Activity recognition using multiplex limited penetrable visibility graph
Source abstract
Abstract
To solve the dynamic problem of different activities in human activity recognition research, an activity recognition method based on a multiplex limited penetrable visibility graph is proposed. The 21 pressure values for each sampling are mapped to nodes in the first-layer network; then the average path length of nodes in the asynchronous periodic network is obtained, and the second-layer network used to explore different activities is built. Finally, the characteristic parameters and dynamic characteristics of different activities are explored and analyzed. The experimental results demonstrate that through the joint distribution of the average clustering coefficient and the maximum degree parameter of the node, the discrimination problems of different postures can be better realized, and it has good adaptability. It provides a new approach to gait recognition research that can be used in medical clinical diagnosis, rehabilitation training, and public health.
Source: europepmc · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Gait Recognition and Analysis · Context-Aware Activity Recognition Systems · Human Pose and Action Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (29)
Show source-provided references
1. Gait analysis using a shoe-integrated wireless sensor system10.1109/TITB.2007.899493 ↗
2. Network physiology: How organ systems dynamically interact10.1371/journal.pone.0142143 ↗
3. Network physiology reveals relations between network topology and physiological function10.1038/ncomms1705 ↗
4. Biometric recognition by gait: a survey of modalities and features,21910.1016/j.cviu.2018.01.007 ↗
5. Effects of non-parallel combs on reliable operation conditions of capacitive inertial sensor for step and shock signals10.1016/j.sna.2005.03.048 ↗
6. Optimal inertial sensor location for ambulatory measurement of trunk inclination10.1016/j.jbiomech.2009.06.024 ↗
7. Multiscale limited penetrable horizontal visibility graph for analyzing nonlinear time series10.1038/srep35622 ↗
8. Repeatability of walkinsense® in shoe pressure measurement system: a preliminary study10.1016/j.foot.2011.11.001 ↗
9. Phase synchrony in the cerebral infarction electroencephalogram based on the degree of network-links
10. From time series to complex networks: the visibility graph10.1073/pnas.0709247105 ↗
11. Plasticity of brain wave network interactions and evolution across physiologic states
12. Horizontal visibility graphs: exact results for4 random time series, Physical review
13. Plantar pressure distribution during standing in women with end-stage hip osteoarthritis10.1016/j.gaitpost.2019.10.026 ↗
14. Recognition of gait cycle phases using wearable sensors10.1016/j.robot.2014.10.012 ↗
15. Using hidden markov models for accelerometer-based biometric gait recognition
16. Smart diabetic socks: embedded device for diabetic foot prevention
17. Inertial sensor-based stride parameter calculation from gait sequences in geriatric patients
18. Repeatability of plantar pressure assessment during barefoot walking in people with stroke10.1186/s13047-020-00407-x ↗
19. In-shoe plantar pressure measurement and analysis system based on fabric pressure sensing array10.1109/TITB.2009.2038904 ↗
20. Position-aware activity recognition with wearable devices10.1016/j.pmcj.2017.01.008 ↗
21. The layer-wise training convolutional neural networks using local loss for sensor-based human activity recognition10.1109/JSEN.2020.2978772 ↗
22. The effect of match fatigue in elite bad minton players using plantar pressure measurements and the implications to injury mechanisms
23. Comparison of plantar loads among runners240 with different strike patterns10.1080/02640414.2019.1623990 ↗
24. Research of short-term heart rate variability during sleep based on limited penetrable horizontal visibility graph
25. Multi-segmental motion in foot during counter movement jump with toe manipulation10.3390/app10051893 ↗
26. Normal foot loading parameters and repeatability of the footscan® platform system10.1186/s13047-017-0209-2 ↗
27. T. Yamamoto, Y. Hoshino, N. Kanzaki, K. Nukuto, T. Yamashita, K. Ibaraki, K. Nagamune, K. Nagai, D. Araki, T. Matsushita, R. Kuroda, Plantar pressure sensors indicate women to have a significantly higher peak pressure on the hallux, toes, forefoot, and medial of the foot compared to men, J. Foot Ankle Res. 13.doi: https://doi.org/10.1186/256 s13047-020-00410-2.10.1186/s13047-020-00410-2 ↗
28. Using acceleration measurements for activity recognition: an effective learning algorithm for constructing neural classifiers10.1016/j.patrec.2008.08.002 ↗
29. Deep residual bidir-lstm for human activity recognition using wearable sensors