EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Lower Limb Motion Classification of Actions in Confined Environments Based on Multi-Source Signal Fusion and Muscle Symmetry Features

Dingzhe Li, Xiaorong Guan iD, Zheng Wang, Changlong Jiang iD, Long He, Xiwang Mao, Qiang Zhou

Sensors · 21.08.2026 · 26 (16) · 5314

DOI: 10.3390/s26165314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.08.2026. Verfasst von Dingzhe Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Nanjing University of Science and Technology, No. 200, Xiaolingwei, Nanjing 210094, China. Hauptthemen laut MEDLINE: Lower Extremity, Muscle, Skeletal. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, advances in exoskeleton technology have increased the demand for human motion classification in terms of both movement diversity and recognition accuracy, making the effective classification of more complex asymmetric movements increasingly important. This study integrated surface electromyography (sEMG) and inertial measurement unit (IMU) signals and employed mutual information (MI) and muscle symmetry features (MSF) to analyze the characteristic differences between symmetrical muscles in both legs during asymmetric movements, with the aim of improving the accuracy of asymmetric motion classification. sEMG and IMU signals were collected from six movements, including three asymmetric postures: asymmetrical stance, single-knee kneeled position, and crouching advance. The acquired signals were processed through energy envelope analysis, active segment extraction, empirical mode decomposition (EMD), feature extraction, MI extraction, and MSF extraction. The relevance based on weight feature selection (RWFS) combined with conditional mutual information (CMI) method was then applied to reduce feature dimensionality, prioritize features with significant fluctuations, and preserve key characteristics. Finally, the CNN-LSTM-Attention algorithm was used for classification. Experimental results showed that fusing sEMG and IMU signals achieved 96.30% accuracy in lower limb motion recognition. The proposed method improves asymmetric movement classification and may provide a potential basis for exoskeleton motion classification in special environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lower ExtremityMuscle, SkeletalHumansElectromyographyAlgorithmsSignal Processing, Computer-AssistedMovementMale

Stichwörter der Autor:innen

assisted exoskeletonsmotion classificationmulti-source fusionmuscle symmetry featuresmutual information

Autor:innen und Institutionen

  • School of Mechanical Engineering, Nanjing University of Science and Technology, No. 200, Xiaolingwei, Nanjing 210094, China.
  • Hangzhou Zhiyuan Research Institute Co., Ltd., No. 188 Yunzhan Road, Hangzhou 310000, China.
  • Air Force Hospital of Eastern Theater Command, Nanjing 210002, China.

ORCID-Profile: Xiaorong Guan, Changlong Jiang

Zitieren

APA

Li, D., Guan, X., Wang, Z., Jiang, C., He, L., Mao, X., & Zhou, Q. (2026). Lower Limb Motion Classification of Actions in Confined Environments Based on Multi-Source Signal Fusion and Muscle Symmetry Features. Sensors, 26(16), 5314. https://doi.org/10.3390/s26165314

Vancouver

Li D, Guan X, Wang Z, Jiang C, He L, Mao X, et al. Lower Limb Motion Classification of Actions in Confined Environments Based on Multi-Source Signal Fusion and Muscle Symmetry Features. Sensors. 2026;26(16):5314. doi:10.3390/s26165314

BibTeX
@article{Li2026,
  author = {Li, Dingzhe and Guan, Xiaorong and Wang, Zheng and Jiang, Changlong and He, Long and Mao, Xiwang and Zhou, Qiang},
  title = {Lower Limb Motion Classification of Actions in Confined Environments Based on Multi-Source Signal Fusion and Muscle Symmetry Features},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {16},
  pages = {5314},
  doi = {10.3390/s26165314}
}
Kostenlos starten →