Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/62680
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Beh, Choon Keat | |
dc.date.accessioned | 2015-04-27T04:27:25Z | |
dc.date.available | 2015-04-27T04:27:25Z | |
dc.date.copyright | 2015 | en_US |
dc.date.issued | 2015 | |
dc.identifier.uri | http://hdl.handle.net/10356/62680 | |
dc.description.abstract | In this project, the author developed an Android application to explore the possibility of monitoring queue duration using smartphone built-in sensors. This application adopted a 2-tier framework. Layer 1 detects user’s micro activities by classifying features extracted from raw accelerometer data. These micro activities include standing, walking and sitting. Features extracted from training data are collected and used to build a classification model using J48 decision tree algorithm provided by WEKA. This classification model is integrated into the application to recognise user’s micro activity. Layer 2 extracts high level activity features from the micro activity sequence to detect high level activity. High level activity is categorized into two types, namely physical queue and others. Training data undergoes a pattern mining technique to extract high level features. These features will then be used to build the classification model using J48 algorithm. This model will then be implemented into the application to classify MA sequence to detect queuing process. The application was evaluated by the author and 2 subjects during peak hours of NTU Canteen A. Result shows that the application has a detection rate of 100%. Each queuing process successfully detected. Detection of queuing activity took a maximum of 4 seconds and an average of 5 seconds between detected time and actual queue duration. New classification algorithm should be explored to increase the accuracy in the future development of this application. | en_US |
dc.format.extent | 37 p. | en_US |
dc.language.iso | en | en_US |
dc.rights | Nanyang Technological University | |
dc.subject | DRNTU::Engineering::Computer science and engineering | en_US |
dc.title | Human centric sensing by Android phone | en_US |
dc.type | Final Year Project (FYP) | en_US |
dc.contributor.supervisor | Luo Jun | en_US |
dc.contributor.school | School of Computer Engineering | en_US |
dc.description.degree | Bachelor of Engineering (Computer Science) | en_US |
item.fulltext | With Fulltext | - |
item.grantfulltext | restricted | - |
Appears in Collections: | SCSE Student Reports (FYP/IA/PA/PI) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
CK_FYP_Report_2.pdf Restricted Access | 1.61 MB | Adobe PDF | View/Open |
Page view(s)
314
Updated on Mar 28, 2024
Download(s)
13
Updated on Mar 28, 2024
Google ScholarTM
Check
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.