CN107300971A - The intelligent input method and system propagated based on osteoacusis vibration signal - Google Patents
The intelligent input method and system propagated based on osteoacusis vibration signal Download PDFInfo
- Publication number
- CN107300971A CN107300971A CN201710433231.5A CN201710433231A CN107300971A CN 107300971 A CN107300971 A CN 107300971A CN 201710433231 A CN201710433231 A CN 201710433231A CN 107300971 A CN107300971 A CN 107300971A
- Authority
- CN
- China
- Prior art keywords
- signal
- training sample
- central point
- vibration signal
- class
- 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
- G04—HOROLOGY
- G04G—ELECTRONIC TIME-PIECES
- G04G21/00—Input or output devices integrated in time-pieces
- G04G21/02—Detectors of external physical values, e.g. temperature
- G04G21/025—Detectors of external physical values, e.g. temperature for measuring physiological data
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24143—Distances to neighbourhood prototypes, e.g. restricted Coulomb energy networks [RCEN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/014—Hand-worn input/output arrangements, e.g. data gloves
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Physiology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention provides a kind of intelligent input method propagated based on osteoacusis vibration signal and system, the intelligent input method includes：S1. receiving step, smart machine vibrating sensor reception vibration signal, and noise reduction process is carried out to vibration signal；S2. extraction step, is detected using double threshold end-point detection method and extracted due to tapping the vibration signal fragment that human body appointed part is produced；S3. process step, extracts signal characteristic, based on RNM algorithms come category signal position.The beneficial effects of the invention are as follows：The problem of present invention not only solves intelligent watch text input mode, moreover it is possible to reach high discrimination, and can quickly be inputted, the cruising time of intelligent watch is not lost yet.
Description
Technical field
The present invention relates to intelligent wearable device technical field, more particularly to the intelligence propagated based on osteoacusis vibration signal
Input method and system.
Background technology
In recent years, we witnessed the fast development of intelligent wearable device, Intelligent bracelet, intelligent earphone, Brilliant Eyes
The wearable devices such as mirror, intelligent helmet and intelligent watch increased popularity in people's daily life, is received by people.In intelligence
The innovative space of mobile phone constantly reduces and the market growth is close in the case of saturation, and intelligent wearable device is used as mobile terminal
Next focus of industry is accepted extensively by market, is foretold that the invention of mobile phone will be replaced.
Intelligent watch is popular as a kind of portable set.But, the compact and light of it also faces what can not be evaded
Technical problem.Because screen is smaller, several keys are only able to display every time, and can block the display of other guide, and efficiency is very low.
Current intelligent watch realizes that the mode of text input mainly has three kinds：Conventional keyboard, text prediction and speech recognition.But with top
Either formula is not convenient, flexible enough, or it is not safe enough.In the case where there is ambient noise conditions, phonetic recognization rate is extremely difficult to ideal effect,
And the use of phonetic entry is in public that significant discomfort is closed in terms of for protection user cipher and other privacies.Although
Multinational Research Team develops finger tracking identification technology, but the experience that user uses for keyboard all the time can not be with giant-screen intelligence
The effectively quick comfortable text input contrast of energy mobile phone, such as the Research Team of 2016 Washington, DC universities realizes millimeter
The accurate finger tracking technology of level, allows user to realize the handwriting input based on acoustic location, but handwriting input on the mobile apparatus
All the time it is still too slow, it is impossible to meet the demand of people.Want expand intelligent watch the market demand, just must depth excavate its answer
With and solve the problems, such as text input.
The content of the invention
The invention provides a kind of intelligent input method propagated based on osteoacusis vibration signal, comprise the following steps：
S1. receiving step, smart machine vibrating sensor reception vibration signal, and carried out to vibration signal at noise reduction
Reason；
S2. extraction step, is detected using double threshold end-point detection method and extracts what is produced due to tapping human body appointed part
Vibration signal fragment；
S3. process step, extracts signal characteristic, based on RNM algorithms come category signal position.
As a further improvement on the present invention, include in the S2. extraction steps：
Step S21, high and low two thresholdings are set to the signal of processing；
Step S22, when the energy or zero-crossing rate of signal surmount low threshold, primarily determines that knocking starting point, and works as signal
Energy or zero-crossing rate break through high threshold, just determination the real starting point of knocking；When simultaneously signal energy and zero-crossing rate are less than
During low threshold, signaling destination point is determined；
Step S23, retains the data of starting point to the end, obtains the vibration signal fragment produced by percussion the back of the hand.
As a further improvement on the present invention, the S3. process steps include：
Step S31, segment signal is normalized, and extracts Mel-frequency Cepstral Coefficients, obtains signal characteristic；
Step S32, is divided using the RNM algorithms based on stochastic subspace and nearest central point algorithm signal characteristic
Class, and then judge beating position；
The step S32 includes：
Step S321, according to the difference of beating position, the signal characteristic that acquisition step S31 is obtained makees training sample, goes forward side by side
Row classification；
Step S322, each class central point of training sample is calculated using nearest central point algorithm；
Step S323, based on stochastic subspace, the class central point of test sample and training sample is repeatedly contrasted in subspace,
Obtain multiple classification results；
Classification results are used simple majority Voting principle by step S324, and set certain poll ratio, obtain most
Ticket obtains final classification result in the case of reaching certain poll simultaneously；
Step S325, the successful sample that will classify is included into new training sample, in the new class for recalculating new training sample
Heart point.
As a further improvement on the present invention, in the step S321, the back of the hand diverse location is tapped, step is collected
Rapid S31 signal characteristic as training sample, mark position and is divided into n classes according to the difference of position, is tapped m times per class, wherein n
It is more than or equal to 1 with m；
In the step S323, T attribute of random sampling, weight are distinguished into the class center produced each time in step S322
Operation Q times, obtains Q sub-spaces more than multiple, each class center of contrast test sample and training sample one by one in subspace
The Euclidean distance of point, finds nearest central point, that is, obtains the result of Q sub-spaces classification, and wherein T, Q is more than 1.
As a further improvement on the present invention, in the S2. extraction steps, human body appointed part is the back of the hand；
Vibrating sensor is piezoelectric ceramic vibration sensor；
In the S1. receiving steps, carrying out noise reduction process to vibration signal includes：
Step S11, DC component and low-frequency noise are filtered using 20Hz butterworth high pass filter；
Step S12, high-frequency noise is filtered using 800Hz LPFs.
Present invention also offers a kind of intelligent input system propagated based on osteoacusis vibration signal, including：
Receiving module, smart machine receives vibration signal with vibrating sensor, and carries out noise reduction process to vibration signal；
Extraction module, is detected using double threshold end-point detection method and extracted due to tapping the vibration that human body appointed part is produced
Signal segment；
Processing module, extracts signal characteristic, based on RNM algorithms come category signal position.
As a further improvement on the present invention, include in the extraction module：
First extraction module, high and low two thresholdings are set for the signal to processing；
Second extraction module, surmounts low threshold for the energy or zero-crossing rate when signal, primarily determines that knocking starting point,
And when the energy or zero-crossing rate of signal break through high threshold, just determine the real starting point of knocking；When signal energy and zero-crossing rate
When simultaneously less than low threshold, signaling destination point is determined；
3rd extraction module, the data for retaining starting point to the end obtain the vibration signal piece produced by percussion the back of the hand
Section.
As a further improvement on the present invention, the processing module includes：
First processing module, for segment signal to be normalized, extracts Mel-frequency Cepstral Coefficients, obtains signal
Feature；
Second processing module, is calculated for using signal characteristic based on stochastic subspace and the RNM of nearest central point algorithm
Method is classified, and then judges beating position；
The Second processing module includes：
First processing units, for the difference according to beating position, the signal characteristic that acquisition step S31 is obtained makees training sample
This, and classified；
Second processing unit, each class central point for calculating training sample using nearest central point algorithm；
3rd processing unit, for based on stochastic subspace, the class central point of test sample and training sample to be repeatedly in son
Spatial contrast, obtains multiple classification results；
Fourth processing unit, for using simple majority Voting principle to classification results, and sets certain poll ratio,
Final classification result is obtained in the case of gaining the majority while reaching certain poll；
5th processing unit, for that will classify, successful sample is included into new training sample, recalculates new training sample
New class central point.
As a further improvement on the present invention, in the first processing units, the back of the hand diverse location is tapped, gathered
Signal characteristic to step S31 as training sample, mark position and is divided into n classes according to the difference of position, is tapped m times per class,
Wherein n and m is more than or equal to 1；
In the 3rd processing unit, random sampling T is distinguished at the class center produced each time in second processing unit
Individual attribute, repeat more than operation Q times, obtain Q sub-spaces, contrast test sample and training sample one by one is each in subspace
The Euclidean distance of individual class central point, finds nearest central point, that is, obtains the result of Q sub-spaces classification, and wherein T, Q is more than 1.
As a further improvement on the present invention,
In the extraction module, human body appointed part is the back of the hand；
Vibrating sensor is piezoelectric ceramic vibration sensor；
In the receiving module, carrying out noise reduction process to vibration signal includes：
First receiving module, for filtering DC component and low-frequency noise using 20Hz butterworth high pass filter；
Second receiving module, for filtering high-frequency noise using 800Hz LPFs.
The beneficial effects of the invention are as follows：The problem of present invention not only solves intelligent watch text input mode, moreover it is possible to reach
High discrimination, and can quickly be inputted, the cruising time of intelligent watch is not lost yet.
Brief description of the drawings
Fig. 1 is that user taps virtual nine grids typewriting schematic diagram in the back of the hand；
Fig. 2 is the schematic diagram of piezoelectric ceramic vibration sensor；
Fig. 3 is the structure chart of piezoelectric ceramic vibration sensor；
Fig. 4 is original signal waveform figure；
Fig. 5 is adaptive-filtering figure；
Fig. 6 is LPF figure；
Fig. 7 is RNM algorithm flow charts.
Embodiment
As shown in figure 1, the invention discloses a kind of intelligent input method propagated based on osteoacusis vibration signal, including such as
Lower step：
S1. receiving step, smart machine vibrating sensor reception vibration signal, and carried out to vibration signal at noise reduction
Reason；
S2. extraction step, is detected using double threshold end-point detection method and extracts what is produced due to tapping human body appointed part
Vibration signal fragment；
S3. process step, extracts signal characteristic, based on RNM algorithms come category signal position.
In the S2. extraction steps, human body appointed part is the back of the hand；
Vibrating sensor is piezoelectric ceramic vibration sensor, and smart machine includes intelligent watch, piezoelectric ceramic vibration sensing
Device is built in intelligent watch, Fig. 2,3 be piezoelectric ceramic vibration sensor schematic diagram and structure chart.Because piezo-electric effect makes inside
Polarity produces change, externally shows the change of voltage, allows operator to tap the back of the hand, gathers the vibration signal produced by percussion.
Fig. 4 is original signal waveform figure, it can be seen that the primary signal gathered strong antijamming capability to external world, noise compared with
It is few.Fig. 5 uses the oscillogram after LPF using adaptive-filtering and Fig. 6.It is more special that LPF remains signal
Levy, the effect of the vibration signal of classification minute differences is more preferable to after.
In the S1. receiving steps, carrying out noise reduction process to vibration signal includes：
Step S11, DC component and low-frequency noise are filtered using 20Hz butterworth high pass filter；
Step S12, high-frequency noise is filtered using 800Hz LPFs.
Include in the S2. extraction steps：
Step S21, high and low two thresholdings are set to the signal of processing；
Step S22, when the energy or zero-crossing rate of signal surmount low threshold, primarily determines that knocking starting point, and works as signal
Energy or zero-crossing rate break through high threshold, just determination the real starting point of knocking；When simultaneously signal energy and zero-crossing rate are less than
During low threshold, signaling destination point is determined；
Step S23, only retains the data of starting point to the end, obtains the vibration signal fragment produced by percussion the back of the hand.
In S3. process steps, extracting signal characteristic includes：Starting point and terminal in initialization training sample is most long
As the length that segment signal is unified, the signal consistent to length after segment is normalized, and is using formula：Its
Middle x is vibration signal, and n is the dimension of signal.Feature extraction is carried out to the signal after normalization, amount of calculation is reduced, and retain original
Signal most information, feature extraction is the Mel-frequency Cepstral Coefficients of signal, while remain the spy of time domain and frequency domain
Levy.
The S3. process steps include：
Step S31, segment signal is normalized, and extracts Mel-frequency Cepstral Coefficients, obtains signal characteristic；
Step S32, is divided using the RNM algorithms based on stochastic subspace and nearest central point algorithm signal characteristic
Class, and then judge beating position；
As shown in fig. 7, in the step S32, being included based on RNM algorithms come category signal position：Including：
Step S321, according to the difference of beating position, the signal characteristic that acquisition step S31 is obtained makees training sample, goes forward side by side
Row classification (being divided into 9 classes according to nine grids position)；
Step S322, each class central point of training sample is calculated using nearest central point algorithm；
Step S323, based on stochastic subspace, the class central point of test sample and training sample is repeatedly contrasted in subspace,
Obtain multiple classification results；
Classification results are used simple majority Voting principle by step S324, and set certain poll ratio, obtain most
Ticket obtains final classification result in the case of reaching certain poll simultaneously；
Step S325, the successful sample that will classify is included into new training sample, in the new class for recalculating new training sample
Heart point.
In the step S321, the back of the hand diverse location is tapped, step S31 signal characteristic is collected as training
Sample, mark position is simultaneously divided into n classes according to the difference of position, is tapped m times per class, and wherein n and m is more than or equal to 1；
In the step S323, T attribute of random sampling, weight are distinguished into the class center produced each time in step S322
Operation Q times, obtains Q sub-spaces more than multiple, each class center of contrast test sample and training sample one by one in subspace
The Euclidean distance of point, finds nearest central point, that is, obtains the result of Q sub-spaces classification, and wherein T, Q is more than 1.
The invention also discloses a kind of intelligent input system propagated based on osteoacusis vibration signal, including：
Receiving module, smart machine receives vibration signal with vibrating sensor, and carries out noise reduction process to vibration signal；
Extraction module, is detected using double threshold end-point detection method and extracted due to tapping the vibration that human body appointed part is produced
Signal segment；
Processing module, extracts signal characteristic, based on RNM algorithms come category signal position.
Include in the extraction module：
First extraction module, high and low two thresholdings are set for the signal to processing；
Second extraction module, surmounts low threshold for the energy or zero-crossing rate when signal, primarily determines that knocking starting point,
And when the energy or zero-crossing rate of signal break through high threshold, just determine the real starting point of knocking；When signal energy and zero-crossing rate
When simultaneously less than low threshold, signaling destination point is determined；
3rd extraction module, the data for only retaining starting point to the end, remaining makees segment processing, obtains by percussion the back of the hand
The vibration signal fragment of generation.
The processing module includes：
First processing module, for segment signal to be normalized, extracts Mel-frequency Cepstral Coefficients, obtains signal
Feature；
Second processing module, is calculated for using signal characteristic based on stochastic subspace and the RNM of nearest central point algorithm
Method is classified, and then judges beating position；
The Second processing module includes：
First processing units, for the difference according to beating position, the signal characteristic that acquisition step S31 is obtained makees training sample
This, and classified；
Second processing unit, each class central point for calculating training sample using nearest central point algorithm；
3rd processing unit, for based on stochastic subspace, the class central point of test sample and training sample to be repeatedly in son
Spatial contrast, obtains multiple classification results；
Fourth processing unit, for using simple majority Voting principle to classification results, and sets certain poll ratio,
Final classification result is obtained in the case of gaining the majority while reaching certain poll；
5th processing unit, for that will classify, successful sample is included into new training sample, recalculates new training sample
New class central point.
In the first processing units, the back of the hand diverse location is tapped, step S31 signal characteristic conduct is collected
Training sample, mark position is simultaneously divided into n classes according to the difference of position, is tapped m times per class, and wherein n and m is more than or equal to 1；
In the 3rd processing unit, random sampling T is distinguished at the class center produced each time in second processing unit
Individual attribute, repeat more than operation Q times, obtain Q sub-spaces, contrast test sample and training sample one by one is each in subspace
The Euclidean distance of individual class central point, finds nearest central point, that is, obtains the result of Q sub-spaces classification, and wherein T, Q is more than 1.
In the extraction module, human body appointed part is the back of the hand；Vibrating sensor is piezoelectric ceramic vibration sensor.
In the receiving module, carrying out noise reduction process to vibration signal includes：
First receiving module, for filtering DC component and low-frequency noise using 20Hz butterworth high pass filter；
Second receiving module, for filtering high-frequency noise using 800Hz LPFs.
The present invention embedded small thin thin piezoelectric transducer on intelligent watch, this piezoelectric transducer can realize machinery
Electric transformation of energy can be arrived.A virtual nine grids keyboard on the back of the hand, when the grid of finger tapping diverse location, mechanical wave meeting
Blaze abroad from all directions, encounter object back reflection and return.So, the broadcast nature based on mechanical wave, piezoelectric transducer one
It is secondary to receive the mechanical wave signals with different multipath transmisstions.On the one hand this mechanical wave signals are disseminated to by voice signal
In air, on the other hand in the internal communication of hand, and so-called osteoacusis.This some mechanical ripple signal is not by the shadow of ambient noise
Ring, preferably can be received by piezoelectric transducer, change into electric signal and handled by the controller of intelligent watch.Because different grid productions
Raw mechanical wave multipath effect is different, and the signal that intelligent watch is received is just different, using this species diversity, with reference to engineering
The sorting algorithm of habit, can sort out each button of nine grids.Thus, it is possible to realize the intelligence based on the back of the hand bone conduction technology
Can wrist-watch text entry method and system.
The present invention first makees the vibration of the percussion the back of the hand collected in piezoelectric ceramic vibration sensor built in intelligent watch
For the text input mode of intelligent watch, using the back of the hand as the virtual big screen of intelligent watch the small screen, text is easy to implement defeated
Enter；What is gathered is to tap the vibration signal after the back of the hand on human hand after multipath transmisstion, strong interference immunity, and signal is carried out
Noise reduction, segment, normalization is extracted after the processing such as Mel-frequency Cepstral Coefficients, the RNM algorithms for reusing invention are classified,
Its discrimination reaches 92%.Algorithm complex as used herein is also linear rank, it is possible to realize the quick of text
Input.In addition, piezoelectric ceramic vibration sensor power consumption pole bottom, will not be greatly decreased the cruising time of intelligent watch.
The problem of present invention not only solves intelligent watch text input mode, moreover it is possible to reach high discrimination, and can be fast
Speed is inputted, and the cruising time of intelligent watch is not lost yet.
The hardware of the present invention is easy to use into low, simple system, osteoacusis of the realization based on the back of the hand that can be simple and quick
The input for the intelligent watch that vibration signal is propagated.
Above content is to combine specific preferred embodiment further description made for the present invention, it is impossible to assert
The specific implementation of the present invention is confined to these explanations.For general technical staff of the technical field of the invention,
On the premise of not departing from present inventive concept, some simple deduction or replace can also be made, should all be considered as belonging to the present invention's
Protection domain.
Claims (10)
1. a kind of intelligent input method propagated based on osteoacusis vibration signal, it is characterised in that comprise the following steps：
S1. receiving step, smart machine vibrating sensor reception vibration signal, and noise reduction process is carried out to vibration signal；
S2. extraction step, is detected using double threshold end-point detection method and extracted due to tapping the vibration that human body appointed part is produced
Signal segment；
S3. process step, extracts signal characteristic, based on RNM algorithms come category signal position.
2. intelligent input method according to claim 1, it is characterised in that include in the S2. extraction steps：
Step S21, high and low two thresholdings are set to the signal of processing；
Step S22, when the energy or zero-crossing rate of signal surmount low threshold, primarily determines that knocking starting point, and when the energy of signal
Amount or zero-crossing rate break through high threshold, just determine the real starting point of knocking；When signal energy and zero-crossing rate are simultaneously less than low door
In limited time, signaling destination point is determined；
Step S23, retains the data of starting point to the end, obtains the vibration signal fragment produced by percussion the back of the hand.
3. intelligent input method according to claim 1, it is characterised in that the S3. process steps include：
Step S31, segment signal is normalized, and extracts Mel-frequency Cepstral Coefficients, obtains signal characteristic；
Step S32, is classified using the RNM algorithms based on stochastic subspace and nearest central point algorithm to signal characteristic, entered
And judge beating position；
The step S32 includes：
Step S321, according to the difference of beating position, the signal characteristic that acquisition step S31 is obtained makees training sample, and is divided
Class；
Step S322, each class central point of training sample is calculated using nearest central point algorithm；
Step S323, based on stochastic subspace, the class central point of test sample and training sample is obtained repeatedly in subspace contrast
Multiple classification results；
Classification results are used simple majority Voting principle by step S324, and set certain poll ratio, are gained the majority same
When reach certain poll in the case of obtain final classification result；
Step S325, the successful sample that will classify is included into new training sample, recalculates the new class central point of new training sample.
4. intelligent input method according to claim 3, it is characterised in that：
In the step S321, the back of the hand diverse location is tapped, step S31 signal characteristic is collected as training sample
This, mark position is simultaneously divided into n classes according to the difference of position, is tapped m times per class, and wherein n and m is more than or equal to 1；
In the step S323, by the class center produced each time in step S322 distinguish T attribute of random sampling, repeatedly with
Upper operation Q times, obtains Q sub-spaces, each class central point of contrast test sample and training sample one by one in subspace
Euclidean distance, finds nearest central point, that is, obtains the result of Q sub-spaces classification, and wherein T, Q is more than 1.
5. intelligent input method according to claim 1, it is characterised in that：
In the S2. extraction steps, human body appointed part is the back of the hand；
Vibrating sensor is piezoelectric ceramic vibration sensor；
In the S1. receiving steps, carrying out noise reduction process to vibration signal includes：
Step S11, DC component and low-frequency noise are filtered using 20Hz butterworth high pass filter；
Step S12, high-frequency noise is filtered using 800Hz LPFs.
6. a kind of intelligent input system propagated based on osteoacusis vibration signal, it is characterised in that including：
Receiving module, smart machine receives vibration signal with vibrating sensor, and carries out noise reduction process to vibration signal；
Extraction module, is detected using double threshold end-point detection method and extracted due to tapping the vibration signal that human body appointed part is produced
Fragment；
Processing module, extracts signal characteristic, based on RNM algorithms come category signal position.
7. intelligent input system according to claim 6, it is characterised in that include in the extraction module：
First extraction module, high and low two thresholdings are set for the signal to processing；
Second extraction module, surmounts low threshold for the energy or zero-crossing rate when signal, primarily determines that knocking starting point, and works as
The energy or zero-crossing rate of signal break through high threshold, just determine the real starting point of knocking；When signal energy and zero-crossing rate simultaneously
During less than low threshold, signaling destination point is determined；
3rd extraction module, the data for retaining starting point to the end obtain the vibration signal fragment produced by percussion the back of the hand.
8. intelligent input system according to claim 6, it is characterised in that the processing module includes：
First processing module, for segment signal to be normalized, extracts Mel-frequency Cepstral Coefficients, obtains signal special
Levy；
Second processing module, for being entered to signal characteristic using the RNM algorithms based on stochastic subspace and nearest central point algorithm
Row classification, and then judge beating position；
The Second processing module includes：
First processing units, for the difference according to beating position, the signal characteristic that acquisition step S31 is obtained makees training sample,
And classified；
Second processing unit, each class central point for calculating training sample using nearest central point algorithm；
3rd processing unit, for based on stochastic subspace, the class central point of test sample and training sample to be repeatedly in subspace
Contrast, obtains multiple classification results；
Fourth processing unit, for using simple majority Voting principle to classification results, and sets certain poll ratio, obtains
Majority vote obtains final classification result in the case of reaching certain poll simultaneously；
5th processing unit, for that will classify, successful sample is included into new training sample, recalculates the new of new training sample
Class central point.
9. intelligent input system according to claim 8, it is characterised in that：
In the first processing units, the back of the hand diverse location is tapped, step S31 signal characteristic is collected as training
Sample, mark position is simultaneously divided into n classes according to the difference of position, is tapped m times per class, and wherein n and m is more than or equal to 1；
In the 3rd processing unit, T category of random sampling is distinguished at the class center produced each time in second processing unit
Property, repeat more than operation Q times, obtain Q sub-spaces, each class of contrast test sample and training sample one by one in subspace
The Euclidean distance of central point, finds nearest central point, that is, obtains the result of Q sub-spaces classification, and wherein T, Q is more than 1.
10. intelligent input system according to claim 6, it is characterised in that：
In the extraction module, human body appointed part is the back of the hand；
Vibrating sensor is piezoelectric ceramic vibration sensor；
In the receiving module, carrying out noise reduction process to vibration signal includes：
First receiving module, for filtering DC component and low-frequency noise using 20Hz butterworth high pass filter；
Second receiving module, for filtering high-frequency noise using 800Hz LPFs.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710433231.5A CN107300971B (en) | 2017-06-09 | 2017-06-09 | The intelligent input method and system propagated based on osteoacusis vibration signal |
| PCT/CN2017/092769 WO2018223489A1 (en) | 2017-06-09 | 2017-07-13 | Intelligent input method and system based on bone conduction vibration signal propagation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710433231.5A CN107300971B (en) | 2017-06-09 | 2017-06-09 | The intelligent input method and system propagated based on osteoacusis vibration signal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107300971A true CN107300971A (en) | 2017-10-27 |
| CN107300971B CN107300971B (en) | 2019-04-02 |
Family
ID=60134750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710433231.5A Active CN107300971B (en) | 2017-06-09 | 2017-06-09 | The intelligent input method and system propagated based on osteoacusis vibration signal |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107300971B (en) |
| WO (1) | WO2018223489A1 (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108681709A (en) * | 2018-05-16 | 2018-10-19 | 深圳大学 | Intelligent input method and system based on osteoacusis vibration and machine learning |
| CN109840480A (en) * | 2019-01-04 | 2019-06-04 | 深圳大学 | A kind of exchange method and interactive system of smartwatch |
| CN109933202A (en) * | 2019-03-20 | 2019-06-25 | 深圳大学 | A kind of intelligent input method and system based on osteoacusis |
| CN110058689A (en) * | 2019-04-08 | 2019-07-26 | 深圳大学 | A kind of smart machine input method based on face's vibration |
| CN110414196A (en) * | 2019-07-29 | 2019-11-05 | 深圳大学 | A kind of smartwatch auth method based on vibration signal |
| WO2019243633A1 (en) * | 2018-06-22 | 2019-12-26 | iNDTact GmbH | Sensor arrangement, use of the sensor arrangement, and method for detecting structure-borne noise |
| CN110931031A (en) * | 2019-10-09 | 2020-03-27 | 大象声科（深圳）科技有限公司 | Deep learning voice extraction and noise reduction method fusing bone vibration sensor and microphone signals |
| CN111741419A (en) * | 2020-08-21 | 2020-10-02 | 瑶芯微电子科技(上海)有限公司 | Bone conduction sound processing system, bone conduction microphone and signal processing method thereof |
| CN111752388A (en) * | 2020-06-19 | 2020-10-09 | 深圳振科智能科技有限公司 | Application control method, device, equipment and storage medium |
| CN113342159A (en) * | 2021-05-07 | 2021-09-03 | 哈尔滨工业大学 | Wrist wearable system identified through wrist vibration |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112272019A (en) * | 2020-10-22 | 2021-01-26 | 广东美的制冷设备有限公司 | Control method and device for sound-control knocking switch, household appliance and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130329918A1 (en) * | 2012-06-06 | 2013-12-12 | Google Inc. | External Vibration Reduction in Bone-Conduction Speaker |
| CN104461004A (en) * | 2014-12-12 | 2015-03-25 | 北京奇虎科技有限公司 | Wearable intelligent equipment |
| CN106339104A (en) * | 2016-08-24 | 2017-01-18 | 广州市香港科大霍英东研究院 | Text input method and device for smart watch |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9377850B2 (en) * | 2010-03-15 | 2016-06-28 | Nec Corporation | Input device, input method and medium |
| CN102436345A (en) * | 2011-10-31 | 2012-05-02 | 广州市动景计算机科技有限公司 | Method for interface operation and control of mobile device and implement device |
| US9199098B2 (en) * | 2012-09-05 | 2015-12-01 | Olympus Corporation | Ultrasonic treatment device |
| CN106128452A (en) * | 2016-07-05 | 2016-11-16 | 深圳大学 | Acoustical signal detection keyboard is utilized to tap the system and method for content |
-
2017
- 2017-06-09 CN CN201710433231.5A patent/CN107300971B/en active Active
- 2017-07-13 WO PCT/CN2017/092769 patent/WO2018223489A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130329918A1 (en) * | 2012-06-06 | 2013-12-12 | Google Inc. | External Vibration Reduction in Bone-Conduction Speaker |
| CN104461004A (en) * | 2014-12-12 | 2015-03-25 | 北京奇虎科技有限公司 | Wearable intelligent equipment |
| CN106339104A (en) * | 2016-08-24 | 2017-01-18 | 广州市香港科大霍英东研究院 | Text input method and device for smart watch |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108681709B (en) * | 2018-05-16 | 2020-01-17 | 深圳大学 | Intelligent input method and system based on bone conduction vibration and machine learning |
| CN108681709A (en) * | 2018-05-16 | 2018-10-19 | 深圳大学 | Intelligent input method and system based on osteoacusis vibration and machine learning |
| WO2019218725A1 (en) * | 2018-05-16 | 2019-11-21 | 深圳大学 | Intelligent input method and system based on bone-conduction vibration and machine learning |
| WO2019243633A1 (en) * | 2018-06-22 | 2019-12-26 | iNDTact GmbH | Sensor arrangement, use of the sensor arrangement, and method for detecting structure-borne noise |
| CN109840480A (en) * | 2019-01-04 | 2019-06-04 | 深圳大学 | A kind of exchange method and interactive system of smartwatch |
| CN109840480B (en) * | 2019-01-04 | 2021-08-13 | 深圳大学 | Interaction method and interaction system of smart watch |
| CN109933202A (en) * | 2019-03-20 | 2019-06-25 | 深圳大学 | A kind of intelligent input method and system based on osteoacusis |
| CN110058689A (en) * | 2019-04-08 | 2019-07-26 | 深圳大学 | A kind of smart machine input method based on face's vibration |
| CN110414196A (en) * | 2019-07-29 | 2019-11-05 | 深圳大学 | A kind of smartwatch auth method based on vibration signal |
| CN110414196B (en) * | 2019-07-29 | 2021-09-17 | 深圳大学 | Smart watch identity verification method based on vibration signal |
| CN110931031A (en) * | 2019-10-09 | 2020-03-27 | 大象声科（深圳）科技有限公司 | Deep learning voice extraction and noise reduction method fusing bone vibration sensor and microphone signals |
| CN111752388A (en) * | 2020-06-19 | 2020-10-09 | 深圳振科智能科技有限公司 | Application control method, device, equipment and storage medium |
| CN111741419A (en) * | 2020-08-21 | 2020-10-02 | 瑶芯微电子科技(上海)有限公司 | Bone conduction sound processing system, bone conduction microphone and signal processing method thereof |
| CN111741419B (en) * | 2020-08-21 | 2020-12-04 | 瑶芯微电子科技(上海)有限公司 | Bone conduction sound processing system, bone conduction microphone and signal processing method thereof |
| CN113342159A (en) * | 2021-05-07 | 2021-09-03 | 哈尔滨工业大学 | Wrist wearable system identified through wrist vibration |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018223489A1 (en) | 2018-12-13 |
| CN107300971B (en) | 2019-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107300971B (en) | The intelligent input method and system propagated based on osteoacusis vibration signal | |
| Du et al. | Wordrecorder: Accurate acoustic-based handwriting recognition using deep learning | |
| WO2019218725A1 (en) | Intelligent input method and system based on bone-conduction vibration and machine learning | |
| US10061389B2 (en) | Gesture recognition system and gesture recognition method | |
| CN106919958B (en) | Human body finger action recognition method based on smart watch | |
| Qifan et al. | Dolphin: Ultrasonic-based gesture recognition on smartphone platform | |
| CN105938399B (en) | The text input recognition methods of smart machine based on acoustics | |
| CN109508728B (en) | Novel identity authentication method for wearable equipment | |
| CN106128452A (en) | Acoustical signal detection keyboard is utilized to tap the system and method for content | |
| CN106237604A (en) | Wearable device and the method utilizing its monitoring kinestate | |
| US20210109598A1 (en) | Systems, methods and devices for gesture recognition | |
| CN110110616A (en) | A kind of electronic equipment and control method | |
| CN103442129A (en) | Interactive method and system between intelligent watch and mobile terminal | |
| CN106527716A (en) | Wearable equipment based on electromyographic signals and interactive method between wearable equipment and terminal | |
| CN109271901A (en) | A kind of sign Language Recognition Method based on Multi-source Information Fusion | |
| CN110123314A (en) | Judge that brain is absorbed in the method for relaxation state based on EEG signals | |
| CN107491254A (en) | A kind of gesture operation method, device and mobile terminal | |
| Zou et al. | AcouDigits: Enabling users to input digits in the air | |
| CN108108015A (en) | A kind of action gesture recognition methods based on mobile phone gyroscope and dynamic time warping | |
| CN103070682A (en) | Extraction method and extraction device for direction of eye movement based on electro-oculogram signals | |
| CN112069483A (en) | User identification and authentication method of intelligent wearable device | |
| Zheng et al. | L-sign: Large-vocabulary sign gestures recognition system | |
| Bi et al. | Smartge: identifying pen-holding gesture with smartwatch | |
| CN115793844A (en) | IMU facial gesture recognition-based true wireless earphone interaction method | |
| CN110413106B (en) | Augmented reality input method and system based on voice and gestures |
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 |