Click here to load reader
Upload
poo-kuan-hoong
View
96
Download
0
Embed Size (px)
Citation preview
CONTEXT AWARE ROAD TRAFFIC SPEECH INFORMATION
SYSTEM FROM SOCIAL MEDIA
This project focuses on developing a
mobile application that transmits real-time
traffic state to motorcyclists. The traffic
data is collected from Twitter. The data
collected is subjected to various processes
like Named Entity Recognition, Sentiment
Analysis and Statistical Analysis and the
derived traffic state will be transmitted to
the user’s mobile application. A Bluetooth
enabled helmet of a motorcyclist will then
playback the traffic state to the user
according to their location.
Lim Cheng Yang, Ian K.T. Tan, Bhawani Selvaretnam, Poo Kuan Hoong (Multimedia University)
Ewe Kok Howg, Lau Heng Kar (Intel)
Overview
1) To derive traffic state from various
traffic condition reports.
2) To provide traffic state information
based on user’s coordinates.
3) To develop a mobile application for
vocal transmission of traffic state to
users.
Objectives
The dynamics that occur on daily
road traffic conditions can be taxing and
disruptive for many motorists. Having prior
knowledge of the traffic conditions ahead
can alleviate some of the stress. Recently,
approaches using crowd sourced
information has been successful in
applications such as Waze. However,
these applications generally serve
motorists in enclosed vehicles that have
the luxury of on-board information
systems. Meanwhile, motorcyclist aren’t
able to use these applications, making
them vulnerable to the sudden changes of
traffic conditions.
Twitter contains real-time information
that could be useful to the road users. The
traffic tweets can be classified into formal
and informal sources. These data could be
extracted and processed into useful traffic
information that could help out the road
user, and in this case, motorists.
Traditional traffic applications used
Global Positioning systems to determine
the user’s position and this method is used
in this project. The GPS coordinates will
determine the users location and the
application will use it to grab the respective
data from the database.
Using Bluetooth helmet as a medium
to transmit the data to the user is a must
as motorcyclist are not encouraged to use
enclosed headphones.
Background Study
Development Requirements
1) Android Studio 1.0 or higher
2) PyCharm
3) Spring Tool Suite
4) MongoDB
Hardware Requirements
1) Android phone (4.3 & above)
2) Bluetooth speaker integrated helmet
Requirements
Figure 1: Request for traffic condition ahead
Figure 2: Detection of congestion ahead
Figure 3: Report to the user
Idea
In this project, the traffic tweets
will be collected through Twitter API
and the location and traffic
conditions will be extracted through
NER. The tweets will then go though
semantic analysis to determine the
polarity of the traffic state. An
Android application will request the
traffic state according to the location
of the user. The traffic state will then
be reported to the user through the
Bluetooth helmet. With the usage of
this Android application,
motorcyclists could get traffic
information based on their locations.
Conclusion
Named
Entity
Recognition
Phone Application
raw traffictweet
User location (GPS)
Traffic state ahead
Implementation
1. Li, Chenliang, et al. "Twiner: named
entity recognition in targeted twitter
stream." Proceedings of the 35th
international ACM SIGIR conference on
Research and development in
information retrieval. ACM, 2012.APA
2. Java, Akshay, et al. "Why we twitter:
understanding microblogging usage and
communities." Proceedings of the 9th
WebKDD and 1st SNA-KDD 2007
workshop on Web mining and social
network analysis. ACM, 2007.
3. Agarwal, Apoorv, et al. "Sentiment
analysis of twitter data." Proceedings of
the workshop on languages in social
media. Association for Computational
Linguistics, 2011.
4. Ritter, Alan, Sam Clark, and Oren Etzioni.
"Named entity recognition in tweets: an
experimental study." Proceedings of the
Conference on Empirical Methods in
Natural Language Processing.
Association for Computational
Linguistics, 2011.
References
Sentiment
Analysis
Statistical
Analysis Database
traffictweet
Location and state
Location, state
Request location state
Location traffic state
Request Web service:
Sending GPS coordinates
Jalan Pudu is
jam