College of Computer Science and Technology, Ocean University of China, Qingdao 266404, China.
Sensors (Basel). 2022 Nov 4;22(21):8499. doi: 10.3390/s22218499.
In recent years, with the diversification of people's modes of transportation, a large amount of traffic data is generated when people travel every day, and this data can help transportation mode detection to be of great use in a variety of applications. Although transportation mode detection has been investigated, there are still challenges in terms of accuracy and robustness. This paper presents a novel transportation mode detection algorithm, DFTrans, which is based on Temporal Block and Attention Block. Low- and high-frequency components of traffic sequences are obtained using discrete wavelet transforms. A two-channel encoder is carefully designed to accurately capture the temporal and spatial correlation between low- and high-frequency components in both long- and short-term patterns. With the Temporal Block, the inductive bias of the CNN is introduced at high frequencies to improve generalization performance. At the same time, the network is generated with the same length as the input, ensuring a long effective history. Low frequencies are passed through Attention Block, which has fewer parameters to capture the global focus and solves the problem that RNNs cannot be computed in parallel. After fusing the output of the feature by Temporal Block and Attention Block, the classification results are output by MLP. Extensive experimental results show that the DFTrans algorithm achieves macro F1 scores of 86.34% on the real-world SHL dataset and 87.64% on the HTC dataset. Our model can better identify eight modes of transportation, including stationary, walking, running, cycling, bus, car, underground, and train, and has better performance in transportation mode detection than other baseline algorithms.
近年来，随着人们出行方式的多样化，人们每天出行时都会产生大量的交通数据，这些数据可以帮助交通模式检测在各种应用中发挥巨大的作用。尽管交通模式检测已经得到了研究，但在准确性和鲁棒性方面仍然存在挑战。本文提出了一种新的交通模式检测算法 DFTrans，它基于时间块和注意力块。使用离散小波变换获取交通序列的低、高频分量。精心设计了双通道编码器，以准确捕捉长短期模式中低频和高频分量之间的时空相关性。通过时间块，在高频处引入 CNN 的归纳偏差，提高泛化性能。同时，网络生成的长度与输入相同，保证了长的有效历史。低频通过具有较少参数的注意力块传递，以捕获全局焦点，并解决 RNN 无法并行计算的问题。通过时间块和注意力块对特征进行融合后，由 MLP 输出分类结果。广泛的实验结果表明，DFTrans 算法在真实的 SHL 数据集上的宏 F1 得分达到 86.34%，在 HTC 数据集上的宏 F1 得分达到 87.64%。我们的模型可以更好地识别包括静止、步行、跑步、骑行、公交车、汽车、地铁和火车在内的八种交通模式，并且在交通模式检测方面的性能优于其他基线算法。
