Li Qiaoqin

TL;DR: In this article, an exercise prescription recommendation method for the for hypertensive old people based on deep learning was proposed, which comprises the steps: collecting health data; testing the cardiac function state of the hypertensive older people in a quiet state, and evaluating the heart rate, the blood pressure and the variability of heart rate variability; identifying daily actions of the elderly people; evaluating the cardiopulmonary function of the old people; and making personalized exercise prescriptions by referring to FITT rules according to BMI, age, clinical diagnosis and exercise preference.

TL;DR: In this paper, a drug target affinity prediction method based on deep learning was proposed, which relates to the technical field of drug target affinities prediction, and consists the steps of: obtaining a drug compound and target protein data from a Davis data set and a KIBA data set; encoding the compound, and representing the protein by using a position specificity scoring matrix; inputting a compound label code into a CNN model, and performing feature extraction on the compound to obtain molecular representation of the compound; and learning an order relationship between amino acids in a protein sequence.

TL;DR: In this paper, a fall type and injury part detection method based on feature classification is presented, which includes collecting user accelerometer and gyroscope data by a wearable sensor system; performing numerical normalization processing on the acquired sensor data; acquiring time domain and frequency domain features of the preprocessed data; carrying out feature screening by adopting principal component analysis; establishing a tumble detection model based on a random forest, and performing tumble detection and tumble category judgment; and judging a matched fall injury part according to the fall type.

TL;DR: In this paper, an automatic evaluation method of an upper limb motion function in stroke based on deep learning is presented. But the method comprises the following steps: collecting inertial sensing data andmyoelectric data of the upper limb motions of a patient based on a wearable sensor system; performing length normalization and numerical normalization preprocessing on the collected data; respectively inputting the inertial sensors data and myoelectrics data into two convolutional neural networks for feature extraction, performing fusing all characteristics to generate a motion function level based on the Brunnstrom scale

TL;DR: In this paper, a human body tumble detection method based on multi-source heterogeneous data fusion was proposed, which comprises the following steps: acquiring a behavior depth image and skeleton information through Kinect, and getting rid of constraints of a wearable sensor on selection of the sensor; secondly, solving theproblem that wearable sensors cannot be used in specific scenes such as bathrooms and toilets, and meanwhile, avoiding the problem that human privacy is invaded due to the fact that a common camera isused for monitoring.