AKTMD: Attention-KAN-Based Neural Networks for Transportation Mode Detection

In recent years, with the development of sensor technology and the popularity of smartphones, transportation mode detection has become increasingly integrated into people’s lives, assisting various mobile intelligent services in improving personal health, optimizing urban traffic, etc. Al...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Li, Xueyi Song, Yunmei Wu, Xubo Yu, Hua Huang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10960293/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699977459138560
author Rui Li
Xueyi Song
Yunmei Wu
Xubo Yu
Hua Huang
author_facet Rui Li
Xueyi Song
Yunmei Wu
Xubo Yu
Hua Huang
author_sort Rui Li
collection DOAJ
description In recent years, with the development of sensor technology and the popularity of smartphones, transportation mode detection has become increasingly integrated into people’s lives, assisting various mobile intelligent services in improving personal health, optimizing urban traffic, etc. Although previous studies have addressed fine-grained transportation mode detection, challenges including complex temporal correlations, non-linearities and interpretability required to further addressed. To this end, we propose a novel attention-KAN (Kolmogorov-Arnold Networks) based deep model for transportation mode detection, which primarily consists of three modules: convolutional KAN, multi-head attention and linear KAN. By introducing learnable B-spline functions, KAN can express more abundant feature information with fewer parameters which strengthens the non-linearities modeling and interpretability. Specifically, we employ convolutional KAN, which combines the advantages of KAN and convolutional neural network (CNN) to capture the short-term temporal correlations for distinct sensor features. Then we exploit multi-head attention to effectively capture long-term temporal correlations for linked sensor features in parallel, resulting in better trade-off between accuracy and efficiency. Extensive experimental results demonstrate that our proposed AKTMD model outperforms the state-of-the-art TMD-BERT model among the compared baselines, achieving an accuracy of 98.12% on the SHL dataset and 95.52% on the HTC dataset, with improvements of 5.05% and 3.29% over the TMD-BERT model on each dataset.
format Article
id doaj-art-5d2af437e8fe453cb3d523ced3c89bfe
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-5d2af437e8fe453cb3d523ced3c89bfe2025-08-20T03:18:24ZengIEEEIEEE Access2169-35362025-01-0113636906370210.1109/ACCESS.2025.355941710960293AKTMD: Attention-KAN-Based Neural Networks for Transportation Mode DetectionRui Li0https://orcid.org/0009-0001-9529-9265Xueyi Song1https://orcid.org/0009-0008-9842-4739Yunmei Wu2https://orcid.org/0009-0005-7515-7162Xubo Yu3https://orcid.org/0000-0003-0420-7255Hua Huang4https://orcid.org/0009-0008-5081-8325Zhejiang Technical Institute of Economics, Hangzhou, Zhejiang, ChinaChina Construction Civil Engineering Company Ltd., Beijing, ChinaZhejiang Technical Institute of Economics, Hangzhou, Zhejiang, ChinaThe Institute of Service-Oriented Manufacturing, Hangzhou, Zhejiang, ChinaZhejiang Technical Institute of Economics, Hangzhou, Zhejiang, ChinaIn recent years, with the development of sensor technology and the popularity of smartphones, transportation mode detection has become increasingly integrated into people’s lives, assisting various mobile intelligent services in improving personal health, optimizing urban traffic, etc. Although previous studies have addressed fine-grained transportation mode detection, challenges including complex temporal correlations, non-linearities and interpretability required to further addressed. To this end, we propose a novel attention-KAN (Kolmogorov-Arnold Networks) based deep model for transportation mode detection, which primarily consists of three modules: convolutional KAN, multi-head attention and linear KAN. By introducing learnable B-spline functions, KAN can express more abundant feature information with fewer parameters which strengthens the non-linearities modeling and interpretability. Specifically, we employ convolutional KAN, which combines the advantages of KAN and convolutional neural network (CNN) to capture the short-term temporal correlations for distinct sensor features. Then we exploit multi-head attention to effectively capture long-term temporal correlations for linked sensor features in parallel, resulting in better trade-off between accuracy and efficiency. Extensive experimental results demonstrate that our proposed AKTMD model outperforms the state-of-the-art TMD-BERT model among the compared baselines, achieving an accuracy of 98.12% on the SHL dataset and 95.52% on the HTC dataset, with improvements of 5.05% and 3.29% over the TMD-BERT model on each dataset.https://ieeexplore.ieee.org/document/10960293/Transportation mode detection (TMD)sensorsKolmogorov-Arnold Networks (KAN)convolutional KANmulti-head attention
spellingShingle Rui Li
Xueyi Song
Yunmei Wu
Xubo Yu
Hua Huang
AKTMD: Attention-KAN-Based Neural Networks for Transportation Mode Detection
IEEE Access
Transportation mode detection (TMD)
sensors
Kolmogorov-Arnold Networks (KAN)
convolutional KAN
multi-head attention
title AKTMD: Attention-KAN-Based Neural Networks for Transportation Mode Detection
title_full AKTMD: Attention-KAN-Based Neural Networks for Transportation Mode Detection
title_fullStr AKTMD: Attention-KAN-Based Neural Networks for Transportation Mode Detection
title_full_unstemmed AKTMD: Attention-KAN-Based Neural Networks for Transportation Mode Detection
title_short AKTMD: Attention-KAN-Based Neural Networks for Transportation Mode Detection
title_sort aktmd attention kan based neural networks for transportation mode detection
topic Transportation mode detection (TMD)
sensors
Kolmogorov-Arnold Networks (KAN)
convolutional KAN
multi-head attention
url https://ieeexplore.ieee.org/document/10960293/
work_keys_str_mv AT ruili aktmdattentionkanbasedneuralnetworksfortransportationmodedetection
AT xueyisong aktmdattentionkanbasedneuralnetworksfortransportationmodedetection
AT yunmeiwu aktmdattentionkanbasedneuralnetworksfortransportationmodedetection
AT xuboyu aktmdattentionkanbasedneuralnetworksfortransportationmodedetection
AT huahuang aktmdattentionkanbasedneuralnetworksfortransportationmodedetection