Gait recognition via random forests based on wearable inertial measurement unit

In recent years, gait detection has been widely used in medical rehabilitation, smart phone, criminal investigation, navigation and positioning and other fields. With the rapid development of micro-electro mechanical systems, inertial measurement unit (IMU) has been widely used in the field of gait recognition with many advantages, such as low cost, small size, and light weight. Therefore, this paper proposes a gait recognition algorithm based on IMU, which is named as FPRF-GR. Firstly, a fusion feature engineering operator is designed to eliminate redundant and defective features, which is mainly based on Fast Fourier Transform and principal component analysis. Then, in the design of classifier, in order to meet the requirements of gait recognition model for accuracy, generalization ability, speed, and noise resistance, this paper compares random forest (RF) and several commonly used classification algorithms, and finds that the model constructed by RF can meet the requirements. FPRF-GR builds the model based on RF, and uses the tenfold cross validation method to evaluate the model. Finally, this paper proposes an optimization scheme for the two parameters of decision tree number and sample number in RF. The results show that FPRF-GR can identify five gaits (walk, stationary, run, and up and down stairs) with the average accuracy of 98.2%.

[1]  S. Sprager,et al.  A cumulant-based method for gait identification using accelerometer data with principal component analysis and support vector machine , 2009 .

[2]  Vishesh Vikas,et al.  Measurement of Robot Link Joint Parameters Using Multiple Accelerometers and Gyroscope , 2013 .

[3]  Yuji Watanabe,et al.  Influence of Holding Smart Phone for Acceleration-Based Gait Authentication , 2014, 2014 Fifth International Conference on Emerging Security Technologies.

[4]  Hongnian Yu,et al.  Optimal Foot Location for Placing Wearable IMU Sensors and Automatic Feature Extraction for Gait Analysis , 2018, IEEE Sensors Journal.

[5]  Hu,et al.  Accelerometer-based Gait Authentication via Neural Network , 2012 .

[6]  Qian Wang,et al.  Deep Learning-Based Gait Recognition Using Smartphones in the Wild , 2018, IEEE Transactions on Information Forensics and Security.

[7]  A. B. Drought,et al.  WALKING PATTERNS OF NORMAL MEN. , 1964, The Journal of bone and joint surgery. American volume.

[8]  Luca Martino,et al.  Cooperative parallel particle filters for online model selection and applications to urban mobility , 2015, Digit. Signal Process..

[9]  Hou Jian,et al.  Gait recognition based on MEMS accelerometer , 2010, IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS.

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

[11]  Michael J. Black,et al.  Modeling and decoding motor cortical activity using a switching Kalman filter , 2004, IEEE Transactions on Biomedical Engineering.

[12]  Davrondzhon Gafurov,et al.  A Survey of Biometric Gait Recognition: Approaches, Security and Challenges , 2007 .

[13]  D.V. Thiel,et al.  Measurement of Energy Expenditure in Elite Athletes Using MEMS-Based Triaxial Accelerometers , 2007, IEEE Sensors Journal.

[14]  Luca Martino,et al.  A multi-model particle filtering algorithm for indoor tracking of mobile terminals using RSS data , 2009, 2009 IEEE Control Applications, (CCA) & Intelligent Control, (ISIC).

[15]  Janice K. Loudon,et al.  The Clinical Orthopedic Assessment Guide , 1998 .

[16]  Yunqiang Sun,et al.  Application and research of MEMS sensor in gait recognition algorithm , 2018, Cluster Computing.

[17]  Ling-Feng Shi,et al.  An orientation estimation algorithm based on multi-source information fusion , 2018, Measurement Science and Technology.

[18]  Noel E. O'Connor,et al.  Automatic Activity Classification and Movement Assessment During a Sports Training Session Using Wearable Inertial Sensors , 2014, 2014 11th International Conference on Wearable and Implantable Body Sensor Networks.

[19]  Farid Golnaraghi,et al.  An Algorithm for the In-Field Calibration of a MEMS IMU , 2017, IEEE Sensors Journal.

[20]  Guanglie Zhang,et al.  A gait recognition system for rehabilitation based on wearable micro inertial measurement unit , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[21]  Omid Dehzangi,et al.  IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion , 2017, Sensors.

[22]  Muhammad Younus Javed,et al.  An implementation of optimized framework for action classification using multilayers neural network on selected fused features , 2019, Pattern Analysis and Applications.

[23]  Shuai Tao,et al.  Gait based biometric personal authentication by using MEMS inertial sensors , 2018, Journal of Ambient Intelligence and Humanized Computing.

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

[25]  Tein-Yaw Chung,et al.  Testing and evaluating recommendation algorithms in internet of things , 2016, Journal of Ambient Intelligence and Humanized Computing.