# KDTMD: Knowledge distillation for transportation mode detection based on KAN

## TL;DR

This paper introduces KDTMD, a new model for detecting transportation modes using sensor data, which is efficient and suitable for lightweight devices.

## Contribution

The novel KDTMD model combines discrete wavelet transform and knowledge distillation for efficient transportation mode detection.

## Key findings

- KDTMD achieves 97.27% accuracy and 97.29% F1-Score on the SHL dataset.
- The model uses only about 10% of the parameters of the smallest baseline model.
- It effectively handles non-stationary time variations and nonlinear fitting.

## Abstract

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.