CN106980773B - Gas-liquid diphase detection system data fusion method based on artificial smell-taste technology - Google Patents

Gas-liquid diphase detection system data fusion method based on artificial smell-taste technology Download PDF

Info

Publication number
CN106980773B
CN106980773B CN201710391501.0A CN201710391501A CN106980773B CN 106980773 B CN106980773 B CN 106980773B CN 201710391501 A CN201710391501 A CN 201710391501A CN 106980773 B CN106980773 B CN 106980773B
Authority
CN
China
Prior art keywords
response
electrode array
artificial
data
taste
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
Application number
CN201710391501.0A
Other languages
Chinese (zh)
Other versions
CN106980773A (en
Inventor
刘涛
周雯
林远
刘鑫
田菲
殷俊兰
龚清峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing University
Original Assignee
Chongqing University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing University filed Critical Chongqing University
Priority to CN201710391501.0A priority Critical patent/CN106980773B/en
Publication of CN106980773A publication Critical patent/CN106980773A/en
Application granted granted Critical
Publication of CN106980773B publication Critical patent/CN106980773B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
    • 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
    • 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
    • G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method, e.g. intermittent, or the display, e.g. digital
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00—Subject matter not provided for in other main groups of this subclass
    • 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
    • G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method, e.g. intermittent, or the display, e.g. digital
    • G01N2033/0068—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method, e.g. intermittent, or the display, e.g. digital using a computer specifically programmed
    • 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

Abstract

The invention belongs to the technical field of gas phase and liquid phase chemical analysis and detection, and discloses a gas-liquid diphase detection system data fusion method based on an artificial smell-taste technology, which comprises the following steps: the method comprises the steps of acquiring an original response of an electrode array of an artificial taste system in a one-time working process, calculating the position of a single-period electrode array response and acquiring the searched single-period electrode array response; the redundant information is removed after the electrode array signal searching stage is processed, the original response length is reduced from N to M, the data dimension reduction method is utilized in the time sequence length optimization stage, and the data length of the electrode array and the gas sensor array response is optimized on the premise of keeping the main response information, so that the data lengths of the two responses are consistent. The invention reduces the complexity of the data and reduces the dimension of the original data to 58; part of interference is removed, so that the recognition accuracy is improved to a certain extent.

Description

Gas-liquid diphase detection system data fusion method based on artificial smell-taste technology
Technical Field
The invention belongs to the technical field of gas-phase and liquid-phase chemical analysis and detection, and particularly relates to a gas-liquid dual-phase detection system data fusion method based on an artificial smell-taste technology.
Background
As a novel bionic gas phase analysis means, the artificial olfactory system has the advantages of high analysis speed, simple and convenient operation and the like, and the structure of the artificial olfactory system generally comprises: a gas sensor array, a gas sample injection system, a pattern recognition algorithm and the like. Artificial taste systems are focused on analyzing liquid phase samples, generally comprising: electrode arrays with cross sensitivity simulate human taste perception cells, and pattern recognition algorithms simulate human thinking processes for analysis and judgment. Besides the traditional chemical method, the artificial olfactory and gustatory systems are integrated, so that the gas-liquid dual-phase detection of the same object to be detected is completed, and the method has practical significance. The response speed of the sensor in the artificial olfactory system is related to the airflow velocity in the sample injection system, and the change frequency order of magnitude is between 1 and 10 hertz; whereas artificial taste systems typically have an analog signal on their working electrode in the range of tens to thousands of hertz due to the high frequency pulses used as system excitation. To facilitate the digitization process, the high frequency analog signal needs to be converted into a digital signal. To reflect the details of the high frequency analog signal as truly as possible, the sampling rate in the analog-to-digital conversion process of the artificial taste system is typically much higher than that of the artificial olfactory system; the data dimensions that result in the digitized responses of the two systems are greatly different, thereby negatively impacting the use of subsequent pattern recognition methods.
In summary, the problems of the prior art are: the imbalance of the response of the artificial taste and olfactory system in the data dimension can bias the judgment result of the subsequent pattern recognition method to the artificial taste system with larger data dimension, so as to weaken the influence of the artificial olfactory system; so that the overall judgment accuracy of the artificial olfactory-gustatory system is insufficient. Therefore, there is a need for a data fusion method that unifies the response dimensions of artificial olfactory and gustatory systems while preserving as much as possible the useful information in the original response.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a gas-liquid dual-phase detection system data fusion method based on an artificial smell-taste technology.
The invention is realized in such a way that the gas-liquid diphase detection system data fusion method based on the artificial smell-taste technology comprises the following steps:
step one, the original response of the electrode array of the artificial taste system acquired in one working process is calculated, the position of the response of the single-period electrode array is calculated, and the searched response of the single-period electrode array is acquired;
and step two, after the processing of the electrode array signal searching stage, redundant information is removed, and meanwhile, the length of the original response is reduced from N to M, and the data dimension reduction method is utilized in the time sequence length optimization stage, so that the data length of the electrode array and the gas sensor array response is optimized on the premise of keeping the main response information, and the data lengths of the two responses are consistent.
Further, the gas-liquid dual-phase detection system data fusion method based on the artificial smell-taste technology comprises the following steps: an electrode array signal searching stage and a time sequence length optimizing stage.
Further, the electrode array signal search stage includes:
1) The correlation coefficient matrix c= { C is calculated as follows i' }：
Figure BDA0001307620960000021
Wherein M is less than N and M, N is a natural number; the single period excitation pulse signal is denoted s (t) and t e {1,2, …, M }; the original response of the electrode of the artificial taste system is x k (i) Representing the original response of the kth working electrode at time i and i e {1,2, …, N };
2) Calculating the position of the response of the single-period electrode array according to the maximum element in the correlation coefficient matrix C and obtaining the searched response X of the single-period electrode array 1 ：
Figure BDA0001307620960000022
Further, the time sequence length optimization stage specifically includes:
1) Time of gas sensorMean value of the etch response
Figure BDA0001307620960000031
And the mean value of the response of the electrodes at each moment ∈ ->
Figure BDA0001307620960000032
Figure BDA0001307620960000033
Figure BDA0001307620960000034
Wherein r is p (i) Representing the response of the P-th gas sensor at the ith moment in a working period of the artificial olfaction system, wherein i is {1,2, …, N' }, P is {1,2, …, P }; order the
Figure BDA0001307620960000035
X 1 Representing a monocycle electrode array response of the artificial taste system;
2) Calculating a similarity matrix
Figure BDA0001307620960000036
And->
Figure BDA0001307620960000037
Figure BDA0001307620960000038
Figure BDA0001307620960000039
Where (i, j) e {1,2, …, N' } (t, l) e {1,2, …, M };
3) For similarity matrix S r And S is x Respectively decomposing the characteristic values and carrying out characteristic values and characteristic vectors according to the characteristic valuesDescending order of characteristic values is obtained respectively
Figure BDA00013076209600000310
And->
Figure BDA00013076209600000311
Feature vector matrix EV r And EV x Obtaining a mapped artificial olfactory system response matrix R 1 And artificial taste response matrix X 2 ：
R 1 ＝R·EV r ；
X 2 ＝X 1 ·EV x ；
4) Defining a eigenvalue contribution ratio
Figure BDA00013076209600000312
Wherein e i Representing the characteristic values>
Figure BDA00013076209600000313
Representing the sum of the first j eigenvalues; taking eta as a fixed value between (0, 1), if for +.>
Figure BDA00013076209600000314
The existence of the first n eigenvalues satisfies lambda.gtoreq.eta
Figure BDA00013076209600000315
Satisfying the first m eigenvalues and satisfying lambda not less than eta, the response length after data fusion is beta:
Figure BDA0001307620960000041
5) R is taken respectively 1 And X 2 As a result of the fusion of the final system original response. If R is 1 Or X 2 And if the number of columns is smaller than beta, adding zero to complement.
Another object of the present invention is to provide an artificial olfactory system using the method for data fusion of a gas-liquid dual-phase detection system based on artificial olfactory-gustatory technology.
The invention also aims to provide an artificial taste system applying the gas-liquid diphase detection system data fusion method based on the artificial smell-taste technology.
The invention has the advantages and positive effects that: the electrode array and the gas sensor array response have the same data dimension on the premise of keeping useful information as far as possible through electrode array signal searching and time sequence length optimization, so that the data are fully fused, and the accuracy of a subsequent pattern recognition method is improved; as can be seen from the results in table 1, the method of the present invention reduces the complexity of the data: for electrode influence, the ratio of the original response time dimension of the olfactory and gustatory systems is changed from 20:1 to 1:1, and the data balance is improved; therefore, on the premise of adopting the same pattern recognition method, the recognition accuracy is improved from 61.9% to 76.2%. In addition, the data input amount of the pattern recognition method is reduced from 228000 (=30000×6+1500×32) to 2204 (=58×6+58×32), which is beneficial to reducing the computational complexity and the computational overhead of the pattern recognition method.
Drawings
Fig. 1 is a flow chart of a data fusion method of a gas-liquid dual-phase detection system based on an artificial smell-taste technology provided by an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The principle of application of the invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for fusing data of a gas-liquid dual-phase detection system based on an artificial smell-taste technology provided by the embodiment of the invention comprises the following steps:
s101: the method comprises the steps of acquiring an original response of an electrode array of an artificial taste system in a one-time working process, calculating the position of a single-period electrode array response and acquiring the searched single-period electrode array response;
s102: after the electrode array signal searching stage is processed, redundant information is removed, and meanwhile, the length of the original response is reduced from N to M, so that the original data length of the electrode array signal searching stage is more approximate to that of the gas sensor array of the artificial olfactory system; and in the time sequence length optimization stage, the data length of the response of the electrode array and the gas sensor array is optimized by using a data dimension reduction method on the premise of keeping the main response information, so that the data lengths of the two responses are consistent.
The gas-liquid dual-phase detection system data fusion method based on the artificial smell-taste technology provided by the embodiment of the invention comprises the following steps: an electrode array signal searching stage and a time sequence length optimizing stage.
1. Electrode array signal search stage
The artificial taste system has higher sampling rate and the corresponding excitation pulse has shorter single-cycle duration (in seconds), while the artificial olfactory system has slower sampling rate and longer single-cycle working time (in minutes), so that the electrode array signal of the artificial taste system has periodicity due to the continuous repetition of the excitation pulse.
The method specifically comprises the following steps:
assume that: the original response X= { X of the electrode array of the artificial taste system collected in one working process k (i) X, where x k (i) Representing the original response of the kth working electrode at time i and i e {1,2, …, N }, K e {1,2, …, K }; the single period excitation pulse signal is denoted s (t) and t.epsilon.1, 2, …, M is present where M < N.
1) The correlation coefficient matrix c= { C is calculated according to the following formula i' }：
Figure BDA0001307620960000051
2) Calculating the position of the response of the single-period electrode array according to the maximum element in the correlation coefficient matrix C and obtaining the searched response X of the single-period electrode array 1 ：
Figure BDA0001307620960000061
2. Time series length optimization stage
After the electrode array signal searching stage is processed, redundant information is removed, and meanwhile, the length of the original response is reduced from N to M, so that the original data length of the electrode array signal searching stage is more approximate to that of the gas sensor array of the artificial olfactory system; and in the time sequence length optimization stage, the data length of the response of the electrode array and the gas sensor array is optimized by using a data dimension reduction method on the premise of keeping the main response information, so that the data lengths of the two responses are consistent.
The method specifically comprises the following steps:
assume that: gas sensor array raw response r= { R of artificial olfactory system p (i) -where r p (i) Represents the response of the P-th gas sensor at time i and i e {1,2, …, N' }, P e {1,2, …, P }. The original response is 1 period in the whole working process; response of single period electrode array to X 1 Expressed as:
Figure BDA0001307620960000062
1) Averaging the responses of the gas sensor at each moment
Figure BDA0001307620960000063
And the mean value of the response of the electrodes at each moment ∈ ->
Figure BDA0001307620960000064
Figure BDA0001307620960000065
Figure BDA0001307620960000066
2) The similarity matrix is calculated as follows
Figure BDA0001307620960000067
And->
Figure BDA0001307620960000068
Figure BDA0001307620960000069
Figure BDA00013076209600000610
Where (i, j) e {1,2, …, N' } (t, l) e {1,2, …, M }.
3) For similarity matrix S r And S is x Respectively decomposing the characteristic values, and arranging the characteristic values and the characteristic vectors thereof in descending order according to the characteristic values to respectively obtain the characteristic values
Figure BDA0001307620960000071
And->
Figure BDA0001307620960000072
Feature vector matrix EV r And EV x The mapped artificial olfactory system response matrix R can be obtained 1 And artificial taste response matrix X 2 ：
R 1 ＝R·EV r ；
X 2 ＝X 1 ·EV x ；
4) Defining a eigenvalue contribution ratio
Figure BDA0001307620960000073
Wherein e i Representing the characteristic values>
Figure BDA0001307620960000074
Representing the sum of the first j eigenvalues. Taking eta as a fixed value between (0, 1), if for +.>
Figure BDA0001307620960000075
There are first n eigenvaluesMeet lambda not less than eta for
Figure BDA0001307620960000076
Satisfying the first m eigenvalues and satisfying lambda not less than eta, the response length after data fusion is beta:
Figure BDA0001307620960000077
5) R is taken respectively 1 And X 2 As a result of the fusion of the final system original response. If R is 1 Or X 2 And if the number of columns is smaller than beta, adding zero to complement.
The following describes the application effects of the present invention in detail with reference to specific examples.
7 substances such as black tea, green tea, puer tea, oolong tea, red wine, white wine, beer and the like are analyzed by using a gas-liquid double-phase detection system of an artificial smell-taste technology. Each material was collected at 9 times at different concentrations. In the data acquisition process, the number of gas sensors P=32, the number of working electrodes K=6, the sampling rate of an artificial olfactory system is 1Hz, the sampling rate of the artificial gustatory system is 20Hz, the acquisition time length is 25min, 1500 gas sensors are acquired in total, and 30000 gas sensors are acquired in total. Let η=0.9, the electrode array excitation pulse length is 150, and after calculation by the method of the present invention, β=58 is obtained.
In order to verify the effect of the data fusion method, 6 times of data acquisition results are selected from each substance for training, the rest 3 times are used as test samples, and a nearest neighbor algorithm KNN is used as a classifier for recognition. Two raw data processing methods are employed in table 1: the invention provides a method, and the other method directly adopts original response without data fusion. From the results in Table 1, it can be seen that the method provided by the invention reduces the complexity of the data, changes the ratio of the original data dimension 20:1 into 1:1, and improves the response type balance. The input data quantity is reduced from 228000 (=30000×6+1500×32) to 2204 (=58×6+58×32), so that the complexity and the calculation cost of the pattern recognition method are reduced; .
Table 1 data fusion method identifies accuracy
Figure BDA0001307620960000081
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.

Claims (1)

1. The gas-liquid dual-phase detection system data fusion method based on the artificial smell-taste technology is characterized by comprising the following steps of:
step one, the original response of the electrode array of the artificial taste system acquired in one working process is calculated, the position of the response of the single-period electrode array is calculated, and the searched response of the single-period electrode array is acquired;
step two, after the electrode array signal searching stage is processed, redundant information is removed, the original response length is reduced from N to M, a data dimension reduction method is utilized in the time sequence length optimization stage, and the data length of the electrode array and the gas sensor array response is optimized on the premise of keeping the main response information, so that the data lengths of the two responses are consistent;
the gas-liquid diphase detecting system data fusion method based on the artificial smell-taste technology comprises the following steps: an electrode array signal searching stage and a time sequence length optimizing stage of the second step;
the electrode array signal searching stage comprises the following steps:
1) The correlation coefficient matrix c= { C is calculated as follows i '}：
Figure FDA0004122678660000011
Wherein M is less than N and M, N is a natural number; the single period excitation pulse signal is denoted s (t) and t e {1,2, …, M }; the original response of the electrode of the artificial taste system is x k (i) Representing the original response of the kth working electrode at time i and i e {1,2, …, N };
2) Calculating the position of the response of the single-period electrode array according to the maximum element in the correlation coefficient matrix C and obtaining the searched response X of the single-period electrode array 1 ：
Figure FDA0004122678660000012
The time sequence length optimization stage specifically comprises the following steps:
1) Averaging the responses of the gas sensor at each moment
Figure FDA0004122678660000013
And the mean value of the response of the electrodes at each moment ∈ ->
Figure FDA0004122678660000014
Figure FDA0004122678660000015
Figure FDA0004122678660000016
Wherein r is p (i) Representing the response of the P-th gas sensor at the ith moment in a working period of the artificial olfaction system, wherein i is {1,2, …, N' }, P is {1,2, …, P }; order the
Figure FDA0004122678660000019
X1 represents the monocycle electrode array response of the artificial taste system;
2) Calculating a similarity matrix
Figure FDA0004122678660000017
And->
Figure FDA0004122678660000018
Figure FDA0004122678660000021
Figure FDA0004122678660000022
Where (i, j) e {1,2, …, N' } (t, l) e {1,2, …, M };
3) For similarity matrix S r And S is x Respectively decomposing the characteristic values, and arranging the characteristic values and the characteristic vectors thereof in descending order according to the characteristic values to respectively obtain the characteristic values
Figure FDA0004122678660000023
And->
Figure FDA0004122678660000024
Feature vector matrix EV r And EV x Obtaining a mapped artificial olfactory system response matrix R 1 And artificial taste response matrix X 2 ：
R1＝R·EVr；
X2＝X1·EVx；
4) Defining a eigenvalue contribution ratio
Figure FDA0004122678660000025
Wherein e i Representing the characteristic values>
Figure FDA0004122678660000026
Representing the sum of the first j eigenvalues; taking eta as a fixed value between (0, 1), if for +.>
Figure FDA0004122678660000027
The presence of the first n eigenvalues satisfies λ.gtoreq.eta.for +.>
Figure FDA0004122678660000028
Satisfying the first m eigenvalues and satisfying lambda not less than eta, the response length after data fusion is beta:
Figure FDA0004122678660000029
5) Respectively taking the front beta columns of R1 and X2 as the final result after the original response of the system is fused; if the number of R1 or X2 columns is less than beta, zero is added to complement.
CN201710391501.0A 2017-05-27 2017-05-27 Gas-liquid diphase detection system data fusion method based on artificial smell-taste technology Active CN106980773B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710391501.0A CN106980773B (en) 2017-05-27 2017-05-27 Gas-liquid diphase detection system data fusion method based on artificial smell-taste technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710391501.0A CN106980773B (en) 2017-05-27 2017-05-27 Gas-liquid diphase detection system data fusion method based on artificial smell-taste technology

Publications (2)

Publication Number Publication Date
CN106980773A CN106980773A (en) 2017-07-25
CN106980773B true CN106980773B (en) 2023-06-06

Family

ID=59343070

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710391501.0A Active CN106980773B (en) 2017-05-27 2017-05-27 Gas-liquid diphase detection system data fusion method based on artificial smell-taste technology

Country Status (1)

Country Link
CN (1) CN106980773B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101996413A (en) * 2009-08-10 2011-03-30 韩国电子通信研究院 Method of encoding haptic information on image, method of decoding haptic information from image and apparatus for processing haptic information for the same
CA2869914A1 (en) * 2012-04-16 2013-10-24 Stephen Charles Trowell Methods and systems for detecting an analyte or classifying a sample
CN105005783A (en) * 2015-05-18 2015-10-28 电子科技大学 Method of extracting classification information from high dimensional asymmetric data
CN105377448A (en) * 2013-02-22 2016-03-02 天那高有限公司 Interactive entertainment apparatus and system and method for interacting with water to provide audio, visual, olfactory, gustatory or tactile effect

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080255949A1 (en) * 2007-04-13 2008-10-16 Lucid Systems, Inc. Method and System for Measuring Non-Verbal and Pre-Conscious Responses to External Stimuli

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101996413A (en) * 2009-08-10 2011-03-30 韩国电子通信研究院 Method of encoding haptic information on image, method of decoding haptic information from image and apparatus for processing haptic information for the same
CA2869914A1 (en) * 2012-04-16 2013-10-24 Stephen Charles Trowell Methods and systems for detecting an analyte or classifying a sample
CN105377448A (en) * 2013-02-22 2016-03-02 天那高有限公司 Interactive entertainment apparatus and system and method for interacting with water to provide audio, visual, olfactory, gustatory or tactile effect
CN105005783A (en) * 2015-05-18 2015-10-28 电子科技大学 Method of extracting classification information from high dimensional asymmetric data

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
侯长军等."基于液体阵列味觉仿生传感器鉴别白酒香型的新方法".《高等学校化学学报》.2013,第34卷(第34期),全文. *
陈栋琳."电子鼻/舌系统设计及气—味信息融合技术应用".《中国优秀硕士学位论文全文数据库 信息科技辑》.2015,(第undefined期),全文. *

Also Published As

Publication number Publication date
CN106980773A (en) 2017-07-25

Similar Documents

Publication Publication Date Title
CN105938116B (en) Gas sensor array concentration detection method based on fuzzy division and model integrated
Chen et al. Identification of the green tea grade level using electronic tongue and pattern recognition
Wei et al. Tracing floral and geographical origins of honeys by potentiometric and voltammetric electronic tongue
CN104792826A (en) System and method for detecting milk freshness based on electronic nose
Lin et al. Lightweight residual convolutional neural network for soybean classification combined with electronic nose
CN101788517A (en) Pungent traditional Chinese medicine odor fingerprint map construction system and method based on bionic olfaction
CN111340132B (en) Machine olfaction mode identification method based on DA-SVM
CN104849321B (en) A kind of method based on smell finger-print quick detection Quality Parameters in Orange
CN103389323A (en) Method for evaluating ages of precious medicinal materials quickly and losslessly
CN107132311A (en) A kind of fast gas recognizer extracted based on frequency domain character
CN113008805A (en) Radix angelicae decoction piece quality prediction method based on hyperspectral imaging depth analysis
Wang et al. Research on air pollution gases recognition method based on lstm recurrent neural network and gas sensors array
Hou et al. A hand-held electronic nose system for rapid identification of Chinese liquors
CN106980773B (en) Gas-liquid diphase detection system data fusion method based on artificial smell-taste technology
Li et al. Local dynamic neural network for quantitative analysis of mixed gases
Shao et al. LightBGM for human activity recognition using wearable sensors
CN109146003A (en) A kind of classifying identification method based on high light spectrum image-forming, apparatus and system
Ren et al. A CNN-Based E-Nose Using Time Series Features for Food Freshness Classification
Anthony et al. Electronic honey quality analyser
CN110633741B (en) Time sequence classification method based on improved impulse neural network
CN111191475A (en) Passive behavior identification method based on UHF RFID
Yang et al. Recognition algorithms in E-nose: A Review
CN115014451A (en) Gas-solid two-phase flow measuring method of multi-network characteristic fusion model
Wójcik et al. Deep learning assisted distinguishing of honey seasonal changes using quadruple voltammetric electrodes
Li et al. Emerging Data Processing Methods for Single‐Entity Electrochemistry

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