Mobile phone sensor data labeling method based on weak supervised learning

Abstract

The invention discloses a mobile phone sensor data annotation method based on weak supervised learning, which comprises the following steps of: 1, establishing an annotation task, generating a fuzzy query problem corresponding to the annotation task, and judging whether the answer of the fuzzy query problem is yes or no; 2, sending a request for answering the fuzzy query question to a collected person providing data, and collecting a fuzzy label obtained by answering the fuzzy query question by the collected person and mobile phone sensor data associated with the fuzzy label; 3, training a dichotomy depth model by using the fuzzy label acquired in the step 2 and the associated mobile phone sensor data; and 4, processing subsequently collected to-be-labeled mobile phone sensor data through the trained dichotomy depth model to deduce an accurate label of the to-be-labeled mobile phone sensor data, and labeling the to-be-labeled mobile phone sensor data by using the obtained accurate label. According to the method, fuzzy question query of the mobile phone sensor becomes easier, the manual process in the process is simplified, and accurate label data is obtained only through algorithm post-processing of fuzzy answers of a collector.

Description

technical field [0001] The invention relates to the field of mobile computing, in particular to a mobile phone sensor data labeling method based on weakly supervised learning. Background technique [0002] Machine learning and deep learning methods often rely on a large amount of labeled data, and obtaining such a data set requires huge manpower and material resources, and the overhead and cost are high. Especially for mobile phone sensor data (including accelerometers, gyroscopes, etc.), this type of data is different from pictures and audio, and annotators cannot directly give corresponding labels from the appearance of sensor data values, waveforms, etc. For example, this section of data corresponds to The ongoing activities of cell phone holders (running, walking, going upstairs, etc.), which also greatly increases the labeling cost of such data. [0003] The existing mobile phone sensor labeling methods mainly include the following types: [0004] (1) When an annotato...

AI Technical Summary

Problems solved by technology

[0007]Aiming at the problems existing in the existing methods, the purpose of the present invention is to provide a method for labeling mobile phone sensor data based on weakly supervised learning, which can solve the existing problem of mobile phone sensor data The labeling method often has high requirements for the collection environment and the collector, and also requires the labeler to have certain professional knowledge, making it difficult to collect large-scale mobile phone sensor data

Images