|
|
|
| Research Advance in Lightweight Methods for Sensing and Intelligent Analysis of Lumbar Electromyographic Signals |
| Feng Jinghui1, Yu Yu1, Xi Jianing1,2* |
1(School of Biomedical Engineering, Guangzhou Medical University, Guangzhou 511436, China)
2(Guangdong Provincial Engineering Research Center of Respiratory Rehabilitation Devices, Guangzhou Medical University, Guangzhou 511436, China) |
|
|
|
|
Abstract The issue of lumbar health has garnered increasing attention in the light of the aging population trend. Lumbar electromyography (EMG) signals contain information about the lumbar and are commonly used to analyze lumbar conditions, and in recent years, related research has focused on detecting lumbar muscle fatigue and assisting in diagnosis. With the development of signal acquisition technology and analysis algorithms, it is possible to collect and transmit real-time data in large quantities from lumbar EMG and analyze them using complex neural network algorithms. However, complex acquisition and analysis systems increase resource consumption and are not conducive to lightweight deployment. In this paper, we reviewed the lightweighting of signal acquisition and analysis systems for lumbar EMG.Regarding the lightweight requirements of the waist electromyography signal acquisition and analysis system, this article reviewed the progress of waist electromyography acquisition technology, and summarized the lightweight research progress in this field from multiple dimensions, including hardware devices, data storage, and algorithm models. The key technologies of related system, such as high-performance communication chips and knowledge distillation neural networks, were introduced. And the future application of waist electromyography technology was also discussed.
|
|
Received: 14 April 2024
|
|
|
|
|
|
[1] 刘丹. 中国人口老龄化发展现状、成因与对策 [J]. 中国老年学杂志, 2022, 42(16): 4123-4126.
[2] Barry DT. Muscle sounds from evoked twitches in the hand [J]. Arch Phys Med Rehabil, 1991, 72(8): 573-575.
[3] Sanes JR, Lichtman JW. Development of the vertebrate neuromuscular junction [J]. Annual Review of Neuroscience, 1999, 22(1): 389-442.
[4] Yoshihara K, Nakayama Y, Fujii N, et al. Atrophy of the multifidus muscle in patients with lumbar disk herniation: histochemical and electromyographic study [J]. Orthopedics, 2003, 26(5): 493-495.
[5] Hofste A, Soer R, Salomons E, et al. Intramuscular EMG versus surface EMG of lumbar multifidus and erector spinae in healthy participants [J]. Spine, 2020, 45(20): E1319-E1325.
[6] Hermens HJ, Freriks B, Disselhorst-Klug C, et al. Development of recommendations for SEMG sensors and sensor placement procedures [J]. Journal of Electromyography and Kinesiology, 2000, 10(5): 361-374.
[7] Wei Jie, Zhu Haibei, Wang Fei, et al. Clinical utility of flexion-extension ratio measured by surface electromyography for patients with nonspecific chronic low-back pain [J]. Journal of the Chinese Medical Association, 2019, 82(1): 35-39.
[8] Moniri A, Terracina D, Rodriguez-Manzano J, et al. Real-time forecasting of sEMG features for trunk muscle fatigue using machine learning [J]. IEEE Trans Biomed Eng, 2021, 68(2): 718-727.
[9] 冯景辉,余宇,习佳宁. 腰部肌电信号数据采集与智能传感方式研究进展 [J]. 中国医疗器械杂志, 2024, 48(2): 119-125.
[10] Zhang Shanshan, Xu Yi, Han Xiulan, et al. Functional and morphological changes in the deep lumbar multifidus using electromyography and ultrasound [J]. Scientific Reports, 2018, 8(1): 6539.
[11] Tamartash H, Bahrpeyma F, Dizaji MM. The effect of transcutaneous electrical nerve stimulation on pain and electrical stimulation muscle thickness in patients withnon-specific chronic low back pain-based ultrasonographic evaluation [J]. Pain Management, 2023, 13(2): 87-94.
[12] Daube JR, Rubin DI. Needle electromyography [J]. Muscle & Nerve, 2009, 39(2): 244-270.
[13] Lee SP, Bailey JP, Smith JA, et al. Adaptations of lumbar biomechanics after four weeks of running training with minimalist footwear and technique guidance: implications for running-related lower back pain [J]. Physical Therapy in Sport, 2018, 29: 101-107.
[14] Peach JP, McGill SM. Classification of low back pain with the use of spectral electromyogram parameters [J]. Spine, 1998, 23(10): 1117-1123.
[15] Ullah K, Khan K, Amin M, et al. Multi-channel surface EMG spatio-temporal image enhancement using multi-scale hessian-based filters [J]. Applied Sciences-Basel, 2020, 10(15): 5099.
[16] Ferro HF, Chamon LFO, Lopes CG. FIR-IIR adaptive filters hybrid combination [J]. Electronics Letters, 2014, 50(7): 501-503.
[17] 吴梦实. 基于表面肌电信号的人机交互方法研究及其系统设计 [D]: 南京:南京邮电大学, 2023.
[18] 李兵倩,吴端坡,李婧涵,等. 智能运动信息采集分析系统研究 [J]. 电子设计工程, 2024, 32(11): 124-130.
[19] 尹文姝,王意,张成俊. 胎儿心率采集信号噪声滤波电路设计及仿真 [J]. 武汉纺织大学学报, 2024, 37(1): 81-88.
[20] Zhou Ruogu. Exploiting cross-technology interference for efficient network services in wireless systems [M]. East Lansing: Michigan State University, 2014.
[21] Li Zhou, Fu Jialong, Zhou Xiaoyan, et al. Ionic conduction in polymer-based solid electrolytes [J]. Advanced Science, 2023, 10(10): 2201718.
[22] 黄峰,李胜平,朱全庆,等. DSP体系结构发展的新趋势 [J]. 计算机工程, 2002, 28(4): 1-2, 218.
[23] 宋文娜,徐东君,陈亮. DSP体系结构发展综述 [J]. 微电子学与计算机, 2023, 40(4): 1-7.
[24] Codrescu L. Architecture of the Hexagon? 680 DSP for mobile imaging and computer vision [C]//2015 IEEE Hot Chips 27 Symposium (HCS). Cupertino: IEEE, 2015: 1-26.
[25] 杰理科技. 杰理“梧桐”WIFI/BT双模音视频AIoT芯片正式发布 [J]. 中国集成电路, 2020, 29(Z3): 22-22.
[26] 意法半导体. 意法半导体(ST)推出新一代低能耗蓝牙芯片,推动智能互联硬件市场发展 [J]. 世界电子元器件, 2017 (7): 13-13.
[27] Jiang Naifu, Xue Jinwei, Li Guanglin. Assessment of lumbar muscles coordinated activity based on high-density surface electromyography: a pilot study [C]//2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2019). Berlin: IEEE, 2019: 2238-2241.
[28] Srhoj-Egekher V, Cifrek M, Peharec S. Feature modeling for interpretable low back pain classification based on surface EMG [J]. IEEE Access, 2022, 10: 73702-73727.
[29] 赵陈,宋泊明. 基于ZigBee的可穿戴多元数据采集节点设计 [J]. 科学技术创新, 2024, (6): 112-115.
[30] Varrecchia T, Ranavolo A, Chini G, et al. High-density surface electromyography allows to identify risk conditions and people with and without low back pain during fatiguing frequency-dependent lifting activities [J]. Journal of Electromyography and Kinesiology, 2023, 73: 102839.
[31] Arvanitidis M, Jiménez-Grande D, Haouidji-Javaux N, et al. People with chronic low back pain display spatial alterations in high-density surface EMG-torque oscillations [J]. Scientific Reports, 2022, 12(1): 15178.
[32] 孙瑞. 固态硬盘与机械硬盘综合比较探究 [J]. 科技尚品, 2016 (1): 172-173.
[33] Akram S. Performance evaluation of intel optane memory for managed workloads [J]. ACM Transactions on Architecture and Code Optimization, 2021, 18(3): 45683.
[34] Mei Fei, Cao Qiang, Jiang Hong, et al. LSM-Tree managed storage for large-scale key-value store [J]. IEEE Transactions on Parallel and Distributed Systems, 2019, 30(2): 400-414.
[35] Yu C, Bailey J, Montefusco J, et al. Enhancing the B+-tree by dynamic node popularity caching [J]. Information Processing Letters, 2010, 110(7): 268-273.
[36] Jiang Naifu, Luk KDK, Hu Yong. A machine learning-based surface electromyography topography evaluation for prognostic prediction of functional restoration rehabilitation in chronic low back pain [J]. Spine, 2017, 42(21): 1635-1642.
[37] 任利强,贾舒宜,王海鹏,等. 基于深度学习的时间序列分类研究综述 [J]. 电子与信息学报, 2024, 46(8): 3094-3116.
[38] Zhao Bowen, Xing Huanlai, Wang Xinhan, et al. Rethinking attention mechanism in time series classification [J]. Information Sciences, 2023, 627: 97-114.
[39] Liu Minghao, Ren Shengqi, Ma Siyuan, et al. Gated transformer networks for multivariate time series classification [EB/OL]. https://www.arxiv.org/abs/2103.14438v1,2021-03-26/2024-04-14.
[40] Usmankhujaev S, Ibrokhimov B, Baydadaev S, et al. Time series classification with inception FCN [J]. Sensors, 2022, 22(1): 157.
[41] Fukushima K. Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position [J]. Biological Cybernetics, 1980, 36(4): 193-202.
[42] Wang Zhiguang, Oates T. Encoding time series as images for visual inspection and classification using tiled convolutional neural networks [C]//Workshops at the Twenty-ninth AAAI Conference on Artificial Intelligence. Austin: AAAI Press, 2015: 40-46.
[43] Le-Guennec A, Malinowski S, Tavenard R. Data augmentation for time series classification using convolutional neural networks [C]//ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data. Riva del Garda: Springer, 2016: 1-9.
[44] Hermans M, Schrauwen B. Training and analysing deep recurrent neural networks [C]//Advances in Neural Information Processing Systems 26 (NIPS 2013). Lake Tahoe: Curran Associates, Inc., 2013: 190-198.
[45] Bittibssi TM, Zekry A, Genedy MA, et al. sEMG pattern recognition based on recurrent neural network [J]. Biomedical Signal Processing and Control, 2021, 70: 103048.
[46] Gauch M, Kratzert F, Klotz D, et al. Rainfall-runoff prediction at multiple timescales with a single long short-term memory network [J]. Hydrology and Earth System Sciences, 2021, 25(4): 2045-2062.
[47] Chung J, Gulcehre C, Cho K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling [EB/OL]. https://www.arxiv.org/abs/1412.3555v1,2014-12-11/2024-04-14.
[48] Luong MT, Pham H, Manning CD. Effective approaches to attention-based neural machine translation [EB/OL]. https://arxiv.org/abs/1508.04025,2015-09-20/2024-04-14.
[49] Abdelhady M, Damiano DL, Bulea TC. Attention-based deep recurrent neural network to estimate knee angle during walking from lower-limb EMG [C]//2023 International Conference on Rehabilitation Robotics (ICORR). Singapore: IEEE, 2023: 1-6.
[50] 王美,苏雪松,刘佳,等. 时频域多尺度交叉注意力融合的时间序列分类方法 [J]. 计算机应用, 2024, 44(6): 1842-1847.
[51] Weiss K, Khoshgoftaar TM, Wang Dingding. A survey of transfer learning [J]. Journal of Big Data, 2016, 3: 1-40.
[52] 姚旭,王晓丹,张玉玺,等. 特征选择方法综述 [J]. 控制与决策, 2012, 27(2): 161-166,192.
[53] 张聪. 多通道表面肌电信号特征提取关键技术研究 [D]. 合肥: 中国科学技术大学, 2021.
[54] Robinson M, Lu Lei, Tan Ying, et al. Feature identification framework for back injury risk in repetitive work with application in sheep shearing [J]. IEEE Trans Biomed Eng, 2023, 70(2): 616-627.
[55] Mishra A, Nurvitadhi E, Cook JJ, et al. WRPN: Wide reduced-precision networks [EB/OL]. https://arxiv.org/abs/1709.01134,2017-09-04/2024-04-14.
[56] Ye Xucheng, Dai Pengcheng, Luo Junyu, et al. Accelerating CNN training by pruning activation gradients [C]//Computer Vision–ECCV 2020: 16th European Conference. Glasgow: Springer, 2020: 322-338.
[57] Mirzadeh SI, Farajtabar M, Li A, et al. Improved knowledge distillation via teacher assistant [C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York: AAAI, 2020: 5191-5198.
[58] 司兆峰,齐洪钢. 知识蒸馏方法研究与应用综述 [J]. 中国图象图形学报, 2023, 28(9): 2817-2832.
[59] Ko JW. Multi-band transceiver architectures and circuits for chip-to-chip communication [M]. Los Angeles: University of California, 2006.
[60] 赖菊兰,王晓品,刘强. 嵌入式技术下无线传感通信网络拥塞控制系统 [J]. 现代电子技术, 2024, 47(4): 48-52.
[61] 楼亦文,李琳,陈潜. 腰部肌群稳定性康复训练结合肌内效贴扎技术在腰椎间盘突出症康复治疗中的应用 [J]. 中山大学学报(医学科学版), 2024, 45(1): 152-160.
[62] 郑翔,张明兴,黄雅,等. 生物反馈助力电刺激对慢性非特异性腰痛患者下肢步行功能的改善 [J]. 中国组织工程研究, 2025, 29(3): 547-553. |
|
|
|
