Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/77186
Title: Evaluation of machine learning methodologies on Wi-Fi activity recognition
Authors: Lim, Hao Zhe
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Issue Date: 2019
Abstract: Activity recognition using Wi-Fi remains as a wide topic for many researchers due to its potential for a lower cost and wider area coverage when compared to traditional motion capturing devices and hardware. In this project, several machine learning algorithms will be applied to Wi-Fi captured packet data containing various actions performed by a user to determine which algorithms have a higher rate of classifying the right user actions. Firstly, experimental data will be captured using a router and a receiver and CSI data will be extracted through the AtherosCSI tool. Feature Selection will then be performed on the captured data to generate datasets. These generated datasets will then be put through several machine learning models to evaluate the predictive accuracies for each machine learning model. Experimental results show that using Logistic Regression and Linear Discriminant Analysis Algorithms gave the best prediction accuracy on classifying new inputs of data.
URI: http://hdl.handle.net/10356/77186
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP Report.pdf
  Restricted Access
1.38 MBAdobe PDFView/Open

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.