An Emergency Event Detection Ensemble Model Based on Big Data

Emergency events arise when a serious, unexpected, and often dangerous threat affects normal life. Hence, knowing what is occurring during after emergency critical to mitigate the effect of incident on humans’ life, environment our infrastructures, as well inherent financial consequences. Social network utilization in event detection models can play an important role information shared users’ status updated once occurs. Besides, big data proved its significance tool assist alleviate by processing enormous amount over short time interval. This paper shows that it necessary have appropriate ensemble model (EEDEM) respond quickly such unfortunate occur. Furthermore, integrates Snapchat maps propose novel method pinpoint exact location event. Moreover, merging social networks accelerate system: data, those from Twitter Snapchat, allow us manage, monitor, analyze detect events. The main objective this efficient data-based EEDEM employing collected networks, “Twitter” “Snapchat”, while integrating (BD) machine learning (ML). evaluates performance five ML base proposed approach Results show achieved very high accuracy 99.87% which outperform other models. yields level accuracy: 99.72%, 99.70% for LSTM decision tree, respectively, with acceptable training time.