CN111626093A - Electric transmission line related bird species identification method based on sound power spectral density - Google Patents
Electric transmission line related bird species identification method based on sound power spectral density Download PDFInfo
- Publication number
- CN111626093A CN111626093A CN202010229304.0A CN202010229304A CN111626093A CN 111626093 A CN111626093 A CN 111626093A CN 202010229304 A CN202010229304 A CN 202010229304A CN 111626093 A CN111626093 A CN 111626093A
- Authority
- CN
- China
- Prior art keywords
- bird
- singing
- transmission line
- seed
- spectral density
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000003595 spectral effect Effects 0.000 title claims abstract description 35
- 230000005540 biological transmission Effects 0.000 title claims abstract description 31
- 240000003705 Senecio vulgaris Species 0.000 claims abstract description 53
- 241000894007 species Species 0.000 claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000001228 spectrum Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 9
- 238000012423 maintenance Methods 0.000 claims abstract description 8
- 238000010801 machine learning Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 6
- 238000013145 classification model Methods 0.000 claims abstract description 5
- 238000007689 inspection Methods 0.000 claims abstract description 4
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 238000009432 framing Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000002265 prevention Effects 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 241000271566 Aves Species 0.000 description 6
- 241000208152 Geranium Species 0.000 description 5
- 241001137251 Corvidae Species 0.000 description 4
- 241000272184 Falconiformes Species 0.000 description 4
- 235000005770 birds nest Nutrition 0.000 description 4
- 235000005765 wild carrot Nutrition 0.000 description 4
- 241000287462 Phalacrocorax carbo Species 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 241000272168 Laridae Species 0.000 description 2
- 210000003608 fece Anatomy 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 241000272170 Larus novaehollandiae Species 0.000 description 1
- 241001233305 Xanthisma Species 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 210000003323 beak Anatomy 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- ZFXYFBGIUFBOJW-UHFFFAOYSA-N theophylline Chemical compound O=C1N(C)C(=O)N(C)C2=C1NC=N2 ZFXYFBGIUFBOJW-UHFFFAOYSA-N 0.000 description 1
- 229960000278 theophylline Drugs 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a method for identifying bird species related to a power transmission line based on a sound power spectrum density. According to the method, a bird-species singing signal preprocessing algorithm module and a characteristic extraction algorithm module are constructed by establishing a transmission line bird-related fault bird-singing database, and the power spectral density value of a singing signal is extracted by using a discrete Fourier transform and power spectral estimation method and is used as a characteristic vector for distinguishing different bird species; constructing a machine learning algorithm module for classifying and identifying bird seed singing signals, and training a multi-classification model by using a power spectral density feature set of bird seed singing signals related to bird fault to obtain an intelligent bird seed identification model; and leading bird seed singing signals recorded in the inspection process of the operation and maintenance personnel of the power transmission line into the preprocessing module, the feature extraction module and the intelligent identification model, and outputting corresponding bird seed information. The method is beneficial to improving the accuracy of bird classification identification, and further improving the pertinence and the effectiveness of the prevention and treatment of the transmission line bird fault.
Description
Technical Field
The invention relates to the field of operation and maintenance of power transmission lines, in particular to a method for identifying bird species related to a power transmission line based on the sound power spectral density.
Background
Bird activity is one of the important causes of overhead transmission line faults, different birds can cause bird-related faults of different types of transmission lines, and the control measures of the bird-related faults are different. At present, various bird prevention devices are widely applied in actual operation, but still have great blindness, the rising trend of bird-related faults cannot be effectively inhibited, and line tripping faults caused by the failure of the bird prevention devices also occur occasionally. Because the bird related fault is transient, after the fault occurs, it is often difficult for operation and maintenance personnel to judge the bird species causing the fault, and intelligent bird species identification and fault cause judgment methods are lacked, so that it is difficult to take bird related fault prevention measures in a targeted manner. Therefore, it is necessary to develop an intelligent identification research on the bird species related to the overhead transmission line bird related failure, and provide a basis for line operation and maintenance personnel to correctly identify birds.
At present, related researchers have proposed various methods for identifying bird nests on towers of a power transmission line, and bird nests on towers can be identified through aerial images, however, bird related faults are not only bird nest faults, but also bird dung faults, bird body short-circuit faults and bird pecking faults, which are mainly caused by birds close to the power transmission line or staying on the towers, and therefore, different bird species must be accurately identified, and control measures can be taken pertinently. In the prior art, bird species classification is mainly realized through images and sounds, wherein the method for identifying based on the bird song signal mainly extracts the main frequency, the resonant frequency, the frequency amplitude, the formants and the like of the signal as characteristic vectors of the bird species. Such features may cross different species of birds in the same family and may not be effectively distinguished. The other method is to draw the spectrograms of different bird species and take the texture information with difference on the spectrograms as the characteristic vector. The method is more applied to extracting 24-dimensional Mel Frequency Cepstrum Coefficients (MFCC) of the bird song signals as characteristic vectors, and due to the fact that characteristic parameters are few, cross parts exist among different bird species, the distinguishing degree is not enough, and the recognition accuracy rate is low.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide a method for identifying bird species related to a power transmission line based on the power spectral density of a singing sound, and provides a basis for correctly identifying birds for line operation and maintenance personnel.
In order to achieve the purpose, the invention adopts the technical scheme that the method for identifying the bird species related to the power transmission line based on the sound power spectral density comprises the following steps:
s1: collecting the chirping signals of related bird species and establishing a chirping database of related bird species related to bird faults;
s2: constructing a bird seed singing signal preprocessing algorithm module, converting the singing signals of bird seeds related to bird faults into time-domain waveforms, and preprocessing the time-domain waveforms;
s3: constructing a bird seed singing signal feature extraction algorithm module, performing discrete Fourier transform on the preprocessed bird seed singing signals, calculating the power spectral density value of each singing signal by a power spectrum estimation method, performing logarithmic conversion, drawing a relation curve of the power spectral density value of each bird and corresponding frequency points of the power spectral density value, extracting the power spectral density values corresponding to N frequency points from the curve as feature vectors for distinguishing different bird species, and establishing a feature set of bird seed singing signals related to bird related faults;
s4: establishing a bird seed singing signal classification and identification algorithm module, establishing a multi-classification model by adopting a machine learning algorithm, and training the model by utilizing a power spectral density feature set of bird seed singing signals related to bird faults to obtain an intelligent bird seed identification model;
s5: and recording bird seed singing sounds in the inspection process by operation and maintenance personnel of the power transmission line through the recording device, guiding the bird seed singing sounds into the singing signal preprocessing algorithm module and the feature extraction algorithm module, acquiring a singing sound power spectrum density feature set of bird seeds related to the power transmission line, guiding the singing sound power spectrum density feature set into the bird seed intelligent identification model, and outputting corresponding bird seed information.
Further, the preprocessing algorithm module in S2 includes analog-to-digital conversion, pre-emphasis, framing windowing, and endpoint detection.
Further, the power spectrum estimation method in S3 may select an average periodogram method, a Bartlett method, or a weighted overlap-and-overlap averaging method (Welch method).
Further, the machine learning method in S4 may select a random forest or a multi-class support vector machine.
Compared with the prior art, the invention has the beneficial effects that:
the method for identifying the bird species related to the power transmission line based on the sound power spectrum density overcomes the defects of insufficient bird species sound characteristic information and insufficient discrimination in the prior art, can effectively represent the difference of different bird species sound signals through the power spectrum density characteristics corresponding to different frequency points, is favorable for improving the accuracy of bird classification identification, and can improve the pertinence and the effectiveness of bird-related fault prevention and treatment of the power transmission line.
Drawings
FIG. 1 is a flow chart of a method for identifying birds related to a power transmission line based on a whistling power spectral density according to the present invention;
FIG. 2 is a time domain waveform of a preprocessed bird seed chirp signal in accordance with an embodiment of the present invention; (a) - (h) singing signal time domain waveforms of geranium, aigren, doodle, teng, cormorant, respectively;
FIG. 3 is a power spectral density plot of different bird song signals in an embodiment of the present invention; (a) - (h) are the power spectral density curves of geranium oriental, aigren, doodle, tennons, magpie, gull, cang, cormorant, respectively.
Detailed Description
The present invention is further described in the following examples, which should not be construed as limiting the scope of the invention, but rather as providing the following examples which are set forth to illustrate and not limit the scope of the invention.
The following is described in detail through acoustic signal processing, feature extraction and classification and identification of typical bird species with a power transmission line bird fault, and a flowchart thereof is shown in fig. 1. The method comprises the following steps:
s1: collecting the chirping signals of related bird species and establishing a chirping database of related bird species related to bird faults.
In this embodiment, according to the operation experience of an overhead transmission line in China, major dangerous bird species causing bird faults are summarized, 8 representative bird species such as oriental geranium, aigret, crow, falcon, magpie, gull, eagle, corbel and the like are selected from the 4 kinds of bird faults causing bird faults such as bird nests, bird droppings, bird body shorts and bird pecks as identification objects, and sound files of the bird species are downloaded from websites such as a wild bird sound network in the world to establish a sound database.
S2: and constructing a bird seed singing signal preprocessing algorithm module, converting the singing signals of bird seeds related to bird faults into time-domain waveforms, and preprocessing the time-domain waveforms.
Using MATLAB software to write an algorithm program for analog-to-digital conversion, pre-emphasis, framing windowing and endpoint detection of bird song signals, first converting bird song sound files into time-domain waveforms through analog-to-digital conversion, taking 1 song sample as an example, respectively, and the time-domain waveforms of 8 bird song signals in this embodiment are shown in fig. 2. A first-order high-pass filter is adopted to pre-emphasize the bird song signal, the high-frequency part of the bird song signal is emphasized, the radiation of the bird beak is removed, the high-frequency resolution of the bird song is increased, and meanwhile, the low-frequency part is attenuated, so that the dynamic range of the frequency spectrum is reduced; then, a Hamming window is adopted to perform frame windowing on the ringing signal x (n), and the process is as follows:
where y (n) is the windowed chirp signal, w (n) is a window function, and the Hamming window can be expressed as
Wherein N is the window length.
After framing and windowing, performing end point detection on the bird seed singing signals by adopting a double-threshold method based on short-time energy and a short-time average zero-crossing rate, and calculating the short-time energy E (i) and the short-time average zero-crossing rate Z (i) of the ith frame of bird singing signals according to the following formula.
And setting a secondary criterion according to the short-term energy and the short-term average zero-crossing rate, and detecting by using a double-threshold method to obtain a sound section in the bird seed singing signal.
S3: the method comprises the steps of constructing a bird seed singing signal feature extraction algorithm module, carrying out discrete Fourier transform on preprocessed bird seed singing signals, calculating the power spectral density value of each singing signal through a power spectrum estimation method, carrying out logarithmic conversion, drawing a relation curve between the power spectral density value of each bird and corresponding frequency points of each bird, extracting the power spectral density values corresponding to N frequency points from the curve to serve as feature vectors for distinguishing different bird species, and establishing a feature set of bird seed singing signals related to bird related faults.
And dividing the bird seed singing signal subjected to frame windowing and end point detection into L sections according to 256 sampling points in each section. FFT of 256 samples per section of the bird song signal, i.e.
Where w (n) is a window function whose power spectral density is obtained by taking the square of the modulus value:
in the formula (I), the compound is shown in the specification,is the power spectrum of the window function.
The power spectral densities of the L-segment signals are then averaged, i.e.
Carrying out logarithmic conversion on the extracted power spectral density value, wherein the conversion relation is that P' is 10 × log10And P, drawing a power spectral density curve, and extracting power spectral density characteristics corresponding to 129 frequency points of the bird song signal from the curve to form a characteristic set for representing the bird song signal, as shown in FIG. 3.
S4: the method comprises the steps of constructing a bird seed singing signal classification and identification algorithm module, establishing a multi-classification model by adopting a machine learning algorithm, and training the model by utilizing a power spectral density feature set of bird seed singing signals related to bird faults to obtain an intelligent bird seed identification model.
The multi-classification model can be constructed by adopting a random forest and a support vector machine, in the embodiment, an 8-classification machine learning model is established by adopting the random forest, and is an integrated learning algorithm combined by a plurality of decision tree classifiers. And training the random forest model by using 8 bird seed singing signal power spectrum density feature sets in the training sample set to obtain an intelligent bird seed identification model.
S5: and recording bird seed singing sounds in the inspection process by operation and maintenance personnel of the power transmission line through the recording device, guiding the bird seed singing sounds into the singing signal preprocessing algorithm module and the feature extraction algorithm module, acquiring a singing sound power spectrum density feature set of bird seeds related to the power transmission line, guiding the singing sound power spectrum density feature set into the bird seed intelligent identification model, and outputting corresponding bird seed information.
And taking the bird seed singing signals to be predicted as test samples, preprocessing the singing signals, extracting the characteristics to obtain a power spectral density characteristic set, inputting the power spectral density characteristic set into the intelligent bird seed identification model based on the random forest, outputting bird seed identification results, and counting the classification and identification accuracy.
In this embodiment, the sample numbers and the classification recognition results of 8 typical bird species causing the failure of the bird in the transmission line, such as the oriental white geranium, the aigren, the dovu, the red falcon, the magpie, the silver gull, the xanthium, the cormorant and the like, are shown in table 1, and it is apparent that the total recognition accuracy reaches 94.87%, and the recognition accuracy of the oriental white geranium, the aigren, the dovu, the magpie, the eagle and the cornt reaches 100%.
TABLE 1
It should be understood that parts of the specification not set forth in detail are well within the prior art.
Although specific embodiments of the present invention have been described above with reference to the accompanying drawings, it will be appreciated by those skilled in the art that these are merely illustrative and that various changes or modifications may be made to these embodiments without departing from the principles and spirit of the invention. The scope of the invention is only limited by the appended claims.
Claims (4)
1. A method for identifying bird species related to a power transmission line based on a sound power spectrum density is characterized by comprising the following steps: the method comprises the following steps:
s1: collecting the chirping signals of related bird species and establishing a chirping database of related bird species related to bird faults;
s2: constructing a bird seed singing signal preprocessing algorithm module, converting the singing signals of bird seeds related to bird faults into time-domain waveforms, and preprocessing the time-domain waveforms;
s3: constructing a bird seed singing signal feature extraction algorithm module, performing discrete Fourier transform on the preprocessed bird seed singing signals, calculating the power spectral density value of each singing signal by a power spectrum estimation method, performing logarithmic conversion, drawing a relation curve of the power spectral density value of each bird and corresponding frequency points of the power spectral density value, extracting the power spectral density values corresponding to N frequency points from the curve as feature vectors for distinguishing different bird species, and establishing a feature set of bird seed singing signals related to bird related faults;
s4: establishing a bird seed singing signal classification and identification algorithm module, establishing a multi-classification model by adopting a machine learning algorithm, and training the model by utilizing a power spectral density feature set of bird seed singing signals related to bird faults to obtain an intelligent bird seed identification model;
s5: and recording bird seed singing sounds in the inspection process by operation and maintenance personnel of the power transmission line through the recording device, guiding the bird seed singing sounds into the singing signal preprocessing algorithm module and the feature extraction algorithm module, acquiring a singing sound power spectrum density feature set of bird seeds related to the power transmission line, guiding the singing sound power spectrum density feature set into the bird seed intelligent identification model, and outputting corresponding bird seed information.
2. The method for identifying the bird species related to the transmission line based on the chirped power spectral density according to claim 1, wherein the method comprises the following steps: the preprocessing algorithm module in S2 includes analog-to-digital conversion, pre-emphasis, framing windowing, and endpoint detection.
3. The method for identifying the bird species related to the transmission line based on the chirped power spectral density according to claim 1, wherein the method comprises the following steps: the power spectrum estimation method in S3 may select an average periodogram method, a Bartlett method, or a weighted overlap-and-overlap averaging method.
4. The method for identifying the bird species related to the transmission line based on the chirped power spectral density according to claim 1, wherein the method comprises the following steps: the machine learning method in S4 may select a random forest or a multi-class support vector machine.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010229304.0A CN111626093B (en) | 2020-03-27 | 2020-03-27 | Method for identifying related bird species of power transmission line based on sound power spectral density |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010229304.0A CN111626093B (en) | 2020-03-27 | 2020-03-27 | Method for identifying related bird species of power transmission line based on sound power spectral density |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111626093A true CN111626093A (en) | 2020-09-04 |
CN111626093B CN111626093B (en) | 2023-12-26 |
Family
ID=72271747
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010229304.0A Active CN111626093B (en) | 2020-03-27 | 2020-03-27 | Method for identifying related bird species of power transmission line based on sound power spectral density |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111626093B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113111618A (en) * | 2021-03-09 | 2021-07-13 | 电子科技大学 | Analog circuit fault diagnosis method based on improved empirical wavelet transform |
CN113255661A (en) * | 2021-04-15 | 2021-08-13 | 南昌大学 | Bird species image identification method related to bird-involved fault of power transmission line |
CN113707159A (en) * | 2021-08-02 | 2021-11-26 | 南昌大学 | Electric network bird-involved fault bird species identification method based on Mel language graph and deep learning |
Citations (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010044719A1 (en) * | 1999-07-02 | 2001-11-22 | Mitsubishi Electric Research Laboratories, Inc. | Method and system for recognizing, indexing, and searching acoustic signals |
JP2002189495A (en) * | 2000-12-19 | 2002-07-05 | Atr Onsei Gengo Tsushin Kenkyusho:Kk | Feature extractor for speech recognition, and speech recognition device |
JP2002278547A (en) * | 2001-03-22 | 2002-09-27 | Matsushita Electric Ind Co Ltd | Music piece retrieval method, music piece retrieval data registration method, music piece retrieval device and music piece retrieval data registration device |
US20020172372A1 (en) * | 2001-03-22 | 2002-11-21 | Junichi Tagawa | Sound features extracting apparatus, sound data registering apparatus, sound data retrieving apparatus, and methods and programs for implementing the same |
JP2006227564A (en) * | 2005-01-20 | 2006-08-31 | Advanced Telecommunication Research Institute International | Sound evaluating device and program |
CN102708860A (en) * | 2012-06-27 | 2012-10-03 | 昆明信诺莱伯科技有限公司 | Method for establishing judgment standard for identifying bird type based on sound signal |
CN102930870A (en) * | 2012-09-27 | 2013-02-13 | 福州大学 | Bird voice recognition method using anti-noise power normalization cepstrum coefficients (APNCC) |
US20130097112A1 (en) * | 2011-10-13 | 2013-04-18 | Edward B. Loewenstein | Determination of Statistical Upper Bound for Estimate of Noise Power Spectral Density |
CN103117061A (en) * | 2013-02-05 | 2013-05-22 | 广东欧珀移动通信有限公司 | Method and device for identifying animals based on voice |
CN103474072A (en) * | 2013-10-11 | 2013-12-25 | 福州大学 | Rapid anti-noise twitter identification method by utilizing textural features and random forest (RF) |
CN104658538A (en) * | 2013-11-18 | 2015-05-27 | 中国计量学院 | Mobile bird recognition method based on birdsong |
US20150186742A1 (en) * | 2013-12-27 | 2015-07-02 | Xerox Corporation | Weighting scheme for pooling image descriptors |
CN104882144A (en) * | 2015-05-06 | 2015-09-02 | 福州大学 | Animal voice identification method based on double sound spectrogram characteristics |
CN105513614A (en) * | 2015-12-03 | 2016-04-20 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Voice activation detection method based on noise power spectrum density Gamma distribution statistical model |
CN105550636A (en) * | 2015-12-04 | 2016-05-04 | 中国电子科技集团公司第三研究所 | Method and device for identifying target types |
CN105956546A (en) * | 2016-04-28 | 2016-09-21 | 杭州电子科技大学 | Emotion recognition method based on EEG signals |
CN106504762A (en) * | 2016-11-04 | 2017-03-15 | 中南民族大学 | Bird community quantity survey system and method |
CN107393542A (en) * | 2017-06-28 | 2017-11-24 | 北京林业大学 | A kind of birds species identification method based on binary channels neutral net |
CN107610715A (en) * | 2017-10-10 | 2018-01-19 | 昆明理工大学 | A kind of similarity calculating method based on muli-sounds feature |
CN108197591A (en) * | 2018-01-22 | 2018-06-22 | 北京林业大学 | A kind of birds individual discrimination method based on multiple features fusion transfer learning |
CN108471943A (en) * | 2015-10-14 | 2018-08-31 | 哈佛大学校长及研究员协会 | Automatic classification animal behavior |
KR20190013251A (en) * | 2017-08-01 | 2019-02-11 | 한양대학교 산학협력단 | Real-time speech derverberation method and apparatus using multi-channel linear prediction with estimation of early speech psd for distant speech recognition |
CN109409308A (en) * | 2018-11-05 | 2019-03-01 | 中国科学院声学研究所 | A method of the birds species identification based on birdvocalization |
CN109493874A (en) * | 2018-11-23 | 2019-03-19 | 东北农业大学 | A kind of live pig cough sound recognition methods based on convolutional neural networks |
CN110059564A (en) * | 2019-03-19 | 2019-07-26 | 西安交通大学 | Feature extracting method based on power spectral density and cross-correlation entropy-spectrum density fusion |
-
2020
- 2020-03-27 CN CN202010229304.0A patent/CN111626093B/en active Active
Patent Citations (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010044719A1 (en) * | 1999-07-02 | 2001-11-22 | Mitsubishi Electric Research Laboratories, Inc. | Method and system for recognizing, indexing, and searching acoustic signals |
JP2002189495A (en) * | 2000-12-19 | 2002-07-05 | Atr Onsei Gengo Tsushin Kenkyusho:Kk | Feature extractor for speech recognition, and speech recognition device |
JP2002278547A (en) * | 2001-03-22 | 2002-09-27 | Matsushita Electric Ind Co Ltd | Music piece retrieval method, music piece retrieval data registration method, music piece retrieval device and music piece retrieval data registration device |
US20020172372A1 (en) * | 2001-03-22 | 2002-11-21 | Junichi Tagawa | Sound features extracting apparatus, sound data registering apparatus, sound data retrieving apparatus, and methods and programs for implementing the same |
JP2006227564A (en) * | 2005-01-20 | 2006-08-31 | Advanced Telecommunication Research Institute International | Sound evaluating device and program |
US20130097112A1 (en) * | 2011-10-13 | 2013-04-18 | Edward B. Loewenstein | Determination of Statistical Upper Bound for Estimate of Noise Power Spectral Density |
CN102708860A (en) * | 2012-06-27 | 2012-10-03 | 昆明信诺莱伯科技有限公司 | Method for establishing judgment standard for identifying bird type based on sound signal |
CN102930870A (en) * | 2012-09-27 | 2013-02-13 | 福州大学 | Bird voice recognition method using anti-noise power normalization cepstrum coefficients (APNCC) |
CN103117061A (en) * | 2013-02-05 | 2013-05-22 | 广东欧珀移动通信有限公司 | Method and device for identifying animals based on voice |
CN103474072A (en) * | 2013-10-11 | 2013-12-25 | 福州大学 | Rapid anti-noise twitter identification method by utilizing textural features and random forest (RF) |
CN104658538A (en) * | 2013-11-18 | 2015-05-27 | 中国计量学院 | Mobile bird recognition method based on birdsong |
US20150186742A1 (en) * | 2013-12-27 | 2015-07-02 | Xerox Corporation | Weighting scheme for pooling image descriptors |
CN104882144A (en) * | 2015-05-06 | 2015-09-02 | 福州大学 | Animal voice identification method based on double sound spectrogram characteristics |
CN108471943A (en) * | 2015-10-14 | 2018-08-31 | 哈佛大学校长及研究员协会 | Automatic classification animal behavior |
CN105513614A (en) * | 2015-12-03 | 2016-04-20 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Voice activation detection method based on noise power spectrum density Gamma distribution statistical model |
CN105550636A (en) * | 2015-12-04 | 2016-05-04 | 中国电子科技集团公司第三研究所 | Method and device for identifying target types |
CN105956546A (en) * | 2016-04-28 | 2016-09-21 | 杭州电子科技大学 | Emotion recognition method based on EEG signals |
CN106504762A (en) * | 2016-11-04 | 2017-03-15 | 中南民族大学 | Bird community quantity survey system and method |
CN107393542A (en) * | 2017-06-28 | 2017-11-24 | 北京林业大学 | A kind of birds species identification method based on binary channels neutral net |
KR20190013251A (en) * | 2017-08-01 | 2019-02-11 | 한양대학교 산학협력단 | Real-time speech derverberation method and apparatus using multi-channel linear prediction with estimation of early speech psd for distant speech recognition |
CN107610715A (en) * | 2017-10-10 | 2018-01-19 | 昆明理工大学 | A kind of similarity calculating method based on muli-sounds feature |
CN108197591A (en) * | 2018-01-22 | 2018-06-22 | 北京林业大学 | A kind of birds individual discrimination method based on multiple features fusion transfer learning |
CN109409308A (en) * | 2018-11-05 | 2019-03-01 | 中国科学院声学研究所 | A method of the birds species identification based on birdvocalization |
CN109493874A (en) * | 2018-11-23 | 2019-03-19 | 东北农业大学 | A kind of live pig cough sound recognition methods based on convolutional neural networks |
CN110059564A (en) * | 2019-03-19 | 2019-07-26 | 西安交通大学 | Feature extracting method based on power spectral density and cross-correlation entropy-spectrum density fusion |
Non-Patent Citations (6)
Title |
---|
GONG CHEN ET AL: "Individual identification of birds with complex songs: The case of green-backed flycatchers Ficedula elisae", 《BEHAVIOURAL PROCESSES》, pages 1 - 8 * |
ILYA A. VOLODIN ET AL.: "Gender identification using acoustic analysis in birds without external sexual dimorphism", 《AVIAN RESEARCH》, pages 1 - 17 * |
JINSHAN LIN: "Identification of Road Surface Power Spectrum Density Based on a New Cubic Spline Weight Neural Network", pages 534 - 539 * |
任芳: "鸟类鸣声特征提取及音素分类研究", 《中国优秀硕士学位论文全文数据库》, pages 5 - 27 * |
况燕军等: "基于鸟鸣功率谱密度的输电线路涉鸟故障相关鸟种智能识别", 《2021年江西省机电工程学会年会论文集》, pages 109 - 113 * |
况燕军等: "基于鸟鸣功率谱密度的输电线路涉鸟故障相关鸟种智能识别", 《水电能源科学 》, pages 156 - 159 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113111618A (en) * | 2021-03-09 | 2021-07-13 | 电子科技大学 | Analog circuit fault diagnosis method based on improved empirical wavelet transform |
CN113111618B (en) * | 2021-03-09 | 2022-10-18 | 电子科技大学 | Analog circuit fault diagnosis method based on improved empirical wavelet transform |
CN113255661A (en) * | 2021-04-15 | 2021-08-13 | 南昌大学 | Bird species image identification method related to bird-involved fault of power transmission line |
CN113255661B (en) * | 2021-04-15 | 2022-07-12 | 南昌大学 | Bird species image identification method related to bird-involved fault of power transmission line |
CN113707159A (en) * | 2021-08-02 | 2021-11-26 | 南昌大学 | Electric network bird-involved fault bird species identification method based on Mel language graph and deep learning |
CN113707159B (en) * | 2021-08-02 | 2024-05-03 | 南昌大学 | Power grid bird-involved fault bird species identification method based on Mel language graph and deep learning |
Also Published As
Publication number | Publication date |
---|---|
CN111626093B (en) | 2023-12-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111626093B (en) | Method for identifying related bird species of power transmission line based on sound power spectral density | |
Drugman et al. | Glottal closure and opening instant detection from speech signals | |
CN103117061B (en) | A kind of voice-based animals recognition method and device | |
CN106653032A (en) | Animal sound detecting method based on multiband energy distribution in low signal-to-noise-ratio environment | |
CN105825852A (en) | Oral English reading test scoring method | |
CN109817227B (en) | Abnormal sound monitoring method and system for farm | |
CN111508517A (en) | Intelligent micro-motor product control method based on noise characteristics | |
CN109408660A (en) | A method of the music based on audio frequency characteristics is classified automatically | |
CN110299141A (en) | The acoustic feature extracting method of recording replay attack detection in a kind of Application on Voiceprint Recognition | |
CN112820275A (en) | Automatic monitoring method for analyzing abnormality of suckling piglets based on sound signals | |
CN116778964A (en) | Power transformation equipment fault monitoring system and method based on voiceprint recognition | |
CN107369451B (en) | Bird voice recognition method for assisting phenological study of bird breeding period | |
CN115048984A (en) | Sow oestrus recognition method based on deep learning | |
CN116861303A (en) | Digital twin multisource information fusion diagnosis method for transformer substation | |
Lin et al. | Automatic classification of delphinids based on the representative frequencies of whistles | |
CN115376526A (en) | Power equipment fault detection method and system based on voiceprint recognition | |
CN116776075A (en) | Fan blade health monitoring system and monitoring method thereof | |
CN115510265A (en) | Method and system for judging animal hazard distribution of pole tower in power transmission line | |
CN112033656A (en) | Mechanical system fault detection method based on broadband spectrum processing | |
CN116881712A (en) | Electromagnetic pulse signal identification method for movable cracks of concrete dam | |
CN112908343B (en) | Acquisition method and system for bird species number based on cepstrum spectrogram | |
CN113707159B (en) | Power grid bird-involved fault bird species identification method based on Mel language graph and deep learning | |
CN115064182A (en) | Fan fault feature identification method of self-adaptive Mel filter in strong noise environment | |
US20230320329A1 (en) | Poultry voiceprint identification method and system | |
CN117290670B (en) | Transformer bushing insulation state estimation method based on enhancement filter algorithm |
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 |