Traffic Incident Detection Based on Extreme Machine Learning

Linchao Li ； Xu Qu ； Jian Zhang ； Bin Ran

《淡江理工學刊》 20卷4期 (2017/12) Pp. 409-416

https://doi.org/10.6180/jase.2017.20.4.01

摘要

Traffic incident detection is an essential part of the intelligent transportation system and attracts lots of attention from researchers in different areas. To reduce the computation and to avoid over-fitting of the traditional feed-forward neural network, an extreme machine learning is implemented to detect traffic incidents. Using the real-world data, the proposed model is compared with feed-forward neural network and other two commonly used models by several evaluation criteria. The results indicate the proposed model has the highest accuracy, detection rate and lowest false alarm rate. Moreover, it consumes less time. In conclusion, the performance of the proposed model is better than other benchmark models and suit to detect traffic incidents.

關鍵字

Intelligent Transportation System ； Extreme Machine Learning ； Feed-forward Neural Network ； Performance