Real-Time Earthquake Detection Using Convolutional Neural Network and Social Data

Hosted By Quinn Fawcett
July 29 9:09 PM- August 1 3:32 AM
1 Favourite
1 Guest
Event Ongoing.
Login to give your RSVP
  • Attending
    Quinn  Fawcett

When & Where


Basic Info
When & Where
Meta Info
  • Twitter has become a potential data source to explore useful information mentioned by users. For instance, Twitter tweets related to an earthquake will be utilized to detect temporal occurrence as well as location information by a humanitarian organization. Therefore, we proposed a Convolution Neural Network (CNN) based method to determine informative tweet and the real-time event detection algorithm to detect the timely occurrence of the given event. In this study, CNN model trained from the tweets related to the earthquake in the past labeled by crowdsourcing plays a role as the classifier to predict an earthquake keyword related tweet is informative or not. Then these informative tweets are considered as input streaming data of time detection phase. Our system with the aid of CNN module can detect the earthquake after it happens in the level of tolerance and ensure earlier than an announcement from official disaster website of government.

    The event is especially organized to introduce the new technology that how we can detect real-time earthquakes at early stages.
Other Info