CN111443165B - Odor identification method based on gas sensor and deep learning - Google Patents
Odor identification method based on gas sensor and deep learning Download PDFInfo
- Publication number
- CN111443165B CN111443165B CN202010229387.3A CN202010229387A CN111443165B CN 111443165 B CN111443165 B CN 111443165B CN 202010229387 A CN202010229387 A CN 202010229387A CN 111443165 B CN111443165 B CN 111443165B
- Authority
- CN
- China
- Prior art keywords
- gas sensor
- dimensional
- window
- sample
- data
- 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.)
- Active
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
- G01N33/0001—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00 by organoleptic means
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Combustion & Propulsion (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Investigating Or Analyzing Materials By The Use Of Fluid Adsorption Or Reactions (AREA)
Abstract
The invention discloses a smell identification method based on a gas sensor and deep learning, which is characterized in that a response curve cluster of a smell to be detected is obtained through a gas sensor array, the original data is directly used as an input sample of a smell identification deep neural network, data preprocessing and data amplification are carried out on the input sample, time series response data hierarchical characteristics are automatically extracted by utilizing the deep learning, global characteristic extraction and long-range dynamic characteristic extraction are simultaneously carried out, and a smell label is output through a classifier, so that high-sensitivity and specific smell identification is realized. The method has high sensitivity and high reliability, and can be widely applied to the fields of industrial production, medical treatment, environment, safety and the like.
Description
Technical Field
The invention belongs to the technical field of artificial olfaction, and particularly relates to a smell identification method based on a gas sensor and deep learning.
Background
The electronic nose constructed based on the gas sensor is a typical portable artificial olfactory system, generates signals through the reaction of a sensor array and atmosphere, can identify simple and complex odors by combining a pattern recognition technology, has the characteristics of convenient use, low price and easy popularization compared with common laboratory gas component analysis methods (such as an electrochemical method, an optical method, a chromatographic separation method and the like), is suitable for on-site rapid detection and distributed on-line monitoring of various gases/odors, and has been practically applied in the fields of food industry, agricultural production, environmental monitoring and the like. For example, it is a development trend of artificial olfaction technology to identify freshness of food by detecting atmosphere generated in food deterioration process through an electronic nose, identify different odors generated in brewing process to control brewing process, identify tobacco grade according to different odors of tobacco, detect disease markers in exhaled gas of human body to predict related diseases, and further improve field environment adaptability and identification accuracy.
With the significant breakthrough of various "bio-heuristic" sensors and artificial intelligence algorithm technologies, the performance of artificial vision, auditory and tactile systems has reached and even surpassed that of humans. Compared with thousands of odor receptors in a human olfactory system, due to the limitation of volume and power consumption of the gas sensors, the number of the gas sensors in the current electronic nose artificial olfactory system is very limited, and the pattern recognition technology mainly depends on the artificial extraction of data features of the gas sensors, only one-sided features such as sensitivity, response time and the like are extracted to be used as input data of a neural network, an effective feature extraction means specially aiming at original signals of an odor sensor array is lacked, and systematic and comprehensive big data cannot be provided for a deep learning algorithm to mine high-level and abstract odor features. Therefore, compared with intelligent image and voice recognition based on sensing of physical quantities such as optics and acoustics, the development of an artificial olfactory system based on a gas sensor and deep learning is delayed seriously.
In the Chinese invention patent of a portable intelligent electronic nose system and a smell identification method (publication number: CN106841308A, publication date: 2017, 6 and 13 months) features are extracted from a response curve by a difference method, and dimension reduction algorithms such as Principal Component Analysis (PCA) and the like are adopted to reduce the dimension of the extracted features. On one hand, in the process of preprocessing, feature extraction and dimension reduction of original data, the information compression ratio is very high, so that many distinguishable features are lost, and the performance of a subsequent classifier is limited; meanwhile, although the method can decompose a complex parent problem into a plurality of simple, controllable and clear-structured sub-problems, the method can only seek an optimal solution on each sub-problem, and cannot obtain a global optimal solution of the parent problem, so that the generalization performance and the capability of solving the complex problem are limited.
The original signal is characterized by a two-dimensional Convolutional neural Network in a paper published by "Development of a LeNet-5 Gas Identification CNN Structure for Electronic Nos" in No. 1 of 2019 and a paper published by "IEEE Access" in No. 7 of 2019. This approach has two drawbacks: firstly, the response curve of the gas sensor array is a multi-dimensional time series signal, different from a two-dimensional image, and the one-dimensional time series signals from different sensor units have no spatial correlation and are not suitable for feature extraction by adopting two-dimensional convolution; second, two-dimensional convolution has higher temporal and spatial complexity than one-dimensional convolution, which results in increased computational and memory costs.
A method for simulating biological Olfactory behaviors by using a Neuromorphic chip is reported in a paper "Rapid Online Learning and Robust Recall in a neurological oxygen Circuit", published by Nature Machine science, 2 nd 2020. The method is based on a gas sensor database disclosed by a network, 30-180s of response data (interval time is 5s) are intercepted from response time sequence signal original data of a plurality of metal oxide gas sensors, the signal complexity is reduced through simple data quantization processing, and a Loihi nerve morphology chip developed by Intel company is used for simulating signals processed and quantized by biological olfactory organ olfactory bulbs and outputting an odor recognition result. The method simplifies the acquisition and quantification of the original data of the sensor array response signals so as to meet the processing and calculation capabilities of the Loihi chip, and therefore, the accuracy in identification of complex atmospheres and atmospheres with small differences is low.
Disclosure of Invention
Aiming at the defects or improvement requirements of the prior art, the invention provides an odor identification method based on a gas sensor and deep learning, which aims to solve the problem of spatial independence among multiple channels of time series signals, solve the problem that the existing artificial olfactory system odor identification network based on a two-dimensional convolution kernel cannot model the long-range relation of single-channel time series signals, and solve the problem of influence of sensor baseline drift and environmental factor change on identification accuracy.
In order to realize the purpose, a gas sensor array and a signal acquisition module are adopted to construct the hardware basis of the artificial olfaction system, and the original data is directly used as an input sample of the odor recognition deep neural network. The odor identification method based on the gas sensor and the deep learning specifically comprises the following steps:
(1) acquiring a response curve cluster of the odor to be detected through a gas sensor array;
(2) carrying out data preprocessing and data amplification on the response curve cluster to obtain a sensing signal;
(3) extracting the multi-dimensional time series signal characteristics of the backbone network for the sensing signals, and simultaneously extracting global characteristics and long-range dynamic characteristics;
(4) and performing multi-mode feature fusion and classification to complete the identification of the odor to be detected.
Preferably, in the data preprocessing and data amplification, in order to effectively extract the multi-dimensional time series signal characteristics, the method adopts a one-dimensional residual error network and combines a channel and time attention mechanism, so that the backbone network automatically extracts the characteristics suitable for the odor classification task.
In the aspect of obtaining robust odor identification performance under complex measurement conditions, the main data preprocessing and amplification method provided by the invention specifically comprises the following steps:
(21) sliding window based data clipping. Raw data set
Containing N original data samples and corresponding labels, wherein each original sample
Comprises K gas sensor units; each original sample TiComprises a plurality of window slices, the window slices are defined as
Wherein i is the time label of the start time of the window slice, and j is the time label of the end time.
Sliding a window of length s over an original sample of length n to obtain m +1 time series slices: sliding (T, S) { S }1：s,S1+p：s+p,…,S1+p*m：s+p*mAll the window slices have the same label as the original sample, p is the window sliding step length, and n-s-p m is more than or equal to 0 and less than p; the number of samples of the original dataset was expanded to N × (m + 1);
(22) and (6) normalizing the data. The original data set after data amplification is normalized,
(23) pixel level inverse transform. And performing reciprocal transformation on partial channels in the normalized original data set:
wherein k is the number of the sensor unit needing inverse transformation;
(24) and (4) channel-level random scale transformation. Dividing the processed original data set into a training set and a testing set, carrying out random scale transformation on each sample in the training set, and amplifying the number of the samples of the training set by M times, wherein M is the number of times of the random scale transformation;
(25) and (4) pixel level power function transformation. Performing pixel-level power function transformation on each sample in the training set and the test set:
each sample is takenThe number of channels in (a) is increased from K to K (q +1), wherein K is the number of gas sensitive units of the gas sensor array, and q is the number of power functions.
Preferably, the adopted multi-dimensional time series signal feature extraction backbone network is a multi-stage one-dimensional residual block, each one-dimensional residual block comprises a plurality of residual bottleneck structures, each bottleneck structure adopts 3 one-dimensional convolution layers connected in series to perform feature extraction on the multi-dimensional time series signal, convolution kernels of the bottleneck structures are 1 × 1, 3 × 1 and 1 × 1 in sequence, and a batch normalization layer and a ReLU activation layer follow each one-dimensional convolution layer.
Preferably, a channel and time attention module is added on top of each residual bottleneck structure; the channel attention module and the time attention module are arranged in a serial or parallel mode, and when the channel attention module and the time attention module are arranged in a parallel mode, improved characteristic images are fused by adopting pixel-level addition operation;
the input of the channel attention module is a feature map F of the previous layer, and the output is
Wherein
Point-by-point multiplication; channel attention map MC(F) Is obtained by the following formula:
wherein, AvgPool and MaxPool are average pooling operation and maximum pooling operation respectively, MLP represents multilayer perceptron with shared weight, W0∈RC/r×CAnd W1∈RC×C/rRepresenting the weight of the MLP, wherein r is the compression rate, "+" represents point-by-point addition, and sigma represents a sigmoid activation function;
the input of the time attention module is a feature map F of the previous layer, and the output is
Channel attention map MT(F) ByThe following formula gives:
wherein AvgPool and MaxPool are average pooling operation and maximum pooling operation, respectively, f7×1Representing a multilayer perceptron with shared weight, "; "denotes a connection on a channel.
In order to achieve the purpose, in the aspect of establishing long-range connection of a time sequence signal, two branch networks are adopted to simultaneously extract complementary global static characteristics and long-range dynamic characteristics, so that global information corresponding to an artificial characteristic engineering method is reserved, long-range time sequence information is added, and the odor recognition performance can be effectively improved through the fused characteristics. The global feature extraction network branch adopts global average pooling operation to calculate the average value of each channel time sequence signal, the output of the average value is a one-dimensional feature vector, and the length of the feature vector is consistent with the channel number of the output feature map of the previous layer of network; the long-range dynamic feature extraction network branch adopts a long-and-short-term memory network to model the long-range link in the multidimensional time series signal, and the output of the long-range link is a one-dimensional feature vector; and finally, fusing the one-dimensional feature vectors output by the plurality of network branches together to serve as the output of the stage.
Preferably, the deep neural network takes the output of the cross entropy loss function as a feedback signal, fine tuning is carried out on the weight of each layer of the network by adopting a back propagation algorithm, and the odor recognition precision is continuously improved by the iteration mode. Meanwhile, the types of the sensors suitable for the purposes are identified by analyzing the contribution degree of each sensor to the identification result, the combination mode of the gas sensor array is optimized, and a basis is provided for developing new sensors.
Generally, compared with the prior art, the technical scheme of the invention has the following beneficial effects:
(1) according to the invention, the hierarchical characteristics of time sequence response data of the gas sensor array to different odors are automatically extracted by deep learning, the complementary global static characteristics and long-range dynamic characteristics are simultaneously extracted by adopting a plurality of branch networks, the odor identification performance is greatly improved by the fused characteristics, and then the odor label is output by the classifier, so that high-sensitivity and specific odor identification is realized;
(2) the invention provides a novel one-dimensional convolution backbone network with residual connection, channels and a time attention mechanism, so that an original signal can obtain a differentiable intermediate representation, the method has the characteristics of capacity of virtually amplifying the number of sensors and high operation efficiency, and the defect of information loss when the characteristics are manually extracted by the traditional method can be avoided;
(3) the invention inputs the original response curve cluster of the gas sensor array into the odor identification network, ensures the integrity of odor information, and simultaneously adopts a series of data preprocessing and amplification technologies to make the data more suitable for hierarchical feature extraction.
Drawings
Fig. 1 is an overall flow chart of the artificial olfactory system odor identification method based on the one-dimensional convolutional neural network and the recurrent neural network provided by the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention provides an odor identification method based on a gas sensor and deep learning, which specifically comprises the following steps of:
(1) obtaining a response curve cluster of the odor to be detected through a gas sensor array;
(2) carrying out data preprocessing and data amplification on the response curve cluster to obtain a sensing signal;
(3) extracting the multi-dimensional time series signal characteristics of the backbone network for the sensing signals, and simultaneously extracting global characteristics and long-range dynamic characteristics;
(4) and performing multi-mode feature fusion and classification to complete the identification of the odor to be detected.
There are mainly four implementation parts: 1) obtaining an odor response curve cluster through a gas sensor array; 2) data preprocessing and amplification; 3) a multi-channel time sequence signal feature extraction backbone network; 4) extracting a branch network from the global static characteristics and the long-range dynamic characteristics; 5) a classifier and a loss function. The steps of the present invention will be described in detail below.
The invention adopts a gas sensor array and a signal acquisition module to construct artificial olfaction system hardware, which comprises a sampling system (an air pump), a gas sensor array (comprising 6 semiconductor gas sensors) and a data acquisition module (a data acquisition card).
The data preprocessing and amplification process mainly comprises the following steps:
(21) raw data set
Containing N original data samples and corresponding labels, wherein each original sample
Contains K sensor units. Each original sample TiComprises a plurality of window slices, the window slices are defined as
Wherein i is the time label of the start time of the window slice, and j is the time label of the end time.
Sliding a window of length s over an original sample of length n to obtain m +1 time series slices: sliding (T, S) { S }1：s,S1+p：s+p,…,S1+p*m：s+p*mAnd f, wherein the labels of all window slices are the same as the original sample, p is the window sliding step, and 0 ≦ (n-s-p × m) < p. The number of samples of the original data set was expanded to N × (m + 1).
(22) Normalizing the data set after sample number amplification:
(23) and performing reciprocal transformation on part of channels in the normalized data set sample:
where k is the number of the sensor unit that needs to be inverted.
(24) Dividing the preprocessed and amplified data set into a training set and a testing set, and carrying out random scale transformation on each sample in the training set: s't＝λ·St,λ∈(1,1.1)。
(25) Performing pixel-level power function transformation on each sample in the training set and the test set:
and amplifying the number of channels of each sample from K to K (q +1), wherein K is the number of gas sensitive units of the gas sensor array, and q is the number of power functions.
For multi-channel time sequence signal feature extraction, training the whole network through a cross entropy loss function, wherein the whole network comprises a one-dimensional residual error network, a time attention mechanism and a channel attention mechanism;
(1) one-dimensional residual error network: the one-dimensional residual network is similar to the two-dimensional version, comprising a first one-dimensional convolutional layer and a plurality of repeated stages. Each stage stacks a plurality of one-dimensional residual blocks. The structure of each residual block stacks multiple 1 x 1 convolutional layers and 3 x 1 convolutional layers with batch normalization and ReLU activation layers and forms a bottleneck structure.
(2) The channel attention mechanism is as follows: for the one-dimensional feature map F, it is multiplied point-by-point:
channel attention map MC(F) Is obtained by the following formula:
wherein AvgPool and MaxPool are average pooling operation and maximum pooling operation on a time axis respectively, MLP represents a multilayer perceptron with shared weight, W0∈RC/r×CAnd W1∈RC×C/rRepresents the weight of the MLP, r is the compression ratio, "+" represents point-by-point addition, and σ represents the sigmoid activation function.
(3) Time attention mechanism: for the one-dimensional feature map F, it is multiplied point-by-point:
time attention map MT(F) Is obtained by the following formula:
where AvgPool and MaxPool are the average pooling operation and maximum pooling operation on the channel, respectively, f7×1Representing a multilayer perceptron with shared weight, "; "denotes a connection on a channel.
(4) The channel attention mechanism and the time attention mechanism can be arranged in a serial or parallel mode and integrated into each one-dimensional residual block.
For the extraction of global static features and long-range dynamic features, on one hand, a one-dimensional multi-channel feature map is converted into a one-dimensional feature vector by adopting one-dimensional global average pooling operation, and the length of the feature vector is consistent with the number of channels of the previous layer of network output feature map, so that the global information of each channel is obtained; on the other hand, firstly, the average pooling operation is adopted to extract high-level semantic features and enlarge the receptive field, and then the one-dimensional multi-channel feature map with the shortened length is input into the long-time and short-time memory network to obtain the one-dimensional feature vector containing the long-range dynamic information. Finally, the feature vectors whose information is complementary are connected together as input to the classifier.
Classifying the fused global static characteristics and long-range dynamic characteristics by adopting three full-connection layers and one SoftMax layer, and outputting the prediction probability P of each class as { P }1,p2,…,pcWhere c is the total number of classes. And (4) adopting a cross entropy loss function to supervise the odor recognition network for training.
The invention provides a smell identification method based on a gas sensor and deep learning. The one-dimensional residual error network can be used for well extracting the multi-dimensional time series signal characteristics, and the subsequent extraction of global characteristics and long-range characteristics is facilitated. In addition, a multi-dimensional time series signal characteristic representation with higher discrimination is learned by adopting a channel and time attention network, so that the multi-dimensional time series signal characteristic representation has good robustness on measurement noise. In order to further improve the identification precision, a global pooling branch and a recurrent neural network branch are adopted for extracting and fusing complementary features. Based on these operations, the present invention not only achieves high recognition accuracy, but also enables odor recognition in real time.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (4)
1. A gas sensor and deep learning-based odor identification method is characterized by comprising the following steps:
(1) acquiring a response curve cluster of the odor to be detected through a gas sensor array;
(2) carrying out data preprocessing and data amplification on the response curve cluster to obtain a sensing signal; the method specifically comprises the following steps:
(21) raw data set
Containing N original samples and corresponding labels yrWherein each original sample
Comprises K gas sensor units, wherein the gas sensor units are arranged in a vertical direction,
the response curve of the r original sample on the sensor unit I is shown; each original sample TrComprises a plurality of window slices, the window slices are defined as
Wherein
Slicing the window Si：jA response value on the gas sensor at the time i, i is the starting time of the window slice, j is the ending time of the window slice, and n is the length of the original sample;
sliding a window with the length of S on an original sample with the length of n to obtain m +1 time sequence slices St：Slicing(Tr，s)＝{S1：s，S1+p：s+p，…，S1+p*m：s+p*m"where sliding (-) is a data amplification function with the input of the original sample TrAnd slice length s, the output is m +1 time sequence slices; the labels of all window slices are the same as the original sample, p is the window sliding step length, and n-s-p × m is more than or equal to 0 and less than p; the number of samples of the original dataset was expanded to N × (m + 1);
(22) the window slices after data amplification were normalized,
where min (-) is a minimum function, max (-) is a maximum function, StFor data expansionAugmented Window slice, S'tSlicing the normalized window;
(23) and performing reciprocal transformation on the normalized window slice part channel:
where k is the number of the sensor unit that needs to be inverted,
the channel with the number of k is the sensor unit in the normalized window slice;
(24) dividing the processed original data set into a training set and a testing set, carrying out random scale transformation on each sample in the training set, and amplifying the number of the samples of the training set by M times, wherein M is the number of times of the random scale transformation;
(25) performing pixel-level power function transformation on each sample in the training set and the test set:
amplifying the number of channels of each sample from K to K (q +1), wherein x is the value of each pixel point in each sample,
outputting a value of a qth power function of each pixel point in each sample, wherein K is the number of gas sensitive units of the gas sensor array, and q is the number of the power functions; (3) extracting the multi-dimensional time series signal characteristics of the backbone network for the sensing signals, and simultaneously extracting global characteristics and long-range dynamic characteristics; the adopted multi-dimensional time series signal feature extraction backbone network is a multi-stage one-dimensional residual block, each one-dimensional residual block comprises a plurality of residual bottleneck structures, each bottleneck structure adopts 3 one-dimensional convolution layers connected in series to perform feature extraction on the multi-dimensional time series signal, convolution kernels of the bottleneck structures are 1 multiplied by 1, 3 multiplied by 1 and 1 multiplied by 1 in sequence, and each one-dimensional convolution layer is followed by a batch normalization layer and a ReLU activation layer; adding a channel and time attention module at the top of each residual bottleneck structure; channelThe attention module and the time attention module are arranged in a series or parallel mode, and when the attention module and the time attention module are arranged in a parallel mode, improved characteristic images are fused by adopting pixel-level addition operation;
the input of the channel attention module is a feature map F of the previous layer, and the output is
Wherein
Point-by-point multiplication; channel attention map MC(F) Is obtained by the following formula:
wherein, AvgPool and MaxPool are average pooling operation and maximum pooling operation respectively, MLP represents multilayer perceptron with shared weight, W0∈RC/r×CAnd W1∈RC×C/rRepresenting the weight of the MLP, wherein r is the compression rate, "+" represents point-by-point addition, and sigma represents a sigmoid activation function;
the input of the time attention module is a feature map F of the previous layer, and the output is
Channel attention map MT(F) Is obtained by the following formula:
wherein AvgPool and MaxPool are average pooling operation and maximum pooling operation, respectively, f7×1Multilayer perceptron representing weight sharing "(ii) a "denotes a connection on a channel;
(4) and performing multi-mode feature fusion and classified output of smell labels to finish the identification of the smell to be detected.
2. The odor identification method based on the gas sensor and the deep learning as claimed in claim 1, wherein an artificial olfaction system hardware base is constructed by adopting a gas sensor array and a signal acquisition module, response curve clusters to different odors are obtained through the gas sensor array, the raw data is directly used as an input sample of an odor identification deep neural network, and data dimension reduction or artificial feature extraction is not performed.
3. The method as claimed in claim 1, wherein the global feature extraction network branch adopts global average pooling operation to calculate the average value of each channel time series signal, the output is a one-dimensional feature vector, and the length of the feature vector is consistent with the number of channels of the output feature map of the previous network; the long-range dynamic feature extraction network branch adopts a long-and-short-term memory network to model the long-range link in the multidimensional time series signal, and the output of the long-range link is a one-dimensional feature vector; the one-dimensional feature vectors output by the multiple network branches are fused together and used as the output of the stage.
4. The method as claimed in claim 3, wherein the input feature map is compressed by average pooling in the long-range dynamic feature extraction network branch, and then the long-term memory network is input, so as to improve the execution efficiency of the network branch.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010229387.3A CN111443165B (en) | 2020-03-27 | 2020-03-27 | Odor identification method based on gas sensor and deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010229387.3A CN111443165B (en) | 2020-03-27 | 2020-03-27 | Odor identification method based on gas sensor and deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111443165A CN111443165A (en) | 2020-07-24 |
| CN111443165B true CN111443165B (en) | 2021-06-11 |
Family
ID=71655871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010229387.3A Active CN111443165B (en) | 2020-03-27 | 2020-03-27 | Odor identification method based on gas sensor and deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111443165B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112433028B (en) * | 2020-11-09 | 2021-08-17 | 西南大学 | Electronic nose gas classification method based on memristor cell neural network |
| CN112816122B (en) * | 2020-12-31 | 2023-04-07 | 武汉地震工程研究院有限公司 | Bolt tightness degree monitoring method based on deep learning and piezoelectric active sensing |
| CN112925822B (en) * | 2021-02-08 | 2022-09-27 | 山东大学 | Time series classification method, system, medium and device based on multi-representation learning |
| CN113505654A (en) * | 2021-06-17 | 2021-10-15 | 浙江优特轴承有限公司 | Bearing health state identification method based on multi-view attention network |
| CN113723442B (en) * | 2021-07-08 | 2024-02-20 | 华中科技大学 | Electronic nose gas identification method, system, electronic equipment and storage medium |
| CN113533654A (en) * | 2021-07-21 | 2021-10-22 | 深圳盛方科技有限公司 | Intelligent gas identification method, system, equipment and computer readable storage medium |
| CN113267535A (en) * | 2021-07-21 | 2021-08-17 | 深圳盛方科技有限公司 | Intelligent gas identification method and device |
| CN114252560A (en) * | 2021-12-24 | 2022-03-29 | 无锡学院 | Mixed gas identification method based on improved one-dimensional convolutional neural network |
| CN114067190B (en) * | 2022-01-17 | 2022-04-15 | 广东工业大学 | Health state correlation model construction method and system based on human body odor signals |
| CN114527241B (en) * | 2022-02-21 | 2023-08-04 | 同济大学 | Wavelet transformation-capsule neural network cascading type gas identification method and device |
| CN115684316B (en) * | 2022-11-08 | 2023-12-22 | 中耕生态环境科技(广州)有限公司 | Smell recognition method of bionic electronic nose based on MOS gas sensor array |
| CN116189800B (en) * | 2023-02-23 | 2023-08-18 | 深圳大学 | Pattern recognition method, device, equipment and storage medium based on gas detection |
| CN117761123B (en) * | 2023-12-18 | 2024-05-24 | 山东工商学院 | Quantitative estimation method for gas concentration of electronic nose system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107510452A (en) * | 2017-09-30 | 2017-12-26 | 扬美慧普（北京）科技有限公司 | A kind of ECG detecting method based on multiple dimensioned deep learning neutral net |
| CN107527144A (en) * | 2017-08-21 | 2017-12-29 | 复旦大学 | A kind of detection method of financial field connected transaction |
| CN108564110A (en) * | 2018-03-26 | 2018-09-21 | 上海电力学院 | A kind of Air Quality Forecast method based on clustering algorithm |
| WO2019077494A1 (en) * | 2017-10-16 | 2019-04-25 | King Abdullah University Of Science And Technology | System, apparatus, and method for sequence-based enzyme ec number prediction by deep learning |
| WO2019178561A2 (en) * | 2018-03-16 | 2019-09-19 | The United States Of America, As Represented By The Secretary, Department Of Health & Human Services | Using machine learning and/or neural networks to validate stem cells and their derivatives for use in cell therapy, drug discovery, and diagnostics |
| CN110832596A (en) * | 2017-10-16 | 2020-02-21 | 因美纳有限公司 | Deep convolutional neural network training method based on deep learning |
-
2020
- 2020-03-27 CN CN202010229387.3A patent/CN111443165B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527144A (en) * | 2017-08-21 | 2017-12-29 | 复旦大学 | A kind of detection method of financial field connected transaction |
| CN107510452A (en) * | 2017-09-30 | 2017-12-26 | 扬美慧普（北京）科技有限公司 | A kind of ECG detecting method based on multiple dimensioned deep learning neutral net |
| WO2019077494A1 (en) * | 2017-10-16 | 2019-04-25 | King Abdullah University Of Science And Technology | System, apparatus, and method for sequence-based enzyme ec number prediction by deep learning |
| CN110832596A (en) * | 2017-10-16 | 2020-02-21 | 因美纳有限公司 | Deep convolutional neural network training method based on deep learning |
| WO2019178561A2 (en) * | 2018-03-16 | 2019-09-19 | The United States Of America, As Represented By The Secretary, Department Of Health & Human Services | Using machine learning and/or neural networks to validate stem cells and their derivatives for use in cell therapy, drug discovery, and diagnostics |
| CN108564110A (en) * | 2018-03-26 | 2018-09-21 | 上海电力学院 | A kind of Air Quality Forecast method based on clustering algorithm |
Non-Patent Citations (5)
| Title |
|---|
| "Development of a LeNet-5 Gas Identification CNN Structure for Electronic Noses";Guangfen Wei et al.;《Sensors》;20191231;摘要，第2页2节，第4页第1-2段，第9-10页5.1-5.2节 * |
| "电力线路无人机巡检图像的目标检测";刘欢;《万方数据库》;20191204;第1-56页 * |
| A Fast and Robust Gas Recognition Algorithm Based on Hybrid Convolutional and Recurrent Neural Network";XIAOFANG PAN et al;《IEEE Access》;20190809;摘要 * |
| 基于自适应最优核和卷积神经网络的气液两相流流型识别方法;翁润滢等;《化工学报》;20180919(第12期);第5066-5072页 * |
| 气体传感器阵列中特征参数的提取与优化;邹小波等;《传感技术学报》;20030115(第04期);第282-286页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111443165A (en) | 2020-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111443165B (en) | Odor identification method based on gas sensor and deep learning | |
| Gamboa et al. | Validation of the rapid detection approach for enhancing the electronic nose systems performance, using different deep learning models and support vector machines | |
| CN103544392B (en) | Medical science Gas Distinguishing Method based on degree of depth study | |
| Zhang et al. | Real-time sow behavior detection based on deep learning | |
| Kibriya et al. | Tomato leaf disease detection using convolution neural network | |
| Liu et al. | Review on algorithm design in electronic noses: Challenges, status, and trends | |
| CN110895705B (en) | Abnormal sample detection device, training device and training method thereof | |
| CN111340132B (en) | Machine olfaction mode identification method based on DA-SVM | |
| CN110880369A (en) | Gas marker detection method based on radial basis function neural network and application | |
| CN116612335B (en) | Few-sample fine-granularity image classification method based on contrast learning | |
| CN114049525A (en) | Fusion neural network system, device and method for identifying gas types and concentrations | |
| CN117892915A (en) | Commodity carbon label generation method and system based on accounting unit | |
| Qu et al. | Open-set gas recognition: A case-study based on an electronic nose dataset | |
| Qian et al. | A fire monitoring and alarm system based on channel-wise pruned YOLOv3 | |
| Shi et al. | Feature extraction and classification of cataluminescence images based on sparse coding convolutional neural networks | |
| CN111242028A (en) | Remote sensing image ground object segmentation method based on U-Net | |
| CN114781484A (en) | Cancer serum SERS spectrum classification method based on convolutional neural network | |
| CN114252560A (en) | Mixed gas identification method based on improved one-dimensional convolutional neural network | |
| CN112071423A (en) | Machine learning-based immunochromatography concentration detection method and system | |
| CN111191475A (en) | Passive behavior identification method based on UHF RFID | |
| CN116563603A (en) | Small sample open set identification method based on global-local energy collaborative characterization | |
| De Stefano et al. | Evolutionary computation to implement an IoT-based system for water pollution detection | |
| Alaeddine et al. | Plant leaf disease classification using Wide Residual Networks | |
| Zhu et al. | Rapid freshness prediction of crab based on a portable electronic nose system | |
| Ma | DeepQuality: mass spectra quality assessment via compressed sensing and deep learning |
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 |