CN112364710A - Plant electric signal classification and identification method based on deep learning algorithm - Google Patents
Plant electric signal classification and identification method based on deep learning algorithm Download PDFInfo
- Publication number
- CN112364710A CN112364710A CN202011125913.8A CN202011125913A CN112364710A CN 112364710 A CN112364710 A CN 112364710A CN 202011125913 A CN202011125913 A CN 202011125913A CN 112364710 A CN112364710 A CN 112364710A
- Authority
- CN
- China
- Prior art keywords
- deep learning
- plant
- signal sequence
- data
- identification method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013135 deep learning Methods 0.000 title claims abstract description 29
- 239000013598 vector Substances 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 6
- 241000196324 Embryophyta Species 0.000 claims description 49
- 108010076504 Protein Sorting Signals Proteins 0.000 claims description 27
- 239000011159 matrix material Substances 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 20
- 238000000354 decomposition reaction Methods 0.000 claims description 15
- 238000012795 verification Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 230000006353 environmental stress Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000002262 irrigation Effects 0.000 abstract description 6
- 238000003973 irrigation Methods 0.000 abstract description 6
- 238000005259 measurement Methods 0.000 abstract description 6
- 230000001066 destructive effect Effects 0.000 abstract description 5
- 238000011156 evaluation Methods 0.000 abstract description 5
- 230000003111 delayed effect Effects 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 abstract description 3
- 240000008042 Zea mays Species 0.000 description 4
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 4
- 239000003513 alkali Substances 0.000 description 4
- 210000004027 cell Anatomy 0.000 description 4
- 230000035882 stress Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 2
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 description 2
- 235000005822 corn Nutrition 0.000 description 2
- 230000008641 drought stress Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 235000009973 maize Nutrition 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000036982 action potential Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 235000013339 cereals Nutrition 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a plant electric signal classification and identification method based on a deep learning algorithm. Then, training and recognizing the two-dimensional vector by using an image recognition algorithm in deep learning, and judging the current life state of the plant; the method solves the problems that the existing plant life state judgment is delayed in information acquisition, long in period, and not suitable for rare variety evaluation due to destructive measurement. The method is suitable for various fields such as water-saving irrigation, seedling selection, environmental monitoring and the like.
Description
Technical Field
The invention belongs to the technical field of biological information, and particularly relates to a plant electric signal classification and identification method based on a deep learning algorithm.
Background
Since the twentieth century, the population growth, the waste of water resources, the land reduction and the soil degradation, ecological damage and environmental pollution caused by the excessive use of chemical fertilizers and pesticides have become serious day by day. Under the situation, on one hand, saline-alkali-tolerant and drought-tolerant crops are developed and cultivated, the utilization rate of barren soil is improved, and grain production is maintained; on the other hand, develop accurate irrigation technique, realize the rational utilization to the water resource, be the inevitable trend of wisdom agricultural development.
To develop, utilize and cultivate saline-alkali-tolerant and drought-tolerant crops, an effective crop stress resistance evaluation method and index are needed, and the method and index can sensitively and accurately reflect the state change of the crops under the environmental stress. The realization of the accurate irrigation technology also depends on the method and the index to accurately judge the water shortage state of the crops.
The traditional indexes for evaluating the crop state are mainly divided into two types, namely morphological indexes and physiological and biochemical indexes. But the determination of the form index is complicated, the workload is large, and the measurement period is long; physiological and biochemical indexes need to be subjected to destructive measurement, and the use amount of a sample is large, so that the method is not suitable for measuring rare varieties.
At present, the state of crops is judged by identifying and analyzing the appearance and the shape of plants by using a deep learning technology. However, the method can only effectively identify the plant when the appearance characteristics of the plant are obviously changed, the obtained information has hysteresis, the predicted identification rate is 60-70%, and the identification rate is low.
Disclosure of Invention
The invention aims to provide a plant electric signal classification and identification method based on a deep learning algorithm, and solves the problems of information acquisition lag, long period, destructive measurement and unsuitability for rare variety evaluation in the existing plant life state judgment.
The invention adopts the technical scheme that a plant electric signal classification and identification method based on a deep learning algorithm is implemented according to the following steps:
step 1, sampling the plant electric signal at equal time intervals to form a discrete signal sequence, wherein the discrete signal sequence is defined as D and the length is len (D);
step 2, decomposing the discrete signal sequence D by using an empirical mode decomposition algorithm,obtaining n intrinsic mode functions, and splicing the intrinsic mode functions into a Len (D) x n two-dimensional matrix vector tensor DS(ii) a Tensor D of two-dimensional matrix vectorSLabeled as normal signal;
step 3, for plants under environmental stress, adopting the same processing method as the step 1 and the step 2, and marking the obtained two-dimensional matrix vector tensor as a stressed signal Ds'; the two-dimensional tensors of the normal signal and the stressed signal jointly form a sample data set data;
step 4, dividing the data of the sample data set into a training set, a testing set and a verification set;
step 5, importing the training set into a deep learning network model for training, adjusting the hyper-parameters of the model, primarily evaluating the capability of the model, importing the verification set into a trained network for adjusting the hyper-parameters and monitoring whether the model is over-fitted to obtain an optimized model;
and 6, processing and classifying the new data needing to be identified by using the optimization model so as to identify the life state of the current plant.
The invention is also characterized in that:
step 1, the plant electric signal acquisition position is one of a plant leaf and a plant stem.
Step 2, decomposing by using an empirical mode decomposition algorithm to obtain n intrinsic mode functions, wherein the specific process is as follows:
finding out all maximum value points of data in the discrete signal sequence, and fitting to form an envelope curve e of the maximum value of the original discrete signal sequence by using a cubic spline interpolation function+(t), the upper envelope; finding out all minimum value points of data in the original discrete signal sequence in the same way, and fitting to form a minimum value envelope e of the discrete signal sequence-(t), the lower envelope; the mean value of the upper and lower envelope lines is denoted as m1(t), then:
respectively subtracting upper envelope mean value m and lower envelope mean value m from data in discrete signal sequence1(t) obtaining a new signal sequence with low frequencies removedComprises the following steps:
judgment ofWhether there is a positive local minimum and a negative local maximum, and if so, whether there is a positive local minimum and a negative local maximumIs an intermediate state function, pairRepeating the above steps;
after going through the "screening" for k times,satisfy two conditions of imf, defineIs the first order imf component of the set of signals;
then there are:
subtracting c from the original discrete signal sequence D (t)1(t) obtaining a new signal r1(t) having:
r1(t)=D(t)-c1(t)
handle r1(t) repeating the above steps as a new "original signal" to obtain imf2Component c of (t)2(t) similarly, the nth order component c can be obtainedn(t),
The expression of the original discrete signal sequence d (t) is:
imf thereini(t) is the eigenmode function, rn(t) is the residual of the decomposition.
And 4, dividing the data set into a training set, a testing set and a verification set in a ratio of 3:1: 1.
In step 5, the training set and the verification set are transmitted to the deep learning network, and the number of training iterations is 1000-2000.
And 5, the deep learning network is a convolutional neural network.
The specific process of the step 6 is as follows:
performing empirical mode decomposition on the new data d to obtain a two-dimensional vector matrix, recording the two-dimensional vector matrix as data _ I, wherein the shape of the two-dimensional vector matrix is mxn, and expanding the two-dimensional vector matrix into a [1, N ] vector x, wherein N is mxn; calculating the connection weight and the bias according to the parameters of the optimization model, and calculating a predicted value by combining the following formula:
y_pred=wTx+b
w represents the weight of the connection between neurons, b represents the bias of the neuron connection, and y _ pred is a predicted value.
The invention has the beneficial effects that:
the invention relates to a plant electric signal classification and identification method based on a deep learning algorithm. Then, training and recognizing the two-dimensional vector by using an image recognition algorithm in deep learning, and judging the current life state of the plant; the method solves the problems that the existing plant life state judgment is delayed in information acquisition, long in period, and not suitable for rare variety evaluation due to destructive measurement. The method is suitable for various fields such as water-saving irrigation, seedling selection, environmental monitoring and the like.
Detailed Description
The present invention will be described in detail with reference to the following embodiments.
The invention relates to a plant electric signal classification and identification method based on a deep learning algorithm, which is implemented according to the following steps:
step 1, sampling the plant electric signal at equal time intervals to form a discrete signal sequence, wherein the discrete signal sequence is defined as D and the length is len (D);
the plant electric signal acquisition position is one of a plant leaf and a plant stem.
Step 2, decomposing the discrete signal sequence D by an empirical mode decomposition algorithm to obtain n intrinsic mode functions, and splicing the intrinsic mode functions into a Len (D) x n two-dimensional matrix vector tensor DS(ii) a Tensor D of two-dimensional matrix vectorSLabeled as normal signal;
the specific process of obtaining n intrinsic mode functions by decomposing with an empirical mode decomposition algorithm is as follows:
finding out all maximum value points of data in the discrete signal sequence, and fitting to form an envelope curve e of the maximum value of the original discrete signal sequence by using a cubic spline interpolation function+(t), the upper envelope; finding out all minimum value points of data in the original discrete signal sequence in the same way, and fitting to form a minimum value envelope e of the discrete signal sequence-(t), the lower envelope; the mean value of the upper and lower envelope lines is denoted as m1(t), then:
respectively subtracting upper envelope mean value m and lower envelope mean value m from data in discrete signal sequence1(t) obtaining a new signal sequence with low frequencies removedComprises the following steps:
judgment ofWhether there is a positive local minimum and a negative local maximum, and if so, whether there is a positive local minimum and a negative local maximumIs an intermediate state function, pairRepeating the above steps;
after going through the "screening" for k times,satisfy two conditions of imf, defineIs the first order imf component of the set of signals;
then there are:
subtracting c from the original discrete signal sequence D (t)1(t) obtaining a new signal r1(t) having:
r1(t)=D(t)-c1(t)
handle r1(t) repeating the above steps as a new "original signal" to obtain imf2Component c of (t)2(t) similarly, the nth order component c can be obtainedn(t),
The expression of the original discrete signal sequence d (t) is:
imf thereini(t) is the eigenmode function, rn(t) is the residual of the decomposition.
Step 3, for plants under environmental stress, adopting the same processing method as the step 1 and the step 2, and marking the obtained two-dimensional matrix vector tensor as a stressed signal Ds'; the two-dimensional tensors of the normal signal and the stressed signal jointly form a sample data set data;
step 4, dividing the data of the sample data set into a training set, a testing set and a verification set;
the data set is divided into a training set, a testing set and a verification set in a ratio of 6:2: 2.
Step 5, importing the training set into a deep learning network model for training, adjusting the hyper-parameters of the model, primarily evaluating the capability of the model, importing the verification set into a trained network for adjusting the hyper-parameters and monitoring whether the model is over-fitted to obtain an optimized model;
the training set and the verification set are transmitted into a deep learning network, and the number of training iterations is 1000-2000.
The deep learning network is a convolutional neural network.
Step 6, using the optimization model to process and classify the new data to be identified, thereby identifying the life state of the current plant;
the specific process of the step 6 is as follows:
performing empirical mode decomposition on the new data d to obtain a two-dimensional vector matrix, recording the two-dimensional vector matrix as data _ I, wherein the shape of the two-dimensional vector matrix is mxn, and expanding the two-dimensional vector matrix into a [1, N ] vector x, wherein N is mxn; calculating the connection weight and the bias according to the parameters of the optimization model, and calculating a predicted value by combining the following formula:
y_pred=wTx+b
w represents the weight of the connection between neurons, b represents the bias of the neuron connection, and y _ pred is a predicted value.
The invention relates to a plant electric signal classification and identification method based on a deep learning algorithm, which has the working principle that:
in the life activity of plants, there is fluctuation of electric potential, i.e., electric signal, which is a comprehensive reflection of the electrophysiological activity of cell groups highly related to plant cells, and is closely related to the physiological state of plant cells. In the case where the plant is not affected by external factors, the plant leaf electrical signal is considered to be a normal signal. When a plant is stimulated (such as drought and saline-alkali stress), action potential and variable potential are generated by cells, and are rapidly transmitted in tissues and organs at a relatively high speed, and the electrical signals of plant leaves are changed and taken as abnormal signals influenced by stimulation factors. The electrical signal of a plant is the most direct and rapid manifestation of its life state. The signals are accurately identified, so that the current life state of the plant can be sensitively detected. The method can be used in the fields of automatic irrigation control, selection and breeding of saline-alkali tolerant and drought resistant varieties and the like.
Examples
Collecting electric signals of leaves of the normally growing corn seedlings, wherein the electric signals are divided into one group in 10 minutes, and the total number of the groups is 500; 500 groups of leaf electric signals under saline-alkali stress and drought stress are collected by the same method, each signal is randomly divided into a training set, a testing set and a verification set according to the ratio of 6:2:2, and corresponding labels are marked. The method comprises the following specific steps:
normal maize signal label: [100]
corn saline-alkali stress signals: [010]
maize drought stress signals: [001]
and decomposing the data by adopting an empirical mode decomposition algorithm (EMD) to obtain intrinsic mode functions of each group of signals, and splicing the intrinsic mode functions to obtain a two-dimensional tensor D corresponding to each growth state. And combining the three states D to obtain a data set I.
Sampling the two-dimensional matrix in the I by using a convolution method, performing pooling processing on data by using a max _ posing method to obtain high-dimensional characteristics of the data, and using a data set I1To indicate.
Data set I1Forward propagation is performed with a learning rate of 10-3And iterating for 1000-1500 times, and adjusting the hyper-parameter by using a back propagation algorithm (BP algorithm).
And leading the verification set into a trained neural network to verify the recognition rate. If the recognition rate is higher, the obtained weights and biases of the training are retained. If the recognition rate is low, the learning rate and the iteration times are adjusted, and finally a matrix with the weight and the bias of 3 x 128 is obtained.
And performing convolution pooling on the data to be identified, calculating a predicted value y _ pred by using the weight and the bias obtained by the deep learning network, and classifying the input data according to the y _ pred.
The recognition rate is calculated according to the classification result and is 86%, compared with the existing prediction recognition rate of 60-70%, the recognition rate of the method is obviously improved.
Through the mode, the method adopts a variable modal decomposition algorithm with self-adaptive characteristics, and by collecting the plant leaf electric signals and adopting a two-dimensional decomposition algorithm, the one-dimensional electric signals are expanded into two-dimensional vectors which are distributed from low frequency to high frequency in sequence. Then, training and recognizing the two-dimensional vector by using an image recognition algorithm in deep learning, and judging the current life state of the plant; the method solves the problems that the existing plant life state judgment is delayed in information acquisition, long in period, and not suitable for rare variety evaluation due to destructive measurement. The method is suitable for various fields such as water-saving irrigation, seedling selection, environmental monitoring and the like.
Claims (7)
1. A plant electric signal classification and identification method based on a deep learning algorithm is characterized by comprising the following steps:
step 1, sampling the plant electric signal at equal time intervals to form a discrete signal sequence, wherein the discrete signal sequence is defined as D and the length is len (D);
step 2, decomposing the discrete signal sequence D by an empirical mode decomposition algorithm to obtain n intrinsic mode functions, and splicing the intrinsic mode functions into a Len (D) x n two-dimensional matrix vector tensor DS(ii) a Tensor D of two-dimensional matrix vectorSLabeled as normal signal;
step 3, for plants under environmental stress, adopting the same processing method as the step 1 and the step 2, and marking the obtained two-dimensional matrix vector tensor as a stressed signal Ds'; the two-dimensional tensors of the normal signal and the stressed signal jointly form a sample data set data;
step 4, dividing the data of the sample data set into a training set, a testing set and a verification set;
step 5, importing the training set into a deep learning network model for training, adjusting the hyper-parameters of the model, primarily evaluating the capability of the model, importing the verification set into a trained network for adjusting the hyper-parameters and monitoring whether the model is over-fitted to obtain an optimized model;
and 6, processing and classifying the new data needing to be identified by using the optimization model so as to identify the life state of the current plant.
2. The plant electrical signal classification and identification method based on the deep learning algorithm as claimed in claim 1, wherein the plant electrical signal collection position in step 1 is one of a plant leaf and a plant stem.
3. The deep learning algorithm-based plant electrical signal classification and identification method according to claim 1, wherein the empirical mode decomposition algorithm is used for decomposing in the step 2, and the specific process of obtaining n intrinsic mode functions is as follows:
finding out all maximum value points of data in the discrete signal sequence, and fitting to form an envelope curve e of the maximum value of the original discrete signal sequence by using a cubic spline interpolation function+(t), the upper envelope; finding out all minimum value points of data in the original discrete signal sequence in the same way, and fitting to form a minimum value envelope e of the discrete signal sequence-(t), the lower envelope; the mean value of the upper and lower envelope lines is denoted as m1(t), then:
respectively subtracting upper envelope mean value m and lower envelope mean value m from data in discrete signal sequence1(t) obtaining a new signal sequence with low frequencies removedComprises the following steps:
judgment ofWhether there is a positive local minimum and a negative local maximum, and if so, whether there is a positive local minimum and a negative local maximumIs an intermediate state function, pairRepeating the above steps;
after going through the "screening" for k times,satisfy two conditions of imf, defineIs the first order imf component of the set of signals;
then there are:
subtracting c from the original discrete signal sequence D (t)1(t) obtaining a new signal r1(t) having:
r1(t)=D(t)-c1(t)
handle r1(t) repeating the above steps as a new "original signal" to obtain imf2Component c of (t)2(t) similarly, the nth order component c can be obtainedn(t),
The expression of the original discrete signal sequence d (t) is:
imf thereini(t) is the eigenmode function, rn(t) is the residual of the decomposition.
4. The deep learning algorithm-based plant electric signal classification and identification method as claimed in claim 1, wherein the data set is divided into a training set, a test set and a verification set in a ratio of 3:1:1 in step 4.
5. The method as claimed in claim 1, wherein the training set and the verification set are introduced into the deep learning network in step 5, and the number of training iterations is 1000-2000.
6. The plant electric signal classification and identification method based on the deep learning algorithm as claimed in claim 1, wherein the deep learning network in step 5 is a convolutional neural network.
7. The deep learning algorithm-based plant electric signal classification and identification method according to claim 1, wherein the specific process of step 6 is as follows:
performing empirical mode decomposition on the new data d to obtain a two-dimensional vector matrix, recording the two-dimensional vector matrix as data _ I, wherein the shape of the two-dimensional vector matrix is mxn, and expanding the two-dimensional vector matrix into a [1, N ] vector x, wherein N is mxn; calculating the connection weight and the bias according to the parameters of the optimization model, and calculating a predicted value by combining the following formula:
y_pred=wTx+b
w represents the weight of the connection between neurons, b represents the bias of the neuron connection, and y _ pred is a predicted value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011125913.8A CN112364710B (en) | 2020-10-20 | 2020-10-20 | Plant electric signal classification and identification method based on deep learning algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011125913.8A CN112364710B (en) | 2020-10-20 | 2020-10-20 | Plant electric signal classification and identification method based on deep learning algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112364710A true CN112364710A (en) | 2021-02-12 |
CN112364710B CN112364710B (en) | 2024-04-05 |
Family
ID=74507837
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011125913.8A Active CN112364710B (en) | 2020-10-20 | 2020-10-20 | Plant electric signal classification and identification method based on deep learning algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112364710B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113126050A (en) * | 2021-03-05 | 2021-07-16 | 沃尔夫曼消防装备有限公司 | Life detection method based on neural network |
CN113392771A (en) * | 2021-06-16 | 2021-09-14 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Plant growth state diagnosis method, system and device based on deep learning |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180357542A1 (en) * | 2018-06-08 | 2018-12-13 | University Of Electronic Science And Technology Of China | 1D-CNN-Based Distributed Optical Fiber Sensing Signal Feature Learning and Classification Method |
CN109740544A (en) * | 2019-01-07 | 2019-05-10 | 哈尔滨工业大学(深圳) | The recognition methods of sense of hearing attention state degree of awakening, device and storage medium |
CN111407243A (en) * | 2020-03-23 | 2020-07-14 | 华南理工大学 | Pulse signal pressure identification method based on deep learning |
WO2020156348A1 (en) * | 2019-01-31 | 2020-08-06 | 青岛理工大学 | Structural damage identification method based on ensemble empirical mode decomposition and convolution neural network |
-
2020
- 2020-10-20 CN CN202011125913.8A patent/CN112364710B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180357542A1 (en) * | 2018-06-08 | 2018-12-13 | University Of Electronic Science And Technology Of China | 1D-CNN-Based Distributed Optical Fiber Sensing Signal Feature Learning and Classification Method |
CN109740544A (en) * | 2019-01-07 | 2019-05-10 | 哈尔滨工业大学(深圳) | The recognition methods of sense of hearing attention state degree of awakening, device and storage medium |
WO2020156348A1 (en) * | 2019-01-31 | 2020-08-06 | 青岛理工大学 | Structural damage identification method based on ensemble empirical mode decomposition and convolution neural network |
CN111407243A (en) * | 2020-03-23 | 2020-07-14 | 华南理工大学 | Pulse signal pressure identification method based on deep learning |
Non-Patent Citations (2)
Title |
---|
周亦人;邱小林;郭志强;: "基于深度学习理论的发动机气门机构故障识别", 制造业自动化, no. 11 * |
袁银;王东斌;刘永金;: "基于深度学习的植物图像识别方法研究", 现代农业科技, no. 23 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113126050A (en) * | 2021-03-05 | 2021-07-16 | 沃尔夫曼消防装备有限公司 | Life detection method based on neural network |
CN113392771A (en) * | 2021-06-16 | 2021-09-14 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Plant growth state diagnosis method, system and device based on deep learning |
Also Published As
Publication number | Publication date |
---|---|
CN112364710B (en) | 2024-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102524024B (en) | Crop irrigation system based on computer vision | |
CN110109193B (en) | Intelligent eggplant greenhouse temperature detection device based on DRNN neural network | |
CN107169621A (en) | A kind of Dissolved Oxygen in Water Forecasting Methodology and device | |
CN112906298B (en) | Blueberry yield prediction method based on machine learning | |
CN110069032B (en) | Eggplant greenhouse environment intelligent detection system based on wavelet neural network | |
CN110119766B (en) | Green pepper greenhouse temperature intelligent early warning device of multi-combination intelligent model | |
CN112364710B (en) | Plant electric signal classification and identification method based on deep learning algorithm | |
CN110119767B (en) | Intelligent cucumber greenhouse temperature detection device based on LVQ neural network | |
CN112634072A (en) | Evaluation method for cold resistance of rice in seedling stage based on principal component analysis | |
CN110119169A (en) | A kind of tomato greenhouse temperature intelligent early warning system based on minimum vector machine | |
CN117540908A (en) | Agricultural resource integration method and system based on big data | |
CN113139717B (en) | Crop seedling condition grading remote sensing monitoring method and device | |
Monica et al. | Soil NPK prediction using enhanced genetic algorithm | |
CN109934400B (en) | Rain collecting, regulating and deficiency crop water demand prediction method based on improved neural network | |
CN116894514A (en) | Crop yield prediction method and system based on soil quality index | |
CN108038586A (en) | A kind of water environment evaluation method and system of culture of Chinese mitten crab | |
CN112036470A (en) | Cloud transmission-based multi-sensor fusion cucumber bemisia tabaci identification method | |
CN109472320B (en) | Method for automatically correcting variety parameters of crop growth period model under uncertain conditions | |
CN116563714A (en) | Method and system for automatically distinguishing growth stage of rice | |
CN114034672B (en) | Crop cold injury degree grading method based on chlorophyll fluorescence technology | |
Chatterjee et al. | Hybrid regression model for soil moisture quantity prediction | |
Manivasagam et al. | An efficient crop yield prediction using machine learning | |
Gehlot et al. | Technical analysis of crop production prediction using Machine Learning and Deep Learning Algorithms | |
CN114004389A (en) | Hybrid method for crop yield prediction | |
CN112131954A (en) | China northern winter wheat remote sensing estimated yield based on convolutional neural network |
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 |