Animal health monitoring system and wearable health monitor
Through multimodal data acquisition and fusion technology, combined with heart rate variability analysis and machine learning, the problem that existing equipment cannot comprehensively monitor animal health is solved, and accurate identification and real-time monitoring of animal physiological and motor status is achieved, providing scientific health management support.
Patent Information
- Application Number
- CN202510654635.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-21
- Publication Date
- 2025-07-04
AI Technical Summary
Existing animal health monitoring equipment mostly uses a single sensor, lacks multimodal data fusion technology, cannot fully reflect the physiological and motor status of animals, and lacks effective abnormal sign recognition capabilities, making it difficult to provide scientific health management support.
The multimodal data acquisition module is adopted, and the micro acceleration sensor, a patch temperature sensor and an inertial measurement unit are integrated. The multimodal data fusion is combined with the data processing module. The abnormal signs are identified using heart rate variability analysis and machine learning algorithms, and data is transmitted in real time through the wireless communication module.
It realizes the synchronous collection of multi-dimensional physiological data of animals and the accurate identification of abnormal signs, provides more comprehensive health information, supports timely intervention measures, and meets the practical needs of breeding and pet feeding.
Smart Images
Figure CN120241010A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of animal health monitoring, and specifically refers to an animal health monitoring system and a wearable health monitor. Background Art
[0002] In the fields of modern animal farming and pet breeding, the importance of animal health monitoring has become increasingly prominent. Traditional animal health monitoring methods, such as manual observation, rely on the experience and subjective judgment of breeders, making it difficult to quantitatively analyze the animal's health status, and there are problems such as untimely monitoring and easy omission of subtle health changes; regular physical examinations have the limitations of a long cycle and the inability to real-time grasp the dynamic health of animals.
[0003] Most of the existing animal health monitoring devices only use a single type of sensor for data collection. For example, some devices only use temperature sensors to monitor body temperature, or only monitor animal activities through simple motion sensors, and cannot comprehensively reflect the physiological and motion states of animals. Even if a few devices adopt a multi-sensor design, in terms of data processing, there is a lack of effective multi-modal data fusion technology, and the data collected by different sensors cannot be organically integrated and synergistically analyzed, resulting in insufficient accuracy and reliability of the monitoring results.
[0004] In terms of abnormal sign recognition, the existing technologies are mostly based on preset simple threshold judgments, which are difficult to adapt to individual animal differences and complex physiological changes. Moreover, there is a lack of the ability to deeply analyze animal sign data using advanced machine learning algorithms, unable to accurately identify the abnormal signs of animals, and unable to provide effective decision-making support for animal health management.
[0005] Therefore, an animal health monitoring system and a wearable health monitor have become problems that people urgently need to solve. Summary of the Invention
[0006] The technical problem to be solved by the present invention is to provide an animal health monitoring system and a wearable health monitor, which can realize real-time monitoring of multiple health indicators such as animal heart rate, respiratory rate, body movement, body temperature, and activity level through multi-modal data collection and fusion, combined with intelligent analysis algorithms, and can accurately identify the abnormal signs of animals, providing a scientific basis for animal health management.
[0007] To solve the above technical problem, the technical solution provided by the present invention is: an animal health monitoring system, specifically including the following modules:
[0008] Data acquisition module: This module integrates a micro acceleration sensor, a patch temperature sensor, and an inertial measurement unit (IMU). Among them, the micro acceleration sensor or piezoelectric film is deployed at the body surface position close to the animal's heart or respiratory movement area, which can accurately capture the BCG signal generated by the animal's heart beat and the mechanical signal caused by respiratory movement; the patch temperature sensor can monitor the animal's body temperature in real time; the IMU is responsible for monitoring the animal's body movement. Multiple sensors work together to achieve synchronous acquisition of multi-dimensional physiological data of the animal.
[0009] Data processing module: It performs fusion processing on the collected multi-modal data to synchronously obtain key health indicators of the animal, such as heart rate, respiratory rate, body movement, body temperature, activity level, etc. In the specific processing process, for the original BCG signal, first use a band-pass filter to filter out noise interference, then amplify the signal through a programmable gain amplifier, flexibly adjust the amplification factor according to the signal strength, then filter again, then perform peak detection and identify the J wave, and then accurately calculate the heart rate; for the respiratory signal, extract the low-frequency signal of 0.1 - 0.5 Hz to calculate the respiratory rate; for the IMU data, perform activity index (AI) analysis to comprehensively evaluate the animal's activity.
[0010] Abnormal detection module: On the one hand, through heart rate variability (HRV) analysis, it can identify the possible stress response of the animal after wearing the instrument; on the other hand, this module has a built-in machine learning model. By training classifiers such as support vector machines (SVM), and using a large amount of normal and abnormal sign data of animals for learning, it can accurately distinguish between normal and abnormal sign patterns of animals. In addition, the abnormal detection module can also store the identified abnormal sign information, and send the data to the terminal device through wireless communication modules such as Bluetooth module, Wi-Fi module, or 4G / 5G communication module, facilitating the breeding personnel to timely grasp the animal's health status.
[0011] Based on the above animal health monitoring system, the present invention also provides an animal wearable health monitor, including a collar, a display device, and the above animal health monitoring system. There is a storage bag on the collar, and the display device is stored in the storage bag. The display device is equipped with the animal health monitoring system, which is convenient to be worn on the animal to realize real-time monitoring and display of the animal's health status.
[0012] The advantages of the present invention compared with the prior art are as follows: Through multi-modal data acquisition, the present invention can comprehensively obtain the physiological and movement data of animals, providing richer and more accurate health information compared with single-sensor monitoring, and providing a more comprehensive basis for animal health assessment.
[0013] The present invention adopts advanced data processing and intelligent analysis algorithms, such as multi-modal data fusion, HRV analysis, SVM classification, etc., which improve the calculation accuracy of animal health indicators and the recognition ability of abnormal signs, can timely detect the health problems of animals, and helps to take intervention measures in advance to ensure animal health.
[0014] The animal wearable health monitor makes the monitoring device easy to be worn on the animal, realizes real-time and continuous monitoring of the animal's health status, meets the needs of actual breeding and pet raising scenarios, and has good practicability and popularization value. Brief Description of the Drawings
[0015] Figure 1 It is a system block diagram of an animal health monitoring system and a wearable health monitor of the present invention.
[0016] Figure 2 It is a schematic structural diagram of the wearable health monitor.
[0017] Figure 3 It is a schematic structural diagram of the collar.
[0018] As shown in the figure: 1. Data acquisition module, 2. Data processing module, 3. Abnormality detection module, 4. Power module, 5. Collar, 6. Display instrument, 7. Storage bag. Detailed Embodiments
[0019] Next, various exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements, numerical expressions, and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present invention.
[0020] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended as a limitation on the present invention or its application or use.
[0021] Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such technologies, methods, and devices should be regarded as part of the specification.
[0022] In all the examples shown and discussed here, any specific value should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values.
[0023] The following further details the animal health monitoring system and the wearable health monitor of the present invention with reference to the accompanying drawings.
[0024] Combined with the attached Figures 1-3 , the specific implementation process of the animal health monitoring system and the wearable health monitor of the present invention is as follows:
[0025] Example 1: Animal Health Monitoring System
[0026] 1. The data acquisition module 1 is the basis for the entire system to obtain animal physiological and motion data, and includes a micro acceleration sensor, a patch temperature sensor, and an IMU (Inertial Measurement Unit).
[0027] Micro acceleration sensor: A high-precision, low-power micro acceleration sensor is selected, such as the ADXL362 of Analog Devices, Inc. It is closely attached to the animal's body surface, such as parts close to the heart and respiratory organs like the chest or abdomen. This sensor can highly sensitively detect the weak micro vibrations generated by the animal's heart beat on the body surface, thereby capturing the BCG (Ballistocardiogram) signal; at the same time, it can also effectively sense the mechanical signals generated by respiratory movements and convert these signals into electrical signals, which are transmitted to the data processing module 2 in the form of analog signals.
[0028] Patch temperature sensor: A flexible, biocompatible patch temperature sensor is adopted, such as the DS18B20 temperature sensor of Maxim Integrated Products, Inc. It is pasted on the animal's skin surface, such as parts with relatively stable temperatures and easy to measure like the ear or armpit. This sensor monitors the animal's body temperature in real time at a certain sampling frequency (such as once per second) and sends the temperature data to the data processing module 2 in the form of digital signals.
[0029] IMU: An IMU module integrated with a three-axis accelerometer, a three-axis gyroscope, and a three-axis magnetometer is selected, such as the MPU-9250 of InvenSense. It is installed at a suitable position on the animal's body, such as the back, to monitor the animal's body movement conditions, including information such as movement direction, speed, and acceleration, and transmits these data to the data processing module 2 in the form of digital signals.
[0030] 2. The data processing module 2 is responsible for fusing the collected multi-modal data and calculating various key health indicators.
[0031] BCG signal processing: When the data processing module 2 receives the BCG raw signal, first a band-pass filter is used to filter the signal. According to the frequency characteristics of the BCG signal, the passband frequency range of the band-pass filter is set to 0.5 - 20 Hz to remove high-frequency noise and low-frequency drift interference. Then, a programmable gain amplifier is used to amplify the filtered signal. The gain multiple of the amplifier can be set by programming according to the actual signal strength (such as adjustable from 10 to 1000 times) to ensure that the signal strength is appropriate. Then, filtering is performed again to further improve the signal quality. Finally, the peaks in the signal are identified through a peak detection algorithm, and the J wave is accurately identified, and the animal's heart rate is calculated based on the time interval between adjacent J waves.
[0032] Respiratory signal processing: For the respiratory signal obtained from the micro-accelerometer, the data processing module 2 uses a low-pass filter for low-frequency extraction, and the extraction frequency range is set to 0.1 - 0.5 Hz to isolate the respiratory signal. By calculating the number of respiratory signal cycles per unit time, the respiratory rate of the animal is obtained.
[0033] IMU data analysis: The data processing module 2 performs activity index AI analysis on the data collected by the IMU. Through a specific algorithm, the data of the triaxial accelerometer, gyroscope, and magnetometer are comprehensively processed to calculate parameters such as the exercise intensity and exercise distance of the animal, and according to the preset activity assessment model, the activity index AI of the animal is obtained to reflect the daily activity of the animal.
[0034] Multi-modal data fusion: The data processing module 2 performs multi-modal fusion on the processed data such as heart rate, respiratory rate, body movement, body temperature, and activity level to form a data set that comprehensively reflects the health status of the animal, providing accurate data support for subsequent anomaly detection.
[0035] 3. The anomaly detection module 3 is a key part to ensure the accuracy and timeliness of animal health monitoring.
[0036] Stress response recognition: The anomaly detection module 3 analyzes the heart rate variability HRV to identify the stress response of the animal after wearing the instrument. Specifically, the differences between adjacent heartbeat cycles are calculated, and statistical analysis is performed on these differences to obtain the heart rate variability index. When this index exceeds the preset threshold range, it is judged that the animal may have a stress response.
[0037] Sign pattern classification: The anomaly detection module 3 contains a machine learning-based model. A large number of labeled normal and abnormal sign data of animals are used to train a support vector machine (SVM) classifier. During the training process, a suitable kernel function (such as the radial basis function RBF) is selected, and the parameters of the SVM (such as the penalty factor C and the kernel function parameter γ) are optimized to improve the accuracy and generalization ability of the classifier. The trained classifier can perform real-time analysis on the data output by the data processing module 2 to distinguish the normal and abnormal sign patterns of the animal.
[0038] Anomaly information processing: When the anomaly detection module 3 identifies the abnormal sign information of the animal, these information will be stored in the local storage unit, such as EEPROM or Flash memory. At the same time, the anomaly information is sent to the terminal device, such as a smartphone, tablet computer or computer, through the wireless communication module, so that the breeder or veterinarian can timely understand the health status of the animal and take corresponding measures.
[0039] 4. The wireless communication module is responsible for transmitting the abnormal physical sign information identified by the abnormal detection module 3 to the terminal device. According to the actual application scenarios and requirements, one or more of the following modules can be selected: a Bluetooth module (such as nRF52832 of Nordic), a Wi-Fi module (such as ESP8266 of ESPRESSIF), or a 4G / 5G communication module. In the scenario of short-distance transmission, the Bluetooth module is preferably used to achieve low-power and fast data transmission. In the scenario of remote monitoring, the Wi-Fi module or 4G / 5G communication module can be adopted to ensure that the data can be stably and real-time transmitted to the remote terminal device.
[0040] 5. The power module 4 provides stable power support for the entire animal health monitoring system and uses a rechargeable battery, such as a lithium polymer battery. The battery capacity is selected according to the power consumption and working duration requirements of the system to ensure that the system can work continuously for a certain period of time (such as more than 72 hours). At the same time, a charging management circuit is equipped to realize functions such as charging, discharging protection, and power monitoring of the battery, extend the battery life, and ensure the normal operation of the system.
[0041] Embodiment 2: Wearable health monitor
[0042] The animal wearable health monitor consists of a collar 5, a display 6, and the above-mentioned animal health monitoring system.
[0043] Collar 5: The collar 5 is made of soft, comfortable, and durable materials, such as silicone, leather, or woven belt, to ensure the comfort and safety of the animal when wearing. The size of the collar 5 can be adjusted according to the neck size of different animals to meet the wearing needs of various animals.
[0044] Display 6: The display 6 is placed in the storage bag 7 on the collar 5. The shell of the display 6 is designed to be waterproof and dustproof to adapt to different usage environments. The display 6 is equipped with the animal health monitoring system and a display screen, which can display key health indicators of the animal, such as heart rate, respiratory rate, body temperature, and activity level, in real time, facilitating the breeder to quickly understand the health status of the animal on-site. At the same time, the display 6 is also provided with operation buttons for operations such as parameter setting and function switching of the system.
[0045] The above describes the present invention and its implementation manners. This description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. Generally speaking, if those of ordinary skill in the art are inspired by it and without departing from the purpose of the present invention creation, they design similar structural manners and embodiments to this technical solution without creative efforts, which should all fall within the protection scope of the present invention.
Claims
1. An animal health monitoring system, characterized in that, Including: A data acquisition module, including a micro-accelerometer, a patch temperature sensor, and an IMU; the micro-accelerometer is used to detect the micro-vibrations on the animal's body surface to capture the BCG signal generated by the heart beat and the mechanical signal generated by the respiratory movement; the patch temperature sensor is used to monitor the animal's body temperature, and the IMU is used to monitor the animal's body movement; A data processing module, used for multi-modal data fusion of the collected data to synchronously monitor heart rate, respiratory rate, body movement, body temperature, and activity level; the data processing module filters the raw BCG signal, amplifies the signal, filters it again, detects the peak and identifies the J wave, and then calculates the heart rate; extracts the low frequency of the respiratory signal, and the extraction frequency range is 0.1 - 0.5 Hz, so as to calculate the respiratory rate; analyzes the activity index AI of the IMU data; An anomaly detection module, used to identify the stress response after wearing the instrument through heart rate variability HRV analysis; the anomaly detection module also includes a machine learning model, the machine learning model trains a classifier, and the classifier is used to distinguish the normal and abnormal physical signs patterns of the animal.
2. The animal health monitoring system according to claim 1, characterized in that: When the data processing module filters the raw BCG signal, a band-pass filter is used.
3. The animal health monitoring system according to claim 2, wherein: When the data processing module amplifies the raw BCG signal, a programmable gain amplifier is used.
4. The animal health monitoring system according to claim 3, characterized in that: The classifier trained by the machine learning model is an SVM.
5. The animal health monitoring system according to claim 4, characterized in that: The anomaly detection module is also used to store the identified abnormal physical sign information and send it to the terminal device through the wireless communication module.
6. The animal health monitoring system according to claim 5, characterized in that: The wireless communication module is one or more of a Bluetooth module, a Wi-Fi module, or a 4G / 5G communication module.
7. An animal health monitoring system according to claim 6, characterized in that: It also includes a power module, and the power module is a rechargeable battery, used to supply power to the data acquisition module, the data processing module, and the anomaly detection module.
8. An animal wearable health monitor, characterized in that: Including a collar, a display instrument, and the animal health monitoring system according to any one of claims 1 - 7, wherein a storage bag is provided on the collar, the display instrument is stored in the storage bag, and the display instrument is equipped with the animal health monitoring system.