Please use this identifier to cite or link to this item:
|Title:||Smart hand gesture sensing with millimeter wave radar and machine learning||Authors:||Sang, Jiajun||Keywords:||Engineering::Electrical and electronic engineering||Issue Date:||2022||Publisher:||Nanyang Technological University||Source:||Sang, J. (2022). Smart hand gesture sensing with millimeter wave radar and machine learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157270||Project:||A3137-211||Abstract:||Since the COVID-19 outbreak in 2020 worldwide, it has been more than two years since the pandemic outbreak. Residents worldwide are generally becoming more aware of personal hygiene, especially in crowded urban areas. And thus, scientists are developing more advanced technology for remote control. Such development not only contributes to the control of virus spreading, but also improves the effectiveness and experience of human life. Although voice control technology is becoming popular among others, gesture control using radar is also gaining popularity and serving as an enhancement to improve the overall remote-control performance. This project will focus on gesture sensing technology using millimetre wave radar with the implementation of machine learning and data processing. After numerous testing and selection, four gestures are finalized to be the experimental targets, including holding, pushing, swiping, and waving. These four gestures are relatively identifiable from the data extracted. Before diving into the testing phase, this project also provides a literature review on relevant topics, including Radar basics, and Fourier Transforms. After that, the project will test different data processing techniques to handle gesture data, mainly manipulated in MATLAB. This will involve numerous transforms, data visualizations, and calculations. Lastly, the project will also explore different machine learning techniques to identify different gestures. An innovative way of “democratic voting” of machine learning will be introduced, where the prediction results will follow the majority out of five machine learning model predictions. This method effectively improves the credibility and accuracy of the algorithm.||URI:||https://hdl.handle.net/10356/157270||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Student Reports (FYP/IA/PA/PI)|
Updated on May 25, 2022
Updated on May 25, 2022
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.