earticle

영어

Multi-observation areas based ensemble learning models are proposed for general fatigue performance identification. It is believed that although the expression of fatigue is not obvious. If the observation areas are concerned, the performance of fatigue will be relatively concentrated and the law of expression changes will be much clearer. Another advantage of feature extraction from the observation areas is that it can greatly reduce the interference caused by redundant information in the face when learning classifiers. For each observation area, a C4.5 base classification model is built. Each base model is equivalent to an independent decision maker. But due to its limited capacity, it may not be able to give accurate decisions. However, if the information provided by each decision maker is combined together, it will form comprehensive evidence. Driver status classification results given by ensemble learning approach are more accurate and stable.