The invention provides a time series data labeling method and device, wherein the method comprises the following steps: obtaining a plurality of pieces of time series data, and carrying out preprocessing of the plurality of pieces of time series data; performing feature extraction on the plurality of pieces of preprocessed time series data through Tsfresh, and obtaining contribution degree information of the extracted time series features; performing PCA dimension reduction on the time series features according to the contribution degree information; and labeling the time series features afterthe dimension reduction through IForest. According to the invention, the tagging of the label-free time series data can be conveniently and accurately realized, and the labor cost can be saved.

Time series data labeling method and device

The invention provides a time series data processing method and device, wherein the method comprises the following steps: obtaining a plurality of pieces of time series data, and carrying out preprocessing of the plurality of pieces of time series data; performing feature extraction on the plurality of preprocessed time series data through Tsfresh, and obtaining contribution degree information ofthe extracted time series features; and performing PCA dimension reduction on the time series features according to the contribution degree information. According to the method, feature construction and feature dimension reduction are closely combined, the calculation amount can be reduced, and the efficiency and accuracy of time sequence feature selection are improved.

Time series data processing method and device

The invention discloses an adaptive decision tree fall detection method and system, and belongs to the technical field of human body behavior recognition and judgment. The method comprises the following steps: 1, acquiring three-axis acceleration and three-axis angular velocity data of falling and non-falling actions of a human body, and performing screening; 2, calculating resultant accelerationand resultant angular acceleration, dividing a training set, substituting a test set and a verification set into a TSFRESH library to calculate features, and screening and deleting useless features; 3, selecting preliminary important features by using a random forest sieve; 4, establishing a decision tree model for training and verification, and testing a result; 5, continuing to obtain a new sample, repeating the steps 2 to 4, and updating the decision tree model. According to the invention, an accurate tumble judgment result can be obtained through a decision tree algorithm with a small calculation amount; after a certain number of samples are collected, the decision tree model is updated, so the judgment precision of the algorithm can be further improved.

Xiang Yonghong

Papers

Adaptive decision tree fall detection method and system