Please use this identifier to cite or link to this item:
|Title:||Touchless detection and classification of finger actions using radar sensor and machine learning||Authors:||Shen, Chen||Keywords:||Engineering::Electrical and electronic engineering::Antennas, wave guides, microwaves, radar, radio||Issue Date:||2021||Publisher:||Nanyang Technological University||Source:||Shen, C. (2021). Touchless detection and classification of finger actions using radar sensor and machine learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/153497||Project:||P3021-201||Abstract:||With the increasing threat of viruses to people in today's society, there is a growing expectation that we can minimize various contact actions in our daily lives, reducing unnecessary contact and thus reducing the spread of the virus and reducing the chance of infection. In this project, we will explore the use of low-cost millimeter-wave radar to remotely sense the corresponding gestures to replace some popular finger touch gestures, and then analyze and filter the collected gestures through the MATLAB program and convert them to the corresponding gestures. The action instructions are output to the operation panel and executed, which can then form a complete set of non-contact operating systems to provide convenience for people's daily lives. For example, it can be used for simple on/off buttons, and it can also be used for digital buttons for more complex applications, such as replacing traditional elevator buttons to enter buildings. This report focuses on how to use millimeter-wave radar to capture gestures. After the gesture signals are obtained, the captured gestures can be analyzed and filtered through the MATLAB program. The MATLAB program for analyzing gestures will mainly be applied to the Convolutional Neural Network (CNN). Technology to establish a recognition system, an important part of which is the confusion matrix algorithm. Its function is to run a series of recognition and calculations on the collected gesture signals, thereby improving the accuracy of recognizing gesture signals.||URI:||https://hdl.handle.net/10356/153497||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Student Reports (FYP/IA/PA/PI)|
Files in This Item:
|FYP_Project_P3021-201_Final_Report_SHENChen_U1720892H||2.98 MB||Adobe PDF||View/Open|
Updated on Jun 28, 2022
Updated on Jun 28, 2022
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.