Patient behavior multimodal analysis and prediction system based on statistical learning

Abstract

The invention relates to a patient behavior multimodal analysis and prediction system based on statistical learning. The system comprises a multimodal acquisition module, a posture-based patient behavior recognition module, a physiological signal-based patient behavior recognition module, an emotion signal-based patient behavior recognition module, a voice signal-based patient behavior recognitionmodule and a multi-kernel learning-based fusion module. The multi-kernel learning-based fusion module comprises a multi-kernel classifier, and the training process of the multi-kernel learning-basedfusion module specifically comprises the steps that all kernel functions are trained and combined, then overall training is conducted, and the weight coefficient of each kernel function is obtained. Compared with the prior art, according to the invention, the applied multimodal data is closer to the real form of the patient information flow under the background of cloud computing and big data, hascomprehensiveness and complexity, reduces the loss of a large amount of information when facing complex nonlinear multi-modal information processing by utilizing the multi-feature multi-core learningmethod, and has better performance when processing data with larger modal span.

Description

technical field [0001] The invention relates to the field of patient behavior recognition, in particular to a multimodal analysis and prediction system of patient behavior based on statistical learning. Background technique [0002] Patient behavior refers to a behavioral response mediated by subjective feelings such as patient cognition, emotion, and past experience in a medical setting. Specifically, it refers to patient image information, voice information, and physiological signals collected by medical diagnostic equipment, such as B-ultrasound, computerized tomography (CT), nuclear magnetic resonance, and fixed-point 3D motion capture systems. [0003] Facing the field of medical diagnosis scenarios and patient behavior analysis, in today's rapid development of artificial intelligence, statistical learning is used to adopt a data-driven approach to analyze and predict multi-modal patient behavior data, which can provide a basis for the next step in the correlation analy...

AI Technical Summary

Problems solved by technology

Traditional statistical learning methods tend to cause a large amount of information loss when faced with complex nonlinear multi-modal information processing, and perform poorly when dealing with data with large modal spans.

[0006] Restricted by the level of medical technology and computing resources, the existing statistical learning methods often deal with small and medium-sized data sets, which are lacking in the processing of huge multi-modal data sets of patient behavior, such as case record text information processing , Image information processing and other tasks extracted by the video surveillance system, most of them require technical personnel to participate in the process of feature extraction and processing, which causes a lot of waste of human resources while the accuracy is not high

[0007] Although the research on patient behavior recognition based on single modality has achieved good results, these methods are generally limited to specific scenarios and a single data set, and are easily disturbed by data noise. and the generalization ability of the data set is weak

Images