Wearable Sensor-Based Gait Analysis for Age and Gender Estimation

Wearable sensor-based systems and devices have been expanded in different application domains, especially in the healthcare arena. Automatic age and gender estimation has several important applications. Gait has been demonstrated as a profound motion cue for various applications. A gait-based age and gender estimation challenge was launched in the 12th IAPR International Conference on Biometrics (ICB), 2019. In this competition, 18 teams initially registered from 14 countries. The goal of this challenge was to find some smart approaches to deal with age and gender estimation from sensor-based gait data. For this purpose, we employed a large wearable sensor-based gait dataset, which has 745 subjects (357 females and 388 males), from 2 to 78 years old in the training dataset; and 58 subjects (19 females and 39 males) in the test dataset. It has several walking patterns. The gait data sequences were collected from three IMUZ sensors, which were placed on waist-belt or at the top of a backpack. There were 67 solutions from ten teams—for age and gender estimation. This paper extensively analyzes the methods and achieved-results from various approaches. Based on analysis, we found that deep learning-based solutions lead the competitions compared with conventional handcrafted methods. We found that the best result achieved 24.23% prediction error for gender estimation, and 5.39 mean absolute error for age estimation by employing angle embedded gait dynamic image and temporal convolution network.

[1]  Miao Sun,et al.  Age Group and Gender Estimation in the Wild With Deep RoR Architecture , 2017, IEEE Access.

[2]  Umair Ahmed,et al.  Predicting physiological developments from human gait using smartphone sensor data , 2017, 1712.07958.

[3]  Emin Anarim,et al.  Age group detection using smartphone motion sensors , 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

[4]  Maria Kyrarini,et al.  A robust algorithm for gait cycle segmentation , 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

[5]  Mohammad Hossein Sedaaghi,et al.  A Comparative Study of Gender and Age Classification in Speech Signals , 2009 .

[6]  Tao Liu,et al.  Gait Analysis Using Wearable Sensors , 2012, Sensors.

[7]  Yasushi Makihara,et al.  Similar gait action recognition using an inertial sensor , 2015, Pattern Recognit..

[8]  Richard W. Bohannon.  Comfortable and maximum walking speed of adults aged 20-79 years: reference values and determinants. , 1997, Age and ageing.

[9]  Illhoi Yoo,et al.  A Systematic Review of Healthcare Applications for Smartphones , 2012, BMC Medical Informatics and Decision Making.

[10]  Yasushi Yagi,et al.  Gait-based age estimation using multi-stage convolutional neural network , 2019, IPSJ Transactions on Computer Vision and Applications.

[11]  Mao-Jiun J. Wang,et al.  The change of gait parameters during walking at different percentage of preferred walking speed for healthy adults aged 20-60 years. , 2010, Gait & posture.

[12]  Jianxin Wu,et al.  Age Estimation Using Expectation of Label Distribution Learning , 2018, IJCAI.

[13]  Yasushi Makihara,et al.  Unsupervised GEI-Based Gait Disorders Detection From Different Views , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Jean-Luc Dugelay,et al.  Apparent Age Estimation from Face Images Combining General and Children-Specialized Deep Learning Models , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[16]  Yasushi Makihara,et al.  The largest inertial sensor-based gait database and performance evaluation of gait-based personal authentication , 2014, Pattern Recognit..

[17]  L. Mollinger,et al.  Age- and gender-related test performance in community-dwelling elderly people: Six-Minute Walk Test, Berg Balance Scale, Timed Up & Go Test, and gait speeds. , 2002, Physical therapy.

[18]  Xiang Li,et al.  Gait-based human age estimation using age group-dependent manifold learning and regression , 2018, Multimedia Tools and Applications.

[19]  Suiping Zhou,et al.  Wearable Device-Based Gait Recognition Using Angle Embedded Gait Dynamic Images and a Convolutional Neural Network , 2017, Sensors.

[20]  Jianxin Wu,et al.  Deep Label Distribution Learning With Label Ambiguity , 2016, IEEE Transactions on Image Processing.

[21]  Young-Geun Park,et al.  Smart Sensor Systems for Wearable Electronic Devices , 2017, Polymers.

[22]  Yasushi Makihara,et al.  OU-ISIR Wearable Sensor-based Gait Challenge: Age and Gender , 2019, 2019 International Conference on Biometrics (ICB).

[23]  Benno M. Nigg,et al.  Gait characteristics as a function of age and gender , 1994 .

[24]  Md. Atiqur Rahman Ahad,et al.  A Comparative Approach to Classification of Locomotion and Transportation Modes Using Smartphone Sensor Data , 2018, UbiComp/ISWC Adjunct.

[25]  Roongtiwa Vachalathiti,et al.  Age, gender and speed effects on spinal kinematics during walking , 1997 .

[26]  T. Oberg,et al.  Basic gait parameters: reference data for normal subjects, 10-79 years of age. , 1993, Journal of rehabilitation research and development.

[27]  Begonya Garcia-Zapirain,et al.  Gait Analysis Methods: An Overview of Wearable and Non-Wearable Systems, Highlighting Clinical Applications , 2014, Sensors.

[28]  Manuel J. Marín-Jiménez,et al.  An End-to-End Multi-Task and Fusion CNN for Inertial-Based Gait Recognition , 2019, IEEE Access.

[29]  Md. Atiqur Rahman Ahad,et al.  An Approach to Classify Human Activities in Real-time from Smartphone Sensor Data , 2019, 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR).

[30]  I. Heyligers,et al.  Assessment of physical function following total hip arthroplasty: Inertial sensor based gait analysis is supplementary to patient-reported outcome measures. , 2016, Clinical biomechanics.

[31]  Yu Zhong,et al.  Sensor orientation invariant mobile gait biometrics , 2014, IEEE International Joint Conference on Biometrics.

[32]  S. Delp,et al.  How robust is human gait to muscle weakness? , 2011, Gait & posture.

[33]  Masud Ahmed,et al.  Prediction of Gender and Age from Inertial Sensor-based Gait Dataset , 2019, 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR).

[34]  J. V. van Dieën,et al.  The effect of walking speed on quality of gait in older adults. , 2018, Gait & posture.

[35]  Gang Wang,et al.  Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions , 2014, IEEE Transactions on Information Forensics and Security.

[36]  Jiwen Lu,et al.  Gait-Based Human Age Estimation , 2010, IEEE Transactions on Information Forensics and Security.

[37]  Cao,et al.  Sudden turns and stops while walking: kinematic sources of age and gender differences. , 1998, Gait & posture.

[38]  D. Cunningham,et al.  Age-related changes in speed of walking. , 1988, Medicine and science in sports and exercise.

[39]  Sungkuk Chun,et al.  Gait Estimation from Anatomical Foot Parameters Measured by a Foot Feature Measurement System using a Deep Neural Network Model , 2018, Scientific Reports.

[40]  Feng Duan,et al.  The Effect of Treadmill Walking on Gait and Upper Trunk through Linear and Nonlinear Analysis Methods , 2019, Sensors.

[41]  Mi Zhang,et al.  Motion primitive-based human activity recognition using a bag-of-features approach , 2012, IHI '12.

[42]  Jochen Klucken,et al.  The Diagnostic Scope of Sensor-Based Gait Analysis in Atypical Parkinsonism: Further Observations , 2019, Front. Neurol..

[43]  Kota Aoki,et al.  Early Detection of Lower MMSE Scores in Elderly Based on Dual-Task Gait , 2019, IEEE Access.

[44]  Luis Fernando Aragón-Vargas,et al.  Gait characteristics and sensory abilities of older adults are modulated by gender. , 2015, Gait & posture.

[45]  Minoru Yamada,et al.  Development and validation of Comprehensive Gait Assessment using InerTial Sensor score (C-GAITS score) derived from acceleration and angular velocity data at heel and lower trunk among community-dwelling older adults , 2019, Journal of NeuroEngineering and Rehabilitation.

[46]  Patrick Kenny,et al.  Eigenvoice modeling with sparse training data , 2005, IEEE Transactions on Speech and Audio Processing.

[47]  Eduardo Palermo,et al.  Gait Partitioning Methods: A Systematic Review , 2016, Sensors.

[48]  Qaiser Riaz,et al.  Move Your Body: Age Estimation Based on Chest Movement During Normal Walk , 2019, IEEE Access.

[49]  Yasushi Makihara,et al.  Orientation-Compensative Signal Registration for Owner Authentication Using an Accelerometer , 2014, IEICE Trans. Inf. Syst..

[50]  A. Kluttig,et al.  Inertial sensor based reference gait data for healthy subjects. , 2011, Gait & posture.

[51]  C. Winstein,et al.  Age Affects the Attentional Demands of Stair Ambulation: Evidence From a Dual-Task Approach , 2009, Physical Therapy.

[52]  Seiichi Serikawa,et al.  Automatic Fall Detection System of Unsupervised Elderly People Using Smartphone , 2017 .

[53]  Omar Shahid,et al.  Vision-based Action Understanding for Assistive Healthcare: A Short Review , 2019, CVPR Workshops.

[54]  G. Pera,et al.  Incidence and consequences of falls among elderly people living in the community. , 2004, Medicina clinica.

[55]  Vladlen Koltun,et al.  An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling , 2018, ArXiv.

[56]  Kyung-Sup Kwak,et al.  The Internet of Things for Health Care: A Comprehensive Survey , 2015, IEEE Access.

[57]  Lama Nachman,et al.  Unobtrusive gait verification for mobile phones , 2014, SEMWEB.

[58]  Tapas Mondal,et al.  Wearable Sensors for Remote Health Monitoring , 2017, Sensors.

[59]  Sudeep Sarkar,et al.  The humanID gait challenge problem: data sets, performance, and analysis , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[60]  Daniel Roggen,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

[61]  Enrique Argones-Rúa,et al.  Biometric Template Protection Using Universal Background Models: An Application to Online Signature , 2012, IEEE Transactions on Information Forensics and Security.

[62]  Brett W Fling,et al.  Two-minute walk tests demonstrate similar age-related gait differences as a six-minute walk test. , 2019, Gait & posture.

[63]  Wouter Joosen,et al.  A Systematic Comparison of Age and Gender Prediction on IMU Sensor-Based Gait Traces , 2019, Sensors.

[64]  Saeid Sanei,et al.  A Review on Accelerometry-Based Gait Analysis and Emerging Clinical Applications , 2018, IEEE Reviews in Biomedical Engineering.

[65]  Yasushi Makihara,et al.  Gait-based age estimation using a whole-generation gait database , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[66]  Christian A. Clermont,et al.  Using wearable sensors to classify subject-specific running biomechanical gait patterns based on changes in environmental weather conditions , 2018, PloS one.

[67]  Björn Krüger,et al.  One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor , 2015, Sensors.

[68]  Lars Kotthoff,et al.  Auto-WEKA 2.0: Automatic model selection and hyperparameter optimization in WEKA , 2017, J. Mach. Learn. Res..