Method, system, device and medium for matching electrocardiographic signal and music signal
An ECG signal and signal matching technology, applied in the field of signal processing, can solve problems such as difficulty in quantification, semantic gap between ECG signal and music, etc.
Active Publication Date: 2022-05-20
HEFEI HEART VOICE HEALTH TECH CO LTD
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In order to solve the technical problems existing in the background technology, the present invention proposes a matching method, system and device for electrocardiographic signals and music signals, which uses the emotional information contained in the two signals as a link to solve the problem between electrocardiographic signals and music. Difficult to quantify the relationship between the two caused by the semantic gap
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0035] A technical solution for matching electrocardiographic signals and music signals in an embodiment of the present invention is used to evaluate the similarity of emotional information between electrocardiographic signals and music signals by establishing a deep learning model. refer to figure 1 , the deep learning model includes two branches: the music branch and the ECG branch. Each branch is specifically composed of the following parts: feature extraction module, valence-wake predictor, and similarity predictor. Among them, valence-arousal is a commonly used emotional model, and the value of valence-arousal can be used to measure emotions. Valence represents degrees of pleasure and unpleasantness (i.e., positive and negative), and arousal represents degrees of excitement and calm.
[0036] In the present invention, the emotion-based matching deep learning algorithm of ECG signal and music signal includes: preprocessing the ECG signal sample and the music signal sampl...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method, system, device and medium for matching an electrocardiogram signal and a music signal. The method comprises: preprocessing the samples of the electrocardiogram signal and the samples of the music signal respectively, and obtaining the sample data of the electrocardiogram signal and the sample data of the music signal Carry out feature vector extraction to described ECG signal sample data and described music signal sample data respectively, obtain ECG feature vector and music feature vector; According to described ECG emotion information, described music emotion information, described similarity The similarity prediction model is optimized and trained to obtain a target similarity prediction model; ECG signals and music signals to be matched are obtained, and the similarity is obtained based on the target similarity prediction model. The invention uses the emotional information contained in the two signals as a link to solve the problem that it is difficult to quantify the relationship between the ECG signal and the music caused by the semantic gap.
Description
technical field [0001] The present invention relates to the technical field of signal processing, in particular to a method, system, device and medium for matching electrocardiographic signals and music signals. Background technique [0002] ECG (electrocardiogram, electrocardiogram) signal is a physiological electrical signal that records periodic and rhythmic myocardial activity, and music signal is a creative sound signal with melody and sound produced by humans. The two types of signals, ECG and music, have very different semantics. The human ECG signal is a very weak physiological low-frequency electrical signal, usually the maximum amplitude does not exceed 5mV, the signal frequency is between 0.05-100Hz, and the frequency of the music signal is generally between 300-3400Hz. Compared with music signals, ECG signals are weaker, lower frequency, and have interference noise. At present, there are a wide range of applications by quantifying the relationship between ECG s...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/635A61B5/318A61B5/16A61B5/00A61M21/02
Inventor 韩玉虎耿世佳洪申达周荣博俞杰鄂雁祺傅兆吉田城恺
Owner HEFEI HEART VOICE HEALTH TECH CO LTD