• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>9th World conference on transport research (9th WCTR) >APPLYING FUZZY ARTMAP NEURALNETWORKS TO PREDICT DRIVER INJURYSEVERITY IN TRAFFIC ACCIDENTS
【24h】

APPLYING FUZZY ARTMAP NEURALNETWORKS TO PREDICT DRIVER INJURYSEVERITY IN TRAFFIC ACCIDENTS

机译：应用模糊Artmap神经网络预测交通事故中驾驶员的伤害

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Artificial Neural Networks (ANN) from the field of Artificial Intelligence (AI) have recentlyreceived increased attention in the field of transportation. This paper describes a newapproach to analyze and predict driver injury severity using ANN models. The study appliesone of the best well-known neural network architectures; fuzzy Adaptive Resonance TheoryMAP (fuzzy ARTMAP) neural networks. The 1996 and 1997 accident data for the CentralFlorida area was used in this study. Two separate fuzzy ARTMAP neural networks weretrained; a general model and another for two-vehicle accidents occurring at signalizedintersections. The classification accuracy of the two networks were 70.6 and 58.1 percent,respectively. Results of the fuzzy ARTMAP neural network showed that a female driver ismore likely to experience higher severe injury as compared to a male driver. Wearing a seatbelt decreases the chance of having severe injuries. Vehicle speed at the time of an accidentincreases the likelihood of high injury severity. Drivers in passenger cars are more likely toexperience a higher injury severity level than those of vans or pickup trucks. Rural areas aremore dangerous in terms of injury severity than urban areas. Finally, to facilitate theapplication of ANN models, we suggest a series of simulation experiments applying thesemodels.
机译：人工智能（AI）领域的人工神经网络（ANN）最近在交通领域受到了越来越多的关注。本文介绍了一种使用ANN模型分析和预测驾驶员伤害严重性的新方法。该研究采用了最著名的神经网络架构之一。模糊自适应共振TheoryMAP（模糊ARTMAP）神经网络。本研究使用了CentralFlorida地区的1996年和1997年的事故数据。训练了两个独立的模糊ARTMAP神经网络；一个通用模型，另一个用于在信号交叉口发生两车事故的模型。两个网络的分类准确率分别为70.6％和58.1％。模糊ARTMAP神经网络的结果表明，与男性驾驶员相比，女性驾驶员更可能遭受更高的严重伤害。系好安全带可以减少严重受伤的机会。发生事故时的车速增加了造成严重伤害的可能性。乘用车的驾驶员比货车或皮卡车的驾驶员更容易受到伤害。就伤害严重程度而言，农村地区比城市地区更为危险。最后，为促进ANN模型的应用，我们建议了一系列使用这些模型的仿真实验。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号