Optimizing In-Bed Posture Classification Using Tanh-Activated Kolmogorov–Arnold Networks (Tanh-KAN)
In-bed posture classification plays a crucial role in health monitoring. However, existing research on classification involves a limited range of in-bed postures. Meanwhile, in classification tasks, Kolmogorov–Arnold networks (KANs), as an emerging neural network architecture, have research gaps in...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | IET Signal Processing |
| Online Access: | http://dx.doi.org/10.1049/sil2/6740194 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849426194194235392 |
|---|---|
| author | Weiwei Chen Bing Zhou Wai Yie Leong |
| author_facet | Weiwei Chen Bing Zhou Wai Yie Leong |
| author_sort | Weiwei Chen |
| collection | DOAJ |
| description | In-bed posture classification plays a crucial role in health monitoring. However, existing research on classification involves a limited range of in-bed postures. Meanwhile, in classification tasks, Kolmogorov–Arnold networks (KANs), as an emerging neural network architecture, have research gaps in two areas: training strategies and architecture design. In our research, we propose Tanh-KAN, an efficient variant of KAN for in-bed posture classification. First, we validate that disabling the spline scaler not only preserves classification accuracy on the PoPu, Pmat, and SPN datasets, but also contributes to a reduction in model parameters and an increase in throughput. Second, we simplified the cubic B-spline basis functions in the original KAN using a Tanh-kernel. Compared to the original KAN, the accuracy remained stable, while the parameters were reduced by approximately 9% and the backpropagation and inference speeds increased by 42.3% and 53.9%, respectively. Experimental results further demonstrate that Tanh-KAN not only reduces model complexity and accelerates computation but also maintains high accuracy, achieving 99.6% on PoPu, 98.5% on Pmat, and 61.5% on SPN, matching the original KAN’s performance. |
| format | Article |
| id | doaj-art-cc4d8b69dfdd40ef9bc2ac8658b5f7e4 |
| institution | Kabale University |
| issn | 1751-9683 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Signal Processing |
| spelling | doaj-art-cc4d8b69dfdd40ef9bc2ac8658b5f7e42025-08-20T03:29:31ZengWileyIET Signal Processing1751-96832025-01-01202510.1049/sil2/6740194Optimizing In-Bed Posture Classification Using Tanh-Activated Kolmogorov–Arnold Networks (Tanh-KAN)Weiwei Chen0Bing Zhou1Wai Yie Leong2School of Information and Communications TechnologySchool of Information and Communications TechnologyFaculty of Engineering and Quantity SurveyingIn-bed posture classification plays a crucial role in health monitoring. However, existing research on classification involves a limited range of in-bed postures. Meanwhile, in classification tasks, Kolmogorov–Arnold networks (KANs), as an emerging neural network architecture, have research gaps in two areas: training strategies and architecture design. In our research, we propose Tanh-KAN, an efficient variant of KAN for in-bed posture classification. First, we validate that disabling the spline scaler not only preserves classification accuracy on the PoPu, Pmat, and SPN datasets, but also contributes to a reduction in model parameters and an increase in throughput. Second, we simplified the cubic B-spline basis functions in the original KAN using a Tanh-kernel. Compared to the original KAN, the accuracy remained stable, while the parameters were reduced by approximately 9% and the backpropagation and inference speeds increased by 42.3% and 53.9%, respectively. Experimental results further demonstrate that Tanh-KAN not only reduces model complexity and accelerates computation but also maintains high accuracy, achieving 99.6% on PoPu, 98.5% on Pmat, and 61.5% on SPN, matching the original KAN’s performance.http://dx.doi.org/10.1049/sil2/6740194 |
| spellingShingle | Weiwei Chen Bing Zhou Wai Yie Leong Optimizing In-Bed Posture Classification Using Tanh-Activated Kolmogorov–Arnold Networks (Tanh-KAN) IET Signal Processing |
| title | Optimizing In-Bed Posture Classification Using Tanh-Activated Kolmogorov–Arnold Networks (Tanh-KAN) |
| title_full | Optimizing In-Bed Posture Classification Using Tanh-Activated Kolmogorov–Arnold Networks (Tanh-KAN) |
| title_fullStr | Optimizing In-Bed Posture Classification Using Tanh-Activated Kolmogorov–Arnold Networks (Tanh-KAN) |
| title_full_unstemmed | Optimizing In-Bed Posture Classification Using Tanh-Activated Kolmogorov–Arnold Networks (Tanh-KAN) |
| title_short | Optimizing In-Bed Posture Classification Using Tanh-Activated Kolmogorov–Arnold Networks (Tanh-KAN) |
| title_sort | optimizing in bed posture classification using tanh activated kolmogorov arnold networks tanh kan |
| url | http://dx.doi.org/10.1049/sil2/6740194 |
| work_keys_str_mv | AT weiweichen optimizinginbedpostureclassificationusingtanhactivatedkolmogorovarnoldnetworkstanhkan AT bingzhou optimizinginbedpostureclassificationusingtanhactivatedkolmogorovarnoldnetworkstanhkan AT waiyieleong optimizinginbedpostureclassificationusingtanhactivatedkolmogorovarnoldnetworkstanhkan |