CN114527241A - Wavelet transform-capsule neural network cascade type gas identification method and device - Google Patents
Wavelet transform-capsule neural network cascade type gas identification method and device Download PDFInfo
- Publication number
- CN114527241A CN114527241A CN202210157351.8A CN202210157351A CN114527241A CN 114527241 A CN114527241 A CN 114527241A CN 202210157351 A CN202210157351 A CN 202210157351A CN 114527241 A CN114527241 A CN 114527241A
- Authority
- CN
- China
- Prior art keywords
- layer
- neural network
- wavelet transform
- capsule
- gas
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0031—General constructional details of gas analysers, e.g. portable test equipment concerning the detector comprising two or more sensors, e.g. a sensor array
- G01N33/0034—General constructional details of gas analysers, e.g. portable test equipment concerning the detector comprising two or more sensors, e.g. a sensor array comprising neural networks or related mathematical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0036—Specially adapted to detect a particular component
- G01N33/004—Specially adapted to detect a particular component for CO, CO2
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0036—Specially adapted to detect a particular component
- G01N33/005—Specially adapted to detect a particular component for H2
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
- Y02A50/20—Air quality improvement or preservation, e.g. vehicle emission control or emission reduction by using catalytic converters
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Food Science & Technology (AREA)
- Biochemistry (AREA)
- Combustion & Propulsion (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Investigating Or Analyzing Materials By The Use Of Fluid Adsorption Or Reactions (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
Abstract
The invention relates to a wavelet transform-capsule neural network cascade type gas identification method and a device, comprising the steps of inputting mixed gas into a multi-channel sensor array to obtain a gas time domain signal; carrying out five-layer wavelet transformation on the gas time domain signal to obtain a signal sequence; and inputting the signal sequence after dimension conversion into a capsule neural network, and acquiring a gas identification result by combining a dynamic routing algorithm, wherein the capsule neural network comprises an input layer, a convolution layer, a main capsule layer, a digital capsule layer, a classifier layer and an output layer. Compared with the prior art, the method has the advantages of high identification accuracy and the like.
Description
Technical Field
The invention relates to the field of mixed gas detection, in particular to a wavelet transform-capsule neural network cascade type gas identification method and a device.
Background
The gas sensor is widely applied to tail gas monitoring, smoke alarming, civil gas leakage detection, dangerous gas monitoring of chemical plants and the like. Common gas sensors are classified into infrared type, thermal conductivity type, catalytic combustion type, solid electrolyte type, Metal Oxide Semiconductor (MOS) type, and the like according to their operation principles. The MOS gas sensor has the advantages of high sensitivity, small size, low energy consumption, low cost, etc., and thus has attracted much attention in both industrial and academic fields.
The gas-sensitive mechanism of the MOS gas-sensitive sensor is based on the difference of the oxidation-reduction property between the gas to be detected and oxygen, taking an n-type semiconductor as an example, and taking a carrier as an electron, when the gas-sensitive material is positioned in the air, the oxygen in the air can take the electron from a conduction band of the gas-sensitive material to generate a space charge layer, so that the electron potential barrier on the surface of the crystal is raised, and the gas-sensitive material is in a high-resistance state. If the oxidability of the gas to be detected is stronger, the surface of the gas-sensitive material further loses electrons, and the resistance value is further increased; on the contrary, if the reducibility of the gas to be detected is stronger, the surface of the gas sensitive material can obtain electrons again, the resistance value is reduced to some extent, and the reaction process is completely opposite for the p-type semiconductor. It can be seen from the gas sensor mechanism that the MOS gas sensor converts the component and concentration information of the gas to be measured into an electrical signal, and the information of the gas to be measured can be analyzed by performing digital processing and analysis on the electrical signal.
The MOS gas sensor has cross sensitivity, that is, there is no MOS gas sensor having single sensitivity, so that the single MOS gas sensor does not perform well for component detection of mixed gas. In order to solve the problem, on one hand, researchers improve the gas selectivity and inhibit the cross sensitivity by means of element doping, surface modification, micro-morphology modification and the like from the physicochemical property of the sensitive material; on the other hand, a series of MOS gas sensors with different sensitivity characteristics form an array sensor, and the identification of the composition of the mixed gas is realized by comparing and analyzing the response signal difference of the MOS gas sensors of each channel.
The identification algorithms commonly used at present based on the MOS gas sensor comprise a principal component analysis algorithm (PCA), an independent component analysis algorithm (ICA), a local preserving projection algorithm (LPP), a kernel principal component analysis algorithm (KPCA), a K-nearest neighbor algorithm (KNN) and a support vector machine algorithm (SVM). The PCA, ICA and LPP algorithms are mainly used for extracting linear characteristics, and nonlinear characteristics in a dynamic response stage cannot be effectively extracted; although the KPCA algorithm can extract nonlinear features, when classification is carried out by combining the KNN algorithm, along with the increase of sample size, the calculation amount of the KNN algorithm is increased rapidly, and the classification time is prolonged; although the SVM can extract nonlinear characteristics and has low requirements on sample quantity, the kernel function of the SVM needs to meet the Mercer condition, and different gases to be measured need to be adjusted frequently.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a wavelet transformation-capsule neural network cascade type gas identification method and device.
The purpose of the invention can be realized by the following technical scheme:
a wavelet transform-capsule neural network cascade type gas identification method comprises the following steps:
s1, inputting the mixed gas into a multi-channel sensor array to obtain a gas time domain signal;
s2, carrying out five-layer wavelet transformation on the gas time domain signal to obtain a signal sequence;
and S3, inputting the signal sequence after dimension conversion into a capsule neural network, and acquiring a gas identification result by combining a dynamic routing algorithm, wherein the capsule neural network comprises an input layer, a convolution layer, a main capsule layer, a digital capsule layer, a classifier layer and an output layer.
Further, in the five-layer wavelet transform, each layer of wavelet transform decomposes an input signal into a signal high-frequency part and a signal low-frequency part, the signal low-frequency part obtained by each layer is used as the input of the next layer of wavelet transform, and finally the signal high-frequency part obtained by the fifth layer and the signal low-frequency part obtained by each layer are superposed to be used as an output signal sequence.
Further, the number of the digital capsules in the digital capsule layer is the same as the number of the types of the gas in the gas to be detected.
Further, the dimension transformation in step S3 specifically includes:
and performing point-spaced sampling on the signal sequence to obtain sampling data, and arranging the sampling data of all channels according to the channel sequence to obtain a wavelet transform coefficient image after dimension transformation, wherein the wavelet transform coefficient image is used as the input of the capsule neural network.
Further, the input layers include 256 convolution kernels of 9 × 9 with a step of 1, and the convolutional layers include 32 convolution kernels of 9 × 9 with a step of 2.
A wavelet transform-capsule neural network cascade type gas identification device comprises a memory and a processor; the memory for storing a computer program; the processor, when executing the computer program, is configured to implement the following method:
s1, inputting the mixed gas into a multi-channel sensor array to obtain a gas time domain signal;
s2, carrying out five-layer wavelet transformation on the gas time domain signal to obtain a signal sequence;
and S3, inputting the signal sequence into a capsule neural network after dimension conversion, wherein the capsule neural network comprises an input layer, a convolution layer, a main capsule layer, a digital capsule layer, a classifier layer and an output layer, and acquiring a gas identification result by combining a dynamic routing algorithm.
Compared with the prior art, the invention has the following advantages:
1. after extracting the time domain signal of the mixed gas, the invention carries out five-layer wavelet transform, and simultaneously obtains low-frequency data and high-frequency data, namely simultaneously extracts the linear characteristics under the steady state and the nonlinear characteristics in the dynamic response stage, so that the subsequent discrimination based on the characteristics is more accurate, and the identification accuracy is improved; and the capsule neural network is used for processing a large amount of data and then outputting a judgment result, so that the calculation is simplified and the recognition efficiency is improved.
2. In the setting of the capsule neural network, the invention only needs to set the number of capsules of the digital capsule layer according to the number of the types of the gas to be detected, does not need to set other parameters due to the change of the gas, has strong universality and can be suitable for gas detection in different application scenes.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
FIG. 2 is a block diagram of a process for obtaining a time domain signal of a gas mixture according to the present invention.
Fig. 3 is a schematic diagram of a five-layer wavelet transform used in the present invention.
Fig. 4 is an architecture diagram of a capsule neural network used in the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
The embodiment provides a wavelet transformation-capsule neural network cascade type gas identification method which is characterized by comprising the following steps of:
s1, inputting the mixed gas into a multi-channel sensor array, and obtaining a gas time domain signal through the calculation of an acquisition board and an upper computer;
s2, performing five-layer wavelet transformation on the gas time domain signal, and acquiring a signal sequence according to the extracted low-frequency data and high-frequency data;
and step S3, inputting the wavelet transform coefficient image obtained after the signal sequence is subjected to dimension transform into a capsule neural network, wherein the capsule neural network comprises an input layer, a convolution layer, a main capsule layer, a digital capsule layer, a classifier layer and an output layer, and a gas identification result is obtained by combining a dynamic routing algorithm.
In this embodiment, step S1 specifically includes:
first, the present example uses CO gas and H2The gas and the gas mixed with the gas are used as the gas for detection, and the acquisition method comprises the following steps:
with 100% CO and 20% H280% concentration N2The mixed gas is used as a gas source, the gas proportion of the two gas sources is controlled by a mass flow meter, and mixed gas samples with different concentrations are obtained after the gas is fully mixed in a gas mixing cavity.
After the mixed gas is obtained, the mixed gas is conveyed to a multi-channel sensor array, in the embodiment, an 8-channel sensor array is adopted, an 8-channel 12-bit a/D conversion signal acquisition board acquires the mixed gas at a frequency of 10Hz, and transmits the signal to an upper computer carrying Labview-based signal acquisition software, so that an 8-channel gas time domain signal curve is finally obtained. The whole signal acquisition flow chart is shown in fig. 1.
In this embodiment, step S2 specifically includes:
five layers of wavelet transformation are carried out on the gas time domain signals of all channels, each layer of wavelet transformation decomposes input signals into high-frequency data reflecting signal details and low-frequency data reflecting signal profiles, and the obtained low-frequency data is used as input of the next layer of wavelet transformation for further decomposition, as shown in fig. 3. In conjunction with the Mallat algorithm, the original signal can be represented as a superposition of the low frequency data of the last layer (fifth layer) and all the high frequency data, with the expression:
S=A5+D5+D4+D3+D2+D1
wherein S represents a gas time domain signal, A5 represents low-frequency data after the fifth-layer wavelet transform, and Di represents high-frequency data after the ith-layer wavelet transform.
Finally, the superimposed data is output as a signal sequence.
In this embodiment, step S3 specifically includes:
firstly, performing alternate sampling on a signal sequence of each channel to obtain 512 data in total, performing 8 channels to obtain 4096 data in total, sequentially arranging the data according to the channel sequence, converting dimensionality into a wavelet transform coefficient image with the size of 64 × 64, inputting the wavelet transform coefficient image into an input layer of a capsule neural network, performing convolution by adopting 256 convolution kernels with the size of 9 × 9 and the step size of 1, selecting a ReLU as an activation function, and obtaining a tensor of 256 × 056 × 156, wherein the aim is to extract low-level features in the input image. Then, after passing through the convolutional layer, the 256 × 356 × 456 tensor is convolved with 32 convolutional kernels of 9 × 29 size with a step of 2 to obtain a 32 × 524 × 624 tensor, and then the dimensions thereof are converted into 32 × 1 × 24 × 24, and the operations in the convolutional layer are repeated 8 times due to the data sharing 8 channels, and the results are combined to finally obtain a 32 × 8 × 24 × 24 tensor. Then passes through the main capsule layer and contains 32 main capsules, wherein each main capsule contains 24 × 24 sub-capsules of 1 × 8. The gas types of the gas to be measured selected in the embodiment are CO gas and H gas in common2Three gases and two mixed gases, therefore three digital capsules are arranged on the digital capsule layer, each capsule receives the input tensor of 32 multiplied by 8 multiplied by 24, carries out matrix transformation on the sub-capsules through the attitude matrix of 8 multiplied by 16, and combines the motionAnd (4) outputting a 3 × 16 matrix by using a state routing algorithm. Through the convolution dimension conversion, the data characteristics of the gas time domain signal can be fed back more accurately. The L2 norm of each row vector of the 3 x 16 matrix is the probability of the corresponding category, the row number of the maximum value in the 3 corresponding probabilities is input to the classifier layer, and the classifier layer can obtain the corresponding specific gas category and transmit the specific gas category to the output layer. The architecture diagram of the capsule neural network is shown in fig. 4.
And finally, obtaining a gas identification result through the output layer.
The embodiment also provides a wavelet transformation-capsule neural network cascade type gas identification device, which comprises a memory and a processor; a memory for storing a computer program; a processor for, when executing a computer program, implementing the method of:
s1, inputting the mixed gas into a multi-channel sensor array, and obtaining a gas time domain signal through the calculation of an acquisition board and an upper computer;
s2, performing five-layer wavelet transformation on the gas time domain signal, and acquiring a signal sequence according to the extracted low-frequency data and high-frequency data;
and step S3, inputting the wavelet transform coefficient image obtained after the signal sequence is subjected to dimension transform into a capsule neural network, wherein the capsule neural network comprises an input layer, a convolution layer, a main capsule layer, a digital capsule layer, a classifier layer and an output layer, and a gas identification result is obtained by combining a dynamic routing algorithm.
This embodiment further proposes a computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing a wavelet transform-capsule neural network cascade-type gas identification method as mentioned in the above embodiment, which may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. A wavelet transform-capsule neural network cascade type gas identification method is characterized by comprising the following steps:
s1, inputting the mixed gas into a multi-channel sensor array to obtain a gas time domain signal;
s2, carrying out five-layer wavelet transformation on the gas time domain signal to obtain a signal sequence;
and S3, inputting the signal sequence after dimension conversion into a capsule neural network, and acquiring a gas identification result by combining a dynamic routing algorithm, wherein the capsule neural network comprises an input layer, a convolution layer, a main capsule layer, a digital capsule layer, a classifier layer and an output layer.
2. The wavelet transform-capsule neural network cascade type gas identification method according to claim 1, wherein in five layers of wavelet transforms, each layer of wavelet transform decomposes an input signal into a signal high frequency part and a signal low frequency part, the signal low frequency part obtained by each layer is used as the input of the next layer of wavelet transform, and finally the signal high frequency part obtained by the fifth layer and the signal low frequency part obtained by each layer are superposed to be used as the output signal sequence.
3. The wavelet transform-capsule neural network cascade type gas identification method according to claim 1, wherein the number of digital capsules in the digital capsule layer is the same as the number of types of gas in the gas to be detected.
4. The wavelet transform-capsule neural network cascade type gas identification method according to claim 1, wherein the dimension transform in step S3 specifically comprises:
and performing point-spaced sampling on the signal sequence to obtain sampling data, and arranging the sampling data of all channels according to the channel sequence to obtain a wavelet transform coefficient image after dimension transformation, wherein the wavelet transform coefficient image is used as the input of the capsule neural network.
5. The wavelet transform-capsule neural network cascade-type gas identification method of claim 1, wherein the input layer comprises 256 convolution kernels with steps of 1 and 9 × 9, and the convolution layer comprises 32 convolution layers with steps of 2 and 9 × 9.
6. A wavelet transform-capsule neural network cascade type gas identification device is characterized by comprising a memory and a processor; the memory for storing a computer program; the processor, when executing the computer program, is configured to implement the following method:
s1, inputting the mixed gas into a multi-channel sensor array to obtain a gas time domain signal;
s2, carrying out five-layer wavelet transformation on the gas time domain signal to obtain a signal sequence;
and S3, inputting the signal sequence after dimension conversion into a capsule neural network, and acquiring a gas identification result by combining a dynamic routing algorithm, wherein the capsule neural network comprises an input layer, a convolution layer, a main capsule layer, a digital capsule layer, a classifier layer and an output layer.
7. The wavelet transform-capsule neural network cascade type gas identification device according to claim 6, wherein in the five-layer wavelet transform, each layer of wavelet transform decomposes an input signal into a signal high frequency part and a signal low frequency part, the signal low frequency part obtained from each layer is used as the input of the next layer of wavelet transform, and finally the signal high frequency part obtained from the fifth layer and the signal low frequency part obtained from each layer are superposed to be used as the output signal sequence.
8. The wavelet transform-capsule neural network cascade-type gas identification device according to claim 6, wherein the number of digital capsules in the digital capsule layer is the same as the number of types of gas in the gas to be detected.
9. The wavelet transform-capsule neural network cascade type gas identification device according to claim 6, wherein the dimension transform in step S3 specifically comprises:
and performing point-spaced sampling on the signal sequence to obtain sampling data, and arranging the sampling data of all channels according to the channel sequence to obtain a wavelet transform coefficient image after dimension transformation, wherein the wavelet transform coefficient image is used as the input of the capsule neural network.
10. The wavelet transform-capsule neural network cascade-type gas identification device of claim 6, wherein the input layer comprises 256 convolution kernels with steps of 1 and 9 × 9, and the convolution layer comprises 32 convolution layers with steps of 2 and 9 × 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210157351.8A CN114527241B (en) | 2022-02-21 | 2022-02-21 | Wavelet transformation-capsule neural network cascading type gas identification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210157351.8A CN114527241B (en) | 2022-02-21 | 2022-02-21 | Wavelet transformation-capsule neural network cascading type gas identification method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114527241A true CN114527241A (en) | 2022-05-24 |
CN114527241B CN114527241B (en) | 2023-08-04 |
Family
ID=81625391
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210157351.8A Active CN114527241B (en) | 2022-02-21 | 2022-02-21 | Wavelet transformation-capsule neural network cascading type gas identification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114527241B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6105015A (en) * | 1997-02-03 | 2000-08-15 | The United States Of America As Represented By The Secretary Of The Navy | Wavelet-based hybrid neurosystem for classifying a signal or an image represented by the signal in a data system |
CN111443165A (en) * | 2020-03-27 | 2020-07-24 | 华中科技大学 | Odor identification method based on gas sensor and deep learning |
CN113823403A (en) * | 2021-08-05 | 2021-12-21 | 山东大学 | Neural network-based early lung cancer exhaled breath component detection and recognition system |
-
2022
- 2022-02-21 CN CN202210157351.8A patent/CN114527241B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6105015A (en) * | 1997-02-03 | 2000-08-15 | The United States Of America As Represented By The Secretary Of The Navy | Wavelet-based hybrid neurosystem for classifying a signal or an image represented by the signal in a data system |
CN111443165A (en) * | 2020-03-27 | 2020-07-24 | 华中科技大学 | Odor identification method based on gas sensor and deep learning |
CN113823403A (en) * | 2021-08-05 | 2021-12-21 | 山东大学 | Neural network-based early lung cancer exhaled breath component detection and recognition system |
Non-Patent Citations (2)
Title |
---|
谭光韬;张文文;王磊;: "气体传感器阵列混合气体检测算法研究", 电子测量与仪器学报, no. 07 * |
黄家锐, 刘锦淮: "基于单传感器动态检测和神经网络的气体识别", 传感器世界, no. 01 * |
Also Published As
Publication number | Publication date |
---|---|
CN114527241B (en) | 2023-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yan et al. | Calibration transfer and drift compensation of e-noses via coupled task learning | |
Kloosterman et al. | The interface between forensic science and technology: how technology could cause a paradigm shift in the role of forensic institutes in the criminal justice system | |
CN111443165B (en) | Odor identification method based on gas sensor and deep learning | |
Cetó et al. | Simultaneous identification and quantification of nitro-containing explosives by advanced chemometric data treatment of cyclic voltammetry at screen-printed electrodes | |
KR101852074B1 (en) | Electronic Nose System and Method for Gas Classification | |
Zhang et al. | A novel sensor selection using pattern recognition in electronic nose | |
Zhang et al. | A novel background interferences elimination method in electronic nose using pattern recognition | |
Hanh et al. | Enhancing the performance of transferred efficientnet models in leaf image-based plant disease classification | |
Zhou et al. | Early-stage gas identification using convolutional long short-term neural network with sensor array time series data | |
Bastuck et al. | DAV 3 E–a MATLAB toolbox for multivariate sensor data evaluation | |
Luo et al. | A novel chemical detector using colorimetric sensor array and pattern recognition methods for the concentration analysis of NH3 | |
Ichinohe et al. | Neural network-based anomaly detection for high-resolution X-ray spectroscopy | |
Ansari et al. | A novel technique of mixed gas identification based on the group method of data handling (GMDH) on time-dependent MOX gas sensor data | |
Wilson et al. | Rank extraction in tin-oxide sensor arrays | |
Chaudhri et al. | A novel principal component-based virtual sensor approach for efficient classification of gases/odors | |
Davari et al. | Deep learning models for data-driven laser induced breakdown spectroscopy (LIBS) analysis of interstitial oxygen impurities in czochralski-si crystals | |
CN114527241B (en) | Wavelet transformation-capsule neural network cascading type gas identification method and device | |
Yang et al. | Accurate real-time monitoring of fine dust using a densely connected convolutional networks with measured plasma emissions | |
Yahyaoui et al. | One-Class Machine Learning Classifiers-Based Multivariate Feature Extraction for Grid-Connected PV Systems Monitoring under Irradiance Variations | |
Ma et al. | Small-sample stacking model for qualitative analysis of aluminum alloys based on femtosecond laser-induced breakdown spectroscopy | |
Yamashita et al. | Direct feature extraction from two-dimensional X-ray diffraction images of semiconductor thin films for fabrication analysis | |
Wang et al. | Exploiting the self-attention mechanism in gas sensor array (GSA) data with neural networks | |
CN115984624A (en) | Electronic nose-based gas detection model training method, device, medium and equipment | |
Oh et al. | Multichannel convolution neural network for gas mixture classification | |
Guaman et al. | Multivariate discrimination model for TNT and gunpowder using an electronic nose prototype: A proof of concept |
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 |