Analysis and detection method of feeding behavior based on chewing and swallowing action and electrocardiographic activity

Abstract

The invention discloses a method for analyzing and detecting feeding behavior based on chewing and swallowing actions and electrocardiographic activities. Wearable two myoelectric activity sensors, sound sensors, and two electrocardiogram sensors are used. One myoelectric activity sensor is placed on the skin surface of the masticatory muscle in front of the ear, and the other is placed on the thyrohyoid muscle of the neck. The skin surface of the skin, the myoelectric activity sensor is connected to the earphone-type connection structure, the sound sensor and one of the ECG sensors are set at the suprasternal fossa of the neck, the other ECG sensor is set at the back of the neck, the sound sensor and The ECG sensors are all connected to the collar-like connection structure; according to the detected EMG signal combined with the detected sound signal and ECG activity signal, the feeding behavior pattern is analyzed, identified and recorded, and the type of food ingested and the type of food ingested are analyzed and identified respectively. Habit and record the interval and time of eating, the test results are sent to the user's mobile phone, and the results are displayed and suggestions are formed through the user's mobile phone.

Description

technical field [0001] The invention relates to a method for analyzing and detecting feeding behavior. The present invention also relates to a feeding behavior monitoring system using the above feeding behavior analysis and detection method. Background technique [0002] Human feeding is a complex behavioral process, and multiple systems are involved in this process, including the central nervous system, autonomic nervous system, skeletal muscle (chewing and swallowing) system, endocrine system, digestive system and so on. Among them, the autonomic nervous system can be detected by electrocardiographic activity; chewing and swallowing can be detected and recorded by recording the myoelectric activity of related muscles and / or swallowing sounds. By comparing and analyzing the above detection and recording, it can be more objective to reflect different individuals The characteristics and habits of eating behaviors, such as the interval between meals, the type of food preferen...

AI Technical Summary

Problems solved by technology

The data obtained simply recorded the action of eating, and failed to link the emotional activity, autonomic nervous activity, and endocrine and exocrine activities (the above activities are closely related to electrocardiographic activity), and could not fully reflect people's eating behavior. It is impossible to make accurate judgments on eating habits, etc., and it is also impossible to give reasonable dietary advice. For example, if we observe that a person has a rapid heart rate before eating, and the amount of food eaten afterward will increase significantly, this suggests that the possible cause is meal. Pre-hypoglycemia or emotional agitation will cause the person to eat too much, and we can provide targeted intervention and management based on this. If there is no ECG activity record, we will not be able to obtain a complete picture of the patient's eating behavior

[0004] Another technical disadvantage of the existing technology is that the chewing and swallowing actions during the feeding process are very close to some other non-ingesting actions of the human body. Therefore, when the above-mentioned monitoring method is used to monitor the feeding behavior, it is often impossible to rule out the non-ingesting actions during the monitoring process. impact, resulting in unreliable monitoring results

[0005] At the same time, the existing monitoring methods are often unable to distinguish the type of food ingested, for example: whether the food is dry solid, juicy solid or liquid food, semi-liquid food, etc.;

[0006] Most of the feeding monitoring systems used in the prior art cannot be worn around, and cannot achieve long-term continuous monitoring, which affects the monitoring effect

Images