Research on User-Independent Gesture Recognition Based on Bilinear Models for sEMG Signals
Cheng Juan# Chen Xun#* Peng Hu
Department of Biomedical Engineering,School of Instrument Science and Opto\|electronics Engineering Hefei University of Technology, Hefei 230009, China
Abstract：Due to the fact that surface electromyography (sEMG) signals of the same gesture vary from different individuals (user-related) and various gestures produce different sEMG signals (motion-related), the sEMG signals can be treated as the interaction of the two factors. This study utilized bilinear models to extract user-independent features. We first factorized original training features into two factors, and the determination of the factor dimensions can help the reconstructed features have the maximum similarity. When original testing features from a novel user were available, they were used to adapt the two factors with the aid of the aforementioned model parameters and the reconstructed testing features by using the adapted factors were finally sent to the trained classifier for recognition. Eleven subjects were recruited with each performing 4 types of gestures. Three classifiers (linear discriminant classifier, K-nearest neighbor and support vector machine) were employed for the classification of the three tasks, termed as user-dependent cross-time (UDC), original-user-independent (OUI) and bilinear-models-user-independent (BMUI). Experimental results showed that the averaged classification accuracy of BMUI was at least 85% whereas that of OUI was not higher than 75%. The one-way ANOVA analysis demonstrated the significant improvement of BMUI (P<0.001). Besides, although the averaged accuracy of UDC was above 90%, higher than that of BMUI, they were statistically insignificant (P>0.24). The proposed method provided a practical solution to the interaction implementation of myoelectric control system based on gesture recognition techniques, and the training samples could be significantly reduced since each subject will conduct only once experiment for training.
基金资助:国家自然科学基金(61401138;81571760;61501164); 中国生物医学工程学会高级会员(Senior member, Chinese Society of Biomedical Engineering)
引用本文:
成娟, 陈勋, 彭虎. 基于双线性模型的动作肌电信号用户无关识别研究[J]. 中国生物医学工程学报, 2016, 35(5): 526-532.
Cheng Juan Chen Xun Peng Hu. Research on User-Independent Gesture Recognition Based on Bilinear Models for sEMG Signals. Chinese Journal of Biomedical Engineering, 2016, 35(5): 526-532.
[1] International Diabetes Federation[R]. Annual Report 2014. www.idf.org. [2] Yang WY, Lu JM, Weng JP, et al. Prevalence of diabetes among men and women in China[J]. N Engl J Med, 2010,362(25):2425-2425. [3] Xu Y, Wang LM, He J, et al. Prevalence and control of diabetes in Chinese adults[J]. JAMA, 2013,310(9):948-959. [4] Porte D, Schwartz MW. Diabetes complications: why is glucose potentially toxic?[J]. Science,1996,272(5262):699-700. [5] Georgia P, Tina C, Demetrius E, et al. The 30-year natural history of type 1 diabetes complications: the Pittsburgh Epidemiology of Diabetes Complications Study experience[J]. Diabetes, 2006,55(5):1463-1469. [6] Perkins BA, Aiello LP, Krolewski AS. Diabetes complications and the reninangiotensin system[J]. N Engl J Med,2009,361(1):83-85. [7] Intine RV, Sarras MP. Metabolic memory and chronic diabetes complications: Potential role for epigenetic mechanisms[J]. Curr Diab Rep, 2012,12(5):551-559. [8] Buckloh LM, Lochrie AS, Holly A, et al. Diabetes complications in youth[J]. Diabetes Care, 2008,31(8):1516-1520. [9] MP Gilbert. Screening and treatment by the primary care provider of common diabetes complications[J]. Med Clin North Am, 2015,99(1):201-219. [10] Shah BR, Hwee J, CauchDudek K, et al. Diabetes selfmanagement education is not associated with a reduction in longterm diabetes complications: an effectiveness study in an elderly population[J]. Journal Eval in Clin Pract,2015,21(4):656-661. [11] Kuhn M, Kuhn P, Villeval MC. Self control and inter temporal choice: evidence from glucose and depletion interventions[C]//CESifo Working Paper Series. Munich: CES, 2014: No 4609. [12] Beedie CJ，Lane AM. The role of glucose in selfcontrol: Another look at the evidence and an alternative conceptualization[J]. Pers Soc Psychol Rev, 2011,16(2):143-153. [13] Zamzow KL, Schmidt DG, Shults MC, et al. Development and evaluation of a wearable blood glucose monitor[J]. Assaio Transactions,1990,36(3):M588-M591. [14] Rayman G, Spencer PD, Tillyer CR, et al. Evaluation of a selfcalibrating blood glucose monitor[J]. Diabetes Care, 1984,7(4):378-380. [15] Jones PM. Use of a course on selfcontrol behavior techniques to increase adherence to prescribed frequency for selfmonitoring blood glucose[J]. Diabetes Educ,1990,16(4):296-303. [16] Fine J. Glucose content of normal urine [J]. British Medical Journal. 1965,1(5444):1209-1214. [17] Street HV. Determination of glucose in biological fluids with ethylenediaminetetraacetic acid[J]. Analyst,1958,83(992):628-634. [18] Bantle JP, Thomas W. Glucose measurement in patients with diabetes mellitus with dermal interstitial fluid[J]. J Lab Clinl Med,1997,130(4):436-441. [19] Vesper HW, Wang PM, Archibold E, et al. Assessment of trueness of a glucose monitor using interstitial fluid and whole blood as specimen matrix[J]. Diabetes Technol Ther,2006,8(1):76-80. [20] Rebrin K, Sheppard NF, Steil GM. Use of subcutaneous interstitial fluid glucose to estimate blood glucose: revisiting delay and sensor offset[J]. J Diabetes Sci Technol,2010, 4(5):1087-1098. [21] Weiss TR. Google Testing Smart Contact Lenses for Diabetes Patients[N]. Eweek,2014. [22] Zhang J, Hodge W, Hutnick C, et al. Noninvasive diagnostic devices for diabetes through measuring tear glucose[J].J Diabetes Sci Technol,2011,5(1):166-172. [23] Baca JT, Finegold DN, Asher SA. Tear Glucose Analysis for the noninvasive detection and monitoring of diabetes mellitus[J]. Ocul Surf,2007,5(4)280-293. [24] Yao HF, Shum AJ, Cowan M. et.al. A contact lens with embedded sensor for monitoring tear glucose level[J]. Biosens Bioelectron, 2011 15:26(7): 3290-3296. [25] Yang X, Pan X, Blyth J, et al. Towards the realtime monitoring of glucose in tear fluid: holographic glucose sensors with reduced interference from lactate and pH[J]. Biosens Bioelectron, 2008,23(6):899-905. [26] Lee H, Choi TK, Lee YB, et al. A graphenebased electrochemical device with thermoresponsive microneedles for diabetes monitoring and therapy[J]. Nat Nanotechnol, 2016,11(6):566-572. [27] Cengiz E, Tamborlane WV. A tale of two compartments: interstitial versus blood glucose monitoring[J]. Diabetes Technol Ther, 2009,11（Suppl 1）:S11-S16. [28] Mraovic B. Analysis: Continuous glucose monitoring during intensive insulin therapy[J]. Diabetes Technol Ther, 20093(4):960-963. [29] Buckingham B, Caswell K, Wilson DM. Realtime continuous glucose monitoring[J]. Curr Opin Endocrinol Diabetes Obes, 2007,14(4):288-295. [30] Taylor JR. What′s new in continuous glucose monitors?[J]. Endocrine Today,2009(8):1-2. [31] Hermanns N, Schumann B, KulzerB, et al. The impact of continuous Glucose monitoring on low interstitial glucose values and low blood glucose values assessed by pointofcare blood glucose meters: Results of a crossover trial[J]. J Diabetes Technol Ther, 20148(3):516-522. [32] Facchinetti A, Del Favero S, Sparacino G. et al. Model of glucose sensor error components: identification and assessment for new Dexcom G4 generation devices[J]. Med Biol Eng Comput, 2015, 53(12):1-11 [33] Facchinetti A, Del Favero S, Sparacino G. et al. Modeling the glucose sensor error[J].IEEE Trans Biomed Eng, 2014,61(3):620-629. [34] Peyser TA, Nakamura K, Price D, et al. Hypoglycemic accuracy and improved low glucose alerts of the latest Dexcom G4 platinum continuous glucose monitoring system[J]. Diabetes Technol Ther, 2015,17(8):548-554. [35] Hirsch IB. Clinical review: Realistic expectations and practical use of continuous glucose monitoring for the endocrinologist[J]. J Clin Endocrinol Metab,2009;94(7):2232-2238 [36] Dassau E, Cameron F, Lee H, et al. Realtime hypoglycemia prediction suite using continuous glucose monitoring: a safety net for the artificial pancreas[J]. Diabetes Care,2010,33(6):1249-1254. [37] Turner A, Gifford R. Implanted sensors[J]. Springer Series on Chemical Sensors and Biosensors, 201213:159-189. [38] Tierney MJ, Tamada JA, Potts RO, et al. The GlucoWatch biographer: a frequent automatic and noninvasive glucose monitor[J].Ann Med, 2000, 32(9):632-641. [39] Keenan DB, Mastrototaro JJ, Voskanyan G, et al. Delays in minimally invasive continuous glucose monitoring devices: a review of current technology[J]. J Diabetes Sci Technol, 2009, 3(5):1207-1214. [40] Mazze RS, Strock E, Borgman S, et.al. Evaluating the accuracy, reliability, and clinical applicability of continuous glucose monitoring(CGM):Is CGM ready for real time?[J]. Diabetes Technol Ther, 2009,11(1):11-18. [41] Fischbacher C, Jagemann KU, Danzer K, et al. Enhancing calibration models for noninvasive nearInfrared spectroscopicalblood glucose determination[J]. Fresen J Anal Chem,1997, 359(1):78-82. [42] Liakat S, Bors KA, Huang TY, et al. In vitro measurements of physiological glucose concentration in biological fluids using midinfrared light[J]. Biomed Opt Express, 2013,4(7):1083-1090. [43] Cooper PJ, Barker TQ. Individual Calibration of blood glucose for supporting noninvasive selfmonitoring blood glucose[P]. EP, US6309884 B1 2001. [44] Barman I. Unraveling the puzzles of spectroscopybased noninvasive blood glucose detection[D]. Boston: Massachusetts Institute of Technology, 2011. [45] Liakat S, Bors KA, Xu L, et al. Noninvasive in vivo glucose sensing on human subjects using midinfrared light[J]. Biomed Opt Express, 2014,5(7):2397-2404. [46] Gao L，Tao W，Zhao H，et al. Research and design of photoacoustic cell of noninvasive blood glucose measurement[J]. Optical Instruments, 2012,34(2):55-60. [47] Xing Zhang, Li Xiaoqing. Strictly regulated blood glucose oscillations linked to rat mortality after severe burn injury[J]. Faseb J, 2012, 26(9):832-842. [48] Zhao Z, Myllyla RA. Photoacoustic blood glucose and skin measurement based on optical scattering effect[J]. Proceedings of SPIE,2002,4707:1-5. [49] Ren Z, Liu G, Huang Z, et al. Laserinduced photoacoustic glucose spectrum denoising using an improved wavelet threshold translationinvariant algorithm[J]. Proceedings of SPIE, 2009, 7382:1-8. [50] Firdous S, Nawaz M, Ahmed M, et al. Measurement of diabetic sugar concentration in human blood using Raman spectroscopy[J]. Laser Physics, 2012, 22(6):1090-1094 [51] Dingari NC, Barman I, Singh GP, et al. Investigation of the specificity of Raman spectroscopy in noninvasive blood glucose measurements[J]. Anal Bioanal Chem,2011,400(9):2871-2880 [52] Enejder AM, Koo TW, Oh J, et al. Blood analysis by Raman spectroscopy[J]. Optics Lett, 2002, 27(22):2004-2006. [53] Shao J, Lin M, Li Y, et al. In vivo blood glucose quantification using raman spectroscopy[J]. PLoS ONE, 2012, 7(10):e48127 [54] Segman Y. Finger mounted noninvasive device for measuring physiological parameters[P]. US687150 2013 [55] Segman Y. Finger deployed device for measuring blood and physiological characteristics[P]. US8489165 2013 [56] Lipson J, Bernhardt J, Block U, et al. Noninvasive technologies for glucose monitoring: requirements for calibration in noninvasive glucose monitoring by Raman spectroscopy[J]. J Diabetes Sci Technol, 2009,3(2):233-241. [57] Lipson J，Bernhardt J，U Block, et al. Requirements for calibration in noninvasive glucose monitoring by Raman spectroscopy[J]. J Diabetes Sci Technol, 2009,3(2): 233-241. [58] Harman-BoehmI I, Gal A, Raykhman AM, et al. Noninvasive glucose monitoring: Increasing accuracy by combination of multitechnology and multisensors[J]. J Diabetes Sci Technol, 2010,4(3):583-595. [59] Harman-Boehm I, Gal A, Raykhman AM, et al. Noninvasive glucose monitoring: a novel approach[J]. J Diabetes Sci Technol, 2009,3(2):253-60. [60] Ramchandani N, Heptulla RA. New technologies for diabetes: a review of the present and the future[J]. Int J of Pediatric Endocrinol,2012,2012(1):1-10. [61] Gravesen P, Raaby PK, Dirac H. Labonachip technology for continuous glucose monitoring[J]. J Diabetes Sci Technol,2007, 1(3):372-374. [62] Pedersen A. GlucoTrack offers painless glucosemonitoring option[J]. Medical Device Daily, 2013, 17(197): 1-7.
