摘要：With the advancement of physical sensors and scientific modelling, we fortunately are able to track, monitor and even predict most of natural destructive forces, e.g. hurricanes and tornadoes. Compared to other natural disasters, earthquakes are particularly traumatic because they occur without explicit and timely warning and therefore are extremely difficult, if at all possible, to detect timely. Meanwhile, anomalous animal behaviours have been widely observed the day even several days before an Earthquake. Therefore, animals can be used as intelligent geo-sensors to tell or estimate when and where an earthquake will potentially occur. This paper presents a framework synthesizing crowdsourcing reports of anomalous animal behaviour from both active sources (designed mobile app and websites) and passive sources (social networks like Twitter, Facebook) for earthquake early prediction. To demonstrate the effectiveness of the proposed framework, a proof-of-concept prototype is then developed to collect, visualize, analyse and mine such crowdsourcing data to detect a potential earthquake.
