Intelligent watch user identification method based on knocking rhythm

Abstract

The invention discloses a smartwatch user identification method based on knocking rhythm, which comprises the following steps: extracting features from knocking rhythm training data, and constructing feature vectors; a One-class DBSCAN algorithm being utilized to train the model, and a core object set being obtained; and the Euclidean distance between the new sample feature vector and each core object being calculated to identify whether the new sample belongs to the class of the core vector. Aiming at the privacy problem caused by the lack of appropriate user identification of the smart watch, the invention provides a novel smart watch user identification method based on the knocking rhythm, and provides a novel one-class classification algorithm One-class DBSCAN, and the method is suitable for setting of a relatively small screen and low power consumption of the smart watch, and has the advantages of being simple in structure and convenient to use. The new class classification algorithm One-class DBSCAN can accurately judge whether a new sample belongs to the current class or not under the condition that only one class of training data exists.

Description

technical field [0001] The invention relates to the technical field of privacy protection of wearable devices, in particular to a smart watch user identification method based on tapping rhythm. Background technique [0002] Wearable devices come in various types such as smart glasses, headphones, fitness wristbands, and smart watches. Since Motorola released the Moto 360 with Android Wear as the operating system in March 2014, fitness wristbands and smart watches have become more and more popular. According to the Cisco Virtual Networking Index, there will be 600 million wearable devices in use in 2020, six times more than in 2015. In addition, more functions of smart watches have been developed, such as Apple Watch can send emails. [0003] The physiological data measured by the sensors of smart watches is the personal information of most users, which is more private and sensitive than mobile phone numbers and email addresses. Malicious actors can infer high-value intell...

AI Technical Summary

Problems solved by technology

However, automatic identification needs to obtain sensor data every moment, which will cause unnecessary large power consumption, and the application of neural network models in smart watches will consume a lot of computing resources

Therefore, this scheme generates unnecessary power consumption

Images