CN107713988A - A kind of obese degree detection means based on the extraction of stomach electrical feature - Google Patents
A kind of obese degree detection means based on the extraction of stomach electrical feature Download PDFInfo
- Publication number
- CN107713988A CN107713988A CN201710936363.XA CN201710936363A CN107713988A CN 107713988 A CN107713988 A CN 107713988A CN 201710936363 A CN201710936363 A CN 201710936363A CN 107713988 A CN107713988 A CN 107713988A
- Authority
- CN
- China
- Prior art keywords
- percentage
- degree detection
- pace
- signalses
- rhythm
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
- A61B5/7207—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
Abstract
A kind of obese degree detection means based on the extraction of stomach electrical feature, the obese degree detection means include：Collection and empirical mode decomposition module, forward and backward electro-gastric signalses are fed for gathering, field experience mode decomposition reconstruction signal, filter out the electrocardio and respiration interference being mixed with electro-gastric signalses；First computing module, for carrying out frequency-domain analysis-Hilbert transform to filtering out the electro-gastric signalses after disturbing, obtain hilbert spectrum；Second computing module, for calculating dominant frequency, the dominant frequency coefficient of variation, main power, main power percentage, postprandial power ratio main before the meal, normal slow wave rhythm and pace of moving things percentage, bradygastria rhythm and pace of moving things percentage, the tachygastria rhythm and pace of moving things percentage feature of electro-gastric signalses；Pattern recognition module, for the input using above-mentioned parameter as pattern-recognition, carry out obese degree detection.The present invention can accurately, objectively carry out obese degree detection, the accuracy and simplicity of fat detection can be effectively improved, and obtain considerable Social benefit and economic benefit.
Description
Technical field
The present invention relates to detection device field, more particularly to a kind of obese degree based on the extraction of stomach electrical feature to detect dress
Put.
Background technology
Due to the change of modern life custom, and living environment is increasingly severe, and the people of developing obesity is increasingly
It is more, all subtle life product for affecting people of secondary obesity either caused by simple obesity or disease
Matter, hidden some dangers for for the health of body each side.Obesity is gradual, belongs to the process of chronic disease, treatment or loss of weight
And it is slowly, but it is far-reaching to be influenceed to caused by body parts.Carry out obese degree and be detected as obesity diagnosis
Flow provides theoretical foundation, and the more clinical more scientific effective fat-reducing mode of formulation treats obesity and provides a kind of reliable amount
Change index.
The electrical activity of intestines and stomach mainly includes：Resting potential, slow potential and spike potential, can be by being placed on mucous membrane or serous coat
Electrode recorded, and the film potential of individual cells can also be measured using microelectrode.Throwing of the Smooth myoelectricity in abdomen body-surface
Shadow, i.e., usually said Electrogastrogram.
The collection of stomach electricity of body surface is faced with extremely severe detection environment.In addition to the ambient noises such as Hz noise, positioned at upper
It is dry to introduce electrocardio, belly myoelectricity, breathing artefact, motion artifactses etc. while electro-gastric signalses are extracted for the skin electrode of belly
Disturb, and the amplitude of these interference is often more much larger than electro-gastric signalses itself.
Most bioelectrical signals are all non-linear, non-stationary signals, the analysis to this kind of signal, are always at signal
The difficult point in reason field.And when some nonlinear and non local boundary value problem aliasings together when, further increase the difficulty of processing.
The content of the invention
The invention provides a kind of obese degree detection means based on the extraction of stomach electrical feature, the present invention can accurately, it is objective
The carry out obese degree detection of sight, can effectively improve the accuracy and simplicity of fat detection, and obtain considerable society's effect
Benefit and economic benefit, it is described below：
A kind of obese degree detection means based on the extraction of stomach electrical feature, the obese degree detection means include：
Collection and empirical mode decomposition module, forward and backward electro-gastric signalses, field experience mode decomposition weight are fed for gathering
Structure filters out the electrocardio and respiration interference being mixed with electro-gastric signalses；
First computing module, for carrying out frequency-domain analysis-Hilbert transform to filtering out the electro-gastric signalses after disturbing, obtain
To hilbert spectrum；
Second computing module, for calculate the dominant frequency of electro-gastric signalses, the dominant frequency coefficient of variation, main power, main power percentage,
Postprandial power ratio main before the meal, normal slow wave rhythm and pace of moving things percentage, bradygastria rhythm and pace of moving things percentage, tachygastria rhythm and pace of moving things percentage bit
Sign；
Pattern recognition module, for the input using above-mentioned parameter as pattern-recognition, carry out obese degree detection.
Wherein, the dominant frequency is tachygastria more than 3.7cpm, and the dominant frequency is bradygastria less than 2.4cpm.
Wherein, the normal slow wave rhythm and pace of moving things percentage is the percentage shared by slow wave of the frequency range in 2.4~3.7cpm
Than.
Further, the bradygastria rhythm and pace of moving things percentage is frequency range<Percentage shared by 2.4cpm slow wave.
Further, the tachygastria rhythm and pace of moving things percentage is frequency range>Percentage shared by 3.7cpm slow wave.
The beneficial effect of technical scheme provided by the invention is：
1st, using empirical mode decomposition, the motion artifactses being mixed with signal, baseline drift and electrocardio has been effective filtered out, has been exhaled
The interference such as suction, extracts more pure electro-gastric signalses；On the basis of empirical mode decomposition, invention introduces electro-gastric signalses
Hilbert spectrums and Hilbert marginal spectrums, instead of traditional power spectrumanalysis, higher time domain can be obtained and frequency domain is differentiated
Rate；
2nd, the dominant frequency of extraction frequency-region signal, the dominant frequency coefficient of variation, main power, main power percentage, postprandial power main before the meal
The input identified than, the characteristic parameter such as normal slow wave rhythm and pace of moving things percentage, bradygastria rhythm and pace of moving things percentage as follow-up mode, so as to
Accurately, obese degree detection is objectively carried out；
3rd, can accurately, objectively carry out obese degree detection, the accuracy and simplicity of fat detection can be effectively improved
Property, and obtain considerable Social benefit and economic benefit；
4th, it is verified by experiments, the accuracy rate of obese degree detection is higher；Core is provided for obesity diagnosis, treatment etc.
The theoretical foundation of the heart and technical support, it is convenient to be brought to practical application, and can be applied to a variety of operative scenarios.
Brief description of the drawings
Fig. 1 is a kind of structural representation of the obese degree detection means based on the extraction of stomach electrical feature；
Fig. 2 is the schematic diagram of the obese degree testing process based on the extraction of stomach electrical feature；
Fig. 3 is empirical mode decomposition flow chart.
In accompanying drawing, the list of parts representated by each label is as follows：
1：Collection and empirical mode decomposition module； 2：First computing module；
3：Second computing module； 4：Pattern recognition module.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, embodiment of the present invention is made below further
It is described in detail on ground.
In order to solve the problems, such as in background technology, the embodiment of the present invention uses empirical mode decomposition to extract more pure stomach
Electric signal.
To calculate the frequency domain character of electro-gastric signalses, it is necessary to first carry out time-frequency conversion to electro-gastric signalses.It is traditional based in Fu
The frequency spectrum or power spectrum of leaf transformation, due to being global change, therefore in frequency spectrum or power spectrum, it is only capable of finding out in signal which be present
A little frequency components, and amplitude or power of the signal at corresponding frequencies, handled suitable for strict periodic signal or stationary signal.
Short Time Fourier Transform is a kind of method by non-stationary signal tranquilization, can obtain one on time, frequency, power
Three-dimensional function result, but Short Time Fourier Transform can not take into account time domain and the resolution ratio of frequency domain simultaneously.
Wavelet transformation is a kind of transform method of local stationary, and multiresolution analysis can be realized by flexible and translation,
But because the resolution ratio of each yardstick is different, therefore the resolution ratio for combining rear totality is not ideal enough.This hair
Bright embodiment chooses Hilbert transform method and does electro-gastric signalses spectrum analysis.With based on the power spectrum of Short Time Fourier Transform with
And Wavelet Spectrum is compared, hilbert spectrum is based on instantaneous frequency, while has high time and spatial resolution, be able to certainly will carry
The degree of accuracy of high fat degree detecting.
Embodiment 1
A kind of obese degree detection means based on the extraction of stomach electrical feature, referring to Fig. 1 and Fig. 2, obese degree detection dress
Put including：
Collection and empirical mode decomposition module 1, forward and backward electro-gastric signalses (EGG), field experience mode are fed for gathering
Decompose (EMD) restructing algorithm and filter out the electrocardio and respiration interference being mixed with electro-gastric signalses；
First computing module 2, for carrying out frequency-domain analysis-Hilbert to filtering out the electro-gastric signalses after disturbing
(Hilber) convert, obtain hilbert spectrum；
Second computing module 3, for calculating the dominant frequency of electro-gastric signalses, the dominant frequency coefficient of variation, main power, main power percentage
Than, postprandial power ratio main before the meal, normal slow wave rhythm and pace of moving things percentage, bradygastria rhythm and pace of moving things percentage and the tachygastria rhythm and pace of moving things hundred
Divide the features such as ratio；
Pattern recognition module 4, for the input using above-mentioned parameter as pattern-recognition, carry out obese degree detection.
In summary, the embodiment of the present invention by above-mentioned module can accurately, objectively carry out obese degree detection, can have
Effect ground improves the accuracy and simplicity of fat detection, and obtains considerable Social benefit and economic benefit.
Embodiment 2
The device in embodiment 1 is further introduced with reference to Fig. 3, specific calculation formula, it is as detailed below
Description：
First, collection and empirical mode decomposition module 1
Electro-gastric signalses include substantial amounts of physiologic information, can be used for detecting obese degree after handling by analysis.Exist respectively
The electro-gastric signalses under the back floating position of 30 minutes durations are gathered with postprandial half an hour before the meal, require during collection to lie on the back and keep breathing
Steadily, not have and significantly act, the interference such as turned over or coughed, not allow to feed, drink water.
Empirical mode decomposition (Empirical Mode Decomposition, EMD) is by U.S. NASA doctor Huang E
In a kind of signal analysis method that 1998 propose.With establishing the Fourier decomposition on the basis of harmonic wave basic function and establishing small
Wavelet decomposition on the basis of ripple basic function is different, and EMD does not need basic function, only relies on the time scale features of data itself to enter
Row signal decomposition, when handling nonlinear and non local boundary value problem, there is obviously advantage.
The core concept that EMD is decomposed, it by signal decomposition is a series of intrinsic mode function sums to be.So-called " intrinsic mode
Function ", it is the function for meeting following two conditions：
(1) in whole data segment, its extreme point and zero passage are counted out equal or most differences one；
(2) at any time, the coenvelope line that is formed by local maximum point and and formed down by local minimum point
The average value of envelope is 0, i.e., upper and lower envelope is relative to time shaft Local Symmetric.
Intrinsic mode function is simple component signal, i.e., there is single frequency content at each moment.And can be frequency modulation
And amplitude modulation, the feature of the instantaneous amplitude and instantaneous frequency at each moment all with signal in itself it is relevant.
The EMD decomposition process that the present invention uses is as shown in Figure 2.A series of intrinsic mode functions finally given, have just
The property handed over and completeness.
2nd, the first computing module 2
Provided with a real non-stationary signal x (t), define its Hilbert and be transformed to：
In above formula, symbol H represents Hilbert conversion,Result after as converting.Signal converts by Hilbert
Afterwards, the amplitude of signal spectrum is constant, has only done phase shift.Original signal is formed into complex signal z (t) together with its Hilbert conversion：
Z (t) is referred to as the analytic signal related to x (t).In above formula, j represent imaginary unit, a (t) andBe on
Time t function, the instantaneous amplitude and instantaneous phase of signal are represented respectively.To instantaneous phase derivation, you can obtain the wink of signal
When frequencies omega (t)：
After carrying out EMD decomposition to electro-gastric signalses in previous step, some intrinsic mode functions are can obtain, select wherein n
Useful intrinsic mode function carries out Hilbert conversion, obtains its each self-corresponding analytic signal respectively.Finally by all parsings
Signal is added, you can is obtained Hilbert spectrums, is shown below：
Real represents to take real part, a in formulai(t) i-th of instantaneous amplitude, ω are representedi(t) i-th of instantaneous frequency is represented.By
Hilbert spectrums have good time, spatial resolution it can be seen that the situation that non-stationary signal changes with time and frequency.
H (ω, t) is integrated to time t, you can obtain Hilber marginal spectrums.
3rd, the second computing module 3
Stomach electrical feature parameter for pattern-recognition can be calculated according to Hilber marginal spectrums, main parameter includes：
1) dominant frequency (Dominant Frequency, DF)：Frequency in power spectrum at power maximum place, represent stomach electricity
The rhythm and pace of moving things of slow wave.
Normal dominant frequency is 2.4~3.7cpm.Dominant frequency is tachygastria (Tachygastria, TG) more than 3.7cpm, dominant frequency
It is bradygastria (Bradygastria, BG) less than 2.4cpm.
2) the dominant frequency coefficient of variation (Dominant Frequency Instability Coefficient, DFIC)：It is average
The standard deviation of dominant frequency and averagely the ratio between dominant frequency, to evaluate the stability of clectrogastrogram dominant frequency.
3) main power (Dominant Power, DP)：Power corresponding to DF.
4) main power variation coefficient (Dominant Power Instability Coefficient, DPIC)：It is average main
The standard deviation of power and average main power ratio, to evaluate the stability of the main power of clectrogastrogram.
5) main power percentage (Dominant Power Proportion, DPP)：Main power accounts for the percentage of general power.
6) postprandial main power ratio (Dominant Power Ratio, DPR) before the meal：Under normal circumstances, after the meal due to stomach
Contraction movement increase, main power always increase.
7) normal slow wave rhythm and pace of moving things percentage (N%)：Percentage shared by slow wave of the frequency range in 2.4~3.7cpm.
8) bradygastria rhythm and pace of moving things percentage (B%)：Frequency range<Percentage shared by 2.4cpm slow wave.
9) tachygastria rhythm and pace of moving things percentage (T%)：Frequency range>Percentage shared by 3.7cpm slow wave.
Above in addition to DPR, other parameters be both needed to detection before the meal with postprandial two groups of data.In the embodiment of the present invention, main power
Refer to the value of peak power and corresponding frequency in Hilbert marginal spectrums with dominant frequency.Hilbert marginal spectrums are integrated, you can
Obtain total power.
That is, the Hilbert marginal spectrums of 0~2.4cpm, 2.4~3.7cpm and 3.7~fs/2 sections are integrated respectively, then
Divided by general power respectively obtains B%, N% and T%.
4th, pattern recognition module 4
Because sample data set is less than normal, after feature extraction, using SVMs (Support Vector Machine,
SVM) feature is identified grader, carries out obese degree detection.
When doing pattern-recognition with SVMs, join the characteristic parameter of extraction as the input of Training Support Vector Machines
Number, the obese degree detection model based on stomach electricity is obtained by training, then carries out automatic detection.
In summary, the embodiment of the present invention by above-mentioned module can accurately, objectively carry out obese degree detection, can have
Effect ground improves the accuracy and simplicity of fat detection, and obtains considerable Social benefit and economic benefit.
To the model of each device in addition to specified otherwise is done, the model of other devices is not limited the embodiment of the present invention,
As long as the device of above-mentioned function can be completed.
It will be appreciated by those skilled in the art that accompanying drawing is the schematic diagram of a preferred embodiment, the embodiments of the present invention
Sequence number is for illustration only, does not represent the quality of embodiment.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc., it should be included in the scope of the protection.
Claims (5)
- A kind of 1. obese degree detection means based on the extraction of stomach electrical feature, it is characterised in that the obese degree detection means Including：Collection and empirical mode decomposition module, forward and backward electro-gastric signalses are fed for gathering, the reconstruct of field experience mode decomposition, Filter out the electrocardio and respiration interference being mixed with electro-gastric signalses；First computing module, for carrying out frequency-domain analysis-Hilbert transform to filtering out the electro-gastric signalses after disturbing, wished You compose Bert；Second computing module, for calculating the dominant frequency of electro-gastric signalses, the dominant frequency coefficient of variation, main power, main power percentage, postprandial Main power ratio, normal slow wave rhythm and pace of moving things percentage, bradygastria rhythm and pace of moving things percentage, tachygastria rhythm and pace of moving things percentage feature before the meal；Pattern recognition module, for the input using above-mentioned parameter as pattern-recognition, carry out obese degree detection.
- A kind of 2. obese degree detection means based on the extraction of stomach electrical feature according to claim 1, it is characterised in that institute It is tachygastria that dominant frequency, which is stated, more than 3.7cpm, and the dominant frequency is bradygastria less than 2.4cpm.
- A kind of 3. obese degree detection means based on the extraction of stomach electrical feature according to claim 1, it is characterised in that institute State percentage of the normal slow wave rhythm and pace of moving things percentage shared by slow wave of the frequency range in 2.4~3.7cpm.
- A kind of 4. obese degree detection means based on the extraction of stomach electrical feature according to claim 1, it is characterised in that institute It is frequency range to state bradygastria rhythm and pace of moving things percentage<Percentage shared by 2.4cpm slow wave.
- A kind of 5. obese degree detection means based on the extraction of stomach electrical feature according to claim 1, it is characterised in that institute It is frequency range to state tachygastria rhythm and pace of moving things percentage>Percentage shared by 3.7cpm slow wave.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710936363.XA CN107713988A (en) | 2017-10-10 | 2017-10-10 | A kind of obese degree detection means based on the extraction of stomach electrical feature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710936363.XA CN107713988A (en) | 2017-10-10 | 2017-10-10 | A kind of obese degree detection means based on the extraction of stomach electrical feature |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107713988A true CN107713988A (en) | 2018-02-23 |
Family
ID=61210080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710936363.XA Pending CN107713988A (en) | 2017-10-10 | 2017-10-10 | A kind of obese degree detection means based on the extraction of stomach electrical feature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107713988A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111110221A (en) * | 2019-12-26 | 2020-05-08 | 天津大学 | Time-frequency-nonlinear multidimensional body surface gastric electrical feature extraction method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070255154A1 (en) * | 2006-04-28 | 2007-11-01 | Medtronic, Inc. | Activity level feedback for managing obesity |
| CN101371783A (en) * | 2007-11-13 | 2009-02-25 | 清华大学深圳研究生院 | Apparatus for testing gastric electricity of body surface |
| GB2512304A (en) * | 2013-03-25 | 2014-10-01 | Toumaz Healthcare Ltd | Apparatus and method for estimating energy expenditure |
-
2017
- 2017-10-10 CN CN201710936363.XA patent/CN107713988A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070255154A1 (en) * | 2006-04-28 | 2007-11-01 | Medtronic, Inc. | Activity level feedback for managing obesity |
| CN101371783A (en) * | 2007-11-13 | 2009-02-25 | 清华大学深圳研究生院 | Apparatus for testing gastric electricity of body surface |
| GB2512304A (en) * | 2013-03-25 | 2014-10-01 | Toumaz Healthcare Ltd | Apparatus and method for estimating energy expenditure |
Non-Patent Citations (2)
| Title |
|---|
| 何峰: "胃电检测方法的研究及相关数据分析", 《中国博士学位论文全文数据库 医药卫生科技辑》 * |
| 常丽丽: "单纯性肥胖者胃肌电活动特征", 《基础医学与临床》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111110221A (en) * | 2019-12-26 | 2020-05-08 | 天津大学 | Time-frequency-nonlinear multidimensional body surface gastric electrical feature extraction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sameni et al. | Multichannel ECG and noise modeling: Application to maternal and fetal ECG signals | |
| Saluja et al. | A supervised machine learning algorithm for heart-rate detection using Doppler motion-sensing radar | |
| CN109745033A (en) | Dynamic electrocardiogram method for evaluating quality based on time-frequency two-dimensional image and machine learning | |
| Mesleh et al. | Heart rate extraction from vowel speech signals | |
| Tang et al. | Segmentation of heart sounds based on dynamic clustering | |
| Tang et al. | Separation of heart sound signal from noise in joint cycle frequency–time–frequency domains based on fuzzy detection | |
| Sobahi | Denoising of EMG signals based on wavelet transform | |
| CN105147248A (en) | Physiological information-based depressive disorder evaluation system and evaluation method thereof | |
| CN103845137A (en) | Stable vision-induced brain-computer interface-based robot control method | |
| CN102697493A (en) | Method for rapidly and automatically identifying and removing ocular artifacts in electroencephalogram signal | |
| Gupta et al. | R-peak detection for improved analysis in health informatics | |
| CN105678780A (en) | Video heart rate detection method removing interference of ambient light variation | |
| Jeyarani et al. | Analysis of noise reduction techniques on QRS ECG waveform-by applying different filters | |
| Liu et al. | Tissue artifact removal from respiratory signals based on empirical mode decomposition | |
| CN109589114A (en) | Myoelectricity noise-eliminating method based on CEEMD and interval threshold | |
| Choudhary et al. | A novel method for aortic valve opening phase detection using SCG signal | |
| CN107530015A (en) | A kind of vital sign analysis method and system | |
| CN104305992A (en) | Interactive method for rapidly and automatically extracting fetus electrocardio | |
| Thilagavathy et al. | Real-time ECG signal feature extraction and classification using support vector machine | |
| Li et al. | A hybrid wavelet-based method for the peak detection of photoplethysmography signals | |
| CN107713988A (en) | A kind of obese degree detection means based on the extraction of stomach electrical feature | |
| CN103536282A (en) | Magnetic induction cardiopulmonary activity signal separation method based on Fast-ICA method | |
| CN110353704A (en) | Mood assessments method and apparatus based on wearable ECG monitoring | |
| Yu et al. | The research of sEMG movement pattern classification based on multiple fused wavelet function | |
| Kew et al. | Wearable patch-type ECG using ubiquitous wireless sensor network for healthcare monitoring application |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180223 |