CN109325402A - A kind of signal processing method, system and computer storage medium - Google Patents
A kind of signal processing method, system and computer storage medium Download PDFInfo
- Publication number
- CN109325402A CN109325402A CN201810885632.9A CN201810885632A CN109325402A CN 109325402 A CN109325402 A CN 109325402A CN 201810885632 A CN201810885632 A CN 201810885632A CN 109325402 A CN109325402 A CN 109325402A
- Authority
- CN
- China
- Prior art keywords
- signal
- useful
- sampled
- slope
- processing method
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of signal processing method, system and computer storage mediums, comprising the following steps: S1, receives the original signal that signal extraction unit is sent, and the corresponding several useful sampled signals of useful signal for extracting any one period；S2, operation successively is merged to useful sampled signal and a historical data according to time sequencing, to export the corresponding available operation result of useful signal；S3, operation result is confirmed, to be confirmed whether to be trained useful signal and its corresponding operation result.Implement the on-line study ability of the invention that can increase to active user, allow signal processing that can more accurately adapt to the signal characteristic of active user and exports the result for being more able to satisfy user demand.
Description
Technical field
The present invention relates to signal processing technology fields, more specifically to a kind of signal processing method, system and calculating
Machine storage medium.
Background technique
In existing signal processing, especially in the man-machine interactive system using biology, to man-machine biology
The processing of signal generallys use the modules such as applicable single-chip microcontroller, by acquiring numerous user data with universals, carries out
Training study is used on product or in signal processing then using trained data as template.Product is in signal processing
In the process, which not will be updated, and the signal processing of product will not use time, Xiang Geng with user
It evolves in good, more accurate direction.
Summary of the invention
The technical problem to be solved in the present invention is that providing a kind of letter for the above-mentioned prior art defect of the prior art
Number processing method, system and computer storage medium.
The technical solution adopted by the present invention to solve the technical problems is: constructing a kind of signal processing method, including following
Step:
S1, the original signal that signal extraction unit is sent is received, and if to extract the useful signal in any one period corresponding
Do useful sampled signal；
S2, operation successively is merged to the useful sampled signal and a historical data according to time sequencing, with output
The corresponding available operation result of the useful signal；
S3, the operation result is confirmed, to be confirmed whether to the useful signal and its corresponding operation result
It is trained.
Preferably, described that operation is merged to the useful sampled signal and a historical data in the step S4
In the process, it also carries out:
Operation is carried out to the useful sampled signal by an initial training data.
Preferably, when confirmation is trained the useful signal and corresponding operation result, the method also includes:
S4, a preset standard is arranged to the useful signal and corresponding operation result, and according to the preset standard pair
The useful signal and corresponding operation result are trained, and output meets the training data of the preset standard；
S5, new initial training data are set by the training data, and returns to step S1.
Preferably, in the step S2, the historical data include any useful sampled signal before it is all
The corresponding operation result of useful sampled signal.
Preferably, in the step S1, the corresponding several useful samplings of useful signal for extracting any one period
Signal includes:
S1-1, the original signal is pre-processed to obtain the first signal for including the useful signal；
S1-2, first signal is sampled with a default sampling rate, to obtain several sampled signals；
S1-3, the constant signal for continuing a preset duration in first signal is obtained, on the basis of the constant signal
The slope of sampled signal described in signal monitoring, and the corresponding useful sampling of the useful signal is obtained by the slope variation and is believed
Number.
Preferably, described to have by the way that the slope variation acquisition useful signal is corresponding in the step S1-3
Include: with sampled signal
S1-301, the acquisition slope are started from scratch in change procedure, and the sampled signal when slope is zero is corresponding
Time point；
S1-302, it obtains in the time point, first time point when the changing wherein slope is started from scratch, and thereafter
The second time point when during the slope variation through zero crossing；
S1-303, the intermediate point for calculating the first time point and second time point, before obtaining the intermediate point
First specific duration t1Second specific duration t after the first interior sampled signal and the intermediate point2The second interior sampled signal；
First sampled signal and second sampled signal merge the useful sampled signal to form a cycle.
Preferably, in the step S1-3, before the corresponding useful sampled signal of the acquisition useful signal；
Also execute:
S1-311, obtain the slope and start from scratch in change procedure, the slope when being maximum value corresponding third adopt
Sample signal and the slope corresponding 4th sampled signal when being minimum value；
S1-312, confirmed according to the difference of the third sampled signal and the 4th sampled signal and the reference signal
It include the useful signal in first signal.
Preferably, in the step S1-1, it is described to the original signal carry out pretreatment include: to the original letter
It number is filtered and normalizes.
The present invention also constructs a kind of signal processing system, comprising: processor, memory,
The memory, for storing program instruction,
The processor, the program instruction for being stored according to the memory execute any of the above one described in letter
Number processing method.
The present invention also constructs a kind of computer readable storage medium, which is characterized in that is stored thereon with computer program, institute
State signal processing method described in realizing any of the above one when computer program is executed than processor.
Implement a kind of signal processing method, system and computer storage medium of the invention, has the advantages that increasing
Add the on-line study ability to active user, allows signal processing that can more accurately adapt to the signal characteristic of active user
And export the result for being more able to satisfy user demand.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is a kind of program flow diagram of signal processing method first embodiment of the present invention；
Fig. 2 is an original signal schematic diagram；
Fig. 3 is original signal and the first signal contrast schematic diagram；
Fig. 4 is a kind of program flow diagram of signal processing method second embodiment of the present invention.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, now control attached drawing is described in detail
A specific embodiment of the invention.
As shown in Figure 1, including the following steps, S1, connecing in a kind of first embodiment of signal processing method of the invention
The original signal that signal extraction unit is sent is received, and the corresponding several useful sampling letters of the useful signal for extracting any one period
Number；Specifically, as shown in Fig. 2, containing usually human body in getting original signal and being generated under improper action mode
, be not required to the signal parsed, both can be understood as the garbage signal without containing useful information, as shown in figure 3, can pass through
Pretreatment movement filters out the signal generated under the improper action mode, retains and produces under the movement therein with human normal
Raw biological signals can be interpreted as the useful signal with useful information, can extract having for any one period herein
With the corresponding several useful sampled signals of signal.It is further appreciated that original signal or biological signals here may include
The muscle current waveform at each position of human body, brain wave patterns, ecg wave form etc..Here signal extraction unit can be various letters
Number sensor.
S2, operation successively is merged to useful sampled signal and a historical data according to time sequencing, it is useful to export
The corresponding available operation result of signal；Specifically, presetting a historical data base, useful sampling is successively handled sequentially in time
Signal, such as when handling a useful sampled signal, by the data in the useful sampled signal and historical data base into
Row merges, and generates one group of input data, then calculates the input data, and output result is obtained after calculating.Operation
The result is that giving a mark to the matching degree of input signal and possible output signal, output function can be provided and each output
The score of Signal Matching, fraction range can be set to 0~1 arbitrary small number.We can be set, when matching score reaches
0.6 or more just thinks that the parameter of input is echo signal, if the several prods score of output is both greater than 0.6, selects score
That maximum result as present input data recognition result.Output the result is that: data currently entered, with standard
Concentration categorical data matching degree.When matching degree is 1, representative exact matching is identical, and the identifying system of this neural network is just
It is a scoring system.The similarity numerical value between input data and various normal datas can exactly be calculated.
Here it is further appreciated that during union operation, by the corresponding operation result of any useful sampled signal with going through
History data merge, and form new historical data.It, can be by the operation after obtaining available operation result in signal processing
As a result and its corresponding useful sampled signal merges with historical data, new historical data is formed, in this way, according to time sequencing
When carrying out the information processing of next useful sampled signal, calculating can be merged based on new historical data, to obtain more
Add accurately calculated result, it is to be understood that, merge and calculating process is circulation, until all in a signal period
Useful sampled signal processing is completed.
S3, operation result is confirmed, to be confirmed whether to be trained useful signal and its corresponding operation result.
Specifically, according to being described above, when confirming that the calculated result is usable results, just by the useful signal and corresponding usable results
Training aids is sent into be trained.Preferable human-computer interaction is obtained to attract user to participate in by the confirmation process of the training, is allowed
More enter training close to the data of the user, evolutionary training is carried out to the processing network in signal processing, to obtain
Closer to the signal characteristic of the user.
Further, in step s 4, useful sampled signal and a historical data are merged in calculating process, also into
Row: operation is carried out to useful sampled signal by an initial training data.Specifically, the process handled in subscriber signal
In, operation is carried out to useful sampled signal using existing initial training data, herein, when first time is to subscriber signal processing
When, default sample data can be trained, obtain corresponding initial training data it can be appreciated that initial training is tied
Fruit optimizes the middle processing network of signal processing by the training result.
Further, in embodiment as shown in Figure 4, when confirmation is trained useful signal and corresponding operation result
When, method further include:
S4, a preset standard is arranged to useful signal and corresponding operation result, and according to preset standard to useful signal
And corresponding operation result is trained, output meets the training data of preset standard；Specifically, in the training process, training
Device can carry out the data of input the arithmetic operation of neural network learning, which can run repeatedly, modify in this neural network
The parameter in face, until the result of training aids output meets the requirements to get to the training data met the requirements, here usually in training
It is first corresponding to current operation result according to historic training data before device is trained useful signal and corresponding operation result
Target training data carry out one anticipation, set a corresponding standard, it is to be understood that, because the signal input fortune
It calculates the result is that user carries out acknowledged, that represents the approval for the operation result that user inputs signal, then it is set
Standard is usually above existing training data, that is, initial training data, when training aids receives trained target, can pass through inside it
Repetition training is crossed, until the result of output meets training objective to get to the training data met the requirements, then will be in the training
The corresponding network parameter of data, which is sent in signal processing, handles network.
S5, new initial training data are set by training data, and returns to step S1.Specifically, when training number
According to meeting target call, so that it may update initial training data in signal processing, after which is updated, behind new letter
In number treatment process, so that it may by updated training data, carry out new signal processing.
Further, in step s 2, all useful sampling letters before historical data includes any useful sampled signal
Number corresponding operation result.Specifically, being based on historical data when the operation result to useful sampled signal calculates
Calculating is merged, then the operation of any one useful sampled signal is all based on the operation of its previous useful sampled signal
As a result, here it is also to be understood that the historical data used is to contain the front in any useful sampled signal calculating process
All useful sampled signals operation result.
Further, in step sl, the corresponding several useful sampled signal packets of useful signal in any one period are extracted
It includes:
S1-1, original signal is pre-processed to obtain the first signal for including useful signal；Specifically, such as Fig. 2 institute
Show, in getting original signal, contain it is that usually human body generates under improper action mode, be not required to the letter parsed
Number, it both can be understood as the garbage signal not comprising useful information, as shown in figure 3, can act by pretreatment this is non-just
The signal generated under normal action mode is filtered out, and the biological signals generated under the movement therein with human normal are retained
To be interpreted as the useful signal with useful information, the first signal for not including garbage signal is formed.
S1-2, the first signal is sampled with a default sampling rate, to obtain several sampled signals；Specifically, right
First signal is sampled, and several sampled signals for meeting and presetting rule are obtained, and default rule here can be adopted by default
Sample rate controls, and guarantees to be not in the loss of useful signal during using, while also avoiding accounting in sampling process as far as possible
With excessive resource, increase the processing load in signal processing.Such as in detailed process, type of action is different, eye electricity
The wave crest of signal or the ratio of trough are different, and sampling rate sets one and normally move generally according to normal movement speed here
The frequency range for making following signal is legal frequency range, is more than this range when the movement of user is too slow or too fast,
Invalid signals will be taken as to filter out.
S1-3, the constant signal for continuing a preset duration in the first signal is obtained, using constant signal as benchmark signal monitoring
The slope of sampled signal, and the corresponding useful sampled signal of useful signal is obtained by slope variation.Specifically, to the first signal
The mean values for carrying out a period of time calculate, and identify in no any useful signal in the first signal, also without any clutter
Under equal disturbed conditions, the amplification value of signal.It is to be understood that the amplification value should be a constant value, with the time
For X-axis, sampled point signal amplitude numerical value is that constant value is defined as constant signal here in the waveform diagram of Y-axis.Here constant
Signal can be understood as the amplitude continued for some time transformation within the allowable range or the signal that varies less of amplitude, rather than office
It is limited to absolute constancy.Here mainly in view of everyone resistivity is different, contact position may also be different, accordingly even when not having
There is any movement, the signal obtained from user is different, the persistence level that can take family here when not having any movement
For the constant signal, for example, it is general can take 5s, the signal level in 5s is averaged.The common week due to useful signal
Phase is relatively more fixed, in order to maximize the influence for reducing clutter, which can be set as to reference signal, then pass through meter
The slope of each sampled signal and reference signal is calculated, and calculates the variation of each slope, one is judged by the variation of slope
The complete useful signal period, it can correspond to the useful sampled signal in a complete cycle.
Further, in step S1-3, obtaining the corresponding useful sampled signal of useful signal by slope variation includes:
S1-301, acquisition slope are started from scratch in change procedure, sampled signal corresponding time point when slope is zero；Tool
Body, when being reference with reference signal, when calculating the slope of sampled signal, when no useful sampled signal, can calculate
The slope arrived is almost unchanged, and when starting as useful sampled signal, slope starts to change, when the period in useful sampled signal
It is interior, it may appear that the state that multiple slope is zero.During recording slope variation, time point when slope is zero.
In S1-302, acquisition time point, wherein slope is started from scratch first time point and its rear slope variation when changing
The second time point when in the process through zero crossing；Specifically, at time point when slope is zero, appear in slope when this time point
During just starting variation, this time point is the approximate starting point of useful sampled signal, and slope variation here can be with
It is increase of starting from scratch, being also possible to start from scratch is reduced to negative value, for example, when useful signal is wave crest, slope variation
It is to increase, when useful signal is trough, slope variation is to reduce.When the approximate starting point that have passed through useful sampled signal,
Due to the presence of wave crest or trough in its slope variation, time point i.e. the second time for being zero by slope can then occur
Point, it is understood that for the end point of a wave crest or trough.
S1-303, the intermediate point for calculating first time point and the second time point obtain the first specific duration before intermediate point
t1Second specific duration t after the first interior sampled signal and intermediate point2The second interior sampled signal；First sampled signal and
Two sampled signals merge the useful sampled signal to form a cycle.Specifically, obtaining time point, two time points are asked
Intermediate point, then can be understood as the intermediate point for obtaining the wave crest or trough or for approximate intermediate point, to the intermediate point
A specific duration t is extended forward1, and another specific duration t is extended backward2, obtain the sampling letter between two specific durations
Number, then all sampled signals between two specific durations can be defined as to useful sampled signal, two specific durations
The period of as one useful signal.
Here, the second specific duration t2Or it is equal to the first specific duration t1Three times.In order to be included in entire useful signal
It, can be according to general signal waveform rule, by the second specific duration t in a previously obtained useful signal period2It is set as
Duration t specific more than or equal to first1Three times.
It is further appreciated that the first specific duration t1For the difference of intermediate point and first time point.In ideal conditions, lead to
The difference of intermediate point and first time point can be often defined as to the half period of a wave crest or trough, then passing through intermediate point
A specific duration t is extended forward1When, it can be understood as the half period for only needing to extend the wave crest or trough, expand to wave crest or
The starting point of trough.So it extends three specific duration t backward1It may make up a complete useful signal period.
Further, in step S1-3, before obtaining the corresponding useful sampled signal of useful signal；Also execute:
S1-311, acquisition slope are started from scratch in change procedure, slope corresponding third sampled signal when being maximum value, and
Slope corresponding 4th sampled signal when being minimum value；S1-312, according to third sampled signal and the 4th sampled signal and benchmark
The difference of signal confirms to include useful signal in the first signal.Specifically, the period due to useful signal is relatively more fixed.In order to most
Bigization reduces the influence of clutter, can judge whether signal reaches wave crest or trough by the variation of slope.For example, when oblique
When rate maximum, then it can be determined that the wave crest for signal, when slope minimum, it is possible to determine that be the trough of signal, getting letter
Number wave crest or trough after, by the difference of the wave crest or trough amplification value and reference signal, whether this is a useful letter
Number wave crest or a useful signal trough.Furthermore here, when judging multiple wave crests or trough, can also pass through
The difference of wave crest or trough and reference signal is same category useful signal come the signal for judging this multiple wave crest or trough
Or different classes of useful signal.Useful signal A and useful signal B as shown in Figure 2 is respectively that two kinds of eye motions generate
Useful signal, it can be seen that, due to Producing reason difference, signal has differences for it, in signal processing, handle is needed to obtain
What is got may be the useful sampled signal in the data period of useful signal A and useful signal B, Network Recognition be carried out, with this
To obtain the similarity degree of the useful sampled signal and two kinds of standard signals.Then by Network Recognition respectively by standard of comparison
The sampled signal that the positive sample of two class signals can be identified as corresponding relationship carries out recognition training.It simultaneously can also will be complete
Be not two class signals i.e. cannot by be by be corresponding relationship using signal carry out constrained learning.
Further, in step S1-1, carrying out pretreatment to original signal includes: that original signal is filtered and is returned
One changes.It, can be with after filtering and normalizing specifically, the processing to the original signal of acquisition includes filtering and normalization
Filter out the signal therein obviously belonged under improper action mode.
In addition, a kind of signal processing system of the invention, comprising: processor, memory, memory refer to for storing program
The step of order, the program instruction that processor is used to be stored according to memory executes any of the above the method.Here at signal
Reason system includes but is not limited to computer etc..
In addition, a kind of computer readable storage medium of the invention, is stored thereon with computer program, the computer program quilt
The step of processor realizes any of the above the method when executing.Here computer readable storage medium can be can keep and
Store the tangible device of the instruction used by instruction execution equipment.Computer readable storage medium can for example be but not limited to electricity
Store equipment, magnetic storage apparatus, light storage device, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate
Combination.
It should be understood that above embodiments only express the preferred embodiment of the present invention, description is more specific and detailed
Carefully, but it cannot be understood as limitations on the scope of the patent of the present invention；It should be pointed out that for the common skill of this field
For art personnel, without departing from the inventive concept of the premise, above-mentioned technical characterstic can be freely combined, can also be done
Several modifications and improvements out, these are all within the scope of protection of the present invention；Therefore, all to be done with scope of the invention as claimed
Equivalents and modification, should belong to the covering scope of the claims in the present invention.
Claims (10)
1. a kind of signal processing method, which comprises the following steps:
S1, the original signal that signal extraction unit is sent is received, and the useful signal that extracts any one period is corresponding several has
Use sampled signal；
S2, operation successively is merged to the useful sampled signal and a historical data according to time sequencing, described in output
The corresponding available operation result of useful signal；
S3, the operation result is confirmed, to be confirmed whether to carry out the useful signal and its corresponding operation result
Training.
2. signal processing method according to claim 1, which is characterized in that described to have to described in the step S4
It is merged in calculating process with sampled signal and a historical data, is also carried out:
Operation is carried out to the useful sampled signal by an initial training data.
3. signal processing method according to claim 2, which is characterized in that when confirmation is to the useful signal and corresponding
When operation result is trained, the method also includes:
S4, a preset standard is arranged to the useful signal and corresponding operation result, and according to the preset standard to described
Useful signal and corresponding operation result are trained, and output meets the training data of the preset standard；
S5, new initial training data are set by the training data, and returns to step S1.
4. signal processing method according to claim 1 to 3, which is characterized in that in the step S2, institute
State the corresponding operation result of all useful sampled signals before historical data includes any useful sampled signal.
5. according to signal processing method described in claim 4 any one, which is characterized in that in the step S1, described
The corresponding several useful sampled signals of useful signal for extracting any one period include:
S1-1, the original signal is pre-processed to obtain the first signal for including the useful signal；
S1-2, first signal is sampled with a default sampling rate, to obtain several sampled signals；
S1-3, the constant signal for continuing a preset duration in first signal is obtained, using the constant signal as benchmark signal
The slope of the sampled signal is monitored, and the corresponding useful sampled signal of the useful signal is obtained by the slope variation.
6. signal processing method according to claim 5, which is characterized in that described to pass through institute in the step S1-3
Stating the corresponding useful sampled signal of the slope variation acquisition useful signal includes:
S1-301, the acquisition slope are started from scratch in change procedure, the sampled signal corresponding time when slope is zero
Point；
S1-302, it obtains in the time point, first time point when the changing wherein slope is started from scratch, and described thereafter
The second time point when during slope variation through zero crossing；
S1-303, the intermediate point for calculating the first time point and second time point, obtain first before the intermediate point
Specific duration t1Second specific duration t after the first interior sampled signal and the intermediate point2The second interior sampled signal；It is described
First sampled signal and second sampled signal merge the useful sampled signal to form a cycle.
7. signal processing method according to claim 5, which is characterized in that in the step S1-3, in the acquisition
Before the corresponding useful sampled signal of the useful signal；Also execute:
S1-311, the acquisition slope are started from scratch in change procedure, the slope corresponding third sampling letter when being maximum value
Corresponding 4th sampled signal when number being minimum value with the slope；
S1-312, according to the confirmation of the difference of the third sampled signal and the 4th sampled signal and the reference signal
It include the useful signal in first signal.
8. signal processing method according to claim 5, which is characterized in that described to described in the step S1-1
It includes: that the original signal is filtered and is normalized that original signal, which carries out pretreatment,.
9. a kind of signal processing system characterized by comprising processor, memory,
The memory, for storing program instruction,
The processor, the program instruction perform claim for being stored according to the memory require any one of 1-8 institute
The signal processing method stated.
10. a kind of computer readable storage medium, which is characterized in that be stored thereon with computer program, the computer program
The signal processing method as described in claim 1-8 any one is realized when executing than processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810885632.9A CN109325402B (en) | 2018-08-06 | 2018-08-06 | Signal processing method, system and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810885632.9A CN109325402B (en) | 2018-08-06 | 2018-08-06 | Signal processing method, system and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109325402A true CN109325402A (en) | 2019-02-12 |
| CN109325402B CN109325402B (en) | 2022-04-15 |
Family
ID=65263352
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810885632.9A Active CN109325402B (en) | 2018-08-06 | 2018-08-06 | Signal processing method, system and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109325402B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110488278A (en) * | 2019-08-20 | 2019-11-22 | 深圳锐越微技术有限公司 | Doppler radar signal kind identification method |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103531207A (en) * | 2013-10-15 | 2014-01-22 | 中国科学院自动化研究所 | Voice sensibility identifying method of fused long-span sensibility history |
| US20140257063A1 (en) * | 2010-03-15 | 2014-09-11 | Nanyang Technological University | Method of predicting acute cardiopulmonary events and survivability of a patient |
| CN105845127A (en) * | 2015-01-13 | 2016-08-10 | 阿里巴巴集团控股有限公司 | Voice recognition method and system |
| CN106197646A (en) * | 2016-06-24 | 2016-12-07 | 深圳艾瑞斯通技术有限公司 | The detection of a kind of fiber-optic vibration reduces the method for error and fine vibration detection device |
| CN107361765A (en) * | 2017-05-04 | 2017-11-21 | 晶神医创股份有限公司 | Brain wave analysis method and device |
| CN107468260A (en) * | 2017-10-12 | 2017-12-15 | 公安部南昌警犬基地 | A kind of brain electricity analytical device and analysis method for judging ANIMAL PSYCHE state |
| TWI609671B (en) * | 2016-09-20 | 2018-01-01 | Signal detection method | |
| CN107944473A (en) * | 2017-11-06 | 2018-04-20 | 南京邮电大学 | A kind of physiological signal emotion identification method based on the subjective and objective fusion of multi-categorizer |
| CN107943583A (en) * | 2017-11-14 | 2018-04-20 | 广东欧珀移动通信有限公司 | Processing method, device, storage medium and the electronic equipment of application program |
| CN108039203A (en) * | 2017-12-04 | 2018-05-15 | 北京医拍智能科技有限公司 | The detecting system of arrhythmia cordis based on deep neural network |
| CN108154398A (en) * | 2017-12-27 | 2018-06-12 | 广东欧珀移动通信有限公司 | Method for information display, device, terminal and storage medium |
| CN108186011A (en) * | 2017-12-13 | 2018-06-22 | 深圳竹信科技有限公司 | Atrial fibrillation detection method, device and readable storage medium storing program for executing |
| CN108269587A (en) * | 2017-12-29 | 2018-07-10 | 诺仪器（中国）有限公司 | Optical cable knocking display methods and system |
| CN108320063A (en) * | 2018-03-26 | 2018-07-24 | 上海积成能源科技有限公司 | To the method for rejecting abnormal data and denoising in a kind of load forecast |
-
2018
- 2018-08-06 CN CN201810885632.9A patent/CN109325402B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140257063A1 (en) * | 2010-03-15 | 2014-09-11 | Nanyang Technological University | Method of predicting acute cardiopulmonary events and survivability of a patient |
| CN103531207A (en) * | 2013-10-15 | 2014-01-22 | 中国科学院自动化研究所 | Voice sensibility identifying method of fused long-span sensibility history |
| CN105845127A (en) * | 2015-01-13 | 2016-08-10 | 阿里巴巴集团控股有限公司 | Voice recognition method and system |
| CN106197646A (en) * | 2016-06-24 | 2016-12-07 | 深圳艾瑞斯通技术有限公司 | The detection of a kind of fiber-optic vibration reduces the method for error and fine vibration detection device |
| TWI609671B (en) * | 2016-09-20 | 2018-01-01 | Signal detection method | |
| CN107361765A (en) * | 2017-05-04 | 2017-11-21 | 晶神医创股份有限公司 | Brain wave analysis method and device |
| CN107468260A (en) * | 2017-10-12 | 2017-12-15 | 公安部南昌警犬基地 | A kind of brain electricity analytical device and analysis method for judging ANIMAL PSYCHE state |
| CN107944473A (en) * | 2017-11-06 | 2018-04-20 | 南京邮电大学 | A kind of physiological signal emotion identification method based on the subjective and objective fusion of multi-categorizer |
| CN107943583A (en) * | 2017-11-14 | 2018-04-20 | 广东欧珀移动通信有限公司 | Processing method, device, storage medium and the electronic equipment of application program |
| CN108039203A (en) * | 2017-12-04 | 2018-05-15 | 北京医拍智能科技有限公司 | The detecting system of arrhythmia cordis based on deep neural network |
| CN108186011A (en) * | 2017-12-13 | 2018-06-22 | 深圳竹信科技有限公司 | Atrial fibrillation detection method, device and readable storage medium storing program for executing |
| CN108154398A (en) * | 2017-12-27 | 2018-06-12 | 广东欧珀移动通信有限公司 | Method for information display, device, terminal and storage medium |
| CN108269587A (en) * | 2017-12-29 | 2018-07-10 | 诺仪器（中国）有限公司 | Optical cable knocking display methods and system |
| CN108320063A (en) * | 2018-03-26 | 2018-07-24 | 上海积成能源科技有限公司 | To the method for rejecting abnormal data and denoising in a kind of load forecast |
Non-Patent Citations (4)
| Title |
|---|
| AMRUTA MHATRE 等: "Temporal Analysis and Remote Monitoring of ECG Signal", 《2015 INTERNATIONAL CONFERENCE ON NASCENT TECHNOLOGIES IN THE ENGINEERING FIELD (ICNTE-2015)》 * |
| SEAN SHENSHENG XU 等: "Towards End-to-End ECG Classification with Raw Signal Extraction and Deep Neural Networks", 《JOURNAL OF LATEX CLASS FILES》 * |
| 刘丽: "脑机交互中 ISVM 分类方法研究及反馈和应用***设计", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 黄佼 等: "基于一维卷积神经网络的患者特异性心拍分类方法研究", 《中国医疗设备》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110488278A (en) * | 2019-08-20 | 2019-11-22 | 深圳锐越微技术有限公司 | Doppler radar signal kind identification method |
| CN110488278B (en) * | 2019-08-20 | 2021-07-27 | 深圳锐越微技术有限公司 | Doppler radar signal type identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109325402B (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109948647B (en) | Electrocardiogram classification method and system based on depth residual error network | |
| CN105511608B (en) | Exchange method and device, intelligent robot based on intelligent robot | |
| Hickey et al. | Reward guides attention to object categories in real-world scenes. | |
| CN107260420B (en) | Intelligent wheel chair human-computer interactive control system and method based on eye motion recognition | |
| CN106940593B (en) | Emotiv brain control UAV system and method based on VC++ and Matlab hybrid programming | |
| CN103699226A (en) | Tri-modal serial brain-computer interface method based on multi-information fusion | |
| CN110221681A (en) | The method of adjustment and equipment of image-recognizing method, image rendering time | |
| CN106264505A (en) | A kind of heart rate spectral peak system of selection based on support vector machine | |
| CN110720900B (en) | Brain state monitoring and regulating device, method, processor and terminal equipment | |
| CN110141216A (en) | A kind of recognition methods, training method and the system of electrocardiosignal QRS characteristic wave | |
| CN104679967B (en) | A kind of method for judging psychological test reliability | |
| CN105590011A (en) | Pulse regression model-based electrocardiography data correction method and system | |
| CN109117729A (en) | Electrocardiogram room escape real-time judge method, apparatus, system and storage medium | |
| CN109325402A (en) | A kind of signal processing method, system and computer storage medium | |
| CN109063652A (en) | A kind of signal processing method, system and computer storage medium | |
| Dai et al. | A shared control framework for human-multirobot foraging with brain-computer interface | |
| CN117357134B (en) | Nerve electric pulse detection method, system and terminal | |
| CN106971132A (en) | One kind scanning gesture simultaneously knows method for distinguishing | |
| CN106778561B (en) | Identity recognition method and device of wearable equipment | |
| CN111967333B (en) | Signal generation method, system, storage medium and brain-computer interface spelling device | |
| CN111805545B (en) | Dexterous hand control method and device and terminal equipment | |
| CN112370039B (en) | Classroom quality detection method and device based on intelligent classroom | |
| WO2020029032A1 (en) | Signal processing method and system, and computer storage medium | |
| CN206594666U (en) | Recognize the system and intelligent dress ornament of destination object state | |
| CN106339656A (en) | Information processing method and fingerprint collector |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |