Convolutional neural network in upper limb functional motion analysis after stroke

In this work, implementation of Convolutional Neural Network (CNN) for the purpose of analysis of functional upper limb movement pattern was applied. The main aim of the study was to compare motion of selected activities of daily living of participants after stroke with the healthy ones (in similar age). The optical, marker-based motion capture system was applied for the purpose of data acquisition. There were some attempts made in order to find the existing differences in the motion pattern of the upper limb. For this purpose, the motion features of dominant and non-dominant upper limb of healthy participants were compared with motion features of paresis and non-paresis upper limbs of participants after stroke. On the basis of the newly collected data set, a new CNN application was presented to the classification of motion data in two different class label configurations. Analyzing individual segments of the upper body, it turned out that the arm was the most sensitive segment for capturing changes in the trajectory of the lifting movements of objects.

[1]  Sudanthi N. R. Wijewickrema,et al.  A rotation and translation invariant method for 3D organ image classification using deep convolutional neural networks , 2019, PeerJ Comput. Sci..

[2]  Chalavadi Krishna Mohan,et al.  Human Action Recognition Based on MOCAP Information Using Convolution Neural Networks , 2014, 2014 13th International Conference on Machine Learning and Applications.

[3]  Gutemberg Guerra-Filho,et al.  Optical Motion Capture: Theory and Implementation , 2005, RITA.

[4]  Travis E. Oliphant,et al.  Guide to NumPy , 2015 .

[5]  Lu Qin,et al.  Movement Disorder Detection via Adaptively Fused Gait Analysis Based on Kinect Sensors , 2018, IEEE Sensors Journal.

[6]  Hongxing Liu,et al.  ECG Heartbeat Classification Using Convolutional Neural Networks , 2020, IEEE Access.

[7]  M. Latash,et al.  What are “normal movements” in atypical populations? , 1996, Behavioral and Brain Sciences.

[8]  Sebastian Thrun,et al.  Real-Time Human Pose Tracking from Range Data , 2012, ECCV.

[9]  Cong Liu,et al.  Learning motion and content-dependent features with convolutions for action recognition , 2015, Multimedia Tools and Applications.

[10]  Sung-Bae Cho,et al.  Human activity recognition with smartphone sensors using deep learning neural networks , 2016, Expert Syst. Appl..

[11]  Alex Mihailidis,et al.  An Automated Classification of Pathological Gait Using Unobtrusive Sensing Technology , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[12]  Valerie M. Pomeroy,et al.  Getting a kinematic handle on reach-to-grasp: a meta-analysis. , 2017, Physiotherapy.

[13]  Alison Porter-Armstrong,et al.  The reliability of the graded Wolf Motor Function Test for stroke , 2020, British Journal of Occupational Therapy.

[14]  Jaap H. Buurke,et al.  Inertial Sensor Measurements of Upper-Limb Kinematics in Stroke Patients in Clinic and Home Environment , 2018, Front. Bioeng. Biotechnol..

[15]  Mesut Sahin,et al.  Convolutional Networks Outperform Linear Decoders in Predicting EMG From Spinal Cord Signals , 2018, Front. Neurosci..

[16]  Yichen Wei,et al.  Simple Baselines for Human Pose Estimation and Tracking , 2018, ECCV.

[17]  Sang Min Yoon,et al.  Divide and Conquer-Based 1D CNN Human Activity Recognition Using Test Data Sharpening † , 2018, Sensors.

[18]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[19]  Adam Switonski,et al.  Quaternions and joint angles in an analysis of local stability of gait for different variants of walking speed and treadmill slope , 2017, Inf. Sci..

[20]  Xiaowei Zhou,et al.  MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[22]  Eiichi Yoshida,et al.  Fusion of Multiple Motion Capture Systems for Musculoskeletal Analysis , 2020, 2020 IEEE/SICE International Symposium on System Integration (SII).

[23]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[24]  Hae Yean Park,et al.  Comparison of the effects of bilateral and unilateral training after stroke: A meta-analysis. , 2017, NeuroRehabilitation.

[25]  K. Sunnerhagen,et al.  Kinematic Variables Quantifying Upper-Extremity Performance After Stroke During Reaching and Drinking From a Glass , 2011, Neurorehabilitation and neural repair.

[26]  Suman Samui,et al.  An experimental study on upper limb position invariant EMG signal classification based on deep neural network , 2020, Biomed. Signal Process. Control..

[27]  Gentiane Venture,et al.  Pathological Gait Detection Based on Multiple Regression Models Using Unobtrusive Sensing Technology , 2021, J. Signal Process. Syst..

[28]  Eric Rogers,et al.  The application of precisely controlled functional electrical stimulation to the shoulder, elbow and wrist for upper limb stroke rehabilitation: a feasibility study , 2014, Journal of NeuroEngineering and Rehabilitation.

[29]  Koushik Maharatna,et al.  Rehab-Net: Deep Learning Framework for Arm Movement Classification Using Wearable Sensors for Stroke Rehabilitation , 2019, IEEE Transactions on Biomedical Engineering.

[30]  Enrique J. Gómez,et al.  Upper Limb Portable Motion Analysis System Based on Inertial Technology for Neurorehabilitation Purposes , 2010, Sensors.

[31]  Yohan Dupuis,et al.  A Study of Vicon System Positioning Performance , 2017, Sensors.

[32]  Mitsuo Kawato,et al.  Neural network control for a closed-loop System using Feedback-error-learning , 1993, Neural Networks.

[33]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[34]  Agnieszka Szczęsna,et al.  Quaternion lifting scheme applied to the classification of motion data , 2018, Inf. Sci..

[35]  Agnieszka Szczesna.  Quaternion Entropy for Analysis of Gait Data , 2019, Entropy.

[36]  M. Goffredo,et al.  A neural tracking and motor control approach to improve rehabilitation of upper limb movements , 2008, Journal of NeuroEngineering and Rehabilitation.

[37]  Guangmin Sun,et al.  Utilization of Color-depth Combination Features and Multi-level Refinement CNN for Upper-limb Posture Recognition , 2018, ICIGP.

[38]  Veronica Cimolin,et al.  Fugl-Meyer Assessment Scores Are Related With Kinematic Measures in People with Chronic Hemiparesis after Stroke. , 2019, Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association.

[39]  Li,et al.  Design and Analysis of Cloud Upper Limb Rehabilitation System Based on Motion Tracking for Post-Stroke Patients , 2019 .

[40]  Haoran Wang,et al.  A Novel Combination Model of Convolutional Neural Network and Long Short-Term Memory Network for Upper Limb Evaluation Using Kinect-Based System , 2019, IEEE Access.

[41]  Adam Switonski,et al.  Dynamic time warping in classification and selection of motion capture data , 2018, Multidimensional Systems and Signal Processing.

[42]  K. Jarrod Millman,et al.  Python for Scientists and Engineers , 2011, Comput. Sci. Eng..

[43]  G. Kwakkel,et al.  Understanding the pattern of functional recovery after stroke: facts and theories. , 2004, Restorative neurology and neuroscience.

[44]  Marek R. Ogiela,et al.  Human Actions Analysis: Templates Generation, Matching and Visualization Applied to Motion Capture of Highly-Skilled Karate Athletes , 2017, Sensors.

[45]  Bradley J. Erickson,et al.  Toolkits and Libraries for Deep Learning , 2017, Journal of Digital Imaging.

[46]  Agnieszka Szczesna,et al.  Functional differences in upper limb movement after early and chronic stroke based on kinematic motion indicators. , 2018, Biomedical papers of the Medical Faculty of the University Palacky, Olomouc, Czechoslovakia.