CN117129998A - Near-ultrasonic-based non-line-of-sight signal identification method - Google Patents
Near-ultrasonic-based non-line-of-sight signal identification method Download PDFInfo
- Publication number
- CN117129998A CN117129998A CN202311101412.XA CN202311101412A CN117129998A CN 117129998 A CN117129998 A CN 117129998A CN 202311101412 A CN202311101412 A CN 202311101412A CN 117129998 A CN117129998 A CN 117129998A
- Authority
- CN
- China
- Prior art keywords
- signal
- line
- sight
- expression
- intermediate frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000001228 spectrum Methods 0.000 claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000005070 sampling Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 5
- 230000008054 signal transmission Effects 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 4
- 230000009467 reduction Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/06—Systems determining the position data of a target
- G01S15/08—Systems for measuring distance only
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
- G01S7/52004—Means for monitoring or calibrating
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
- G01S7/539—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The application discloses a near-ultrasonic-based non-line-of-sight signal identification method, which comprises the following steps: collecting audio positioning data through an audio collecting device; preprocessing the audio positioning data to obtain an intermediate frequency signal spectrum; performing characteristic acquisition on the intermediate frequency signal spectrum to obtain a characteristic set; and inputting the feature set into a machine learning Xgboost model, and outputting a non-line-of-sight recognition result. According to the application, the fact that the sound non-line-of-sight signal often has special characteristics is considered, so that the channel characteristic is selected as the input characteristic, and the Xgboost is used for improving the fitting capacity of the nonlinear characteristic, so that the technical effects of time-space correlation information of the non-line-of-sight and reduction of recognition complexity are simultaneously considered. By the method, extremely high accuracy of cross-room sound non-line-of-sight identification can be obtained.
Description
Technical Field
The application relates to the fields of indoor positioning, signal processing and artificial intelligence, in particular to a near-ultrasonic-based non-line-of-sight signal identification method.
Background
Currently, GNSS positioning systems have been widely used. However, in indoor environments, GNSS cannot be used for positioning because the signals are subject to environmental shadowing. This increases the need for indoor positioning technology. In recent years, the near-ultrasonic positioning technology has become a popular indoor positioning technology due to the characteristics of wide coverage range, strong robustness, high positioning precision, high equipment compatibility and the like.
However, the transmission of acoustic signals in non line of sight (NLOS) environments can be greatly affected, resulting in signal weakening, distortion or complete loss. In order to solve this problem, near-ultrasonic non-line-of-sight signal recognition techniques have been developed in recent years. The technology can realize the identification of non-line-of-sight signals by acquiring signals through the smart phone, processing the signals and identifying the machine learning algorithm.
In the academy, there are often the following decision schemes:
most algorithms will use the previous time ranging value to compare with the current ranging value to form outlier detection. If an outlier is detected, the NLOS signal is discarded. Meanwhile, part of the algorithms use an optimized positioning algorithm to relieve the positioning effect of the non-line-of-sight signals. However, this method requires a certain degree of complexity of the algorithm, and requires a high-precision ranging result, which is not suitable for large-scale use.
Another approach is to use channel quality, channel spectrum models, etc. as samples for machine learning and deep learning to achieve high accuracy non-line-of-sight sample identification. The generalized cross-correlation spectrum is calculated through a large amount of data, so that one-dimensional data identification of the channel impulse response can be realized. Or extracting the characteristics of frequency spectrum, wavelet transformation and the like to realize two-dimensional information identification. With the massive popularization of the deep learning framework, the method also becomes one of the hot methods.
Although near-ultrasonic non-line-of-sight signal recognition technology has advanced to some extent, the prior art still has the problem of low signal recognition rate, especially in the case of cross-room type, the signal cannot be recognized normally. Therefore, the application provides a near-ultrasonic non-line-of-sight signal recognition method, which aims to improve the recognition rate of a non-line-of-sight near-ultrasonic positioning signal under the cross-room condition and further improve the performance and stability of the technology.
Disclosure of Invention
The application aims at overcoming the defects of the prior art and provides a near-ultrasonic-based non-line-of-sight signal identification method.
In order to achieve the above purpose, the application provides a near-ultrasonic-based non-line-of-sight signal identification method, which comprises the following steps:
s1, acquiring audio positioning data;
s2, preprocessing the audio positioning data to obtain an intermediate frequency signal spectrum;
s3, carrying out characteristic acquisition on the intermediate frequency signal spectrum to obtain a characteristic set;
s4, inputting the feature set into an Xgboost identifier, and outputting a non-line-of-sight identification result.
Further, the step S1 specifically includes: acquiring modulation signals through an audio acquisition device to obtain mixed audio data of direct line-of-sight signals, non-line-of-sight diffraction signals and reflected signals, wherein the mixed audio data is audio positioning data; the audio acquisition device comprises a microphone and a smart phone microphone.
Further, the step S2 includes the following sub-steps:
s21, carrying out cross-correlation on the audio positioning data and an original reference signal to obtain theoretical arrival time; calculating the expected arrival time in advance for the theoretical arrival time, and extracting the complete signal in a postponed manner; upsampling the complete signal by a spline interpolation method, and increasing the signal sampling rate to be twice of the original sampling rate to obtain an upsampled signal;
s22, calculating the product of the up-sampled signal and the original reference signal up-sampled by a spline interpolation method to obtain an intermediate frequency signal, wherein the intermediate frequency signal expression is as follows:
wherein s (t) is an original signal sent by the acoustic positioning base station, r is a receiving end receiving signal, and τ is calculated by the base station d For the arrival time of the acoustic signal propagation, B is the bandwidth, d is the acoustic signal transmission distance, c is the speed of sound, T is the signal duration, f min Is the lowest frequency value of the positioning acoustic signal;
s23, performing FFT operation on the intermediate frequency signal obtained in the step S22 to obtain an intermediate frequency spectrum;
the operation window used by the FFT is a Nuttall window, and the expression of the Nuttall window is as follows:
where N is the signal sampling point, and N is the total signal length.
Further, in the step S3, the feature set includes data of a rise time, a first arrival path arrival time, a peak number, an average additional delay, an average root mean square delay, a kurtosis coefficient, a signal energy, and a strongest path energy.
Further, the rise time t rise The expression of (2) is:
t rise =t H -t L
wherein,t H is the maximum value of the frequency spectrum h, t L In order to reach a time starting point, lambda is a signal effective segment extraction threshold value, i represents a current signal index, and h represents an obtained intermediate frequency spectrum;
the first arrival path arrival time t first The expression of (2) is:
wherein, extremum (·) is a first Extremum operator, peaks (·) is a peak finding operator;
the number of peaks num peaks The expression of (2) is:
num peaks =peaks[|h(i)|]
said average additional delay τ m The expression of (2) is:
where τ represents the time index of the signal;
the average root mean square delay tau rms The expression of (2) is:
the kurtosis coefficient kappa has the expression:
wherein,e is the expectation, μ is the first order variance, σ is the variance;
the signal energy epsilon r The expression of (2) is:
the expression of the strongest path energy SPE is as follows:
further, in the step S4, the Xgboost identifier has the expression:
Obj(θ)=L(θ)+Ω(θ)
wherein L (θ) is a loss function, regularized amountGamma and lambda are regularized parameters, theta is an error parameter, J represents the J-th node, b j Representing the predicted value of the j-th node.
Compared with the prior art, the application has the beneficial effects that: the application adopts a frequency modulation continuous wave method to extract the up-sampled signal into an intermediate frequency signal spectrum, and does not directly input the signal or the signal spectrum into a machine learning model. And then, inputting the features extracted from the intermediate frequency spectrum into an Xgboost model, and finally realizing non-line-of-sight identification of the acoustic signals through a tree model. The channel time delay is converted into the distance information distribution of the intermediate frequency, so that the problem of low cross-room recognition rate caused by the signal time delay difference due to different environments in the prior art is solved. According to the application, the fact that the sound non-line-of-sight signal often has special characteristics is considered, so that the channel characteristic is selected as the input characteristic, and the Xgboost is used for improving the fitting capacity of the nonlinear characteristic, so that the technical effects of time-space correlation information of the non-line-of-sight and reduction of recognition complexity are simultaneously considered. By the method, extremely high accuracy of cross-room sound non-line-of-sight identification can be obtained.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a flowchart illustrating a near-ultrasound based non-line-of-sight signal identification method, according to an exemplary embodiment;
FIG. 2 is a block diagram illustrating intermediate frequency signal feature extraction according to an exemplary embodiment;
FIG. 3 is an xgboost identification block diagram shown in accordance with an exemplary embodiment.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
As shown in fig. 1, the method for identifying non-line-of-sight signals based on near ultrasound provided by the application comprises the following steps:
s1, acquiring an original sound positioning signal sample set, namely audio positioning data.
S2, preprocessing the audio positioning data to obtain an intermediate frequency signal spectrum;
s3, carrying out characteristic acquisition on the intermediate frequency signal spectrum to obtain a characteristic set;
s4, inputting the feature set into a machine learning Xgboost model (namely an Xgboost recognizer) and outputting a non-line-of-sight recognition result.
As can be seen from the foregoing description, the present application extracts the up-sampled signal as an intermediate frequency signal spectrum by using a fm continuous wave method, rather than directly inputting the signal or signal spectrum into a machine learning model. And then, inputting the features extracted from the intermediate frequency spectrum into an Xgboost model, and finally realizing non-line-of-sight identification of the acoustic signals through a tree model. The channel time delay is converted into the distance information distribution of the intermediate frequency, so that the problem of low cross-room recognition rate caused by the signal time delay difference due to different environments in the prior art is solved. According to the application, the fact that the sound non-line-of-sight signal often has special characteristics is considered, so that the channel characteristic is selected as the input characteristic, and the Xgboost is used for improving the fitting capacity of the nonlinear characteristic, so that the technical effects of time-space correlation information of the non-line-of-sight and reduction of recognition complexity are simultaneously considered. By the method, extremely high accuracy of cross-room acoustic non-line-of-sight identification is obtained.
In a specific embodiment of S1: and acquiring audio positioning data through an audio acquisition device.
Specifically, the audio collection device may employ a microphone, a smart phone microphone, etc., and preferably a phone microphone is employed to reduce cost. The mixed audio data of the direct line-of-sight signal, the non-line-of-sight diffraction signal and the reflected signal can be obtained through the modulation signals collected by the microphone of the mobile phone, and the mixed audio data is audio positioning data. The modulation signal is a continuous acoustic signal with the period of 0.5 seconds, and a commonly used Chirp acoustic signal with the period of 17kHz-21kHz and 40ms is adopted, so that the refresh rate is ensured, and the universality and the frequency response range of the smart phone microphone are considered.
In the S2 embodiment, the preprocessing is performed on the audio positioning data to obtain an intermediate frequency signal spectrum, as shown in fig. 2, which may include the following sub-steps:
s21, performing cross-correlation on the audio positioning data and an original reference signal (namely an original signal sent by an acoustic positioning base station) to obtain theoretical arrival time.
Calculating an expected arrival time 0.015-0.02 seconds earlier than the theoretical arrival time, and 0.06 seconds later to extract the complete signal;
and up-sampling the complete signal by a spline interpolation method, and increasing the signal sampling rate to be twice as high as the original signal sampling rate (48 kHz), namely 96kHz, so as to obtain an up-sampled signal.
Specifically, the upsampling method is spline interpolation, so that important information of the signal is not lost.
S22, multiplying the up-sampled signal with an original reference signal up-sampled by a spline interpolation method to obtain an intermediate frequency signal. The intermediate frequency signal expression is:
wherein s is mix (t) is an intermediate frequency signal, s (t) is an original signal sent by the acoustic positioning base station, r is a receiving end receiving signal, and τ d For the arrival time of the acoustic signal propagation, B is the bandwidth, d is the acoustic signal transmission distance, c is the speed of sound, T is the signal duration, f min Is the lowest frequency value of the positioning acoustic signal.
S23, performing FFT operation (fast Fourier operation) on the intermediate frequency signal obtained in the step S22 to obtain an intermediate frequency spectrum.
Specifically, the operation window of the FFT should use a nutall window. Wherein the expression of the nutall window is:
wherein w (N) is a nutall window, N is a signal sampling point, and N is the total signal length.
In a specific embodiment of S3, the feature sets are respectively: rise time, first path arrival time, number of peaks, average additional delay, average root mean square delay, kurtosis coefficient, signal energy, and strongest path energy.
Specifically, the rise time t is constructed from the features rise The method comprises the following steps:
t rise =t H -t L
wherein,t H is the maximum value of the frequency spectrum h, t L To reach the time starting point, λ is a signal valid segment extraction threshold, typically set to 0.1-0.2, i represents the current signal index, and h represents the resulting intermediate frequency spectrum.
The first arrival path arrival time t first The method comprises the following steps:
wherein, extremum (·) is the first Extremum operator, peaks (·) is the peak operator.
The number of peaks num peaks The method comprises the following steps:
num peaks =peaks[|h(i)|]
said average additional delay τ m The method comprises the following steps:
where τ represents the time index of the signal and N is the total number of signal points.
The average root mean square delay tau rms The method comprises the following steps:
the kurtosis coefficient κ is:
wherein,e is the expectation, μ is the first order variance, σ is the variance.
The strongest path energy SPE is as follows:
the signal energy epsilon r The method comprises the following steps:
in the specific embodiment of S4: and extracting the frequency spectrum of the intermediate frequency signal by adopting a signal characteristic extraction method, and then inputting the characteristic set into a trained Xgboost identifier. The process is as follows: firstly, data preprocessing is carried out on an input feature set, an Xgboost identifier uses a decision tree as a basic weak classifier, then gradient and second derivative of a loss function are calculated, an objective function is optimized, and finally, the decision tree is updated, so that a non-line-of-sight identification result is output. As shown in fig. 3.
Specifically, the expression of the Xgboost identifier is:
Obj(θ)=L(θ)+Ω(θ)
where L (θ) is the loss function of the system, regularized amount of the loss functionGamma and lambda are regularized parameters, theta is an error parameter, J represents the J-th node, b j Representing the predicted value of the j-th node.
Specifically, the parameters of the xgboost identifier are as follows: total number of trees: 2800-3000, learning rate is 0.01-0.02, maximum depth is 15, and minimum sub-weight is 0.05-0.07. The purpose of adjusting the xgboost identifier parameters is to optimize the performance and generalization ability of the model.
The method is mainly oriented to intelligent mobile terminal users, aims at identifying the sound non-line-of-sight discrimination of the sound indoor positioning signals, and particularly has extremely high accuracy of identifying the sound non-line-of-sight signals crossing rooms. The method of the application considers the characteristic that the sound non-line-of-sight signal always continuously appears, so the channel characteristic is extracted through the intermediate frequency signal, and the Xgboost is utilized for fitting, thereby better adapting the sound non-line-of-sight signal. By adjusting a proper training framework, the training accuracy of the acquired data in a single room can be improved to 99.71%. If the data collected in the room 1 is used as a training set and the data collected in the room 2 is used as a test set, 86% accuracy can be achieved.
Claims (6)
1. The near-ultrasonic-based non-line-of-sight signal identification method is characterized by comprising the following steps of:
s1, acquiring audio positioning data;
s2, preprocessing the audio positioning data to obtain an intermediate frequency signal spectrum;
s3, carrying out characteristic acquisition on the intermediate frequency signal spectrum to obtain a characteristic set;
s4, inputting the feature set into an Xgboost identifier, and outputting a non-line-of-sight identification result.
2. The near-ultrasonic-based non-line-of-sight signal identification method according to claim 1, wherein the step S1 is specifically: acquiring modulation signals through an audio acquisition device to obtain mixed audio data of direct line-of-sight signals, non-line-of-sight diffraction signals and reflected signals, wherein the mixed audio data is audio positioning data; the audio acquisition device comprises a microphone and a smart phone microphone.
3. The near-ultrasonic based non-line-of-sight signal recognition method according to claim 1, wherein the step S2 comprises the sub-steps of:
s21, carrying out cross-correlation on the audio positioning data and an original reference signal to obtain theoretical arrival time; calculating the expected arrival time in advance for the theoretical arrival time, and extracting the complete signal in a postponed manner; upsampling the complete signal by a spline interpolation method, and increasing the signal sampling rate to be twice of the original sampling rate to obtain an upsampled signal;
s22, calculating the product of the up-sampled signal and the original reference signal up-sampled by a spline interpolation method to obtain an intermediate frequency signal, wherein the intermediate frequency signal expression is as follows:
wherein s (t) is an original signal sent by the acoustic positioning base station, r is a receiving end receiving signal, and τ is calculated by the base station d For the arrival time of the acoustic signal propagation, B is the bandwidth, d is the acoustic signal transmission distance, c is the speed of sound, T is the signal duration, f min Is the most frequent of the positioning acoustic signalA low value;
s23, performing FFT operation on the intermediate frequency signal obtained in the step S22 to obtain an intermediate frequency spectrum;
the operation window used by the FFT is a Nuttall window, and the expression of the Nuttall window is as follows:
where N is the signal sampling point, and N is the total signal length.
4. The near-ultrasonic based non-line-of-sight signal recognition method according to claim 1, wherein in the step S3, the feature set includes data of a rise time, a first arrival path arrival time, a peak number, an average additional delay, an average root mean square delay, a kurtosis coefficient, a signal energy, and a strongest path energy.
5. The near-ultrasonic based non-line-of-sight signal recognition method of claim 4, wherein the rise time t rise The expression of (2) is:
t rise =t H -t L
wherein, t H is the maximum value of the frequency spectrum h, t L In order to reach a time starting point, lambda is a signal effective segment extraction threshold value, i represents a current signal index, and h represents an obtained intermediate frequency spectrum;
the first arrival path arrival time t first The expression of (2) is:
wherein, extremum (·) is a first Extremum operator, peaks (·) is a peak finding operator;
the number of peaks num peaks The expression of (2) is:
num peaks =peaks[h(i)]
said average additional delay τ m The expression of (2) is:
where τ represents the time index of the signal;
the average root mean square delay tau rms The expression of (2) is:
the kurtosis coefficient kappa has the expression:
wherein,e is the expectation, μ is the first order variance, σ is the variance;
the signal energy epsilon r The expression of (2) is:
the expression of the strongest path energy SPE is as follows:
6. the near-ultrasonic-based non-line-of-sight signal recognition method according to claim 1, wherein in the step S4, the expression of the Xgboost recognizer is:
Obj(θ)=L(θ)+Ω(θ)
wherein L (θ) is a loss function, regularized amountGamma and lambda are regularized parameters, theta is an error parameter, J represents the J-th node, b j Representing the predicted value of the j-th node.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311101412.XA CN117129998A (en) | 2023-08-29 | 2023-08-29 | Near-ultrasonic-based non-line-of-sight signal identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311101412.XA CN117129998A (en) | 2023-08-29 | 2023-08-29 | Near-ultrasonic-based non-line-of-sight signal identification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117129998A true CN117129998A (en) | 2023-11-28 |
Family
ID=88859540
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311101412.XA Pending CN117129998A (en) | 2023-08-29 | 2023-08-29 | Near-ultrasonic-based non-line-of-sight signal identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117129998A (en) |
-
2023
- 2023-08-29 CN CN202311101412.XA patent/CN117129998A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107393542B (en) | Bird species identification method based on two-channel neural network | |
CN111783558A (en) | Satellite navigation interference signal type intelligent identification method and system | |
CN108847238B (en) | Service robot voice recognition method | |
CN103901401B (en) | A kind of binaural sound source of sound localization method based on ears matched filtering device | |
CN109890043B (en) | Wireless signal noise reduction method based on generative countermeasure network | |
CN102565759B (en) | Binaural sound source localization method based on sub-band signal to noise ratio estimation | |
CN106226739A (en) | Merge the double sound source localization method of Substrip analysis | |
CN106373589B (en) | A kind of ears mixing voice separation method based on iteration structure | |
CN110176250B (en) | Robust acoustic scene recognition method based on local learning | |
CN110610718B (en) | Method and device for extracting expected sound source voice signal | |
CN102426837B (en) | Robustness method used for voice recognition on mobile equipment during agricultural field data acquisition | |
CN113259288A (en) | Underwater acoustic communication modulation mode identification method based on feature fusion and lightweight hybrid neural network | |
CN109767760A (en) | Far field audio recognition method based on the study of the multiple target of amplitude and phase information | |
CN102760435A (en) | Frequency-domain blind deconvolution method for voice signal | |
CN113870893B (en) | Multichannel double-speaker separation method and system | |
CN116665654A (en) | Voice recognition method based on personalized federal learning | |
CN115267671A (en) | Distributed voice interaction terminal equipment and sound source positioning method and device thereof | |
CN113780521B (en) | Radiation source individual identification method based on deep learning | |
CN104665875A (en) | Ultrasonic Doppler envelope and heart rate detection method | |
CN110333484A (en) | The room area grade localization method with analysis is known based on environmental background phonoreception | |
CN116559778B (en) | Vehicle whistle positioning method and system based on deep learning | |
CN110580915B (en) | Sound source target identification system based on wearable equipment | |
CN117081806A (en) | Channel authentication method based on feature extraction | |
CN117129998A (en) | Near-ultrasonic-based non-line-of-sight signal identification method | |
CN117169812A (en) | Sound source positioning method based on deep learning and beam forming |
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 |