Human Activity Recognition Using Multichannel Convolutional Neural Network

Human Activity Recognition (HAR) simply refers to the capacity of a machine to perceive human actions. HAR is a prominent application of advanced Machine Learning and Artificial Intelligence techniques that utilize computer vision to understand the semantic meanings of heterogeneous human actions. This paper describes a supervised learning method that can distinguish human actions based on data collected from practical human movements. The primary challenge while working with HAR is to overcome the difficulties that come with the cyclostationary nature of the activity signals. This study proposes a HAR classification model based on a two-channel Convolutional Neural Network (CNN) that makes use of the frequency and power features of the collected human action signals. The model was tested on the UCI HAR dataset, which resulted in a 95.25% classification accuracy. This approach will help others to conduct further researches on the recognition of human activities based on their biomedical signals.

[1]  Gavin Hackeling,et al.  Mastering Machine Learning With scikit-learn , 2014 .

[2]  Luís Nunes,et al.  Human Activity Recognition and Prediction , 2015 .

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

[4]  Miguel A. Labrador,et al.  Human Activity Recognition: Using Wearable Sensors and Smartphones , 2013 .

[5]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[6]  Abdullah Al Nahid,et al.  Fault Diagnosis of Induction Motor Bearing Using Cepstrum-based Preprocessing and Ensemble Learning Algorithm , 2019, 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE).

[7]  Davide Anguita,et al.  Energy Efficient Smartphone-Based Activity Recognition using Fixed-Point Arithmetic , 2013, J. Univers. Comput. Sci..

[8]  Hermann Ney,et al.  Convolutional neural networks for acoustic modeling of raw time signal in LVCSR , 2015, INTERSPEECH.

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

[10]  Huan Liu,et al.  Feature Engineering for Machine Learning and Data Analytics , 2018 .

[11]  Ying Wu,et al.  Human Action Recognition with Depth Cameras , 2014, SpringerBriefs in Computer Science.

[12]  Patrícia J. Bota,et al.  A Semi-Automatic Annotation Approach for Human Activity Recognition , 2019, Sensors.

[13]  Davide Anguita,et al.  Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine , 2012, IWAAL.

[14]  Aleena Swetapadma,et al.  A Comparative Study of Supervised Learning Techniques for Human Activity Monitoring Using Smart Sensors , 2018, 2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC).

[15]  Niloy Sikder,et al.  Fault Diagnosis of Motor Bearing Using Ensemble Learning Algorithm with FFT-based Preprocessing , 2019, 2019 International Conference on Robotics,Electrical and Signal Processing Techniques (ICREST).

[16]  Petre Stoica,et al.  Spectral Analysis of Signals , 2009 .

[17]  Bandar Saleh Mouhammed ِAlmaslukh,et al.  An effective deep autoencoder approach for online smartphone-based human activity recognition , 2017 .