TY - JOUR
T1 - Classification of indoor human fall events using deep learning
AU - Sultana, Arifa
AU - Deb, Kaushik
AU - Dhar, Pranab Kumar
AU - Koshiba, Takeshi
N1 - Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2021/3
Y1 - 2021/3
N2 - Human fall identification can play a significant role in generating sensor based alarm systems, assisting physical therapists not only to reduce after fall effects but also to save human lives. Usually, elderly people suffer from various kinds of diseases and fall action is a very frequently occurring circumstance at this time for them. In this regard, this paper represents an architecture to classify fall events from others indoor natural activities of human beings. Video frame generator is applied to extract frame from video clips. Initially, a two dimensional convolutional neural network (2DCNN) model is proposed to extract features from video frames. Afterward, gated recurrent unit (GRU) network finds the temporal dependency of human movement. Binary cross-entropy loss function is calculated to update the attributes of the network like weights, learning rate to minimize the losses. Finally, sigmoid classifier is used for binary classification to detect human fall events. Experimental result shows that the proposed model obtains an accuracy of 99%, which outperforms other state-of-the-art models.
AB - Human fall identification can play a significant role in generating sensor based alarm systems, assisting physical therapists not only to reduce after fall effects but also to save human lives. Usually, elderly people suffer from various kinds of diseases and fall action is a very frequently occurring circumstance at this time for them. In this regard, this paper represents an architecture to classify fall events from others indoor natural activities of human beings. Video frame generator is applied to extract frame from video clips. Initially, a two dimensional convolutional neural network (2DCNN) model is proposed to extract features from video frames. Afterward, gated recurrent unit (GRU) network finds the temporal dependency of human movement. Binary cross-entropy loss function is calculated to update the attributes of the network like weights, learning rate to minimize the losses. Finally, sigmoid classifier is used for binary classification to detect human fall events. Experimental result shows that the proposed model obtains an accuracy of 99%, which outperforms other state-of-the-art models.
KW - Convolutional neural network (CNN)
KW - Deep learning
KW - Gated recurrent unit (GRU)
KW - Human fall classification
KW - Recurrent neural network (RNN)
UR - http://www.scopus.com/inward/record.url?scp=85102944817&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102944817&partnerID=8YFLogxK
U2 - 10.3390/e23030328
DO - 10.3390/e23030328
M3 - Article
AN - SCOPUS:85102944817
VL - 23
SP - 1
EP - 20
JO - Entropy
JF - Entropy
SN - 1099-4300
IS - 3
M1 - 328
ER -