Animal body temperature monitoring system and machine learning based body temperature state recognition method

Abstract

The invention discloses an animal body temperature monitoring system and a machine learning based body temperature state recognition method. The monitoring system includes an acquisition device and an intelligent terminal application; the acquisition device can acquire a contact pressure, the body temperature, and the acceleration information of an animal to be monitored, and can determine if there is an effective contact or not according to the contact pressure; and the intelligent terminal application receives effective animal data of the acquisition device, and recognizes the effective animal data as an animal body temperature state. The recognition method can learn and acquire the normal body temperature of the animal to be monitored in different motion states, and can recognize the body temperature state of the animal on the basis of learned information. The monitoring system can achieve automatic detection and remote real-time monitoring of the animal body temperature without manual detection or records, and can save lots of manpower. The recognition method can eliminate differences in species, ages, individuals and motion states of the animals, is really customized for each object to be monitored, and can achieve accurate and effective body temperature monitoring.

Description

technical field [0001] The invention relates to the field of animal health monitoring, in particular to an animal body temperature monitoring system and a body temperature state recognition method based on machine learning. Background technique [0002] Body temperature is an important health indicator of animals. Body temperature monitoring is one of the important ways to evaluate the health status of animals. The timeliness, accuracy and reliability of body temperature monitoring directly affect the prevention, diagnosis, treatment and postoperative recovery of diseases. [0003] Traditional animal body temperature detection uses a single body temperature sample point, which is very inconvenient to track changes in animal body temperature. At present, animal body temperature measurement is mainly done manually. The owner needs to manually measure animal body temperature every day, record body temperature, and draw body temperature curves. This is a very difficult task. Big...

AI Technical Summary

Problems solved by technology

[0003] Traditional animal body temperature detection uses a single body temperature sample point, which is very inconvenient to track changes in animal body temperature. At present, animal body temperature measurement is mainly done manually. The owner needs to manually measure animal body temperature every day, record body temperature, and draw body temperature curves. This is a very difficult task. heavy workload

Moreover, some animals, such as grazing cattle, cannot cooperate with body temperature detection, and often require anesthesia to achieve this. For such animals, traditional body temperature detection methods cannot implement high-frequency detection

[0004] In addition, different kinds of animals, different age groups of the same kind of animals, different individuals of the same kind of animals at the same age, and different exercise states of the same individual animals often have different normal / healthy body temperatures. Body temperature in a sleeping or resting state; another example: the normal body temperature of an adult dog is 37.5-38.5°C, while that of a puppy is slightly higher at 38-39°C. Therefore, the monitoring of animal body temperature should consider the type, age, and individuality of the animal. , sports status and other differences, but it is difficult to fully achieve the traditional method

Images