CN104849328B - The method that benzoic acid in fruit juice is quickly detected based on electronic tongues - Google Patents
The method that benzoic acid in fruit juice is quickly detected based on electronic tongues Download PDFInfo
- Publication number
- CN104849328B CN104849328B CN201510228898.2A CN201510228898A CN104849328B CN 104849328 B CN104849328 B CN 104849328B CN 201510228898 A CN201510228898 A CN 201510228898A CN 104849328 B CN104849328 B CN 104849328B
- Authority
- CN
- China
- Prior art keywords
- mrow
- benzoic acid
- sample
- msub
- fruit juice
- 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.)
- Expired - Fee Related
Links
- WPYMKLBDIGXBTP-UHFFFAOYSA-N benzoic acid Chemical compound OC(=O)C1=CC=CC=C1 WPYMKLBDIGXBTP-UHFFFAOYSA-N 0.000 title claims abstract description 122
- 239000005711 Benzoic acid Substances 0.000 title claims abstract description 61
- 235000010233 benzoic acid Nutrition 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 39
- 210000002105 tongue Anatomy 0.000 title claims abstract description 37
- 235000015203 fruit juice Nutrition 0.000 title claims abstract description 33
- 238000007637 random forest analysis Methods 0.000 claims abstract description 31
- 239000000243 solution Substances 0.000 claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 235000011389 fruit/vegetable juice Nutrition 0.000 claims abstract description 15
- 241000207199 Citrus Species 0.000 claims abstract description 9
- 235000020971 citrus fruits Nutrition 0.000 claims abstract description 9
- 238000000513 principal component analysis Methods 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims description 22
- 238000003066 decision tree Methods 0.000 claims description 20
- 230000004044 response Effects 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 9
- 235000015205 orange juice Nutrition 0.000 claims description 8
- 239000011550 stock solution Substances 0.000 claims description 7
- UIIMBOGNXHQVGW-UHFFFAOYSA-M Sodium bicarbonate Chemical compound [Na+].OC([O-])=O UIIMBOGNXHQVGW-UHFFFAOYSA-M 0.000 claims description 5
- 238000012952 Resampling Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 239000000706 filtrate Substances 0.000 claims description 4
- 239000000796 flavoring agent Substances 0.000 claims description 4
- 235000019634 flavors Nutrition 0.000 claims description 4
- 238000010438 heat treatment Methods 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 4
- 238000003756 stirring Methods 0.000 claims description 4
- 229910021642 ultra pure water Inorganic materials 0.000 claims description 4
- 239000012498 ultrapure water Substances 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 3
- 229910000030 sodium bicarbonate Inorganic materials 0.000 claims 1
- 235000017557 sodium bicarbonate Nutrition 0.000 claims 1
- 230000014860 sensory perception of taste Effects 0.000 abstract description 6
- 238000004451 qualitative analysis Methods 0.000 abstract description 2
- 239000011259 mixed solution Substances 0.000 abstract 1
- 238000011002 quantification Methods 0.000 abstract 1
- 238000004445 quantitative analysis Methods 0.000 abstract 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract 1
- UHOVQNZJYSORNB-UHFFFAOYSA-N Benzene Chemical compound C1=CC=CC=C1 UHOVQNZJYSORNB-UHFFFAOYSA-N 0.000 description 18
- BDAGIHXWWSANSR-UHFFFAOYSA-N methanoic acid Natural products OC=O BDAGIHXWWSANSR-UHFFFAOYSA-N 0.000 description 6
- 235000013399 edible fruits Nutrition 0.000 description 5
- 239000000654 additive Substances 0.000 description 4
- 230000000996 additive effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- OSWFIVFLDKOXQC-UHFFFAOYSA-N 4-(3-methoxyphenyl)aniline Chemical compound COC1=CC=CC(C=2C=CC(N)=CC=2)=C1 OSWFIVFLDKOXQC-UHFFFAOYSA-N 0.000 description 3
- 239000002253 acid Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 235000013361 beverage Nutrition 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 235000019253 formic acid Nutrition 0.000 description 3
- 239000003755 preservative agent Substances 0.000 description 3
- 241001672694 Citrus reticulata Species 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000003750 conditioning effect Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 235000013373 food additive Nutrition 0.000 description 2
- 239000002778 food additive Substances 0.000 description 2
- 150000002632 lipids Chemical class 0.000 description 2
- 239000012528 membrane Substances 0.000 description 2
- 230000002335 preservative effect Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000002798 spectrophotometry method Methods 0.000 description 2
- CHHHXKFHOYLYRE-UHFFFAOYSA-M 2,4-Hexadienoic acid, potassium salt (1:1), (2E,4E)- Chemical compound [K+].CC=CC=CC([O-])=O CHHHXKFHOYLYRE-UHFFFAOYSA-M 0.000 description 1
- CYDQOEWLBCCFJZ-UHFFFAOYSA-N 4-(4-fluorophenyl)oxane-4-carboxylic acid Chemical compound C=1C=C(F)C=CC=1C1(C(=O)O)CCOCC1 CYDQOEWLBCCFJZ-UHFFFAOYSA-N 0.000 description 1
- 241000233866 Fungi Species 0.000 description 1
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 description 1
- 229910021607 Silver chloride Inorganic materials 0.000 description 1
- 229960004365 benzoic acid Drugs 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003304 gavage Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000004128 high performance liquid chromatography Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 235000021056 liquid food Nutrition 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 239000004302 potassium sorbate Substances 0.000 description 1
- 235000010241 potassium sorbate Nutrition 0.000 description 1
- 229940069338 potassium sorbate Drugs 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 230000002000 scavenging effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- HKZLPVFGJNLROG-UHFFFAOYSA-M silver monochloride Chemical compound [Cl-].[Ag+] HKZLPVFGJNLROG-UHFFFAOYSA-M 0.000 description 1
- 229910052708 sodium Inorganic materials 0.000 description 1
- 239000011734 sodium Substances 0.000 description 1
- 239000001540 sodium lactate Substances 0.000 description 1
- 229940005581 sodium lactate Drugs 0.000 description 1
- 235000011088 sodium lactate Nutrition 0.000 description 1
- 235000015040 sparkling wine Nutrition 0.000 description 1
- 231100000820 toxicity test Toxicity 0.000 description 1
- 238000009602 toxicology test Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Landscapes
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of method that benzoic acid in fruit juice is quickly detected based on electronic tongues, by fresh citrus, peeling, squeezes the juice this method, filters, takes pure juice；A certain amount of benzoic acid is weighed, benzoic acid is dissolved into water, the benzoic acid solution of preparation is spare；Fruit juice is mixed with benzoic acid by certain proportion is mixed again, electronic tongue sensor array is contacted with mixed solution, sense of taste finger print information is produced, characteristic is extracted from sense of taste finger print information, qualitative and quantitative analysis is carried out to citrus sample using principal component analysis, random forest modeling；With reference to the prediction model of foundation, the juice solution of unknown concentration of benzoic acid is judged.The present invention is convenient, objective, the content of fast quantification prediction benzoic acid in fruit juice.The invention substantially improves the condition of fruit juice Quality Detection control, has the characteristics that convenient, objective, quick.
Description
Technical field
The invention belongs to food fruit juice additive detection technique field, is related to one kind and is quickly detected based on electronic tongues in fruit juice
The method of benzoic acid.
Background technology
With the continuous development of fruit drink industry, varieties of food items additive is widely used in fruit drink.Food
Additive plays decisive role to the fresh-keeping, stable etc. of fruit juice, and still, the safety problem of additive has caused that people's is extensive
Concern.Each state has all worked out relevant regulation, limits the use of food additives.
Benzoic acid also known as benzoic acid (C6H5COOH), its anti-corrosion effect is preferable, and scope of restraining fungi is wide in acid condition, prevents
Rotten effect is good and price is low simultaneous, therefore is widely made an addition to as preservative in beverage, light sparkling wine and daily flavouring.Eat in China
Product sanitary standard regulation is 1g/kg in general Benzene in Beverages formic acid maximum usage amount, no more than 2g/kg in inspissated juice.
A large amount of toxicology tests that various countries carry out show that big white mouse gavages the feed 90 days added with benzoic acid, pathology occur in its liver, kidney
Change, growth and service life are all affected.If excessive addition preservative in beverage and other liquid foods, people will be seriously endangered
Health.The conventional determining method of benzoic acid content has high performance liquid chromatography, spectrophotometry, fluorescence in food at present
Spectrophotometry etc., but there are the shortcomings of complicated, analysis time is long for these methods.Therefore, explore a kind of fast and convenient
Benzoic acid detection method be necessary.
Electronic tongues are by the use of lipid membrane as taste sensor, and tastant is detected in a manner of the taste perception of similar people.Electricity
Sub- tongue taste sensor have high sensitivity, reliability, repeatability, it sample can be quantified, while can be to some
Component content carries out fast qualitative and quantifies.At present, benzoic acid in fruit juice is measured using taste sensor, quantitative determines benzene in fruit juice
The correlative study of formic acid content is not yet reported.Present invention aims at benzoic acid in Quantitative detection fruit juice, while fill up state
The inside and outside blank quickly detected on benzoic acid content in fruit drink.
The content of the invention
In view of the above-mentioned problems, the object of the present invention is to provide a kind of side that benzoic acid in fruit juice is quickly detected based on electronic tongues
Method, is used for quickly detecting the benzoic acid juice solution of various concentrations using taste sensor.
The purpose of the present invention is what is be achieved through the following technical solutions, one kind quickly detects benzene in fruit juice based on electronic tongues
The method of formic acid, includes the following steps：
(1) citrus of freshly harvested is surface-treated totally, removes the peel, squeezes the juice, filters, the citrus filtrate for obtaining pure concentration is standby
With；
(2) 1.0g, 2.0g, 3.0g are weighed, 4.0g benzoic acid, is added separately to the sodium acid carbonate that 20mL concentration is 40g/L
In solution, heating stirring dissolving, moves into 100mL volumetric flasks, adds ultra-pure water to be settled to 100mL, the benzoic acid of resulting solution
Content is 10g/L, 20g/L, 30g/L, 40g/L, as stock solution；By 10g/L, 20g/L, 30g/L, 40g/L concentration benzene first
Sour stock solution, the orange blossom with pure concentration is with mass ratio 1:19 ratio is mixed and stirred for；Finally obtaining concentration of benzoic acid is
The orange juice solution of 0.5g/kg, 1.0g/kg, 1.5g/kg, 2.0g/kg；
(3) orange juice solution is put in electronic tongues detection special container, electronic tongue sensor array and sample fruit juice
Contact, different flavor material is converted into measurable electric signal in sensor surface in fruit juice；The signal of generation is sent to signal
Conditioning unit is amplified, filters, after analog-to-digital conversion process, obtains sensor array response；
(4) stationary value of each sensor is selected as principal component analysis and the characteristic value of random forest；
(5) in Matlab, the electronic tongues characteristic value that is obtained according to step 4 is adopted again by bootstrap (boot-strap)
Sample technology, is continuously generated training sample and test sample, and some decision trees are generated by training sample, so as to establish random forest mould
Type；In Random Forest model, the number of decision tree carries out in the variable number and random forest to the tree node of decision tree
Optimize, depending on average value of the test result by decision tree voting results；
(6) the unknown sample to be tested of benzoic acid content is obtained into its electronic tongue sensor response by step 3, will sensed
The Random Forest model that device response steps for importing 5 obtains, the final benzoic acid content predicted in sample to be tested.
Further, in the step 3, the juice content is 80ml, and the electronic tongues beaker capacity is 100ml, institute
Stating testing conditions is：Detection time 120s, scavenging period 10s.
Further, in the step 5, by correlation coefficient r, root-mean-square error RMSE value to the random forest after optimization
Model is evaluated, and is specially：
Wherein, N represents the number of samples in modeling process；
XiFor i-th of test value in modeling process；
For the average value of the sample responses value in modeling process；
YiFor the predicted value of i-th of sample in modeling process；
For the average value of the sample predictions value in modeling process.
Predicted the invention has the advantages that establishing good qualitative, quantitative by principal component analysis, random forests algorithm
Model, is evaluated and is predicted to the benzoic acid of different content in juice solution using intelligent sense of taste sensory system, easy to operate,
Quickly, tested truly it is quick indirectly evaluation, for fruit drink industry additive measure provide it is a kind of newly
Method.
Brief description of the drawings
Fig. 1 is signal value of the electronic tongues in detection process in present case；
Fig. 2 is based on benzoic acid qualitative analysis of the principal component analysis to different content in present case；
Fig. 3 is based on forecast analysis of the random forest to benzoic acid content in orange juice in present case.
Embodiment
Electronic tongues are by the use of lipid membrane as taste sensor, and tastant is detected in a manner of the taste perception of similar people.Electricity
Sub- tongue taste sensor have high sensitivity, reliability, repeatability, it sample can be quantified, while can be to some
Component content carries out fast qualitative and quantifies.
A kind of method that benzoic acid in fruit juice is quickly detected based on electronic tongues of the present invention, using taste sensor to different dense
The benzoic acid juice solution of degree is used for quickly detecting, and is established effective Quantitative Prediction Model, is comprised the following steps that：
(1) citrus of freshly harvested is surface-treated totally, removes the peel, squeezes the juice, filters, the citrus filtrate for obtaining pure concentration is standby
With；
(2) 1.0g, 2.0g, 3.0g are weighed, 4.0g benzoic acid, is added separately to the sodium acid carbonate that 20mL concentration is 40g/L
In solution, heating stirring dissolving, moves into 100mL volumetric flasks, adds ultra-pure water to be settled to 100mL, the benzoic acid of resulting solution
Content is 10g/L, 20g/L, 30g/L, 40g/L, as stock solution；By 10g/L, 20g/L, 30g/L, 40g/L concentration benzene first
Sour stock solution, the orange blossom with pure concentration is with mass ratio 1:19 ratio is mixed and stirred for；Finally obtaining concentration of benzoic acid is
The orange juice solution of 0.5g/kg, 1.0g/kg, 1.5g/kg, 2.0g/kg；
(3) orange juice solution is put in electronic tongues detection special container, electronic tongue sensor array and sample fruit juice
Contact, different flavor material is converted into measurable electric signal in sensor surface in fruit juice；The signal of generation is sent to signal
Conditioning unit is amplified, filters, after analog-to-digital conversion process, obtains sensor array response；
(4) stationary value of each sensor is selected as principal component analysis and the characteristic value of random forest；
(5) in Matlab, the electronic tongues characteristic value that is obtained according to step 4 is adopted again by bootstrap (boot-strap)
Sample technology, is continuously generated training sample and test sample, and some decision trees are generated by training sample, so as to establish random forest mould
Type；In Random Forest model, the number of decision tree carries out in the variable number and random forest to the tree node of decision tree
Optimize, depending on average value of the test result by decision tree voting results；
(6) the unknown sample to be tested of benzoic acid content is obtained into its electronic tongue sensor response by step 3, will sensed
The Random Forest model that device response steps for importing 5 obtains, the final benzoic acid content predicted in sample to be tested.
Embodiment
The present invention is suitable for measuring containing for the various fruit juice preservatives such as benzoic acid, potassium sorbate, sodium lactate, dehydroactic acid sodium
It is fixed.Using benzoic acid as detection sample, intelligent sense of taste detecting system is detection instrument, is realized to benzoic acid content in fruit juice for this experiment
Quantitative detection.
The present invention mainly with sample pretreatment and electronic tongues data processing and modeling method.It is quick based on interaction using one
The electronic tongues for learning selective area effect taste sensor array are helped to change, its sensor is joined by 7 sensors and 1 Ag/AgCl
Formed than electrode, the title and performance of each sensor are shown in Table 1.
The title and performance of 1 each sensor of table are as shown in the table：
The function of these sensors is to produce response signal after each component in fruit juice is contacted on its surface.Detect program
It is arranged to one sample clean of every detection once, after each sample detection, sensor array is cleaned into cleaning solution, is avoided
Sample room influences each other.
A kind of method that benzoic acid in fruit juice is quickly detected based on electronic tongues of the present invention, is comprised the following steps：
1st, the citrus of freshly harvested is surface-treated clean, removes the peel, squeezes the juice, with 240 mesh filtered through gauze, obtaining the mandarin orange of pure concentration
Tangerine filtrate is spare；
2nd, 1.0g, 2.0g, 3.0g are weighed, 4.0g benzoic acid, it is molten to be added separately to the sodium acid carbonate that 20mL concentration is 40g/L
In liquid, heating stirring dissolving, moves into 100mL volumetric flasks, adds ultra-pure water to be settled to 100mL, the benzoic acid of resulting solution contains
Measure as 10g/L, 20g/L, 30g/L, 40g/L, as stock solution；By 10g/L, 20g/L, 30g/L, 40g/L concentration benzoic acid
Stock solution, the orange blossom with pure concentration is with mass ratio 1:19 ratio is mixed and stirred for；Finally obtaining concentration of benzoic acid is
The orange juice solution of 0.5g/kg, 1.0g/kg, 1.5g/kg, 2.0g/kg；To be not added with the orange blossom of benzoic acid solution as
Concentration of benzoic acid is the fruit juice of 0.0g/kg；One is obtained the samples of juice of 5 benzoic acid grades, the juice solution of each grade
15 repetitions are taken to test.
3rd, orange blossom is put in electronic tongues detection special container, electronic tongue sensor array is contacted with sample fruit juice, fruit
Different flavor material is converted into measurable electric signal in sensor surface in juice.The signal of generation is sent to signal condition unit
It is amplified, filters, after analog-to-digital conversion process, it is typically containing benzoic acid fruit juice to obtain sensor array response Fig. 1
Signal value change of the electronic tongues detection sensor in 120s detection process.
4th, select each sensor in 120s stationary values as principal component analysis and the characteristic value of random forest；
5th, principal component analysis, analysis result such as Fig. 2 are carried out to the fruit juice containing various concentrations benzoic acid in spss softwares
It is shown, good differentiation has been obtained containing various concentrations benzoic acid fruit juice, in Matlab softwares, has been obtained according to step 2
Electronic tongues characteristic value, by bootstrap (boot-strap) resampling technique, is continuously generated training sample and test sample, by instructing
Practice sample and generate some decision trees, so as to establish Random Forest model, the substantially step of random forest is as follows：
(1) bootstrap (boot-strap) resampling technique is utilized, randomly generates T training set S1,S2,...,ST；It is described
Bootstrap (boot-strap) resampling is specially：If there are n different sample { x in set1,x2,...,xn, if having every time
A sample is extracted from set S with putting back to, extracts n times altogether, forms new set S*, then set S*In include some sample
xiThe probability of (i=1,2 ..., n) isAs n → ∞, haveCause
This, the total sample number newly gathered is identical with former set, but contains repeated sample (putting back to extraction), is only included in new set
The sample of former set S collection and about 1-0.368*100%=63.2%；
(2) each training set is utilized, generates corresponding decision tree C1,C2,...CT；In each non-leaf nodes based on
Best divisional mode in the Split Attribute collection m of front nodal point is to the node into line splitting (in general, in this random forest
Growth course in, the value of m is to maintain constant)；
(3) each tree is completely grown up, and without trimming；
(4) for test set sample X, tested using each decision tree, obtain corresponding classification C1(X),C2
(X),...,CT(X)；
(5) by the way of ballot, the final result of Random Forest model by the average value of T decision tree output valve and
It is fixed.
6th, in Random Forest model, of decision tree in the variable number and random forest to the tree node of decision tree
Number optimizes, and depending on average value of the test result by decision tree voting results, the result finally optimized obtains the change of tree node
Measure as 3, the number of decision tree is 40.By correlation coefficient r, root-mean-square error RMSE value to the Random Forest model after optimization into
Row evaluation, is specially：
Wherein, N represents the number of samples in modeling process；
XiFor i-th of test value in modeling process；
For the average value of the sample responses value in modeling process；
YiFor the predicted value of i-th of sample in modeling process；
For the average value of the sample predictions value in modeling process.
Black square as shown in Figure 3 is sample in modeling process, random forests algorithm by electronic tongue sensor signal with
Benzoic acid content, which is established, in fruit juice good prediction model (R2=0.9859, RMSE=0.0875g/kg).7th, by benzoic acid
The unknown sample to be tested of content obtains its electronic tongue sensor response by step 1, and sensor response steps for importing 4 is obtained
The Random Forest model arrived, the final benzoic acid content predicted in sample to be tested.As Fig. 3 white on triangulation point be unknown benzene first
The sample of acid content, Random Forest model have orange blossom benzoic acid content good predictive ability (R2=0.9756, RMSE=
0.1340g/kg)。
Claims (2)
- A kind of 1. method that benzoic acid in fruit juice is quickly detected based on electronic tongues, it is characterised in that include the following steps：(1) citrus is surface-treated totally, removes the peel, squeezes the juice, filters, the citrus filtrate for obtaining pure concentration is spare；(2) 1.0g, 2.0g, 3.0g are weighed, 4.0g benzoic acid, is added separately to the sodium bicarbonate solution that 20mL concentration is 40g/L In, heating stirring dissolving, moves into 100mL volumetric flasks, adds ultra-pure water to be settled to 100mL, the benzoic acid content of resulting solution For 10g/L, 20g/L, 30g/L, 40g/L, as stock solution；By 10g/L, 20g/L, 30g/L, the storage of 40g/L concentration benzoic acid Standby solution, the orange blossom with pure concentration is with mass ratio 1:19 ratio is mixed and stirred for；It is 0.5g/ to finally obtain concentration of benzoic acid The orange juice solution of kg, 1.0g/kg, 1.5g/kg, 2.0g/kg；(3) orange juice solution being put in electronic tongues detection special container, electronic tongue sensor array is contacted with sample fruit juice, Different flavor material is converted into measurable electric signal in sensor surface in fruit juice；The signal of generation is sent to signal condition list Member is amplified, filters, after analog-to-digital conversion process, obtains sensor array response；(4) stationary value of each sensor is selected as principal component analysis and the characteristic value of random forest；(5) in Matlab, the electronic tongues characteristic value that is obtained according to step (4) passes through bootstrap (boot-strap) resampling Technology, is continuously generated training sample and test sample, and some decision trees are generated by training sample, so as to establish random forest mould Type；In Random Forest model, the number of decision tree carries out in the variable number and random forest to the tree node of decision tree Optimize, depending on average value of the test result by decision tree voting results；(6) the unknown sample to be tested of benzoic acid content is obtained into its electronic tongue sensor response by step (3), by sensor The Random Forest model that response steps for importing (5) obtains, the final benzoic acid content predicted in sample to be tested.
- A kind of 2. method that benzoic acid in fruit juice is quickly detected based on electronic tongues according to claim 1, it is characterised in that In the step (5), the Random Forest model after optimization is evaluated by correlation coefficient r, root-mean-square error RMSE value, is had Body is：<mrow> <mi>r</mi> <mo>=</mo> <mfrac> <mrow> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>N</mi> </munderover> <mrow> <mo>(</mo> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>-</mo> <mover> <mi>X</mi> <mo>&OverBar;</mo> </mover> <mo>)</mo> </mrow> <mrow> <mo>(</mo> <msub> <mi>Y</mi> <mi>i</mi> </msub> <mo>-</mo> <mover> <mi>Y</mi> <mo>&OverBar;</mo> </mover> <mo>)</mo> </mrow> </mrow> <mrow> <msqrt> <mrow> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>N</mi> </munderover> <msup> <mrow> <mo>(</mo> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>-</mo> <mover> <mi>X</mi> <mo>&OverBar;</mo> </mover> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </msqrt> <msqrt> <mrow> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>N</mi> </munderover> <msup> <mrow> <mo>(</mo> <msub> <mi>Y</mi> <mi>i</mi> </msub> <mo>-</mo> <mover> <mi>Y</mi> <mo>&OverBar;</mo> </mover> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </msqrt> </mrow> </mfrac> </mrow><mrow> <mi>R</mi> <mi>M</mi> <mi>S</mi> <mi>E</mi> <mo>=</mo> <msqrt> <mrow> <mfrac> <mn>1</mn> <mi>N</mi> </mfrac> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>N</mi> </munderover> <msup> <mrow> <mo>(</mo> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>-</mo> <msub> <mi>Y</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </msqrt> </mrow>Wherein, N represents the number of samples in modeling process；XiFor i-th of test value in modeling process；For the average value of the sample responses value in modeling process；YiFor the predicted value of i-th of sample in modeling process；For the average value of the sample predictions value in modeling process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510228898.2A CN104849328B (en) | 2015-05-06 | 2015-05-06 | The method that benzoic acid in fruit juice is quickly detected based on electronic tongues |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510228898.2A CN104849328B (en) | 2015-05-06 | 2015-05-06 | The method that benzoic acid in fruit juice is quickly detected based on electronic tongues |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104849328A CN104849328A (en) | 2015-08-19 |
| CN104849328B true CN104849328B (en) | 2018-05-01 |
Family
ID=53849131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510228898.2A Expired - Fee Related CN104849328B (en) | 2015-05-06 | 2015-05-06 | The method that benzoic acid in fruit juice is quickly detected based on electronic tongues |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104849328B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105300766B (en) * | 2015-11-04 | 2018-04-10 | 浙江大学 | A kind of special circulator bath thermostat of food inspection electronic tongues |
| CN105486825B (en) * | 2015-11-24 | 2018-07-24 | 中国食品发酵工业研究院有限公司 | The isotope detection method of external source benzoic acid in dairy products |
| CN109524062A (en) * | 2018-10-26 | 2019-03-26 | 武汉工程大学 | A kind of ion concentration prediction technique based on random forests algorithm |
| CN111693594B (en) * | 2020-05-26 | 2022-01-11 | 江苏大学 | Device and method for quickly detecting physical and chemical indexes of soybean paste based on volt-ampere electronic tongue |
-
2015
- 2015-05-06 CN CN201510228898.2A patent/CN104849328B/en not_active Expired - Fee Related
Non-Patent Citations (3)
| Title |
|---|
| 基于电子鼻和电子舌的樱桃番茄汁品质检测方法研究;洪雪珍;《中国博士学位论文全文数据库 工程科技Ⅰ辑》;20141215(第12期);全文 * |
| 智能人工味觉分析方法在几种食品质量检验中的应用研究;刘淼;《中国博士学位论文全文数据库 工程科技Ⅰ辑》;20130615(第6期);第112、18、93、91、85、138、116-122页 * |
| 镇江香醋挥发性成分分析及醋龄的识别研究;孙宗保;《中国博士学位论文全文数据库 工程科技Ⅰ辑》;20140815(第8期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104849328A (en) | 2015-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104849328B (en) | The method that benzoic acid in fruit juice is quickly detected based on electronic tongues | |
| López et al. | Multivariate characterization of table olives according to their mineral nutrient composition | |
| CN104849323B (en) | A kind of method of fining agent in quick detection fruit juice based on Electronic Nose | |
| CN104849321B (en) | A kind of method based on smell finger-print quick detection Quality Parameters in Orange | |
| Wang et al. | Early detection of Zygosaccharomyces Rouxii—spawned spoilage in apple juice by electronic nose combined with chemometrics | |
| Aceto | The use of ICP-MS in food traceability | |
| CN101382531A (en) | Method for detecting fresh degree of shrimp by electronic nose | |
| CN104849318B (en) | The method for detecting differing maturity Quality Parameters in Orange based on sense of taste smell finger-print | |
| CN103954734B (en) | A kind of mensuration of lichee quality of suitable fruit juice production and evaluation method | |
| Taiti et al. | Nashi or Williams pear fruits? Use of volatile organic compounds, physicochemical parameters, and sensory evaluation to understand the consumer’s preference | |
| CN106568907A (en) | Chinese mitten crab freshness damage-free detection method based on semi-supervised identification projection | |
| CN105527391A (en) | Electric-nose-analysis-based determination method of tuna oil corruption degree in storage process | |
| CN104849327B (en) | A kind of method that benzoic acid content in fruit juice is predicted based on sense of taste finger print information | |
| CN104914225B (en) | A kind of based on the method for fining agent content in sense of smell finger print information prediction fruit juice | |
| CN102998350B (en) | Method for distinguishing edible oil from swill-cooked dirty oil by electrochemical fingerprints | |
| CN104897738B (en) | A kind of method based on smell finger print information quick detection super-pressure fruit juice quality | |
| CN110954499A (en) | Mixed identification method and system for producing areas of imported salmon | |
| CN105741217B (en) | Multi-field comprehensive fast screening method and application system | |
| CN103424526A (en) | Device and method for detecting freshness of beef | |
| CN105738422A (en) | Method for quickly detecting storage time of walnuts based on electronic nose | |
| Ingalsbe et al. | Fruit pigment measurement, anthocyanin pigments as a maturity index for processing dark sweet cherries and purple plums | |
| Özdemir et al. | The effects of physical and chemical changes on the optimum harvest maturity in some avocado cultivars | |
| CN103868821B (en) | Adopt the evaluation method based on hyperacoustic Portable fishing meat freshness detection device | |
| Umeh et al. | Investigation in the use of a yeast specie isolated from a fermented beverage for mixed fruit wine production | |
| Stevan Jr et al. | Discrimination analysis of wines made from four species of blueberry through their olfactory signatures using an E-nose |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180501 |