Granger-causality: An efficient single user movement recognition using a smartphone accelerometer sensor

Abstract In this research paper, a novel framework is proposed to classify and analyze human activities. Granger-causality is applied on a smartphone for the recognition of single user activity. It is done in two different ways. In the first one, human activity is recognized on the basis of casual relationships among X-Y-Z Cartesian axes while the second one is based on the casual relationships among the activities. The graphical representation allowed the understanding of mutual dependencies among activities. A tri-axial accelerometer sensor embedded in a smartphone is used to record the acceleration signal. Six human activities successfully classified are walking, walking-upstairs, walking-downstairs, sitting, standing and lying.

[1]  Kin K. Leung,et al.  Context-Awareness for Mobile Sensing: A Survey and Future Directions , 2016, IEEE Communications Surveys & Tutorials.

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

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

[4]  Jesse Hoey,et al.  Sensor-Based Activity Recognition , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

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

[6]  Grégoire Lefebvre,et al.  Attitude Estimation for Posture Detection in eHealth Services , 2018, 2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS).

[7]  Leonardo L. Gollo,et al.  Modeling positive Granger causality and negative phase lag between cortical areas , 2014, NeuroImage.

[8]  C. Granger.  Investigating Causal Relations by Econometric Models and Cross-Spectral Methods , 1969 .

[9]  Arindam Ghosh,et al.  Recognizing Human Activities from Smartphone Sensor Signals , 2014, ACM Multimedia.

[10]  Song Hui,et al.  Compressed sensing method for human activity recognition using tri-axis accelerometer on mobile phone , 2017 .

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

[12]  Steven L. Bressler,et al.  Foundational perspectives on causality in large-scale brain networks. , 2015, Physics of life reviews.

[13]  Anil K. Seth,et al.  A MATLAB toolbox for Granger causal connectivity analysis , 2010, Journal of Neuroscience Methods.

[14]  Chi Harold Liu,et al.  Unsupervised posture detection by smartphone accelerometer , 2013 .

[15]  Takeshi Nishida,et al.  Deep recurrent neural network for mobile human activity recognition with high throughput , 2017, Artificial Life and Robotics.

[16]  Shuang Wu,et al.  Video Sensor-Based Complex Scene Analysis with Granger Causality , 2013, Sensors.

[17]  Dapeng Tao,et al.  Skeleton embedded motion body partition for human action recognition using depth sequences , 2018, Signal Process..

[18]  Mykola Pechenizkiy,et al.  A survey on using domain and contextual knowledge for human activity recognition in video streams , 2016, Expert Syst. Appl..

[19]  Andrea F. Abate,et al.  What are you doing while answering your smartphone? , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[20]  Hongxun Yao,et al.  Distinctive action sketch for human action recognition , 2018, Signal Process..

[21]  Ah Chung Tsoi,et al.  Investigating the impact of frame rate towards robust human action recognition , 2016, Signal Process..

[22]  Jun Zhu,et al.  Recognizing Human Group Behaviors with Multi-group Causalities , 2012, 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology.

[23]  Xingshe Zhou,et al.  Energy-Efficient Motion Related Activity Recognition on Mobile Devices for Pervasive Healthcare , 2014, Mob. Networks Appl..

[24]  Fernando Fernández Martínez,et al.  Feature extraction from smartphone inertial signals for human activity segmentation , 2016, Signal Process..

[25]  Rubén San-Segundo-Hernández,et al.  Segmenting human activities based on HMMs using smartphone inertial sensors , 2016, Pervasive Mob. Comput..

[26]  Minh-Son Dao,et al.  Daily Human Activities Recognition Using Heterogeneous Sensors from Smartphones , 2017 .

[27]  H. Akaike.  A new look at the statistical model identification , 1974 .

[28]  S. Bressler,et al.  Granger Causality: Basic Theory and Application to Neuroscience , 2006, q-bio/0608035.

[29]  Ahmad Almogren,et al.  A robust human activity recognition system using smartphone sensors and deep learning , 2018, Future Gener. Comput. Syst..

[30]  Marcus Edel,et al.  Binarized-BLSTM-RNN based Human Activity Recognition , 2016, 2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[31]  Tuan Dinh Le,et al.  Human activity recognition by smartphone , 2015, 2015 2nd National Foundation for Science and Technology Development Conference on Information and Computer Science (NICS).

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

[33]  Xiangjian He,et al.  Recognizing Human Activity in Still Images by Integrating Group-Based Contextual Cues , 2015, ACM Multimedia.

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

[35]  Patrick Pérez,et al.  Nonparametric motion characterization using causal probabilistic models for video indexing and retrieval , 2002, IEEE Trans. Image Process..

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