Animal heart rate monitoring system and neural network based heart rate state recognition method

Abstract

The invention discloses an animal heart rate monitoring system and a neural network based heart rate state recognition method. The monitoring system includes an acquisition device and an intelligent terminal application; the acquisition device can acquire a contact pressure, the heart rate, 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 heart rate state. The recognition method is based on a neural network, can perform training and learning based on a sample set, and can recognize the animal heat rate state on the basis of the trained model. The monitoring system can achieve automatic detection and remote real-time monitoring of the animal heart rate 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 heart rate monitoring system and a method for recognizing heart rate state based on a neural network. Background technique [0002] Heart rate is an important health indicator of animals, and heart rate monitoring is one of the important ways to evaluate the health status of animals. The timeliness, accuracy and reliability of heart rate monitoring directly affect the prevention, diagnosis, treatment and postoperative recovery of diseases. [0003] Traditional animal heart rate detection takes a single heart rate sample point, which is very inconvenient to track changes in animal heart rate. At present, the measurement of animal heart rate is mainly done manually. The owner needs to manually measure the animal heart rate every day, record the heart rate, and draw the heart rate curve. large workload. Moreover, some animals, such as grazing cattle, cannot coopera...

AI Technical Summary

Problems solved by technology

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

Moreover, some animals, such as free-range cattle, cannot cooperate with heart rate detection, and often require anesthesia to achieve it. For such animals, traditional heart rate 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 of the same age, and different exercise states of the same individual animals often have different normal heart rates, such as: cats in the state of exercise, fear, excitement, overheating, pregnancy, etc. It can temporarily increase the heart rate; another example: the heart rate of adult dogs is 68-80 beats / min, and the normal heart rate of puppies is 80-120 beats / min. Therefore, the monitoring of animal heart rate should consider the type, age, and Individuals, sports status and other differences, and traditional methods are difficult to fully achieve

Images