CN201212819Y - Adaptive signal processing recognition module for distributed optical fiber disturbing sensing system - Google Patents
Adaptive signal processing recognition module for distributed optical fiber disturbing sensing system Download PDFInfo
- Publication number
- CN201212819Y CN201212819Y CNU2008200343020U CN200820034302U CN201212819Y CN 201212819 Y CN201212819 Y CN 201212819Y CN U2008200343020 U CNU2008200343020 U CN U2008200343020U CN 200820034302 U CN200820034302 U CN 200820034302U CN 201212819 Y CN201212819 Y CN 201212819Y
- Authority
- CN
- China
- Prior art keywords
- module
- signal
- denoising
- master controller
- small echo
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Emergency Alarm Devices (AREA)
Abstract
The utility model relates to an adaptive signal processing and indentifying module of a distributed optical fiber perturbation sensing system. A data signal register (201) positioned at the front end, a data reader (202), a spectral subtraction de-noising module (203), a wavelet de-noising module (205), a de-noising indentifying module (207) are serially connected in sequence, wherein, the 'no' output end of the de-noising indentifying module (207) is connected with the first input end (101-1) of a master controller (101); the 'yes' output end of the de-noising indentifying module (207) is serially connected with a signal separating and normalizing module (208), a feature extracting module (209), a KNN indentifying module (210) and an identification result distinguishing module (212) in sequence; the 'yes' output end of the identification result distinguishing module (212) is connected with the sixth input end (101-6) of the master controller (101) through an identification result displaying memory (213); and the 'no' output end of the identification result distinguishing module (212) is connected with the No.2 input end (208-2) of the signal separating and normalizing module (208).
Description
Technical field
Broad domain all-optical fiber disturbance sensing network system is mainly used in the pipe monitoring of all kinds of conveying danger or high value chemicals pipe safety monitoring etc., and the broad domain all-optical fiber disturbance sensing of the circumference safety guards such as monitoring in important warehouse, storehouse, important boat station and the disturbance positioning signal treatment technology of positioning system, belong to Fibre Optical Sensor detection technique field.
Background technology
Along with science and technology and social development, the competition between each countries and regions becomes more and more fierce, and meanwhile, various dangerous terrorist activities are also more and more fiery.Therefore, need a kind of safety monitoring system that meets modern society's needs to guarantee being perfectly safe of these facilities or zone for some critical facilitys or zone.This system must be efficient, real-time, accurate, intelligent.At present; the technology that is used for the safety check of buildings circumference has infrared, microwave and traditional technology such as iron wire electrical network, but they all have fatal separately shortcoming; and be difficult to signal is carried out accurately complicated processing, therefore the efficient that circumference safeguard protection, prevention are trespassed is very low.Show according to investigations, demand to the circumference safe examination system of a high efficiency smart in the society is extremely strong and huge, and that the whole world has only is external for the few companies of number can produce the circumference safe examination system that meets social demand, and therefore, the present invention has extremely wide application market.Range of application of the present invention is such as having: airport, nuclear power station, oil pipeline, communications optical cable, means of transportation, historic reservation, armory, critical facilitys and zone such as emphasis office and essential industry plant area.
As the broad domain all-optical fiber disturbance sensing network system front end system, full fiber reflection interferes the distributed sensing Circuits System will wrap up in after the mixed signal of taking each noise like and disturbance information receives, store in the data-signal buffer, can the processing that carry out to the received signal this moment have promptly and accurately just become to estimate the key of this network system performance quality with identification.
Summary of the invention
Technical matters: the purpose of this utility model provides a kind of distribution type fiber-optic perturbation sensing system Adaptive Signal Processing identification module, and this device can identify timely and accurately has dangerous incident, thereby takes appropriate measures.
Technical scheme: interfere on the distributed sensing Circuits System basis at full fiber reflection, the utility model is according to the genesis mechanism and the characteristics of all kinds of input signals in the environment, proposed the signal recognition principle of the signal processing method comprehensive utilization of the denoising of employing small echo, ICA Signal Separation and feature extracting methods, artificial intelligence KNN (k-nearest neighbour method), identified timely and accurately and have dangerous incident.This principle implementation procedure comprises the content of two aspects, one, from the data-signal buffer, read out wrapping up in the mixed signal of taking each noise like and disturbance information, it is carried out Signal Pretreatment and separates, carry out the extraction of eigenwert then, enter the KNN identification module at last, identify the type and the character of input signal; They are two years old, when being handled and discern, signal to be identified deposits it in signal storage to be identified, after the recognition result analysis for the treatment of input signal finishes, whether this input signal is manually intercepted by the master controller decision, with the type and the character of further affirmation input signal.
Of the present utility modelly specifically constitute: the data-signal buffer, data reader, spectrum subtraction denoising module, small echo denoising module, the denoising discrimination module that are positioned at front end are connected in series in proper order, the first input end of the "No" output termination master controller of denoising discrimination module; The "Yes" output terminal of denoising discrimination module and Signal Separation and normalization module, characteristic extracting module, KNN identification module, recognition result discrimination module are connected in series in proper order; The "Yes" output terminal of recognition result discrimination module connects the 6th input end of master controller by the recognition result display-memory, the "No" output termination Signal Separation of recognition result discrimination module and No. 2 input ends of normalization module; The 3rd output terminal reception identification signal storer of master controller, the 4th output termination audio player of master controller, the 7th output termination wavelet basis typelib of master controller, the 5th output terminal device taking alarm of master controller; The output termination audio player of signal storage to be identified, No. 1 input termination data reader of signal storage to be identified.Master controller, small echo denoising module, wavelet basis typelib, denoising discrimination module, constituted a small echo denoising self-adaptation loop device, wherein the wavelet basis of storing in the wavelet basis typelib has each rank Daubechies wavelet basis, Haar small echo, Symlets small echo, Biorthogonal small echo, a Morlet small echo.Signal Separation and normalization module, characteristic extracting module, KNN identification module, category feature storehouse, recognition result discrimination module, constituted a signal identification self-adaptation loop device, wherein the feature extracting method in the characteristic extracting module is linear prediction cepstrum coefficient LPCC, and the secondary feature extracting method is independent component analysis ICA and principal component analysis PCA.Signal storage to be identified, audio player realize treating the broadcast of data in the identification signal storer by main controller controls, and concrete broadcast format and method are determined by master controller.
The data-signal buffer order that is positioned at front end is connected in series with data reader, spectrum subtraction denoising module, small echo denoising module, denoising discrimination module, Signal Separation and normalization module, characteristic extracting module, KNN identification module, recognition result discrimination module, recognition result display-memory, master controller; According to the result of recognition result discrimination module, decide to connect recognition result display-memory or Signal Separation and normalization module; According to the result of denoising discrimination module, decide and next connect Signal Separation and normalization module or master controller; Identification signal storer, audio player are received in data reader output in proper order; Master controller has an output reception identification signal storer, wavelet basis typelib, audio player, alarm is respectively arranged.
Master controller is in charge of the running of total system, comprise the realization of optical signal transmitting and reception control and positioning system, recognition result according to artificial intelligence KNN identification module carries out different control operations, for example the analysis result of working as the environment input signal is shown as safety signal, master controller does not just carry out the corresponding subsequent control operation so, and continues work as usual; Be shown as danger signal as analysis result to the environment input signal, master controller just starts alarm so, control signal storage to be identified simultaneously, recognition data is reached audio player, the environment input signal is carried out voice playing and storage, and the maintainer can be according to sound and concrete type and the character of more accurately judging danger signal of the experience of oneself.
Data reader reads data in the buffer memory, when it delivers to data spectrum subtraction denoising module, the input data can be deposited to signal storage to be identified, plays so that carry out voice data when finding danger signal later on.
Spectrum subtraction denoising module is earlier input signal to be carried out simple denoising earlier.
Small echo denoising module is input signal to be carried out the denoising of better effects if, and the signal after the denoising is sent into the denoising discrimination module.The denoising discrimination module is according to the result of small echo denoising module and carry out denoising result from the original signal of data reader and differentiate.If it is good to differentiate the result, just denoised signal is sent into Signal Separation and normalization module; If it is bad to differentiate the result, then notify master controller, and then master controller calls the wavelet basis typelib by the denoising discrimination module, therefrom choose other wavelet basis and carry out the small echo denoising again.
Signal Separation and normalization module still are that the data of mixed signal are carried out Signal Separation by ICA to through denoising, separate laggard line data normalization, are convenient to ensuing feature extraction.
Characteristic extracting module passes the signal of coming to Signal Separation and normalization module and carries out feature extraction, extracts and is characterized as LPCC, utilizes ICA or PCA to carry out the secondary feature extraction after the extraction again.
The KNN identification module calculates judgement with the eigenwert extracted and the eigenwert in the category feature storehouse by the KNN principle, and then provides recognition result.
The recognition result discrimination module can be differentiated KNN identification module recognition result, when the recognition result of KNN identification module is obvious, then enter the recognition result display-memory, otherwise, the recognition result discrimination module can so that identification once more from Signal Separation and normalized mode BOB(beginning of block), it is obvious to make every effort to recognition result by change secondary feature extracting method.
Audio player can realize playing data in the signal storage to be identified by main controller controls, and concrete broadcast format and method are determined by master controller.
Alarm is after the recognition result display-memory is shown as danger signal, started by master controller and realizes warning function.
Electrical schematic diagram of the present utility model constitutes as shown in Figure 2, and the master controller among the present invention, data reader, spectrum subtraction denoising module, signal storage to be identified, small echo denoising module, Signal Separation and normalization module, characteristic extracting module, KNN identification module, recognition result display-memory are included on the system host.The input of data-signal buffer one tunnel output welding system main frame, system host has two outputs to connect the input of audio player, a control signal that is output as master controller, a result who is output as data reader.In addition, system host also has the input of an output device taking alarm.
Beneficial effect: this distributed optical fiber disturbance sensor-based system Adaptive Signal Processing identification module relies on its strict discriminant function and a large amount of alternative disposal routes, can realize processing and recognition effect to various acquired signal the bests under different environment, promptly this method has very strong environmental suitability and very low misclassification rate.
The utility model proposes, utilize wavelet transformation and ICA to carry out denoising and mixed signal is separated to the mixed signal that receives, and then carry out feature extraction by the various features extracting method, the Classification and Identification function that achieves a butt joint and collect mail number by the artificial intelligence recognition system at last, can tell danger signal and non-danger signal, and can carry out as required, the storage and the real-time play of signal.For danger signal, take corresponding action to go to clear immediately; For non-danger signal, then do not need to take action.The present invention can be simultaneously in conjunction with realizing actual time safety early warning to whole important area with the isonomic positioning system of the present invention.
To critical facility and zone, construct in the broad domain all-optical fiber disturbance sensing network system that circumference thing or buried pipeline have the monitoring early warning and safety function supporting in time, signal Processing recognition device accurately.The mixed signal of taking each noise like and disturbance information is wrapped up in utilization of the present invention, adopts signal processing method and artificial intelligence KNN signal recognition principles such as wavelet transformation, ICA, monitors critical facility in real time and disturbs with all kinds of incidents that take place around the zone.
Description of drawings
Fig. 1 is a distribution type fiber-optic perturbation sensing system Adaptive Signal Processing identification module theory diagram,
Fig. 2 is a distribution type fiber-optic perturbation sensing system Adaptive Signal Processing identification module electrical schematic diagram,
Fig. 3 a, Fig. 3 b are the scaling function and the wavelet functions of db4 small echo,
Fig. 4 Haar small echo,
Fig. 5 a, Fig. 5 b are the scaling function and the wavelet functions of sym4 small echo,
Fig. 6 a, Fig. 6 b, Fig. 6 c, Fig. 6 d are the bior4.4 small echos,
Fig. 7 is the Morlet small echo,
Fig. 8 a, Fig. 8 b are that the tweedle signal and the denoising bird afterwards that contain noise are signal,
Fig. 9 a, Fig. 9 b contain the gunslinging signal of noise and the gunslinging signal after the denoising.
Have among the figure:
100: system host; 101: master controller;
201: the data-signal buffer; 202: data reader;
203: spectrum subtraction denoising module; 204: signal storage to be identified;
205: small echo denoising module; 206: the wavelet basis typelib;
207: the denoising discrimination module; 208: Signal Separation and normalization module;
209: characteristic extracting module; The 210:KNN identification module;
211: the category feature storehouse; 212: the recognition result discrimination module;
213: the recognition result display-memory; 214: audio player;
215: alarm;
Embodiment:
Distribution type fiber-optic perturbation sensing system Adaptive Signal Processing identification module of the present utility model can effectively be handled and discern all kinds of ambient signals of input, distinguish user-defined danger signal and non-danger signal, and can make appropriate responsive it.
As shown in Figure 1, what at first be arranged in this contrive equipment front end is the data-signal buffer 201 that full fiber reflection is interfered the distributed sensing Circuits System, the data reader 202 that coupled is in this contrive equipment, what link to each other with 202 is spectrum subtraction denoising module 203 and signal storage to be identified 204, what next link to each other with spectrum subtraction denoising module 203 is small echo denoising module 205, it with link to each other with denoising discrimination module 207 when master controller 101 links to each other, 207 is to link to each other with 101 according to differentiating result's decision again, still Signal Separation links to each other with normalization module 208,208 link to each other with characteristic extracting module 209,209 link to each other with KNN identification module 210, recognition result enters recognition result discrimination module 212, it is to link to each other with 208 that differentiation result according to 212 decides, still link to each other with recognition result display-memory 213,213 deliver to master controller 101 with the result, 101 can determine 213 whether to show recognition result simultaneously; Data reader 202 output reception identification signal storeies 204 are thought when master controller 101 can recognition data to be reached audio player 214 by control signal storage 204 to be identified when needing, and input signal is carried out voice playing.Master controller 101 has the direct control audio player 214 of an output simultaneously.In addition, master controller 101 also directly links to each other with alarm 215.
By master controller 101, small echo denoising module 205, denoising discrimination module 207, constituted a small echo denoising self-adaptation ring.After delivering to denoising discrimination module 207 by the denoising result of small echo denoising module 205, can compare with the objective function in 207, if the result is bad, will notify master controller 101, carry out alternately with wavelet basis typelib 206 by 101, again choose wavelet basis and carry out the denoising process once more, till denoising result the best.
By Signal Separation and normalization module 208, characteristic extracting module 209, KNN identification module 210, category feature storehouse 211, recognition result discrimination module 212, constituted a signal identification self-adaptation ring.After the recognition result of KNN identification module 210 is delivered to recognition result discrimination module 212, think that 210 recognition effect is inadequately obviously the time when 212, then can require identifying to restart, make 210 recognition result reach best by the feature extracting method that changes in the characteristic extracting module 209 from Signal Separation and normalization module 208.
When the user thought that the wrong or recognition result of institute's identification signal is shown as danger signal, audio player 214 can realize playing data in 204 by 101 controls, and concrete broadcast format determines by 101 with method.
Also the present invention is described further with this example embodiment of the present utility model to be described.This example is an experimental prototype.System host comprises digital signal software pretreatment module (in the signal denoising process involved all modules), characteristic extracting module, the artificial intelligence recognition system, this machine model is joined 4CPU8M buffer memory 32G internal memory, I/O:NI PCI-E6251 1.25M 16 channel 16bit for the perfectly sound R630G5 of association; Audio player: use be the diva series Hi-Fi sound-box and the earphone of Hui Wei company.Specifically constitute: one tunnel output of data-signal buffer connects the input of this main frame, read and store for the input data, carry out the spectrum subtraction denoising then, next carry out small echo denoising (seeing Fig. 8 and Fig. 9), can use acquiescence Daubechies wavelet basis (Fig. 3) to carry out small echo denoising (undesirable as denoising effect, as can to select Haar small echo (Fig. 4), Symlets small echo (Fig. 5), Biorthogonal small echo (Fig. 6), Morlet small echo (Fig. 7) etc. for use) earlier.Enter identification link carry out ICA Signal Separation and normalization later on earlier, carry out the LPCC feature extraction then, can use PCA to carry out the secondary feature extraction, the eigenwert of extracting is sent into the KNN identification module, then the recognition result display-memory just can return recognition result to master controller, is that danger signal then starts alarm by the gained recognition result, and the pedestrian worker that goes forward side by side intercepts, if safety signal then continues operate as normal, wait for the arrival of identification requirement next time.
It is available that the hardware of most of module all has general market product in the native system.
100: system host: adopt the perfectly sound R630G5 of association to join the 4CPU8M buffer memory, the 32G internal memory;
I/O：NI?PCI—E6251?1.25M?16?channel?16bit。
101: master controller: be included in the system host.
201: data-signal buffer: be included in the system host.
202: data reader: be included in the system host.
203: spectrum subtraction denoising module: adopt enhancement mode dynamic spectrum subtractive method, be included in the system host.
204: signal storage to be identified: be included in the system host.
205: small echo denoising module: can choose multiple wavelet basis and carry out denoising, be included in the system host.
206: the wavelet basis typelib: contain multiple wavelet basis, leave in the system host storer.
207: denoising discrimination module: be included in the system host.
208: Signal Separation and normalization module: adopt the FastICA disposal route, be included in the system host.
209: characteristic extracting module: extract and be characterized as LPCC, utilize ICA or PCA to carry out the secondary feature extraction after the extraction again, be included in the system host.
210:KNN identification module: adopt the KNN recognition methods, be included in the system host.
211: the category feature storehouse: adopt the data of KNN recognition methods training, leave in the system host storer.
212: recognition result discrimination module: be included in the system host.
213: recognition result display-memory: be included in the system host.
214: audio player: the diva series Hi-Fi sound-box and the earphone that adopt Hui Wei company.
215: alarm: adopt golden rich star alarm (model: JFX-2002-DL-4).
Therefore, the present invention uses the signal analysis recognition principle of means such as the signal processing method comprehensive utilization of small echo denoising, ICA Signal Separation and feature extracting methods, artificial intelligence KNN (k-nearest neighbour method), can effective monitoring major facility and zone, identify the dangerous situation that occurs around critical facility and the zone timely and accurately, be with a wide range of applications.
Claims (4)
1. distribution type fiber-optic perturbation sensing system Adaptive Signal Processing identification module, the data-signal buffer (201), data reader (202), spectrum subtraction denoising module (203), small echo denoising module (205), denoising discrimination module (207) order that it is characterized in that being positioned at front end are connected in series the first input end (101-1) of the "No" output termination master controller (101) of denoising discrimination module (207); The "Yes" output terminal of denoising discrimination module (207) and Signal Separation and normalization module (208), characteristic extracting module (209), KNN identification module (210), recognition result discrimination module (212) order are connected in series; The "Yes" output terminal of recognition result discrimination module (212) connects the 6th input end (101-6) of master controller (101) by recognition result display-memory (213), the "No" output termination Signal Separation of recognition result discrimination module (212) and No. 2 input ends (208-2) of normalization module (208); The 3rd output terminal (101-3) the reception identification signal storer (204) of master controller (101), the 4th output terminal (101-4) of master controller (101) connects audio player (214), the 7th output terminal (101-7) of master controller (101) connects wavelet basis typelib (206), the 5th output terminal (101-5) device taking alarm (215) of master controller (101); The output termination audio player (214) of signal storage to be identified (204), No. 1 input end (204-1) of signal storage to be identified (204) connects data reader (202).
2. distribution type fiber-optic perturbation sensing system Adaptive Signal Processing identification module according to claim 1, it is characterized in that master controller (101), small echo denoising module (205), wavelet basis typelib (206), denoising discrimination module (207), constituted a small echo denoising self-adaptation loop device, wherein the wavelet basis of storing in the wavelet basis typelib has each rank Daubechies wavelet basis, Haar small echo, Symlets small echo, Biorthogonal small echo, a Morlet small echo.
3. distribution type fiber-optic perturbation sensing system Adaptive Signal Processing identification module according to claim 1, it is characterized in that Signal Separation and normalization module (208), characteristic extracting module (209), KNN identification module (210), category feature storehouse (211), recognition result discrimination module (212), constituted a signal identification self-adaptation loop device, wherein the feature extracting method in the characteristic extracting module is linear prediction cepstrum coefficient LPCC, and the secondary feature extracting method is independent component analysis ICA and principal component analysis PCA.
4. distribution type fiber-optic perturbation sensing system Adaptive Signal Processing identification module according to claim 1, it is characterized in that signal storage to be identified (204), audio player (214) realize treating the broadcast of data in the identification signal storer by master controller (101) control, concrete broadcast format and method are determined by master controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNU2008200343020U CN201212819Y (en) | 2008-04-22 | 2008-04-22 | Adaptive signal processing recognition module for distributed optical fiber disturbing sensing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNU2008200343020U CN201212819Y (en) | 2008-04-22 | 2008-04-22 | Adaptive signal processing recognition module for distributed optical fiber disturbing sensing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN201212819Y true CN201212819Y (en) | 2009-03-25 |
Family
ID=40496995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNU2008200343020U Expired - Fee Related CN201212819Y (en) | 2008-04-22 | 2008-04-22 | Adaptive signal processing recognition module for distributed optical fiber disturbing sensing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN201212819Y (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105156901A (en) * | 2015-07-23 | 2015-12-16 | 中国石油天然气集团公司 | Optical fiber early warning system noise reduction method and device based on wavelet analysis |
| CN107505495A (en) * | 2017-08-01 | 2017-12-22 | 南方电网科学研究院有限责任公司 | A kind of detection method and device of voltage signal disturbance type |
| CN110487391A (en) * | 2019-09-04 | 2019-11-22 | 四川光盛物联科技有限公司 | Intelligent optical fiber distribution acoustic wave sensing system and method based on AI chip |
-
2008
- 2008-04-22 CN CNU2008200343020U patent/CN201212819Y/en not_active Expired - Fee Related
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105156901A (en) * | 2015-07-23 | 2015-12-16 | 中国石油天然气集团公司 | Optical fiber early warning system noise reduction method and device based on wavelet analysis |
| CN107505495A (en) * | 2017-08-01 | 2017-12-22 | 南方电网科学研究院有限责任公司 | A kind of detection method and device of voltage signal disturbance type |
| CN110487391A (en) * | 2019-09-04 | 2019-11-22 | 四川光盛物联科技有限公司 | Intelligent optical fiber distribution acoustic wave sensing system and method based on AI chip |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100582679C (en) | Broad domain all-optical fiber disturbance sensing network system self-adapting disturbance signal processing recognition device | |
| CN105139858B (en) | A kind of information processing method and electronic equipment | |
| CN110334241A (en) | Quality detecting method, device, equipment and the computer readable storage medium of customer service recording | |
| CN108897732B (en) | Statement type identification method and device, storage medium and electronic device | |
| CN105957514A (en) | Portable deaf-mute communication equipment | |
| CN108447471A (en) | Audio recognition method and speech recognition equipment | |
| CN104427079B (en) | User speech call method for early warning and device | |
| CN202533990U (en) | Hardware circuit of currency count machine with function of recognizing serial numbers, and currency count machine | |
| CN109800304A (en) | Processing method, device, equipment and the medium of case notes | |
| CN109993044A (en) | Telecommunication fraud identifying system, method, apparatus, electronic equipment and storage medium | |
| CN104538033A (en) | Parallelized voice recognizing system based on embedded GPU system and method | |
| CN201212819Y (en) | Adaptive signal processing recognition module for distributed optical fiber disturbing sensing system | |
| CN104598595A (en) | Fraud webpage detection method and corresponding device | |
| CN105267013B (en) | A kind of head-wearing type intelligent visually impaired accessory system | |
| CN110609908A (en) | Case serial-parallel method and device | |
| CN106383862B (en) | Illegal short message detection method and system | |
| CN102890931A (en) | Method for increasing voice recognition rate | |
| CN108109445A (en) | Teaching class feelings monitoring method | |
| CN107544961A (en) | A kind of sentiment analysis method, equipment and its storage device of social media comment | |
| JP2010273130A (en) | Device for determining progress of fraud, dictionary generator, method for determining progress of fraud, and method for generating dictionary | |
| CN101251950B (en) | Wide field full optical fibre destabilization sensing network system limit type disturbance signal processing recognition device | |
| CN201173390Y (en) | Limit type signal processing and recognition module for distributed optical fibre disturbance sensing system | |
| CN101950564A (en) | Remote digital voice acquisition, analysis and identification system | |
| CN115186095B (en) | Juvenile text recognition method and device | |
| CN201796356U (en) | Computer capable of recognizing voice commands |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090325 Termination date: 20120422 |