Feature-Level Fusion of Surface Electromyography for Activity Monitoring
<p>Muscles in Schematic and real placement.</p> "> Figure 2
<p>Eight activities of daily living. (<b>a</b>) stand-to-squat; (<b>b</b>) squat-to-stand; (<b>c</b>) stand-to-sit; (<b>d</b>) sit-to-stand; (<b>e</b>) walking, stair-ascending and stair-descending; (<b>f</b>) trip-fall.</p> "> Figure 3
<p>Delsys Full Wireless Surface Electromyography Test System (Trigno™ Wireless EMG).</p> "> Figure 4
<p>The SEN and SPE of WGA-GCCA with trial times in two examples. (<b>a</b>) One example result. (<b>b</b>) Another example result.</p> "> Figure 5
<p>Three-dimensional projection figure of gastrocnemius after WGA-GCCA.</p> "> Figure 6
<p>DBI with various numbers of clusters of CCA, GCCA, GA-GCCA, and WGA-GCCA.</p> "> Figure 7
<p>Dimension of feature sets after GA-GCCA fusion compared with GCCA. U<span class="html-italic">n</span> (<span class="html-italic">n</span> = x, y, z, o) Denotes the feature samples; x, y, z, o presents the four channels of data inputs.</p> "> Figure 8
<p>Increasing rate of recognition as the input increased from <span class="html-italic">n</span> to <span class="html-italic">n</span> + 1 (<span class="html-italic">n</span> = 1, 2, 3, 4, 5).</p> ">
Abstract
:1. Introduction
2. Subjects and Experiment Protocol
3. Feature Extraction
3.1. Feature Extraction
3.2. New Feature Space
3.2.1. Global Canonical Correlation Analysis (GCCA)
3.2.2. Weighting Genetic Algorithm of GCCA (WGA-GCCA)
4. Classification and Results
4.1. Davies–Bouldin Index (DBI) of New Feature Space
4.2. Accuracy
4.3. Complexity
4.4. Monotonicity
5. Discussion
6. Conclusions
Acknowledgments
Author Contributions
Conflicts of Interest
References
- Park, K.H.; Lim, S.H. A multipurpose smart activity monitoring system for personalized health services. Inf. Sci. 2015, 314, 240–254. [Google Scholar] [CrossRef]
- Leone, A.; Rescio, G.; Caroppo, A.; Siciliano, P. An EMG-based system for pre-impact fall detection. IEEE Sens. 2016, 1–4. [Google Scholar] [CrossRef]
- Tobón, D.P.; Falk, T.H.; Maier, M. Context awareness in WBANs: A survey on medical and non-medical applications. IEEE Wirel. Commun. 2013, 20, 30–37. [Google Scholar] [CrossRef]
- Roy, S.H.; Cheng, M.S.; Chang, S.S.; Moore, J.; De Luca, G.; Nawab, S.H.; De Luca, C.J. A Combined sEMG and Accelerometer System for Monitoring Functional Activity in Stroke. IEEE Trans. Neural Syst. Rehabil. Eng. 2009, 17, 585–594. [Google Scholar] [CrossRef] [PubMed]
- Mantilla, C.B.; Seven, Y.B.; Hurtado-Palomino, J.N.; Zhan, W.Z.; Sieck, G.C. Chronic assessment of diaphragm muscle EMG activity across motor behaviors. Respir. Physiol. Neurobiol. 2011, 177, 176–182. [Google Scholar] [CrossRef] [PubMed]
- Farooq, M.; Khan, A.A. Effects of shoulder rotation combined with elbow flexion on discomfort and EMG activity of ECRB muscle. Int. J. Ind. Ergon. 2014, 44, 882–891. [Google Scholar] [CrossRef]
- Chiauzzi, E.; Rodarte, C.; Dasmahapatra, P. Patient-centered activity monitoring in the self-management of chronic health conditions. BMC Med. 2015, 13, 77. [Google Scholar] [CrossRef] [PubMed]
- Liu, K.C.; Chan, C.T. Significant Change Spotting for Periodic Human Motion Segmentation of Cleaning Tasks Using Wearable Sensors. Sensors 2017, 17, 187. [Google Scholar] [CrossRef] [PubMed]
- Frauscher, B.; Iranzo, A.; Gaig, C.; Gschliesser, V.; Guaita, M.; Raffelseder, V.; Ehrmann, L.; Sola, N.; Salamero, M.; Tolosa, E.; et al. Normative EMG Values during REM Sleep for the Diagnosis of REM Sleep Behavior Disorder. Sleep 2012, 35, 835–847. [Google Scholar] [CrossRef] [PubMed]
- Istenic, R.; Kaplanis, P.A.; Pattichis, C.S.; Zazula, D. Multiscale entropy-based approach to automated surface EMG classification of neuromuscular disorders. Med. Biol. Eng. Comput. 2010, 48, 773–781. [Google Scholar] [CrossRef] [PubMed]
- Buchner, H.; Petersen, E.; Eger, M.; Rostalski, P. Convolutive blind source separation on surface EMG signals for respiratory diagnostics and medical ventilation control. Eng. Med. Biol. Soc. IEEE 2016. [Google Scholar] [CrossRef]
- Behm, D.G.; Whittle, J.; Button, D.; Power, K. Intermuscle differences in activation. Muscle Nerve 2002, 25, 236–243. [Google Scholar] [CrossRef] [PubMed]
- Lowe, S.A.; Ólaighin, G. Monitoring human health behaviour in one’s living environment: A technological review. Med. Eng. Phys. 2014, 36, 147–168. [Google Scholar] [CrossRef] [PubMed]
- Kuula, A.S. Energy expenditure and muscle activity in active and passive commute among elderly. 2011. [Google Scholar]
- Muhammed, H.H.; Jammalamadaka, R. A new approach for rehabilitation and upper-limb prosthesis control using optomyography (OMG). In Proceedings of the International Conference on Biomedical Engineering, Yogyakarta, Indonesia, 5–6 October 2016; pp. 1–6. [Google Scholar]
- Betthauser, J.L.; Hunt, C.L.; Osborn, L.E.; Masters, M.R.; Levay, G.; Kaliki, R.R.; Thakor, N.V. Limb Position Tolerant Pattern Recognition for Myoelectric Prosthesis Control with Adaptive Sparse Representations from Extreme Learning. IEEE Trans. Biomed. Eng. 2017. [Google Scholar] [CrossRef] [PubMed]
- Hazarika, A.; Dutta, L.; Barthakur, M.; Bhuyan, M. Fusion of projected feature for classification of EMG patterns. In Proceedings of the International Conference on Accessibility to Digital World, Guwahati, India, 16–18 December 2016. [Google Scholar]
- Ishii, A.; Kondo, T.; Yano, S. Improvement of EMG Pattern Recognition by Eliminating Posture-Dependent Components. In International Conference on Intelligent Autonomous Systems; Springer: Cham, Switzerland, 2016; pp. 19–30. [Google Scholar]
- Sun, Q.S.; Zeng, S.G.; Liu, Y.; Heng, P.A.; Xia, D.S. A new method of feature fusion and its application in image recognition. Pattern Recognit. 2005, 38, 2437–2448. [Google Scholar] [CrossRef]
- Liu, J. Feature dimensionality reduction for myoelectric pattern recognition: A comparison study of feature selection and feature projection methods. Med. Eng. Phys. 2014, 36, 1716–1720. [Google Scholar] [CrossRef] [PubMed]
- Buchenrieder, K. Processing of Myoelectric Signals by Feature Selection and Dimensionality Reduction for the Control of Powered Upper-Limb Prostheses. In Computer Aided Systems Theory—EUROCAST 2007; Moreno Díaz, R., Pichler, F., Quesada Arencibia, A., Eds.; Springer: Berlin&Heidelberg, Germany, 2007; Volume 4739, pp. 1057–1065. ISBN 978-3-540-75867-9. [Google Scholar]
- Bose, R.; Samanta, K.; Chatterjee, S. Cross-correlation based feature extraction from EMG signals for classification of neuro-muscular diseases. In Proceedings of the International Conference on Intelligent Control Power and Instrumentation, Kolkata, India, 21–23 October 2016; pp. 241–245. [Google Scholar]
- Akkaladevi, S.; Katangur, A.K.; Luo, X. Protein Structure Prediction by Fusion, Bayesian Methods. Encycl. Artif. Intell. 2009, 23, 2179–2184. [Google Scholar]
- Chu, J.U.; Moon, I.; Lee, Y.J.; Kim, S.-K.; Mun, M.-S. A Supervised Feature-Projection-Based Real-Time EMG Pattern Recognition for Multifunction Myoelectric Hand Control. IEEE/ASME Trans. Mechatron. 2007, 12, 282–290. [Google Scholar] [CrossRef]
- Khushaba, R.N. Correlation Analysis of Electromyogram Signals for Multiuser Myoelectric Interfaces. IEEE Trans. Neural Syst. Rehabil. Eng. 2014, 22, 745–755. [Google Scholar] [CrossRef] [PubMed]
- Correa, N.M.; Li, Y.O.; Adalı, T.; Calhoun, V.D. Canonical Correlation Analysis for Feature-Based Fusion of Biomedical Imaging Modalities and Its Application to Detection of Associative Networks in Schizophrenia. IEEE J. Sel. Top. Signal Process. 2008, 2, 998–1007. [Google Scholar] [CrossRef] [PubMed]
- Mehdi, N.; Somayeh, S. Multi-scale Image Fusion Based on Invariant Moments. International Research J. Appl. Basic Sci. 2017, 11, 134–139. [Google Scholar]
- Tkach, D.; Huang, H.; Kuiken, T.A. Study of stability of time-domain features for electromyographic pattern recognition. J. Neuroeng. Rehabil. 2010, 7, 21. [Google Scholar] [CrossRef] [PubMed]
- Xi, X.; Tang, M.; Miran, S.M.; Luo, Z. Evaluation of Feature Extraction and Recognition for Activity Monitoring and Fall Detection Based on Wearable sEMG Sensors. Sensors 2017, 17, 1229. [Google Scholar] [CrossRef] [PubMed]
- Martins, R.M.; Coimbra, D.B.; Minghim, R.; Telea, A.C. Visual analysis of dimensionality reduction quality for parameterized projections. Comput. Graph. 2014, 41, 26–42. [Google Scholar] [CrossRef]
- Sang, W.L.; Yi, T.; Jung, J.W.; Bien, Z. Design of a Gait Phase Recognition System That Can Cope with EMG Electrode Location Variation. IEEE Trans. Autom. Sci. Eng. 2017, 14, 1429–1439. [Google Scholar]
- Ronao, C.A.; Cho, S.B. Anomalous Query Access Detection in RBAC-Administered Databases with Random Forest and PCA. Inf. Sci. 2016, 369, 238–250. [Google Scholar] [CrossRef]
- Deb, K. An introduction to genetic algorithms. Sadhana 1999, 24, 293–315. [Google Scholar] [CrossRef]
- Davies, D.L.; Bouldin, D.W. A Cluster Separation Measure. IEEE Trans. Pattern Anal. Mach. Intell. 1979, 1, 224–227. [Google Scholar] [CrossRef] [PubMed]
- Pakhira, M.K.; Bandyopadhyay, S.; Maulik, U. Validity index for crisp and fuzzy clusters. Pattern Recognit. 2004, 37, 487–501. [Google Scholar] [CrossRef]
- Suganya, R.; Shanthi, R. Fuzzy c-means algorithm-a review. Int. J. Sci. Res. Publ. 2012, 2, 1. [Google Scholar]
- Ranaee, V.; Ata, E.; Reza, G. Application of the PSO–SVM model for recognition of control chart patterns. ISA Trans. 2010, 49, 577–586. [Google Scholar] [CrossRef] [PubMed]
- Subasi, A. Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. Comput. Biol. Med. 2013, 43, 576–586. [Google Scholar] [CrossRef] [PubMed]
- Wang, S.; Tang, J.; Liu, H. Feature Selection. In Encyclopedia of Machine Learning and Data Mining; Sammut, C., Webb, G.I., Eds.; Springer: Boston, MA, USA, 2017; pp. 503–511. ISBN 978-1-4899-7687-1. [Google Scholar]
Extraction Type | Dimension of Single Inputs | Domain |
---|---|---|
WAMP | 1 | Time domain |
FE | 1 | Entropy domain |
PE | 1 | Entropy domain |
ARCU | 4 | Time domain |
EWT | 5 | Time–frequency domain |
St–Sq | Sq–St | St–Si | Si–St | S–A | S–D | W | Fall | |||
---|---|---|---|---|---|---|---|---|---|---|
CCA | Type I | SEN | 67.22 | 70.64 | 67.22 | 67.22 | 67.22 | 67.22 | 67.22 | 70.22 |
SPE | 72.50 | 69.50 | 69.50 | 69.50 | 69.50 | 69.50 | 69.50 | 69.50 | ||
Type II | SEN | 54.00 | 67.22 | 64.32 | 64.32 | 64.32 | 64.32 | 64.32 | 67.22 | |
SPE | 67.22 | 87.50 | 54.00 | 54.00 | 54.00 | 54.00 | 54.00 | 64.32 | ||
GCCA | Type I | SEN | 88.43 | 88.43 | 88.43 | 88.43 | 88.43 | 88.43 | 88.43 | 88.43 |
SPE | 92.11 | 92.11 | 92.11 | 92.11 | 92.11 | 92.11 | 92.11 | 92.11 | ||
Type II | SEN | 88.25 | 88.25 | 88.25 | 88.25 | 94.59 | 94.59 | 94.59 | 94.59 | |
SPE | 87.50 | 87.50 | 87.50 | 93.33 | 93.33 | 93.33 | 93.33 | 67.22 | ||
GA-GCCA | Type I | SEN | 95.91 | 95.91 | 95.91 | 94.59 | 94.59 | 94.59 | 94.59 | 97.22 |
SPE | 87.50 | 87.50 | 94.59 | 98.59 | 89.74 | 93.33 | 97.22 | 98.50 | ||
Type II | SEN | 90.91 | 90.91 | 91.35 | 91.35 | 91.35 | 91.35 | 91.35 | 95.91 | |
SPE | 87.50 | 87.50 | 87.50 | 90.91 | 87.50 | 87.50 | 89.74 | 91.35 | ||
WGA-GCCA | Type I | SEN | 97.50 | 96.60 | 98.50 | 100 | 98.50 | 100 | 100 | 100 |
SPE | 98.59 | 95.91 | 97.59 | 98.50 | 95.91 | 97.22 | 100 | 100 | ||
Type II | SEN | 95.50 | 95.91 | 90.91 | 97.50 | 90.91 | 100 | 100 | 100 | |
SPE | 97.22 | 90.91 | 94.59 | 98.59 | 90.91 | 95.91 | 98.50 | 100 |
St–Sq | Sq–St | St–Si | Si–St | S–A | S–D | W | Fall | ||
---|---|---|---|---|---|---|---|---|---|
WGA-GCCA | SEN (%) | 97.50 | 96.60 | 98.50 | 100 | 98.50 | 100 | 100 | 100 |
SPE (%) | 98.59 | 95.91 | 97.59 | 98.50 | 95.91 | 97.22 | 100 | 100 | |
Time (s) | 0.5091 | 0.5290 | 0.5123 | 0.4850 | 0.5264 | 0.5004 | 0.5133 | 0. 4505 | |
PCA-GCCA | SEN (%) | 78.75 | 86.25 | 90.88 | 91.25 | 92.35 | 84.35 | 90.88 | 82.56 |
SPE (%) | 80.02 | 92.32 | 86.25 | 86.78 | 88.75 | 81.25 | 87.5 | 80.00 | |
Time (s) | 0.1361 | 0.1396 | 0.1369 | 0.1380 | 0.1431 | 0.1245 | 0.1227 | 0.1311 | |
SVD-GCCA | SEN (%) | 75.50 | 73.75 | 0.6802 | 86.25 | 86.25 | 83.75 | 87.25 | 72.34 |
SPE (%) | 78.29 | 76.68 | 0.6000 | 82.36 | 81.75 | 79.62 | 82.75 | 76.25 | |
Time (s) | 0.0834 | 0.0879 | 0.0880 | 0.0881 | 0.0834 | 0.0903 | 0.0871 | 0.0991 |
St-Sq | Sq-St | St-Si | Si-St | S-A | S-D | W | Fall | |
---|---|---|---|---|---|---|---|---|
St–Sq | 97.5 ± 2.5 | 1.5 ± 2.0 | 0 | 0 | 0 | 0 | 0 | 1.0 ± 0.5 |
Sq–St | 2.1 ± 1.3 | 96.6 ± 3.3 | 1.3 ± 1.0 | 0 | 0 | 0 | 0 | 0 |
St–Si | 0 | 0 | 98.5 ± 1.5 | 1.5 ± 1.5 | 0 | 0 | 0 | 0 |
Si–St | 0 | 0 | 0 | 100 ± 0 | 0 | 0 | 0 | 0 |
S–A | 0 | 0 | 0 | 0 | 98.5 ± 1.5 | 1.5 ± 1.5 | 0 | 0 |
S–D | 0 | 0 | 0 | 0 | 0 | 100 ± 0 | 0 | 0 |
W | 0 | 0 | 0 | 0 | 0 | 0 | 100 ± 0 | 0 |
Fall | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 100 |
One | Two | Three | Four | Five | Six | |
---|---|---|---|---|---|---|
Non-Fusion | 0.6280 | 0.5577 | 0.5229 | 0.5214 | 0.5149 | 0.5464 |
CCA | 0.5 | 0.4996 | 0.5 | 0.5 | 0.5 | 0.5 |
GCCA | 0.7661 | 0.7917 | 0.8024 | 0.8429 | 0.8534 | 0.8754 |
GA-GCCA | 0.7845 | 0.8186 | 0.8357 | 0.8738 | 0.8929 | 0.9095 |
WGA-GCCA | 0.7845 | 0.8456 | 0.8655 | 0.9095 | 0.9392 | 0.9719 |
© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Xi, X.; Tang, M.; Luo, Z. Feature-Level Fusion of Surface Electromyography for Activity Monitoring. Sensors 2018, 18, 614. https://doi.org/10.3390/s18020614
Xi X, Tang M, Luo Z. Feature-Level Fusion of Surface Electromyography for Activity Monitoring. Sensors. 2018; 18(2):614. https://doi.org/10.3390/s18020614
Chicago/Turabian StyleXi, Xugang, Minyan Tang, and Zhizeng Luo. 2018. "Feature-Level Fusion of Surface Electromyography for Activity Monitoring" Sensors 18, no. 2: 614. https://doi.org/10.3390/s18020614
APA StyleXi, X., Tang, M., & Luo, Z. (2018). Feature-Level Fusion of Surface Electromyography for Activity Monitoring. Sensors, 18(2), 614. https://doi.org/10.3390/s18020614