APPARATUS FOR RECOGNIZING FEATURE OF USER METHOD FOR ESTABLISHING BASIS MATRIX BASED ON ORTHOGONAL NON-NEGATIVE MATRIX FACTORIZATION AND METHOD FOR ESTABLISHING BASIS MATRIX BASED ON ORTHOGONAL SEMI-SUPERVISED NON-NEGATIVE MATRIX FACTORIZATION

摘要

Disclosed are a user behavior recognition apparatus based on multiple sensors and label information, an ONMF based basis matrix generation method, and an OSSNMF based basis matrix generation method. According to an aspect, an apparatus for recognizing user behavior includes: a feature vector extractor configured to multiply a transpose matrix of an orthogonal basis matrix by a sensor data matrix of sensor data of frequency domains obtained from two or more sensors; And a multi-class classification unit classifying the extracted ONMF-based feature vector into any one of two or more types of user behaviors.