Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/86019
Title: | Distilling the knowledge from handcrafted features for human activity recognition | Authors: | Chen, Zhenghua Zhang, Le Cao, Zhiguang Guo, Jing |
Keywords: | DRNTU::Engineering::Electrical and electronic engineering Human Activity Recognition Deep Long Short-term Memory (LSTM) Network |
Issue Date: | 2018 | Source: | Chen, Z., Zhang, L., Cao, Z., & Guo, J. (2018). Distilling the Knowledge From Handcrafted Features for Human Activity Recognition. IEEE Transactions on Industrial Informatics, 14(10), 4334-4342. doi:10.1109/TII.2018.2789925 | Series/Report no.: | IEEE Transactions on Industrial Informatics | Abstract: | Human activity recognition is a core problem in intelligent automation systems due to its far-reaching applications including ubiquitous computing, health-care services, and smart living. Due to the nonintrusive property of smartphones, smartphone sensors are widely used for the identification of human activities. However, unlike applications in vision or data mining domain, feature embedding from deep neural networks performs much worse in terms of recognition accuracy than properly designed handcrafted features. In this paper, we posit that feature embedding from deep neural networks may convey complementary information and propose a novel knowledge distilling strategy to improve its performance. More specifically, an efficient shallow network, i.e., single-layer feedforward neural network (SLFN), with handcrafted features is utilized to assist a deep long short-term memory (LSTM) network. On the one hand, the deep LSTM network is able to learn features from raw sensory data to encode temporal dependencies. On the other hand, the deep LSTM network can also learn from SLFN to mimic how it generalizes. Experimental results demonstrate the superiority of the proposed method in terms of recognition accuracy against several state-of-the-art methods in the literature. | URI: | https://hdl.handle.net/10356/86019 http://hdl.handle.net/10220/48267 |
ISSN: | 1551-3203 | DOI: | 10.1109/TII.2018.2789925 | Rights: | © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TII.2018.2789925. | Fulltext Permission: | open | Fulltext Availability: | With Fulltext |
Appears in Collections: | EEE Journal Articles |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Distilling the Knowledge from Handcrafted Features for Human Activity Recognition.pdf | 1 MB | Adobe PDF | ![]() View/Open |
SCOPUSTM
Citations
10
28
Updated on Mar 10, 2021
PublonsTM
Citations
10
16
Updated on Mar 3, 2021
Page view(s)
208
Updated on Jul 2, 2022
Download(s) 5
479
Updated on Jul 2, 2022
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.