Li Rui, Song Xueyi, Xie Yongliang
Zhejiang Technical Institute of Economics, Hangzhou, Zhejiang, China.
China Construction Civil Engineering Co. Ltd., Beijing, China.
PLoS One. 2025 Jun 2;20(6):e0324752. doi: 10.1371/journal.pone.0324752. eCollection 2025.
With the progress in sensor technology and the spread of mobile devices, transportation mode detection (TMD) is gaining importance for health and urban traffic improvements. As mobile devices become more lightweight, they require more efficient, low-power models to handle limited resources effectively. Despite extensive research on TMD, challenges remain in capturing non-stationary temporal dynamics and nonlinear fitting capabilities. Additionally, many existing models exhibit high space complexity, making lightweight deployment on devices with limited computing and memory resources difficult. To address these issues, we propose a novel deep TMD model based on discrete wavelet transform (DWT) and knowledge distillation (KD), called KDTMD. This model consists of two main modules, i.e., DWT and KD. For the DWT module, since non-stationary time variations and event distribution shifts complicate sensor time series analysis, we use the DWT modules to disentangle the sensor time series into two parts: a low-frequency part that indicates the trend and a high-frequency part that captures events. The separated trend data is less influenced by event distribution shifts, effectively mitigating the impact of non-stationary time variations. For the KD module, it includes the teacher model and student model. Specifically, for teacher model, to address the nonlinearities and interpretability, we incorporate T-KAN, which is composed of multiple layers of linear KAN that employ learnable B-spline functions to achieve a richer feature representation with fewer parameters. For student model, we develop the S-CNN, which is trained efficiently by T-KAN through KD. The KDTMD model achieves 97.27% accuracy and 97.29% F1-Score on the SHL dataset, and 96.56% accuracy and 96.72% F1-Score on the HTC dataset. Additionally, the parameters of the KDTMD model are only about 10% of the smallest baseline.
随着传感器技术的进步和移动设备的普及，交通方式检测（TMD）对于健康和城市交通改善正变得越来越重要。随着移动设备变得更加轻便，它们需要更高效、低功耗的模型来有效处理有限的资源。尽管对TMD进行了广泛研究，但在捕捉非平稳时间动态和非线性拟合能力方面仍存在挑战。此外，许多现有模型表现出高空间复杂度，使得在计算和内存资源有限的设备上进行轻量级部署变得困难。为了解决这些问题，我们提出了一种基于离散小波变换（DWT）和知识蒸馏（KD）的新型深度TMD模型，称为KDTMD。该模型由两个主要模块组成，即DWT和KD。对于DWT模块，由于非平稳时间变化和事件分布偏移使传感器时间序列分析变得复杂，我们使用DWT模块将传感器时间序列分解为两部分：表示趋势的低频部分和捕捉事件的高频部分。分离出的趋势数据受事件分布偏移的影响较小，有效减轻了非平稳时间变化的影响。对于KD模块，它包括教师模型和学生模型。具体来说，对于教师模型，为了解决非线性和可解释性问题，我们纳入了T-KAN，它由多层线性KAN组成，这些线性KAN采用可学习的B样条函数以用更少的参数实现更丰富的特征表示。对于学生模型，我们开发了S-CNN，它通过KD由T-KAN进行高效训练。KDTMD模型在SHL数据集上达到了97.27%的准确率和97.29%的F1分数，在HTC数据集上达到了96.56%的准确率和96.72%的F1分数。此外，KDTMD模型的参数仅约为最小基线的10%。
