TY - GEN
T1 - Cross-Subject Respiratory State Recognition Based on Ultrasonic and IMU Signals
AU - Feng, Shuo
AU - Wang, Zhiyong
AU - Wang, Jiaole
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.
PY - 2026
Y1 - 2026
N2 - Continuous and accurate respiratory monitoring is important for early disease detection and health management. This paper presents a novel multimodal data acquisition system that simultaneously collects Inertial Measurement Unit (IMU) and A-mode ultrasound signals from the chest and abdomen to monitor respiratory activity. We systematically evaluate various classification methods and fusion strategies, including feature-level vector concatenation, tensor fusion, a custom IMU-Ultrasound Convolutional Neural Network with Attention Fusion (IU-CNN-AF), decision-level max fusion, and weighted fusion, both single-subject and cross-subject respiratory state recognition across three breathing patterns (normal, deep, and high-frequency). Experiments on data from nine healthy male volunteers, using Leave-One-Group-Out cross-validation, demonstrate that multimodal fusion significantly outperforms corresponding single-modal methods, especially in more challenging cross-individual scenarios, with decision-level max fusion achieving an accuracy rate of 89.02%, outperforming other methods. Although the available dataset size limits the performance of the IU-CNN-AF network, it still demonstrates potential. These findings highlight the effectiveness and robustness of multimodal sensor fusion for wearable respiratory monitoring and provide valuable insights for future development of portable healthcare systems.
AB - Continuous and accurate respiratory monitoring is important for early disease detection and health management. This paper presents a novel multimodal data acquisition system that simultaneously collects Inertial Measurement Unit (IMU) and A-mode ultrasound signals from the chest and abdomen to monitor respiratory activity. We systematically evaluate various classification methods and fusion strategies, including feature-level vector concatenation, tensor fusion, a custom IMU-Ultrasound Convolutional Neural Network with Attention Fusion (IU-CNN-AF), decision-level max fusion, and weighted fusion, both single-subject and cross-subject respiratory state recognition across three breathing patterns (normal, deep, and high-frequency). Experiments on data from nine healthy male volunteers, using Leave-One-Group-Out cross-validation, demonstrate that multimodal fusion significantly outperforms corresponding single-modal methods, especially in more challenging cross-individual scenarios, with decision-level max fusion achieving an accuracy rate of 89.02%, outperforming other methods. Although the available dataset size limits the performance of the IU-CNN-AF network, it still demonstrates potential. These findings highlight the effectiveness and robustness of multimodal sensor fusion for wearable respiratory monitoring and provide valuable insights for future development of portable healthcare systems.
KW - A-mode Ultrasound
KW - Cross-Subject Recognition
KW - Inertial Measurement Unit
KW - Multimodal Sensor Fusion
KW - Respiratory Monitoring
KW - Sensor Fusion
KW - Wearable Healthcare
UR - https://www.scopus.com/pages/publications/105020816600
U2 - 10.1007/978-981-95-2101-2_47
DO - 10.1007/978-981-95-2101-2_47
M3 - 会议稿件
AN - SCOPUS:105020816600
SN - 9789819521005
T3 - Lecture Notes in Computer Science
SP - 573
EP - 584
BT - Intelligent Robotics and Applications - 18th International Conference, ICIRA 2025, Proceedings
A2 - Matsuno, Takayuki
A2 - Liu, Honghai
A2 - Liu, Lianqing
A2 - Yin, Zhouping
A2 - Zhu, Xiangyang
A2 - Ren, Weihong
A2 - Wang, Zhiyong
A2 - Sheng, Yixuan
PB - Springer Science and Business Media Deutschland GmbH
T2 - 18th International Conference on Intelligent Robotics and Applications, ICIRA 2025
Y2 - 6 August 2025 through 9 August 2025
ER -