arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.01259eess.SP
收藏

利用先验知识输入改进基于 LSTM 自编码器的车辆感知数据表征

Prior Knowledge Input to Improve LSTM Auto-encoder-based Characterization of Vehicular Sensing Data

Nima Taherifard, Murat Simsek, Charles Lascelles, Burak Kantarci

AI总结:

针对车辆驾驶数据不平衡与事件稀少问题,提出结合先验知识输入和循环去噪自编码器数据扩充的 LSTM 表征模型,使准确率达到 0.96,较基线提升 14.7%。

摘要:

随着现代车辆具备响应式互联能力,联网车辆中事件表征的精度变得日益重要。通过车辆传感器进行的事件表征被用于车辆安全和自动驾驶应用。尽管已有研究表明表征系统能够预测危险驾驶模式,但此类系统的精度仍是一个尚未解决的问题。在联网车辆环境中,驾驶事件表征系统需要应对的主要问题包括:驾驶数据严重不平衡、事件发生稀少,以及需要存在针对车辆环境优化的时序检测系统。为克服这些问题,我们将先验知识输入方法引入表征系统。此外,我们提出一种基于循环网络的去噪自编码器网络,用于扩充现有数据,从而实现更稳健的训练过程。实验结果表明,引入基于知识的建模使现有系统达到显著更高的准确率和 F1 分数水平。最终,两种方法的结合使所提出模型的准确率达到 0.96,相比基线获得 14.7% 的准确率提升。

英文摘要:

Precision in event characterization in connected vehicles has become increasingly important with the responsive connectivity that is available to the modern vehicles. Event characterization via vehicular sensors are utilized in safety and autonomous driving applications in vehicles. While characterization systems have been shown to be capable of predicting the risky driving patterns, precision of such systems still remains an open issue. The major issues against the driving event characterization systems need to be addressed in connected vehicle settings, which are the heavy imbalance and the event infrequency of the driving data and the existence of the time-series detection systems that are optimized for vehicular settings. To overcome the problems, we introduce the application of the prior-knowledge input method to the characterization systems. Furthermore, we propose a recurrent-based denoising auto-encoder network to populate the existing data for a more robust training process. The results of the conducted experiments show that the introduction of knowledge-based modelling enables the existing systems to reach significantly higher accuracy and F1-score levels. Ultimately, the combination of the two methods enables the proposed model to attain 14.7\% accuracy boost over the baseline by achieving an accuracy of 0.96.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑