Classification of Hand Gestures from Wearable IMUs using Deep Neural Network

IMUs are gaining significant importance in the field of hand gesture analysis, trajectory detection and kinematic functional study. An Inertial Measurement Unit (IMU) consists of tri-axial accelerometers and gyroscopes which can together be used for formation analysis. The paper presents a novel classification approach using a Deep Neural Network (DNN) for classifying hand gestures obtained from wearable IMU sensors. An optimization objective is set for the classifier in order to reduce correlation between the activities and fit the signal-set with best performance parameters. Training of the network is carried out by feed-forward computation of the input features followed by the back-propagation of errors. The predicted outputs are analyzed in the form of classification accuracies which are then compared to the conventional classification schemes of SVM and kNN. A 3-5% improvement in accuracies is observed in the case of DNN classification. Results are presented for the recorded accelerometer and gyroscope signals and the considered classification schemes.

[1]  Claudia V. Isaza,et al.  Artificial Neural Networks as an alternative to traditional fall detection methods , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[2]  Naser El-Sheimy,et al.  The Utilization of Artificial Neural Networks for Multisensor System Integration in Navigation and Positioning Instruments , 2006, IEEE Transactions on Instrumentation and Measurement.

[3]  Ishita Basu,et al.  A neural network-based design of an on-off adaptive control for Deep Brain Stimulation in movement disorders , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Tae-Seong Kim,et al.  A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical Recognizer , 2010, IEEE Transactions on Information Technology in Biomedicine.

[5]  Yongqiang Wang,et al.  An investigation of deep neural networks for noise robust speech recognition , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Thomas George,et al.  An effective approach for human activity recognition on smartphone , 2015, 2015 IEEE International Conference on Engineering and Technology (ICETECH).

[7]  Gerhard Tröster,et al.  Incremental kNN Classifier Exploiting Correct-Error Teacher for Activity Recognition , 2010, 2010 Ninth International Conference on Machine Learning and Applications.

[8]  Wen-Chang Cheng,et al.  Triaxial Accelerometer-Based Fall Detection Method Using a Self-Constructing Cascade-AdaBoost-SVM Classifier , 2013, IEEE Journal of Biomedical and Health Informatics.

[9]  C.J. De Luca,et al.  A Combined sEMG and Accelerometer System for Monitoring Functional Activity in Stroke , 2009, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[10]  Bao-Liang Lu,et al.  Investigating Critical Frequency Bands and Channels for EEG-Based Emotion Recognition with Deep Neural Networks , 2015, IEEE Transactions on Autonomous Mental Development.

[11]  Dong Yu,et al.  Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription , 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

[12]  A. M. Khan,et al.  Accelerometer signal-based human activity recognition using augmented autoregressive model coefficients and artificial neural nets , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  Tanja Schultz,et al.  Pattern learning with deep neural networks in EMG-based speech recognition , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[14]  M. Murugappan Electromyogram signal based human emotion classification using KNN and LDA , 2011, 2011 IEEE International Conference on System Engineering and Technology.

[15]  Zhenyu He,et al.  Activity recognition from acceleration data based on discrete consine transform and SVM , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[16]  Lukun Wang,et al.  Recognition of Human Activities Using Continuous Autoencoders with Wearable Sensors , 2016, Sensors.