CAJ | 학술논문

随着数据采集手段的不断提高和相关研究技术的发展，基于数据挖掘的模型逐渐成为交通事件持续时间研究的主要方向。根据荷兰交通部门提供的交通事件采集数据，进行分类和预处理，观察事件持续时间的频数图，并根据相关的研究按照事件典型的类别把采集的数据进行分类。使用主成分分析和逐步回归提取出显著性的影响因子，利用数据挖掘软件WEKA建立贝叶斯网络模型，用数据集中80%的数据进行学习建模，20%的数据作为测试集来检测模型的预测效果，并做出性能评价。实验结果表明，与同类数据集的其他预测方法相比，贝叶斯网络模型对于变数众多，随机性特别大的交通事件，预测精度较高，证明贝叶斯网络模型的算法是具有一定优越性和实用价值。
수착수거채집수단적불단제고화상관연구기술적발전，기우수거알굴적모형축점성위교통사건지속시간연구적주요방향。근거하란교통부문제공적교통사건채집수거，진행분류화예처리，관찰사건지속시간적빈수도，병근거상관적연구안조사건전형적유별파채집적수거진행분류。사용주성분분석화축보회귀제취출현저성적영향인자，이용수거알굴연건WEKA건립패협사망락모형，용수거집중80%적수거진행학습건모，20%적수거작위측시집래검측모형적예측효과，병주출성능평개。실험결과표명，여동류수거집적기타예측방법상비，패협사망락모형대우변수음다，수궤성특별대적교통사건，예측정도교고，증명패협사망락모형적산법시구유일정우월성화실용개치。
With the continuous improvement of data collection instruments and related research and technological development, establishing models based on data mining has become the main direction for studying the traffic incident duration. Based on traffic incident data from the Dutch transport sector, this paper conducts classification and pre-processing, analyzes the event duration frequency chart, and classifies the collected data according to the typical event category. By using principal component analysis and stepwise regression to extract significant impact factor, it establishes Bayesian network model through data mining software WEKA .Then with 80%of the data in the dataset to learn modeling, 20%of the data as a test set to test the predicted effects, this study makes performance evaluation. Experimental results show that compared to other prediction methods, Bayesian network model algorithm has higher prediction accuracy and high randomicity for a number of large traffic events with many variables.