Efficiency investigation from shallow to deep neural network techniques in human activity recognition

Abstract In the last years, several researchers measured different recognition rates with different artificial neural network (ANN) techniques on public data sets in the human activity recognition (HAR) problem. However an overall investigation does not exist in the literature and the efficiency of complex and deeper ANNs over shallow networks is not clear. The purpose of this paper is to investigate the recognition rate and time requirement of different kinds of ANN approaches in HAR. This work examines the performance of shallow ANN architectures with different hyper-parameters, ANN ensembles, binary ANN classifier groups, and convolutional neural networks on two public databases. Although the popularity of binary classifiers, classifier ensembles and deep learning have been significantly increasing, this study shows that shallow ANNs with appropriate hyper-parameters in combination with extracted features can reach similar or higher recognition rate in less time than other artificial neural network methods in HAR. With a well-tuned ANN we outperformed all previous results on two public databases. Consequently, instead of the more complex ANN techniques, the usage of simple ANN with two or three layers can be an appropriate choice for activity recognition.

[1]  Yi Lu Murphey,et al.  Multi-class pattern classification using neural networks , 2007, Pattern Recognit..

[2]  Min Sheng,et al.  Short-time activity recognition with wearable sensors using convolutional neural network , 2016, VRCAI.

[3]  Thomas Villmann,et al.  A sparse kernelized matrix learning vector quantization model for human activity recognition , 2013, ESANN.

[4]  Jun Gao,et al.  A survey of neural network ensembles , 2005, 2005 International Conference on Neural Networks and Brain.

[5]  Ming Zeng,et al.  Semi-supervised convolutional neural networks for human activity recognition , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[6]  Davide Anguita,et al.  A Public Domain Dataset for Human Activity Recognition using Smartphones , 2013, ESANN.

[7]  Jozsef Suto,et al.  Activity recognition in adaptive assistive systems using artificial neural networks , 2016 .

[8]  G. ÓLaighin,et al.  Direct measurement of human movement by accelerometry. , 2008, Medical engineering & physics.

[9]  Miguel A. Labrador,et al.  A Survey on Human Activity Recognition using Wearable Sensors , 2013, IEEE Communications Surveys & Tutorials.

[10]  Petrica C. Pop,et al.  Feature Analysis to Human Activity Recognition , 2016, Int. J. Comput. Commun. Control.

[11]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[12]  Andrey Ignatov,et al.  Real-time human activity recognition from accelerometer data using Convolutional Neural Networks , 2018, Appl. Soft Comput..

[13]  Teddy Mantoro,et al.  A Comparison Study of Classifier Algorithms for Mobile-phone's Accelerometer Based Activity Recognition , 2012 .

[14]  Fabio Roli,et al.  Design of effective neural network ensembles for image classification purposes , 2001, Image Vis. Comput..

[15]  Francisco Herrera,et al.  An overview of ensemble methods for binary classifiers in multi-class problems: Experimental study on one-vs-one and one-vs-all schemes , 2011, Pattern Recognit..

[16]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[17]  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.

[18]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[19]  Jeen-Shing Wang,et al.  Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers , 2008, Pattern Recognit. Lett..

[20]  Luca Maria Gambardella,et al.  Deep, Big, Simple Neural Nets for Handwritten Digit Recognition , 2010, Neural Computation.

[21]  Abdulkadir Sengür,et al.  Effective diagnosis of heart disease through neural networks ensembles , 2009, Expert Syst. Appl..

[22]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[23]  Yu-Bin Yang,et al.  Lung cancer cell identification based on artificial neural network ensembles , 2002, Artif. Intell. Medicine.

[24]  Stefan Oniga,et al.  Optimal Recognition Method of Human Activities Using Artificial Neural Networks , 2015 .

[25]  Jozsef Suto,et al.  Human activity recognition using neural networks , 2014, Proceedings of the 2014 15th International Carpathian Control Conference (ICCC).

[26]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[27]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Ismail Uysal,et al.  Inertia Based Recognition of Daily Activities with ANNs and Spectrotemporal Features , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[29]  M. S. Hane Aung,et al.  A One-Vs-One Classifier Ensemble With Majority Voting for Activity Recognition , 2013, ESANN.

[30]  Derek C. Rose,et al.  Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] , 2010, IEEE Computational Intelligence Magazine.

[31]  Xiaoli Li,et al.  Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition , 2015, IJCAI.

[32]  Wei Tang,et al.  Ensembling neural networks: Many could be better than all , 2002, Artif. Intell..

[33]  Tahmina Zebin,et al.  Inertial Sensor Based Modelling of Human Activity Classes: Feature Extraction and Multi-sensor Data Fusion Using Machine Learning Algorithms , 2016, eHealth 360°.

[34]  Hongnian Yu,et al.  Elderly activities recognition and classification for applications in assisted living , 2013, Expert Syst. Appl..

[35]  Didier Stricker,et al.  A competitive approach for human activity recognition on smartphones , 2013, ESANN.

[36]  Xin Yao,et al.  Evolving artificial neural network ensembles , 2008 .

[37]  Allen Y. Yang,et al.  Distributed recognition of human actions using wearable motion sensor networks , 2009, J. Ambient Intell. Smart Environ..

[38]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[39]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[40]  Lei Gao,et al.  Evaluation of accelerometer based multi-sensor versus single-sensor activity recognition systems. , 2014, Medical engineering & physics.

[41]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  A review on the combination of binary classifiers in multiclass problems , 2008, Artificial Intelligence Review.

[42]  Jozsef Suto,et al.  Recognition rate difference between real-time and offline human activity recognition , 2017, 2017 International Conference on Internet of Things for the Global Community (IoTGC).

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

[44]  Jozsef Suto,et al.  Efficiency investigation of artificial neural networks in human activity recognition , 2017, Journal of Ambient Intelligence and Humanized Computing.

[45]  Chih-Fong Tsai,et al.  Using neural network ensembles for bankruptcy prediction and credit scoring , 2008, Expert Syst. Appl..

[46]  Bo Yu,et al.  Convolutional Neural Networks for human activity recognition using mobile sensors , 2014, 6th International Conference on Mobile Computing, Applications and Services.

[47]  Zhaozheng Yin,et al.  Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks , 2015, ACM Multimedia.