Fungus stick water loss rate prediction method and system based on neural network

Abstract

The invention relates to a method and system for predicting the water loss rate of a mushroom stick based on a neural network, and the method comprises the steps: obtaining the environmental data of the water loss rate of the mushroom stick, and the environmental data comprise temperature and humidity; preprocessing the environment data through wavelet noise reduction to obtain preprocessed environment data; constructing a data set based on the preprocessed environment data and the corresponding mushroom stick weight data; training the neural network through the data set until the error of the neural network tends to be stable and is lower than a threshold value; and inputting the weight data of the target bacteria stick and the real-time environment data into the trained neural network to obtain the predicted water loss rate of the target bacteria stick. The neural network is trained based on the environmental data of the water loss rate of the mushroom sticks, and the efficiency and intelligence of predicting the water loss rate of the mushroom sticks are improved through the neural network.

Description

Technical Field

[0001] The invention belongs to the technical field of edible and medicinal mushroom stick prediction and neural network, and particularly relates to a method and system for predicting water loss rate of mushroom sticks based on neural network. Background Art

[0002] The edible and medicinal mushroom industry occupies an important position in my country's national economy. The edible and medicinal mushroom germplasm resources are rich and have become an important strategic resource in my country, playing an important role in rural revitalization. There are many cultivated varieties, among which the dominant mushroom varieties in the industry include more than 20 varieties such as shiitake mushrooms, ganoderma lucidum, mulberry yellow, black fungus, nameko, oyster mushroom, enoki mushroom, and king oyster mushroom. These mushroom varieties are all produced on a large scale, intensively, and in a factory-like manner according to the cultivation process of making mushroom sticks, cultivating mushrooms, managing mushrooms, and harvesting. The mushroom stick is a rod-shaped body with hyphae after the material stick is inoculated. The appropriate water content in the mushroom stick is the premise and basis for the growth and development of hyphae, which directly affects the development of hyphae and the yield and quality of fruiting bodies. A key parameter for measuring water loss in mushroom sticks is the water loss rate. The water loss rate of mushroom sticks is affected by many factors such as the cultivation environment and management measures. Therefore, in large-scale production, how to keep the moisture in the mushroom sticks suitable for mycelial growth is a difficult problem. The inappropriate moisture content in the mushroom sticks often leads to poor mycelial development and insufficient accumulated temperature, resulting in slow mycelial development or rotten sticks, making it difficult to ensure stable and high-quality production. However, in large-scale production, the method for monitoring the water loss rate of mushroom sticks mainly relies on traditional manual observation and empirical judgment. This method is not only inefficient, but also difficult to ensure accuracy. Therefore, it is particularly important to study a method and system for predicting the water loss rate of mushroom sticks based on neural networks. By effectively monitoring and predicting the water loss rate of mushroom sticks, it is possible to effectively evaluate the water content in the mushroom sticks, maintain mycelial vitality, achieve accurate water management of mushroom sticks, and improve product quality and yield, which is of great significance.

[0003] Based on the above background, neural network technology, especially BP neural network, convolutional neural network (CNN) and recurrent neural network (RNN), combined with image processing and data analysis technology, can accurately predict the water loss rate of edible and medicinal mushrooms such as shiitake mushrooms, ganoderma lucidum, black fungus, nameko, and mulberry. This can not only improve the production efficiency of edible and medicinal mushrooms, but also promote the modernization and intelligentization of the edible and medicinal mushroom industry. Summary of the invention

[0004] In order to improve the prediction efficiency and intelligence level of mushroom stick water loss rate, a first aspect of the present invention provides a method for predicting mushroom stick water loss rate based on a neural network, comprising: obtaining environmental data of mushroom stick water loss rate, the environmental data including temperature and humidity; preprocessing the environmental data by wavelet denoising to obtain preprocessed environmental data; constructing a data set based on the preprocessed environmental data and corresponding mushroom stick weight data; training the neural network through the data set until the error of the neural network tends to be stable and is lower than a threshold; inputting the target mushroom stick weight data and real-time environmental data into the trained neural network to obtain the predicted water loss rate of the target mushroom stick.

[0005] In some embodiments of the present invention, the preprocessing of the environmental data by wavelet denoising includes: performing wavelet decomposition on the environmental data and calculating the corresponding wavelet coefficients; determining a threshold and reconstructing the wavelet coefficients by a threshold function; restoring the environmental data by the reconstructed wavelet coefficients. Furthermore, the threshold is determined by noise variance, wavelet coefficients and threshold coefficients.

[0006] In some embodiments of the present invention, constructing a data set based on the preprocessed environmental data and the corresponding mushroom stick weight data includes: constructing a data set based on the preprocessed environmental data, the mushroom stick weight data, and the mushroom stick associated data.

[0007] Furthermore, the mushroom stick associated data includes the type, growth environment and growth stage of the mushroom stick.

[0008] In the above embodiments, the neural network includes CNN, BP neural network or RNN.

[0009] The second aspect of the present invention provides a mushroom stick water loss rate prediction system based on a neural network, comprising: an acquisition module for acquiring environmental data of the mushroom stick water loss rate, the environmental data including temperature and humidity; a construction module for preprocessing the environmental data by wavelet denoising to obtain preprocessed environmental data; constructing a data set based on the preprocessed environmental data and corresponding mushroom stick weight data; a training module for training the neural network through the data set until the error of the neural network tends to be stable and is lower than a threshold; a prediction module for inputting the target mushroom stick weight data and real-time environmental data into the trained neural network to obtain the predicted water loss rate of the target mushroom stick.

[0010] Furthermore, the construction module includes: a calculation unit, used to perform wavelet decomposition on the environmental data and calculate the corresponding wavelet coefficients; a determination unit, used to determine a threshold and reconstruct the wavelet coefficients through a threshold function; and a reconstruction unit, used to restore the environmental data through the reconstructed wavelet coefficients.

[0011] The third aspect of the present invention provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method for predicting water loss rate of mushroom sticks based on neural network provided in the first aspect of the present invention.

[0012] A fourth aspect of the present invention provides a computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for predicting water loss rate of a mushroom stick based on a neural network provided in the first aspect of the present invention is implemented.

[0013] The beneficial effects of the present invention are: The invention ensures the data accuracy in the data set through wavelet denoising and preprocessing; trains a neural network through relevant data and features of the water loss rate of mushroom sticks, thereby improving the prediction efficiency and intelligent level of the prediction of the water loss rate of mushroom sticks. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a basic flow chart of a method for predicting water loss rate of mushroom sticks based on a neural network in some embodiments of the present invention; Figure 2 It is a schematic diagram of a specific process of a method for predicting water loss rate of a mushroom stick based on a neural network in some embodiments of the present invention; Figure 3 A schematic diagram of a data fitting toolbox in some embodiments of the present invention; Figure 4 This is an evaluation effect diagram of a validation set for validation of the weight loss rate of spring shiitake mushroom sticks in some embodiments of the present invention; Figure 5 This is an evaluation effect diagram of a test set for verifying the weight loss rate of spring shiitake mushroom sticks in some embodiments of the present invention; Figure 6 It is an evaluation effect diagram of a verification set for verification of weight loss rate of shiitake mushroom sticks in summer in some embodiments of the present invention; Figure 7 This is an evaluation effect diagram of a test set for verifying the weight loss rate of shiitake mushroom sticks in summer in some embodiments of the present invention; Figure 8 This is an evaluation effect diagram of a validation set for validation of the weight loss rate of autumn shiitake mushroom sticks in some embodiments of the present invention; Fig. 9 This is an evaluation effect diagram of a validation set for validation of the weight loss rate of autumn shiitake mushroom sticks in some embodiments of the present invention; Fig.10 It is a structural schematic diagram of a system for predicting water loss rate of mushroom sticks based on a neural network in some embodiments of the present invention; Fig.11 It is a schematic diagram of the structure of an electronic device in some embodiments of the present invention. DETAILED DESCRIPTION

[0015] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0016] refer to Figure 1 and Figure 2 In a first aspect of the present invention, a method for predicting water loss rate of a mushroom stick based on a neural network is provided, comprising: S100. acquiring environmental data of the water loss rate of a mushroom stick, wherein the environmental data comprises temperature and humidity; S200. preprocessing the environmental data by wavelet denoising to obtain preprocessed environmental data; constructing a data set based on the preprocessed environmental data and corresponding mushroom stick weight data; S300. training a neural network by the data set until the error of the neural network tends to be stable and is lower than a threshold; S400. inputting the target mushroom stick weight data and the real-time environmental data into the trained neural network to obtain the predicted water loss rate of the target mushroom stick.

[0017] In step S100 of some embodiments of the present invention, environmental data of water loss rate of mushroom sticks is obtained, and the environmental data includes temperature and humidity; Specifically, environmental parameters, including temperature, humidity, etc., are collected in real time through various sensors and used as input features of the neural network.

[0018] In step S200 of some embodiments of the present invention, preprocessing the environmental data by wavelet denoising includes: S201. Perform wavelet decomposition on the environmental data and calculate the corresponding wavelet coefficients; Specifically, the temperature and humidity signals are decomposed by wavelet, and the corresponding wavelet coefficients are obtained. d j,k ; S202. Determine a threshold value, and reconstruct the wavelet coefficients by using a threshold function; Specifically, a threshold λ is set, and coefficients smaller than the threshold are considered to be generated by noise and will be removed; S203. Restore the environmental data through the reconstructed wavelet coefficients.

[0019] Wavelet coefficients after reconstruction With the approximate coefficients, the temperature and humidity signals are restored.

[0020] Furthermore, the threshold is determined by noise variance, wavelet coefficients and threshold coefficients.

[0021] The hard threshold function in the threshold function is: (1); The soft threshold function is: (2); In formula (2), sgn(·) is the sign function; d j,k and are the wavelet coefficients before and after processing respectively; λ is the threshold. The threshold and threshold function are important factors affecting wavelet threshold denoising, and their selection directly affects the denoising effect of power quality signals. (3), σ is the noise variance, C is the threshold coefficient; the estimation formula of σ is: (4); According to the above process, the denoised signal is obtained. The wavelet denoising effect is evaluated by mainly calculating the signal-to-noise ratio (SNR), mean square error (MSE), and normalized correlation coefficient (NCC) to find the optimal wavelet.

[0022] In step S200 of some embodiments of the present invention, constructing a data set based on the preprocessed environmental data and the corresponding mushroom stick weight data includes: constructing a data set based on the preprocessed environmental data, the mushroom stick weight data, and the mushroom stick associated data.

[0023] Specifically, taking shiitake mushrooms as an example, the collection of data sets requires the collection of a large amount of data related to the water loss rate of shiitake mushroom sticks, including the type of sticks, growth environment, growth stage, quality of the sticks, etc. At the same time, it is also necessary to collect relevant indicators of the water loss rate of the sticks, such as the weight and water content of the sticks. The collected data is cleaned, outliers and missing values ​​are removed, and the data is normalized to facilitate subsequent model training. Features related to the water loss rate of shiitake mushroom sticks are extracted from the collected data, such as the type of sticks, growth environment, growth stage, etc. These features will be used as input variables to train the deep learning model. Without loss of generality, the water loss rate data sets of Ganoderma lucidum, Phellinus linteus, Auricularia auricula, Pleurotus eryngii, Pleurotus ostreatus, Enoki mushroom, and Pleurotus eryngii can all be collected using the above method.

[0024] Furthermore, the shiitake mushroom stick associated data includes the type, growth environment and growth stage of the mushroom stick.

[0025] In step S300 of some embodiments of the present invention, the neural network is trained using the data set until the error of the neural network tends to be stable and is lower than a threshold; Specifically, deep learning technologies such as BP neural network, convolutional neural network (CNN) or recurrent neural network (RNN) are used to build a prediction model for the water loss rate of shiitake mushroom sticks. The model input is the pre-processed environmental parameters and mushroom stick weight data, and the output is the water loss rate of shiitake mushroom sticks.

[0026] The model was constructed by first calling the fitting toolbox using the MATLAB program, according to P(x)=p1* x^n +p2* x^(n-1) + ... + pn *x+ pn+1, where the input is adapted according to the basis function expression as x and y are inputs, x is temperature, y is humidity, and f(x,y) is the output weight loss rate. The deep learning model was trained using the collected data, and the prediction performance of the model was optimized by adjusting the model parameters and structure.

[0027] The trained model is evaluated using the validation set, and the prediction accuracy of the model is evaluated by calculating the error indicators between the predicted value and the actual value (such as mean square error, determination coefficient, etc.). Based on the evaluation results, the parameters and structure of the model are further adjusted to improve the prediction performance of the model.

[0028] In step S400 of some examples of the present invention, the target mushroom stick weight data and real-time environmental data are input into the trained neural network to obtain the predicted water loss rate of the target mushroom stick. Specifically, the pre-treated environmental parameters and mushroom stick weight data are input into the trained deep learning model to predict the water loss rate of the mushroom stick. The prediction results can be displayed through a visual interface, which is convenient for users to understand the growth status of the mushroom stick in real time. Based on the data fitting toolbox provided by MATLAB, it is improved by inputting temperature x humidity y, and can be determined according to the adjustment data set.

[0029] refer to Figures 4 to 9 The BP neural network was used to simulate the weight loss rate of mushroom sticks, and the results of the weight loss rate of mushroom sticks in spring, summer and autumn were verified. Figures 4 to 5 The validation and evaluation results of the spring mushroom stick transpiration model are shown in Table 1. From the analysis of Table 1, it can be seen that the MSE of the validation set is 0.011806, and the MSE of the test set is 0.022304. This shows that the model performs better on the validation set than on the test set, and the prediction error of the validation set is smaller. The RMSEP of the validation set is 0.40897, and the RMSEP of the test set is 0.54635. This also shows that the model performs better on the validation set than on the test set. The R² of the validation set is 0.99734, and the R² of the test set is 0.99423. Both values ​​are very high, indicating that the model has a very good fitting effect on both data sets.

[0030] Table 1:

[0031] according to Figure 6 and Figure 7 It can be seen that the weight loss rate of the mushroom stick is predicted based on the input temperature and humidity data and the output mushroom stick weight loss rate data. Compared with the actual mushroom stick weight loss rate, it is found that the weight loss rate of the mushroom stick predicted in the validation set is 17~21%, and the weight loss rate of the mushroom stick predicted in the test set is 10~20%, which shows better prediction performance.

[0032] Table 2:

[0033] The validation and evaluation results of the summer mushroom stick transpiration model are shown in Table 2. From the analysis of Table 2, it can be seen that the MSE of the validation set is 0.005205, and the MSE of the test set is 0.010952. The MSE of the validation set is low, indicating that the prediction error of the model on the validation set is small, and the performance is good. The R² of the validation set is 0.99138, and the R² of the test set is 0.98152. R² is close to 1, indicating that the model has strong explanatory power and can fit the data well.

[0034] according to Figure 8 and Fig. 9 It can be seen that the weight loss rate of the mushroom stick is predicted based on the input temperature and humidity data and the output mushroom stick weight loss rate data. Compared with the actual mushroom stick weight loss rate, it is found that the weight loss rate of the mushroom stick predicted in the validation set is 16~28%, and the weight loss rate of the mushroom stick predicted in the test set is 15~18%, which shows better prediction performance.

[0035] The validation and evaluation results of the autumn mushroom stick transpiration model are shown in Table 3. From the analysis of Table 3, it can be seen that the MSE of the validation set is 0.003864, and the MSE of the test set is 0.003455. The MSE of both data sets is very low, indicating that the prediction error of the model is very small. The RMSEP of the validation set is 0.13384, and the RMSEP of the test set is 0.084637. The prediction accuracy of the model on this data set is relatively high.

[0036] Table 3:

[0037] Example 2 refer to Fig.10In a second aspect of the present invention, a system 1 for predicting water loss rate of mushroom sticks based on a neural network is provided, comprising: an acquisition module 11, for acquiring environmental data of the water loss rate of mushroom sticks, wherein the environmental data comprises temperature and humidity; a construction module 12, for preprocessing the environmental data by wavelet denoising to obtain preprocessed environmental data; a data set is constructed based on the preprocessed environmental data and corresponding mushroom stick weight data; a training module 13, for training the neural network by the data set until the error of the neural network tends to be stable and is lower than a threshold; a prediction module 14, for inputting the target mushroom stick weight data and the real-time environmental data into the trained neural network to obtain the predicted water loss rate of the target mushroom stick.

[0038] Furthermore, the construction module 12 includes: a calculation unit, used to perform wavelet decomposition on the environmental data and calculate the corresponding wavelet coefficients; a determination unit, used to determine a threshold and reconstruct the wavelet coefficients through a threshold function; and a reconstruction unit, used to restore the environmental data through the reconstructed wavelet coefficients.

[0039] Example 3 refer to Fig.11 According to a third aspect of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for predicting water loss rate of mushroom sticks based on neural network according to the first aspect of the present invention.

[0040] The electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0041] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.11The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Fig.11 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0042] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above functions defined in the method of the embodiment of the present disclosure are executed. It should be noted that the computer-readable medium described in the embodiment of the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus, or a device. In an embodiment of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus, or a device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wire, optical cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

[0043] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device. The computer-readable medium carries one or more computer programs. When the one or more programs are executed by the electronic device, the electronic device: Computer program code for performing the operations of embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, Python, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0044] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0045] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting water loss rate of mushroom sticks based on neural network, characterized in that: include: Acquire environmental data of water loss rate of mushroom sticks, wherein the environmental data includes temperature and humidity; Preprocessing the environmental data by wavelet denoising to obtain preprocessed environmental data; Construct a data set based on the preprocessed environmental data and the corresponding mushroom stick weight data; Training the neural network using the data set until the error of the neural network is stable and below a threshold; The target mushroom stick weight data and real-time environmental data are input into the trained neural network to obtain the predicted water loss rate of the target mushroom stick.

2. The method for predicting water loss rate of mushroom sticks based on neural network according to claim 1, characterized in that: The preprocessing of the environmental data by wavelet denoising comprises: Performing wavelet decomposition on the environmental data and calculating corresponding wavelet coefficients; Determine a threshold value, and reconstruct the wavelet coefficients by using a threshold function; The environmental data is restored through the reconstructed wavelet coefficients.

3. The method for predicting water loss rate of mushroom sticks based on neural network according to claim 2, characterized in that: The threshold is determined by the noise variance, the wavelet coefficient and the threshold coefficient.

4. The method for predicting water loss rate of mushroom sticks based on neural network according to claim 1, characterized in that: The constructing of a data set based on the pre-processed environmental data and the corresponding mushroom stick weight data comprises: A dataset is constructed based on the preprocessed environmental data, mushroom stick weight data, and mushroom stick associated data.

5. The method for predicting water loss rate of mushroom sticks based on neural network according to claim 4, characterized in that: The mushroom stick associated data includes the type, growth environment and growth stage of the mushroom stick.

6. The method for predicting water loss rate of mushroom sticks based on neural network according to claim 1, characterized in that: The neural network includes CNN, BP neural network or RNN.

7. A neural network-based mushroom stick water loss rate prediction system, characterized in that: include: An acquisition module is used to acquire environmental data of water loss rate of mushroom sticks, wherein the environmental data includes temperature and humidity; A construction module is used to pre-process the environmental data by wavelet denoising to obtain pre-processed environmental data; Construct a data set based on the preprocessed environmental data and the corresponding mushroom stick weight data; A training module, used for training a neural network through a data set until an error of the neural network tends to be stable and is lower than a threshold; The prediction module is used to input the target mushroom stick weight data and real-time environmental data into the trained neural network to obtain the predicted water loss rate of the target mushroom stick.

8. The neural network-based mushroom stick water loss rate prediction system according to claim 7, characterized in that: The building blocks include: A calculation unit, used for performing wavelet decomposition on the environmental data and calculating corresponding wavelet coefficients; A determination unit, used to determine a threshold value and reconstruct the wavelet coefficients through a threshold function; The reconstruction unit is used to restore the environmental data through the reconstructed wavelet coefficients.

9. An electronic device, comprising: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the method for predicting water loss rate of mushroom sticks based on neural network as described in any one of claims 1 to 6.

10. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method for predicting water loss rate of a mushroom stick based on a neural network as described in any one of claims 1 to 6 is implemented.

Images