TY - GEN
T1 - Static and Dynamic Human Activity Detection Using Multi CNN-ELM Approach
AU - Ankalaki, Shilpa
AU - Thippeswamy, M. N.
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2022
Y1 - 2022
N2 - Human Activity Recognition (HAR) is leading-edge in today's research field which has its applications in multiple research areas, some of those are Smart Health, Security and Ambient Assisted Living, etc. In today’s ubiquitous computing, HAR can be accomplished by espousing deep learning techniques that replace traditional analytical techniques that depend on the extraction of handcrafted features and classification methods. This work employed the Hierarchical Multi Convolution—Extreme Learning Machine approach for the classification of human activities. In the Hierarchical Multi CNN approach, the root CNN is employed to categorize the activities into static and dynamic activities. In the next level, two CNN-ELM are used to classify static activities into laying down, stand and sit; and classifies dynamic activities into Walking, Walking Downstairs, and walking upstairs. CNN-ELM approach exhibits its major advantages: CNN extracts the features from the dataset which confiscates expert knowledge in extracting features and ELM classifies the transitional results. This framework is evaluated on the UCI-HAR dataset and achieves an accuracy of 96.86%.
AB - Human Activity Recognition (HAR) is leading-edge in today's research field which has its applications in multiple research areas, some of those are Smart Health, Security and Ambient Assisted Living, etc. In today’s ubiquitous computing, HAR can be accomplished by espousing deep learning techniques that replace traditional analytical techniques that depend on the extraction of handcrafted features and classification methods. This work employed the Hierarchical Multi Convolution—Extreme Learning Machine approach for the classification of human activities. In the Hierarchical Multi CNN approach, the root CNN is employed to categorize the activities into static and dynamic activities. In the next level, two CNN-ELM are used to classify static activities into laying down, stand and sit; and classifies dynamic activities into Walking, Walking Downstairs, and walking upstairs. CNN-ELM approach exhibits its major advantages: CNN extracts the features from the dataset which confiscates expert knowledge in extracting features and ELM classifies the transitional results. This framework is evaluated on the UCI-HAR dataset and achieves an accuracy of 96.86%.
UR - https://www.scopus.com/pages/publications/85120535142
UR - https://www.scopus.com/pages/publications/85120535142#tab=citedBy
U2 - 10.1007/978-981-16-1338-8_18
DO - 10.1007/978-981-16-1338-8_18
M3 - Conference contribution
AN - SCOPUS:85120535142
SN - 9789811613371
T3 - Lecture Notes in Electrical Engineering
SP - 207
EP - 218
BT - Emerging Research in Computing, Information, Communication and Applications - ERCICA 2020
A2 - Shetty, N. R.
A2 - Patnaik, L. M.
A2 - Nagaraj, H. C.
A2 - Hamsavath, Prasad N.
A2 - Nalini, N.
PB - Springer Science and Business Media Deutschland GmbH
T2 - 6th International Conference on Emerging Research in Computing, Information, Communication and Applications, ERCICA 2020
Y2 - 25 September 2020 through 26 September 2020
ER -
