TY - JOUR
T1 - ST-DeepHAR
T2 - Deep Learning Model for Human Activity Recognition in IoHT Applications
AU - Abdel-Basset, Mohamed
AU - Hawash, Hossam
AU - Chakrabortty, Ripon K.
AU - Ryan, Michael
AU - Elhoseny, Mohamed
AU - Song, Houbing
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2021/3/15
Y1 - 2021/3/15
N2 - Human activity recognition (HAR) has been regarded as an indispensable part of many smart home systems and smart healthcare applications. Specifically, HAR is of great importance in the Internet of Healthcare Things (IoHT), owing to the rapid proliferation of Internet of Things (IoT) technologies embedded in various smart appliances and wearable devices (such as smartphones and smartwatches) that have a pervasive impact on an individual's life. The inertial sensors of smartphones generate massive amounts of multidimensional time-series data, which can be exploited effectively for HAR purposes. Unlike traditional approaches, deep learning techniques are the most suitable choice for such multivariate streams. In this study, we introduce a supervised dual-channel model that comprises long short-Term memory (LSTM), followed by an attention mechanism for the temporal fusion of inertial sensor data concurrent with a convolutional residual network for the spatial fusion of sensor data. We also introduce an adaptive channel-squeezing operation to fine-Tune convolutional a neural network feature extraction capability by exploiting multichannel dependency. Finally, two widely available and public HAR data sets are used in experiments to evaluate the performance of our model. The results demonstrate that our proposed approach can overcome state-of-The-Art methods.
AB - Human activity recognition (HAR) has been regarded as an indispensable part of many smart home systems and smart healthcare applications. Specifically, HAR is of great importance in the Internet of Healthcare Things (IoHT), owing to the rapid proliferation of Internet of Things (IoT) technologies embedded in various smart appliances and wearable devices (such as smartphones and smartwatches) that have a pervasive impact on an individual's life. The inertial sensors of smartphones generate massive amounts of multidimensional time-series data, which can be exploited effectively for HAR purposes. Unlike traditional approaches, deep learning techniques are the most suitable choice for such multivariate streams. In this study, we introduce a supervised dual-channel model that comprises long short-Term memory (LSTM), followed by an attention mechanism for the temporal fusion of inertial sensor data concurrent with a convolutional residual network for the spatial fusion of sensor data. We also introduce an adaptive channel-squeezing operation to fine-Tune convolutional a neural network feature extraction capability by exploiting multichannel dependency. Finally, two widely available and public HAR data sets are used in experiments to evaluate the performance of our model. The results demonstrate that our proposed approach can overcome state-of-The-Art methods.
KW - Deep learning (DL)
KW - human activity recognition (HAR)
KW - Internet of Healthcare Things (IoHT)
UR - http://www.scopus.com/inward/record.url?scp=85102381696&partnerID=8YFLogxK
UR - https://ieeexplore.ieee.org/xpl/aboutJournal.jsp?punumber=6488907
U2 - 10.1109/JIOT.2020.3033430
DO - 10.1109/JIOT.2020.3033430
M3 - Article
AN - SCOPUS:85102381696
SN - 2327-4662
VL - 8
SP - 4969
EP - 4979
JO - IEEE Internet of Things Journal
JF - IEEE Internet of Things Journal
IS - 6
M1 - 9238036
ER -