A method and system for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis

Abstract

This invention relates to the field of intelligent feeding technology for livestock and poultry farming, and in particular to a method and system for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis. The method includes: acquiring raw EEG signals of pigs in different states in real time using a wearable EEG acquisition device; preprocessing and extracting features from the raw EEG signals, and inputting the processed feature data into a hunger state recognition model for identification; when the identification result indicates a hunger state, sending a feeding command to the corresponding pigpen feeder, which then feeds the pig according to a preset basic feeding amount; and dynamically adjusting feeding parameters based on the feeding feedback after feeding to achieve closed-loop precision feeding. This invention significantly reduces feed waste and labor costs in livestock farming.

Description

Technical Field

[0001] This invention relates to the field of intelligent feeding technology for livestock and poultry farming, and in particular to a method and system for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis. Background Technology

[0002] The large-scale and intelligent development of the pig farming industry has placed higher demands on the precision and automation of the feeding process. Currently, the mainstream feeding methods in pig farms are still mainly manual feeding at fixed times and quantities, and simple automatic feeding at fixed times. Although some intelligent pig farms have introduced feeding control schemes based on weight and feeding behavior, none of them have achieved precise matching of feeding needs from the perspective of the pigs' physiological and subjective feelings, and there are many technical defects: First, the feeding precision is low. There are significant individual differences in the appetite, growth stage, and health status of pigs, and a fixed feeding mode can easily lead to a 20%-30% [unclear] rate of [unclear]. Firstly, there is feed waste, and some pigs are prone to malnutrition, affecting growth efficiency. Secondly, there is a lack of real-time feedback on physiological status. Current technology cannot capture the physiological signals of hunger in pigs. Feeding is regulated solely by external indicators such as time and weight, which is difficult to adapt to the dynamic nutritional needs of pigs and can easily trigger stress reactions. Thirdly, there are high labor and environmental costs. Large-scale pig farms require a large number of people to monitor the pigs' feeding status and adjust the amount of feed. This is labor-intensive, and overfeeding leads to an increase in manure discharge, which increases the environmental treatment burden of pig farms and reduces animal welfare standards.

[0003] Biometric identification technology based on brainwave signals has been applied in the field of biological physiological state detection, but it has not yet been implemented in the pig farming feeding process. How to use brainwave signals to accurately identify the hunger state of pigs and build an automatic feeding system based on the physiological needs of pigs has become a key direction to solve the current problem of insufficient accuracy in pig feeding. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis, aiming to solve or improve at least one of the above-mentioned technical problems.

[0005] To achieve the above objectives, the present invention provides the following solution: A method for precise automated feeding of pigs based on electroencephalogram (EEG) analysis includes: Wearable EEG acquisition devices were used to acquire raw EEG signals of pigs in different states in real time. The raw EEG signal is preprocessed and features are extracted, and the processed feature data is input into the hunger state recognition model for recognition. When the identification result indicates a state of hunger, a feeding instruction is sent to the corresponding pig pen feeder, and the feeder completes the feeding according to the preset basic feeding amount. Feeding parameters are dynamically adjusted based on the feeding feedback after feeding to achieve closed-loop precision feeding.

[0006] Furthermore, the wearable EEG acquisition device is a non-invasive structure that collects EEG signals by attaching dry or flexible electrodes to specific brain regions of the frontal and parietal lobes of a pig's head.

[0007] Furthermore, the raw EEG signal undergoes preprocessing and feature extraction, and the processed feature data specifically includes: The original EEG signals were denoised and filtered to remove environmental interference and invalid signals. Then, the characteristic frequency bands and characteristic values ​​of the EEG signals of pigs under different physiological states of hunger and satiety were extracted.

[0008] Furthermore, the construction process of the hunger state recognition model is as follows: By artificially controlling the amount of feed given to pigs, sample states are constructed. Raw EEG signals are collected under the corresponding states. After preprocessing the raw EEG signals by noise reduction and filtering, characteristic frequency bands and characteristic values ​​of EEG signals in the states of hunger and satiety are extracted to form a EEG sample dataset with state labels. The sample dataset is divided into training set, validation set and test set according to the proportion. The training set is input into the machine learning model for training to complete the construction of the hunger state recognition model.

[0009] Furthermore, the preset basic feeding amount is set according to the breed, age, weight stage and growth cycle of the pigs.

[0010] Furthermore, the dynamic adjustment of feeding parameters includes: After the pigs have finished eating, weigh them using a weighing device, and adjust the amount of feed to be given later based on the amount of feed remaining.

[0011] The present invention also provides a precise automatic feeding system for pigs based on electroencephalogram (EEG) analysis, comprising: an EEG acquisition module, a signal processing module, a feeding execution module, and a parameter optimization module; The brainwaves are used to collect raw brainwave signals of pigs in different states in real time. The signal processing module is used to preprocess and extract features from the raw EEG signals, and to identify the hunger state of pigs through a hunger state recognition model. The feeding execution module includes a feeder that corresponds to each pig pen, which is used to receive feeding instructions and complete precise feeding according to the preset basic feeding amount. The parameter optimization module is used to collect pigs' feeding feedback data, dynamically adjust feeding parameters, and optimize the hunger state recognition model.

[0012] The present invention discloses the following technical effects: This invention uses electroencephalogram (EEG) analysis to accurately identify the physiological state of pig hunger, constructing a closed-loop feeding system encompassing signal acquisition, state recognition, precise feeding, and feedback optimization. This system enables on-demand, personalized feeding centered on the pig's physiological needs, significantly reducing feed waste and labor costs, minimizing stress and improving growth efficiency and animal welfare. Simultaneously, it reduces manure emissions, achieving green farming practices. The system is adaptable to the needs of large-scale pig farms requiring simultaneous multi-pig operations and intelligent management, effectively promoting the upgrading of pig farming towards precision and intelligence. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] The purpose of this invention is to provide a method and system for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis, aiming to solve or improve at least one of the above-mentioned technical problems.

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0018] like Figure 1 As shown, this invention provides a method for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis, comprising: Step 1: Real-time acquisition of EEG signals A non-invasive wearable EEG acquisition device is used to collect raw EEG signals from pigs under different physiological conditions. This device uses dry or flexible electrodes to attach to specific brain regions in the frontal and parietal lobes of the pig's head, enabling continuous, stable, and real-time acquisition of the raw EEG signals, ensuring the accuracy and continuity of signal acquisition.

[0019] Step 2: Signal preprocessing and state recognition The collected raw EEG signals are transmitted to the signal processing module. The raw signals are first denoised and filtered to remove invalid signals such as electromagnetic interference and noise in the pig farm environment. Then, the characteristic frequency bands and characteristic values ​​of the EEG in different physiological states of hunger and satiety are extracted from the processed signals. The extracted feature data are input into a pre-built hunger state recognition model. The model intelligently recognizes the current physiological state of the pig and outputs the recognition result of hunger or non-hunger.

[0020] The hunger state recognition model is constructed as follows: Sample states are constructed by artificially controlling the amount of feed given to pigs. A known hunger state is obtained by fasting the experimental pigs for 12 hours, and a known satiety state is obtained within one hour after allowing the pigs free access to feed. Raw electroencephalogram (EEG) signals from both states are collected, preprocessed, and feature frequency bands and feature values ​​are extracted to form a sample dataset with state labels. The dataset is divided into a training set, a validation set, and a test set in a 7:2:1 ratio. The training set is input into the machine learning model for training. Hyperparameters are adjusted using the validation set, and early stopping is used to prevent overfitting. The model performance is verified using the test set until the model's accuracy in recognizing hunger states reaches over 90%, thus completing the model construction.

[0021] Step 3: Precision Feeding Execution If the signal processing module outputs a hunger status, it immediately sends a feeding instruction to the feeder in the corresponding pig pen. After receiving the instruction, the feeder completes a precise feeding operation according to the basic feeding amount set in advance based on the pig breed, age, weight stage and growth cycle, thus achieving on-demand feeding.

[0022] Step 4: Feedback Optimization and Closed-Loop Control After the pigs finish eating, their weight data is collected by a weighing device, and the amount of feed remaining in the feed trough is also recorded. This data is transmitted to the parameter optimization module as a feeding feedback data. The parameter optimization module dynamically adjusts the subsequent feeding amount based on the feedback data. If there is no feed left after the pigs finish eating and their weight gain is in line with expectations, the feeding amount is maintained. If there is a large amount of feed left, the feeding amount is reduced. If there is no feed left and the weight gain is slow, the feeding amount is appropriately increased.

[0023] Meanwhile, the parameter optimization module supplements the model database with the new EEG data of pigs collected on site. It also fine-tunes and optimizes the hunger state recognition model regularly according to the pig growth cycle (such as nursery period and fattening period), so that the model can adapt to the physiological characteristics of pigs at different growth stages and changes in the pig farm environment, continuously improve the accuracy of state recognition, and realize the closed-loop dynamic control of precise feeding of pigs.

[0024] A precise automatic feeding system for pigs based on electroencephalogram (EEG) analysis is characterized by comprising: an EEG acquisition module, a signal processing module, a feeding execution module, and a parameter optimization module; The brainwaves are used to collect raw brainwave signals of pigs in different states in real time. The signal processing module is used to preprocess and extract features from the raw EEG signals, and to identify the hunger state of pigs through a hunger state recognition model. The feeding execution module includes a feeder that corresponds to each pig pen, which is used to receive feeding instructions and complete precise feeding according to the preset basic feeding amount. The parameter optimization module is used to collect pigs' feeding feedback data, dynamically adjust feeding parameters, and optimize the hunger state recognition model.

[0025] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0026] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis, characterized in that, include: Wearable EEG acquisition devices were used to acquire raw EEG signals of pigs in different states in real time. The raw EEG signal is preprocessed and features are extracted, and the processed feature data is input into the hunger state recognition model for recognition. When the identification result indicates a state of hunger, a feeding instruction is sent to the corresponding pig pen feeder, and the feeder completes the feeding according to the preset basic feeding amount. Feeding parameters are dynamically adjusted based on the feeding feedback after feeding to achieve closed-loop precision feeding.

2. The method for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis according to claim 1, characterized in that, The wearable EEG acquisition device is a non-invasive structure that collects EEG signals by attaching dry or flexible electrodes to specific brain regions in the frontal and parietal lobes of a pig's head.

3. The method for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis according to claim 1, characterized in that, The raw EEG signal is preprocessed and its features are extracted. The processed feature data specifically includes: The original EEG signals were denoised and filtered to remove environmental interference and invalid signals. Then, the characteristic frequency bands and characteristic values ​​of the EEG signals of pigs under different physiological states of hunger and satiety were extracted.

4. The method for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis according to claim 1, characterized in that, The process of constructing the hunger state recognition model is as follows: By artificially controlling the amount of feed given to pigs, sample states are constructed. Raw EEG signals are collected under the corresponding states. After preprocessing the raw EEG signals by noise reduction and filtering, characteristic frequency bands and characteristic values ​​of EEG signals in the states of hunger and satiety are extracted to form a EEG sample dataset with state labels. The sample dataset is divided into training set, validation set and test set according to the proportion. The training set is input into the machine learning model for training to complete the construction of the hunger state recognition model.

5. The method for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis according to claim 1, characterized in that, The preset basic feeding amount is set according to the breed, age, weight stage and growth cycle of the pigs.

6. The method for precise automatic feeding of pigs based on electroencephalogram (EEG) analysis according to claim 1, characterized in that, The dynamic adjustment of feeding parameters includes: After the pigs have finished eating, weigh them using a weighing device, and adjust the amount of feed to be given later based on the amount of feed remaining.

7. A precise automatic feeding system for pigs based on electroencephalogram (EEG) analysis, characterized in that, include: EEG, signal processing module, feeding execution module, and parameter optimization module; The EEG acquisition module is used to acquire raw EEG signals of pigs in different states in real time; The signal processing module is used to preprocess and extract features from the raw electroencephalogram (EEG) signals, and to identify the hunger state of pigs through a hunger state recognition model. The feeding execution module includes a feeder that corresponds to each pig pen, which is used to receive feeding instructions and complete precise feeding according to the preset basic feeding amount. The parameter optimization module is used to collect pigs' feeding feedback data, dynamically adjust feeding parameters, and optimize the hunger state recognition model.

Images