scispace - formally typeset
L

Li Qiaoqin

Publications -  35
Citations -  35

Li Qiaoqin is an academic researcher. The author has contributed to research in topics: Feature extraction & Deep learning. The author has an hindex of 3, co-authored 35 publications receiving 35 citations.

Papers
More filters
Patent

Tongue image quantitative analysis method and platform

TL;DR: In this article, a computer client system for the quantification of traditional Chinese medicine tongue images is presented, which consists of a login module, atongue image quantification module and a data export module.
Patent

Real-time before-collision fall detection method for old people

TL;DR: In this article, an inertial sensor is worn for old people in real time; a human body activity data set in a human activity process is collected in real-time, filtering is conducted through a filter, filtered data are screened through a threshold method to obtain approximate fall and fall action data, the data are labeled and serve as training samples to be inputted to a before-collision fall detection network, model parameters are adjusted, an optimized network model is obtained, accelerometer and gyroscope data acquired in realtime are filtered and are inputted into the optimized before
Patent

Old people falling behavior detection method based on blind source separation

TL;DR: In this article, an old people falling behavior detection method based on blind source separation was proposed, which comprises the following steps: S1, installing a kinect audio sensor at home, and collecting an audio sample data set; S2, performing action category labeling on the audio sample dataset to obtain an original audio data set, S3, performing standardization and whitening processing on the original audio dataset, and S4, establishing a blind-source separation model according to the standard audio dataset and extracting short-time energy characteristics according to independent signal source.
Patent

Stroke patient hand rehabilitation training action recognition method based on array myoelectricity

TL;DR: In this article, a stroke patient hand rehabilitation training action recognition method based on array myoelectricity was proposed, which comprises the steps of collecting myoeectricity sequence data of a forearm of a patient in a training process, and reserving cooperative information of muscles in a physical space and information of muscle activities changing along with time.
Patent

AIDS video propagation and education method and platform based on subject classification

TL;DR: In this paper, an AIDS video propagation and education method and platform based on subject classification is proposed, which consists of a mobile terminal and a server connected through Internet communication, and the mobile terminal requests to obtain the AIDS theme classification through the Internet, and recommends the corresponding AIDS propaganda materials to the users according to the characteristics of the users.