A method for precise control of livestock housing environment based on electromyography signals

Abstract

This invention relates to the field of livestock farming environmental control technology, and in particular to a method for precise regulation of livestock housing environment based on electromyography (EMG) signals. The method includes: collecting EMG signals from livestock under different environmental conditions using a wearable EMG signal acquisition device worn on the livestock; preprocessing the collected EMG signals to extract EMG signal features; constructing a mapping regulation model between environmental changes and livestock physiological states using machine learning algorithms; in actual farming scenarios, collecting EMG signals from a selected number of livestock in real time and transmitting them to the regulation model to analyze and evaluate the livestock's perception of the current environment; summarizing the analysis results using a voting mechanism; and adjusting the environment within the livestock housing according to the regulation results. This invention provides a novel technical solution for intelligent environmental regulation in modern livestock farming, possessing significant technical promotion value and industrial application prospects.

Description

Technical Field

[0001] This invention relates to the field of livestock breeding environment control technology, and in particular to a method for precise control of livestock housing environment based on electromyography signals. Background Technology

[0002] The proper control of livestock housing environmental parameters is a core element in ensuring the healthy growth of livestock and improving the efficiency of large-scale farming. Currently, livestock housing environmental control is mostly based on farmers' experience and fixed industry standards. The core drawback of this approach is that it is divorced from the actual physiological state of livestock and cannot accurately match their environmental comfort needs. When indicators such as temperature, humidity, and concentration of harmful gases in the livestock housing become abnormal, causing physiological reactions such as muscle tension in livestock, existing control technologies struggle to capture these physiological signals and respond promptly.

[0003] Meanwhile, existing technologies lack a correlation model between livestock electromyographic signals and environmental factors in livestock housing, and lack a linkage mechanism between physiological signals and environmental regulation. They rely solely on manually set fixed thresholds for environmental adjustment, ignoring the subjective differences in individual livestock's environmental perceptions. This ultimately leads to insufficient precision and timeliness in environmental regulation, easily triggering stress responses in livestock, increasing breeding risks, and reducing breeding efficiency. Therefore, there is an urgent need for a precise method for regulating the livestock housing environment based on the actual physiological perceptions of livestock, achieving real-time and accurate matching of environmental parameters with the physiological state of livestock. Summary of the Invention

[0004] The purpose of this invention is to provide a precise control method for livestock housing environment based on electromyography signals, which aims to solve the technical problems of existing livestock housing environment control being detached from the actual physiological sensations of livestock, having low control accuracy, and lacking a linkage mechanism between physiological signals and environmental factors, so as to realize intelligent and precise control of livestock housing environment and improve breeding management efficiency.

[0005] To achieve the above objectives, the present invention provides the following solution: A method for precise control of livestock housing environment based on electromyographic signals, comprising: By using a wearable electromyography (EMG) signal acquisition device worn on livestock, EMG signals of livestock under different environmental conditions are collected. The collected electromyographic signals were preprocessed to extract their features, and a mapping and regulation model of environmental changes and livestock physiological state was constructed using machine learning algorithms. In actual farming scenarios, electromyography signals of a selected number of livestock are collected in real time and transmitted to a control model to analyze and evaluate the livestock's perception of the current environment. The voting mechanism is used to summarize and analyze the results, and the environment inside the livestock sheds is adjusted based on the results.

[0006] Furthermore, the environmental indicators include one or more of the following: temperature, relative humidity, ammonia concentration, carbon dioxide concentration, wind speed, and light intensity.

[0007] Furthermore, methods for extracting electromyographic signal features include Fourier transform, wavelet transform, or power spectrum analysis; the electromyographic signal features include power, coherence, and event-related potentials in each frequency band.

[0008] Furthermore, the mapping and regulation model between environmental changes and livestock physiological states is constructed using machine learning algorithms as follows: First, in a laboratory environment, the collected electromyographic signals are time-synchronized and correlated with the corresponding environmental indicator data. Then, the electromyographic signal features are extracted using digital signal processing technology. The electromyographic signal features and environmental indicator data are used as training samples, and machine learning algorithms are used to train the model to establish a mapping relationship between environmental changes, electromyographic signal response patterns and livestock physiological states, thus forming the mapping regulation model.

[0009] Furthermore, the preprocessing of the electromyographic signal includes noise reduction and filtering of the electromyographic signal.

[0010] Furthermore, the number of livestock selected in actual breeding scenarios is an odd number.

[0011] Furthermore, adjusting the environment inside the livestock shed includes regulating the operating parameters of the ventilation equipment, heating / cooling equipment, ammonia removal equipment, and lighting equipment. After adjusting the environment, the livestock electromyography signals are continuously collected, and the regulation model is optimized based on the new signal data.

[0012] Furthermore, the wearable electromyography (EMG) signal acquisition device is a non-invasive acquisition device, worn on the limbs or neck of livestock, and transmits the acquired EMG signals to the control model wirelessly via Bluetooth or WiFi. The present invention discloses the following technical effects: This invention uses electromyography (EMG) signals collected by a non-invasive wearable device as a direct physiological representation of livestock environmental comfort. It combines digital signal processing technology to extract signal features and constructs a mapping model between environmental changes and livestock physiological states through machine learning algorithms. This model can accurately identify the livestock's perception of environmental indicators such as temperature, humidity, concentration of harmful gases, wind speed, and light. By relying on odd-number sample selection rules and voting mechanisms to summarize the group's perception results, it effectively avoids regulation errors caused by individual signal bias and improves the accuracy and reliability of environmental regulation decisions. 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 schematic diagram of the overall process of the precise control method for livestock housing environment based on electromyography signals according to 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] 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.

[0017] As shown in Figure 1, this invention provides a method for precise control of livestock housing environment based on electromyography signals. Taking large-scale pig farming as an example, the method specifically includes the following steps: Electromyography (EMG) signal acquisition: Healthy fattening pigs were selected as experimental subjects. Non-invasive wearable EMG signal acquisition devices were worn on the limbs and neck of the pigs. In a controlled laboratory environment, the changes of different environmental indicators such as temperature, relative humidity, and ammonia concentration in the pigsty were simulated. EMG signals of the pigs were collected simultaneously under different combinations of environmental indicators, and the numerical range of each environmental indicator was recorded.

[0018] Signal preprocessing and feature extraction: The acquired raw electromyographic signals are transmitted to the signal processing terminal. First, the raw signals are denoised and filtered using digital signal processing technology to remove environmental interference and noise. Then, Fourier transform and wavelet transform methods are used to extract key features of the electromyographic signals, such as power, coherence and event-related potentials in each frequency band, to form a standardized electromyographic signal feature dataset.

[0019] Regulation model construction: First, in a laboratory environment, the collected electromyographic (EMG) signals were time-synchronized and correlated with corresponding environmental indicator data. Then, digital signal processing techniques were used to extract EMG signal features. These EMG signal features and environmental indicator data were used as training samples, and machine learning algorithms were employed to train the model. This established a mapping relationship between environmental changes, EMG signal response patterns, and livestock physiological states, forming the mapping and regulation model. Real-time monitoring and analysis: In a real-world large-scale pig farm setting, 11 healthy fattening pigs were randomly selected and fitted with the same wearable electromyography (EMG) signal acquisition device. The device transmitted the real-time collected EMG signals to the intelligent control terminal in the pig farm via Bluetooth. The control terminal then input the EMG signals into a pre-built control model, which analyzed and evaluated each pig's subjective feelings about the current pig farm environment.

[0020] Voting and Environmental Control: A majority-based voting mechanism was used to summarize the environmental perception analysis results of 11 pigs. If the analysis showed that 8 pigs felt cold and 3 pigs did not feel cold significantly, it was determined that the pigsty temperature needed to be increased. The control terminal sent this control request to the central environmental controller, which automatically increased the operating power of the heating equipment in the pigsty and appropriately reduced the ventilation frequency of the ventilation equipment to complete the environmental control. During this process, farm staff were assigned to supervise manually. If the model determined that the pigsty environment was comfortable, but the actual ammonia concentration exceeded the normal range, the system automatically triggered an audible and visual alarm, and the ammonia removal equipment was manually activated. The abnormal data was then fed back to the database.

[0021] Closed-loop model optimization: After temperature regulation, the wearable electromyography (EMG) signal acquisition device continuously collects EMG signals from the pigs. The control model receives new signal data and pigsty environmental indicators in real time, continuously optimizing, training, and iteratively updating the model parameters. This allows the model to adapt to changes in the pigs' growth stages, seasonal environmental changes, and other factors, continuously improving the accuracy of environmental regulation. If new environmental discomfort occurs in the pigsty, the model can quickly identify and trigger precise regulation, forming a closed-loop control system of "collection-analysis-regulation-optimization".

[0022] 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.

[0023] 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 control of livestock housing environment based on electromyography signals, characterized in that, include: By using a wearable electromyography (EMG) signal acquisition device worn on livestock, EMG signals of livestock under different environmental conditions are collected. The collected electromyographic signals were preprocessed to extract their features, and a mapping and regulation model of environmental changes and livestock physiological state was constructed using machine learning algorithms. In actual farming scenarios, electromyography signals of a selected number of livestock are collected in real time and transmitted to a control model to analyze and evaluate the livestock's perception of the current environment. The voting mechanism is used to summarize and analyze the results, and the environment inside the livestock sheds is adjusted based on the results.

2. The method for precise control of livestock housing environment based on electromyography signals according to claim 1, characterized in that, The environmental indicators include one or more of the following: temperature, relative humidity, ammonia concentration, carbon dioxide concentration, wind speed, and light intensity.

3. The method for precise control of livestock housing environment based on electromyography signals according to claim 1, characterized in that, Methods for extracting electromyographic signal features include Fourier transform, wavelet transform, or power spectrum analysis; the electromyographic signal features include power, coherence, and event-related potentials in each frequency band.

4. The method for precise control of livestock housing environment based on electromyography signals according to claim 1, characterized in that, The specific steps for constructing a mapping and regulation model between environmental changes and livestock physiological states using machine learning algorithms are as follows: First, in a laboratory environment, the collected electromyographic signals are time-synchronized and correlated with the corresponding environmental indicator data. Then, the electromyographic signal features are extracted using digital signal processing technology. The electromyographic signal features and environmental indicator data are used as training samples, and machine learning algorithms are used to train the model to establish a mapping relationship between environmental changes, electromyographic signal response patterns and livestock physiological states, thus forming the mapping regulation model.

5. The method for precise control of livestock housing environment based on electromyography signals according to claim 1, characterized in that, The preprocessing of the electromyographic signals includes noise reduction and filtering.

6. The method for precise control of livestock housing environment based on electromyography signals according to claim 1, characterized in that, In actual farming scenarios, the number of livestock selected is odd.

7. The method for precise control of livestock housing environment based on electromyography signals according to claim 1, characterized in that, Regulating the environment inside the livestock shed includes adjusting the operating parameters of ventilation equipment, heating / cooling equipment, ammonia removal equipment, and lighting equipment. After adjusting the environment, the livestock electromyography signals are continuously collected, and the regulation model is optimized based on the new signal data.

8. The method for precise control of livestock housing environment based on electromyography signals according to claim 1, characterized in that, The wearable electromyography (EMG) signal acquisition device is a non-invasive acquisition device that is worn on the limbs or neck of livestock and transmits the acquired EMG signals to the control model via Bluetooth or WiFi wireless transmission.

Images