals obtained by decomposition to obtain reconstructed acceleration signals; and (4) counting steps by using the obtained reconstructed acceleration signal formed by the lower limb movement. The invention separates the acceleration signal generated by the upper limb movement from the acceleration signal generated by the lower limb movement by adopting a signal decomposition method, thereby solving the problem of the interference of the upper limb movement on the accurate calculation of the number of steps of the lower limb; by adopting the method of separating and processing the upper limb movement and the lower limb movement, the high-robustness step-counting algorithm free from the interference of the upper limb movement is realized.
Description
Technical Field
The invention relates to the technical field of accelerometers, in particular to a step counting method and system based on an accelerometer, and particularly relates to a high-robustness step counting method based on an accelerometer.
Background
At present, a plurality of step counting methods are lack of optimization under the condition of movement interference of upper limbs. The acceleration captured at the wrist is a coupling of the upper limb movement and the lower limb movement, and the upper limb movement and the lower limb movement overlap in frequency, and the two cannot be separated by a conventional filtering or frequency-domain signal processing method. The current step counting method is not disturbed much when the upper limb of the user swings regularly or moves slightly. But large errors can occur when the upper limbs move erratically or violently.
The accelerometer-based pedometer estimates the number of steps by calculating the number of peaks of an acceleration signal generated by walking of the lower limbs or a signal of an autocorrelation function thereof, but when the signal collected by the accelerometer is disturbed by the movement of the upper limbs of the human body when the accelerometer is worn on the wrist (such as a smart watch), the correlation between the peaks of the signal and the number of steps is destroyed and cannot be used for accurately estimating the number of steps.
In patent document CN103727959B, a step counting method and apparatus are disclosed, the method comprising repeatedly performing the following steps: a) acquiring three single-axis acceleration signals with preset lengths from three-axis outputs of a three-axis acceleration sensor worn by a runner; b) carrying out high-pass filtering on each single-axis acceleration signal; c) carrying out fundamental frequency detection on each high-pass filtered single-axis acceleration signal; d) setting a low-pass or band-pass filter by using the fundamental frequency obtained by detecting each fundamental frequency as a cut-off frequency, and performing low-pass or band-pass filtering on the corresponding high-pass filtered uniaxial acceleration signal by using the low-pass or band-pass filter; e) obtaining an acceleration signal extreme point in each single-axis acceleration signal after low-pass or band-pass filtering and removing an interference extreme point; f) counting the number of the acceleration signal extreme points after the interference extreme points are removed; g) and determining the accumulated step number of the runner.
Although the above-mentioned techniques can give a rough step-counting result, they do not consider irregular movement or large-amplitude violent movement of the upper limb, and cannot ensure the accuracy of step-counting. Therefore, a technical solution is needed to improve the above technical problems.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a step counting method and system based on an accelerometer.
According to the invention, the step counting method based on the accelerometer comprises the following steps:
step S1: collecting acceleration signals in real time by using an accelerometer at the position where the wrist of a wearer wears a watch;
step S2: carrying out signal decomposition on the collected acceleration signals to obtain sub-signals;
step S3: reconstructing the sub-signals obtained by decomposition to obtain reconstructed acceleration signals;
step S4: and (4) counting steps by using the obtained reconstructed acceleration signal formed by the lower limb movement.
Preferably, the acceleration signal in step S1 includes a sum of accelerations of three axes, an acceleration of one of the three axes, and a sum of accelerations of two of any of the three axes.
Preferably, the step S2 includes the steps of:
step S2.1: decomposing the acceleration signal into a series of sub-signals by a signal time-frequency processing method;
step S2.2: calculating autocorrelation of the decomposed sub-signals respectively;
the signal time-frequency processing method comprises empirical mode decomposition, singular spectrum analysis and wavelet transformation.
Preferably, the step S3 includes the steps of:
step S3.1: obtaining a reconstructed acceleration signal formed by the movement of the lower limbs by linearly superposing the sub-signals;
step S3.2: obtaining a reconstructed acceleration signal formed by the movement of the upper limb by linearly superposing the sub-signals;
step S3.3: and obtaining noise by linearly superposing the sub-signals.
Preferably, in step S4, the peak-to-peak frequency of the reconstructed acceleration signal including the lower limb movement or the peak-to-peak frequency of the autocorrelation function of the reconstructed acceleration signal including the lower limb movement is calculated first, and then the number of steps is estimated by using the peak-to-peak frequency obtained by regression estimation.
The invention also provides a step counting system based on the accelerometer, which comprises the following modules:
module M1: collecting acceleration signals in real time by using an accelerometer at the position where the wrist of a wearer wears a watch;
module M2: carrying out signal decomposition on the collected acceleration signals to obtain sub-signals;
module M3: reconstructing the sub-signals obtained by decomposition to obtain reconstructed acceleration signals;
module M4: and (4) counting steps by using the obtained reconstructed acceleration signal formed by the lower limb movement.
Preferably, the acceleration signal in the module M1 includes a sum of accelerations of three axes, an acceleration of one of the three axes, and a sum of accelerations of any two of the three axes.
Preferably, the module M2 includes the following modules:
module M2.1: decomposing the acceleration signal into a series of sub-signals by a signal time-frequency processing method;
module M2.2: calculating autocorrelation of the decomposed sub-signals respectively;
the signal time-frequency processing method comprises empirical mode decomposition, singular spectrum analysis and wavelet transformation.
Preferably, the module M3 includes the following modules:
module M3.1: obtaining a reconstructed acceleration signal formed by the movement of the lower limbs by linearly superposing the sub-signals;
module M3.2: obtaining a reconstructed acceleration signal formed by the movement of the upper limb by linearly superposing the sub-signals;
module M3.3: and obtaining noise by linearly superposing the sub-signals.
Preferably, the module M4 calculates a peak-to-peak frequency of the reconstructed acceleration signal caused by the lower limb movement or calculates a peak-to-peak frequency of an autocorrelation function of the reconstructed acceleration signal caused by the lower limb movement, and estimates the step number by using the peak-to-peak frequency obtained by regression estimation.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention separates the acceleration signal generated by the upper limb movement from the acceleration signal generated by the lower limb movement by adopting a signal decomposition method, thereby solving the problem of the interference of the upper limb movement on the accurate calculation of the number of steps of the lower limb;
2. according to the invention, by adopting a signal time-frequency processing method such as empirical mode decomposition, the problem of frequency domain aliasing of the acceleration signal of the upper limb movement and the acceleration signal of the lower limb movement is solved;
3. the invention realizes a high-robustness step-counting algorithm free from the interference of upper limb movement by adopting a method of separating and processing the upper limb movement and the lower limb movement;
4. according to the method, an original signal is decomposed into a series of sub-signals in a signal time-frequency transformation mode, the sub-signals are combined into a reconstructed acceleration signal mainly formed by upper limb movement according to autocorrelation of the signals, and the reconstructed acceleration signal mainly formed by lower limb movement and noise are combined, so that the acceleration signal generated by the upper limb movement is separated from the acceleration signal generated by the lower limb movement, accuracy and reliability of step counting are guaranteed, and accurate step estimation under the condition of upper limb movement interference is realized.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
Referring to fig. 1, the invention provides a step counting method and system based on an accelerometer, which uses a series of signal processing methods to process acceleration signals collected by the accelerometer, so as to realize accurate estimation of the step number under the condition of upper limb movement interference, and specifically comprises the following steps:
step S1: collecting acceleration signals in real time by using an accelerometer at the position where people wear the intelligent watch everyday at the wrist; the acceleration signal can be the combined acceleration of three shafts or the acceleration of one shaft in the three shafts or the combined acceleration of any two shafts in the three shafts; the sampling frequency and the preprocessing mode of the acceleration signals are not different from those of the traditional step counting algorithm.
Step S2: carrying out signal decomposition on the collected acceleration signals; step S2.1: decomposing the acceleration signal into a series of sub-signals by using signal time-frequency processing methods such as (but not limited to) empirical mode decomposition, singular spectrum analysis and wavelet transformation; step S2.2: and respectively calculating the autocorrelation of the subsignals obtained by decomposition.
Step S3: reconstructing the sub-signals obtained by decomposition; step S3.1: obtaining a reconstructed acceleration signal mainly composed of lower limb movement by linearly superposing the sub-signals with stronger autocorrelation and larger amplitude; step S3.2: obtaining a reconstructed acceleration signal mainly composed of upper limb movement by linearly superposing the sub-signals with weaker autocorrelation and larger amplitude; step S3.3: and linearly superposing the sub-signals with smaller amplitudes to obtain noise.
Step S4: step counting is carried out by using the obtained reconstructed acceleration signal mainly formed by the lower limb movement; the step counting principle is that firstly, the peak-to-peak frequency of a reconstructed acceleration signal mainly formed by lower limb movement is calculated or the peak-to-peak frequency of an autocorrelation function of the reconstructed acceleration signal mainly formed by the lower limb movement is calculated; and estimating the step number by using the obtained peak-to-peak frequency through regression estimation.
The invention also provides a high-robustness step counting system based on the accelerometer, which comprises the following modules: module M1: collecting acceleration signals in real time by using an accelerometer at the position where the wrist of a wearer wears a watch; the acceleration signal comprises the combined acceleration of three axes, the acceleration of one axis in the three axes and the combined acceleration of any two axes in the three axes.
Module M2: carrying out signal decomposition on the collected acceleration signals to obtain sub-signals; module M2.1: decomposing the acceleration signal into a series of sub-signals by a signal time-frequency processing method; module M2.2: calculating autocorrelation of the decomposed sub-signals respectively; the signal time-frequency processing method comprises empirical mode decomposition, singular spectrum analysis and wavelet transformation.
Module M3: reconstructing the sub-signals obtained by decomposition to obtain reconstructed acceleration signals; module M3.1: obtaining a reconstructed acceleration signal formed by the movement of the lower limbs by linearly superposing the sub-signals; module M3.2: obtaining a reconstructed acceleration signal formed by the movement of the upper limb by linearly superposing the sub-signals; module M3.3: and obtaining noise by linearly superposing the sub-signals.
Module M4: step counting is carried out by using the obtained reconstructed acceleration signal formed by the lower limb movement; the step counting is to calculate the peak-to-peak frequency of the reconstructed acceleration signal composed of the lower limb movement or calculate the peak-to-peak frequency of the autocorrelation function of the reconstructed acceleration signal composed of the lower limb movement, and then estimate the step number by the peak-to-peak frequency obtained by regression estimation.
The invention separates the acceleration signal generated by the upper limb movement from the acceleration signal generated by the lower limb movement by adopting a signal decomposition method, thereby solving the problem of the interference of the upper limb movement on the accurate calculation of the number of steps of the lower limb; by adopting a signal time-frequency processing method such as empirical mode decomposition and the like, the problem of frequency domain aliasing of the acceleration signal of the upper limb movement and the acceleration signal of the lower limb movement is solved; by adopting the method of separating and processing the upper limb movement and the lower limb movement, the high-robustness step-counting algorithm free from the interference of the upper limb movement is realized.
According to the method, an original signal is decomposed into a series of sub-signals in a signal time-frequency transformation mode, the sub-signals are combined into a reconstructed acceleration signal mainly formed by upper limb movement according to autocorrelation of the signals, and the reconstructed acceleration signal mainly formed by lower limb movement and noise are combined, so that the acceleration signal generated by the upper limb movement is separated from the acceleration signal generated by the lower limb movement, accuracy and reliability of step counting are guaranteed, and accurate step estimation under the condition of upper limb movement interference is realized.
Those skilled in the art will appreciate that, in addition to implementing the system and its various devices, modules, units provided by the present invention as pure computer readable program code, the system and its various devices, modules, units provided by the present invention can be fully implemented by logically programming method steps in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system and various devices, modules and units thereof provided by the invention can be regarded as a hardware component, and the devices, modules and units included in the system for realizing various functions can also be regarded as structures in the hardware component; means, modules, units for performing the various functions may also be regarded as structures within both software modules and hardware components for performing the method.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (10)
1. An accelerometer-based step counting method, comprising the steps of:
step S1: collecting acceleration signals in real time by using an accelerometer at the position where the wrist of a wearer wears a watch;
step S2: carrying out signal decomposition on the collected acceleration signals to obtain sub-signals;
step S3: reconstructing the sub-signals obtained by decomposition to obtain reconstructed acceleration signals;
step S4: and (4) counting steps by using the obtained reconstructed acceleration signal formed by the lower limb movement.
2. The accelerometer-based step counting method according to claim 1, wherein the acceleration signals in step S1 include the combined acceleration of three axes, the acceleration of one of the three axes, and the combined acceleration of any two of the three axes.
3. The accelerometer-based step counting method according to claim 1, wherein the step S2 comprises the steps of:
step S2.1: decomposing the acceleration signal into a series of sub-signals by a signal time-frequency processing method;
step S2.2: calculating autocorrelation of the decomposed sub-signals respectively;
the signal time-frequency processing method comprises empirical mode decomposition, singular spectrum analysis and wavelet transformation.
4. The accelerometer-based step counting method according to claim 1, wherein the step S3 comprises the steps of:
step S3.1: obtaining a reconstructed acceleration signal formed by the movement of the lower limbs by linearly superposing the sub-signals;
step S3.2: obtaining a reconstructed acceleration signal formed by the movement of the upper limb by linearly superposing the sub-signals;
step S3.3: and obtaining noise by linearly superposing the sub-signals.
5. The accelerometer-based step counting method according to claim 1, wherein step S4 is to calculate a peak-to-peak frequency of the reconstructed acceleration signal caused by the lower limb movement or calculate a peak-to-peak frequency of an autocorrelation function of the reconstructed acceleration signal caused by the lower limb movement, and estimate the step number by regression estimation using the obtained peak-to-peak frequency.
6. An accelerometer-based pedometer system, comprising the following modules:
module M1: collecting acceleration signals in real time by using an accelerometer at the position where the wrist of a wearer wears a watch;
module M2: carrying out signal decomposition on the collected acceleration signals to obtain sub-signals;
module M3: reconstructing the sub-signals obtained by decomposition to obtain reconstructed acceleration signals;
module M4: and (4) counting steps by using the obtained reconstructed acceleration signal formed by the lower limb movement.
7. The accelerometer-based pedometer system of claim 6, wherein the acceleration signals in module M1 include the combined acceleration of three axes, the acceleration of one of the three axes, and the combined acceleration of any two of the three axes.
8. The accelerometer-based pedometer system of claim 6, wherein the module M2 includes the following modules:
module M2.1: decomposing the acceleration signal into a series of sub-signals by a signal time-frequency processing method;
module M2.2: calculating autocorrelation of the decomposed sub-signals respectively;
the signal time-frequency processing method comprises empirical mode decomposition, singular spectrum analysis and wavelet transformation.
9. The accelerometer-based pedometer system of claim 6, wherein the module M3 includes the following modules:
module M3.1: obtaining a reconstructed acceleration signal formed by the movement of the lower limbs by linearly superposing the sub-signals;
module M3.2: obtaining a reconstructed acceleration signal formed by the movement of the upper limb by linearly superposing the sub-signals;
module M3.3: and obtaining noise by linearly superposing the sub-signals.
10. The accelerometer-based pedometer system of claim 6, wherein the module M4 is configured to calculate the peak-to-peak frequency of the reconstructed acceleration signal caused by the lower limb movement or calculate the peak-to-peak frequency of the autocorrelation function of the reconstructed acceleration signal caused by the lower limb movement, and then estimate the step number by regression estimation using the obtained peak-to-peak frequency.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791326.0A CN113280832A (en) | 2021-07-13 | 2021-07-13 | Step counting method and system based on accelerometer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791326.0A CN113280832A (en) | 2021-07-13 | 2021-07-13 | Step counting method and system based on accelerometer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113280832A true CN113280832A (en) | 2021-08-20 |
Family
ID=77286623
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110791326.0A Pending CN113280832A (en) | 2021-07-13 | 2021-07-13 | Step counting method and system based on accelerometer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113280832A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103727959A (en) * | 2013-12-31 | 2014-04-16 | 歌尔声学股份有限公司 | Step counting method and step counting device |
| CN104990562A (en) * | 2015-06-29 | 2015-10-21 | 合肥工业大学 | Step counting method based on autocorrecting computing |
| CN108592941A (en) * | 2018-06-15 | 2018-09-28 | 成都云卫康医疗科技有限公司 | A kind of step-recording method based on 3-axis acceleration |
| US10716495B1 (en) * | 2016-03-11 | 2020-07-21 | Fortify Technologies, LLC | Accelerometer-based gait analysis |
| US11045116B1 (en) * | 2017-09-15 | 2021-06-29 | David Martin | Enhanced determination of cadence for control in mobile |
-
2021
- 2021-07-13 CN CN202110791326.0A patent/CN113280832A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103727959A (en) * | 2013-12-31 | 2014-04-16 | 歌尔声学股份有限公司 | Step counting method and step counting device |
| CN104990562A (en) * | 2015-06-29 | 2015-10-21 | 合肥工业大学 | Step counting method based on autocorrecting computing |
| US10716495B1 (en) * | 2016-03-11 | 2020-07-21 | Fortify Technologies, LLC | Accelerometer-based gait analysis |
| US11045116B1 (en) * | 2017-09-15 | 2021-06-29 | David Martin | Enhanced determination of cadence for control in mobile |
| CN108592941A (en) * | 2018-06-15 | 2018-09-28 | 成都云卫康医疗科技有限公司 | A kind of step-recording method based on 3-axis acceleration |
Non-Patent Citations (2)
| Title |
|---|
| 郎爱坤等: "基于集合经验模态分解的老年人步态信号的降噪方法", 《北京测绘》, no. 04, 21 April 2020 (2020-04-21), pages 443 - 448 * |
| 陈国良等: "一种基于手机传感器自相关分析的计步器实现方法", 《中国惯性技术学报》, no. 06, 15 December 2014 (2014-12-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106228200B (en) | Action identification method independent of action information acquisition equipment | |
| Thang et al. | Gait identification using accelerometer on mobile phone | |
| Yoneyama et al. | Accelerometry-based gait analysis and its application to Parkinson's disease assessment—part 1: detection of stride event | |
| Groth | Visualization of coupling in time series by order recurrence plots | |
| CN104522949B (en) | A kind of Intelligent bracelet for qualitative assessment disturbances in patients with Parkinson disease motor function | |
| CN104215257B (en) | High-precision and high pseudo-step removing human step-counting method integrating power consumption management | |
| CN105496416A (en) | Human motion state recognition method and device | |
| Wang et al. | Artifact reduction based on Empirical Mode Decomposition (EMD) in photoplethysmography for pulse rate detection | |
| Lee | Motion artifacts reduction from PPG using cyclic moving average filter | |
| CN105989694A (en) | Human body falling-down detection method based on three-axis acceleration sensor | |
| CN105180959A (en) | Anti-interference step counting method for wrist type step counting devices | |
| Allseits et al. | Characterizing the impact of sampling rate and filter design on the morphology of lower limb angular velocities | |
| Turnip et al. | Adaptive principal component analysis based recursive least squares for artifact removal of EEG signals | |
| Sheng et al. | An adaptive time window method for human activity recognition | |
| CN114469073A (en) | Gait analysis and abnormity detection method based on step wearable sensor | |
| JP6794793B2 (en) | Walking state estimation method, walking state estimation program and information processing device | |
| Nema et al. | Wavelet-frequency analysis for the detection of discontinuities in switched system models of human balance | |
| Salarian et al. | An ambulatory system to quantify bradykinesia and tremor in Parkinson's disease | |
| Elbuni et al. | ECG parameter extraction algorithm using (DWTAE) algorithm | |
| CN113280832A (en) | Step counting method and system based on accelerometer | |
| CN108072386B (en) | Step counting method and device | |
| Xie et al. | Combining adaptive filter and phase vocoder for heart rate monitoring using photoplethysmography during physical exercise | |
| Ison et al. | Beyond user-specificity for emg decoding using multiresolution muscle synergy analysis | |
| CN110786863B (en) | Pedestrian gait detection method based on mobile device | |
| Sütő et al. | Real time human activity monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210820 |
|
| RJ01 | Rejection of invention patent application after publication |