eduzhai > Applied Sciences > Engineering >

A Dataset of Human Motion Status Using IR-UWB Through-wall Radar

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 14 pages

Abstract: Ultra-wideband (UWB) through-wall radar has a wide range of applications innon-contact human information detection and monitoring. With the integration ofmachine learning technology, its potential prospects include the physiologicalmonitoring of patients in the hospital environment and the daily monitoring athome. Although many target detection methods of UWB through-wall radar based onmachine learning have been proposed, there is a lack of an opensource datasetto evaluate the performance of the algorithm. This published dataset wasmeasured by impulse radio UWB (IR-UWB) through-wall radar system. Three testsubjects were measured in different environments and several defined motionstatuses. Using the presented dataset, we propose a human-motion-statusrecognition method using a convolutional neural network (CNN), the detaileddataset partition method and recognition process flow is given. On thewell-trained network, the recognition accuracy of testing data for three kindsof motion statuses is higher than 99.7 . The dataset presented in this paperconsiders a simple environment. Therefore, we call on all organizations in theUWB radar field to cooperate to build opensource datasets to further promotethe development of UWB through-wall radar.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...