IEICE TRANSACTIONS on Information
Multi-Channels LSTM Networks for Fence Activity Classification
Summary :
We propose a novel neural networks model based on LSTM which is used to solve the task of classifying inertial sensor data attached to a fence with the goal of detecting security relevant incidents. To evaluate it we deployed an experimental fence surveillance system. By comparing experimental data of different approaches we find out that the neural network outperforms the baseline approach.
- Publication
- IEICE TRANSACTIONS on Information Vol.E101-D No.8 pp.2173-2177
- Publication Date
- 2018/08/01
- Publicized
- 2018/04/23
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2018EDL8004
- Type of Manuscript
- LETTER
- Category
- Biocybernetics, Neurocomputing
Authors
Kelu HU
Chinese Academy of Sciences,University of Chinese Academy of Sciences
Chunlei ZHENG
Chinese Academy of Sciences
Wei HE
Chinese Academy of Sciences
Xinghe BAO
University of Chinese Academy of Sciences
Yingguan WANG
Chinese Academy of Sciences
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Kelu HU, Chunlei ZHENG, Wei HE, Xinghe BAO, Yingguan WANG, "Multi-Channels LSTM Networks for Fence Activity Classification" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 8, pp. 2173-2177, August 2018, doi: 10.1587/transinf.2018EDL8004.
Abstract: We propose a novel neural networks model based on LSTM which is used to solve the task of classifying inertial sensor data attached to a fence with the goal of detecting security relevant incidents. To evaluate it we deployed an experimental fence surveillance system. By comparing experimental data of different approaches we find out that the neural network outperforms the baseline approach.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8004/_p
Copy
@ARTICLE{e101-d_8_2173,
author={Kelu HU, Chunlei ZHENG, Wei HE, Xinghe BAO, Yingguan WANG, },
journal={IEICE TRANSACTIONS on Information},
title={Multi-Channels LSTM Networks for Fence Activity Classification},
year={2018},
volume={E101-D},
number={8},
pages={2173-2177},
abstract={We propose a novel neural networks model based on LSTM which is used to solve the task of classifying inertial sensor data attached to a fence with the goal of detecting security relevant incidents. To evaluate it we deployed an experimental fence surveillance system. By comparing experimental data of different approaches we find out that the neural network outperforms the baseline approach.},
keywords={},
doi={10.1587/transinf.2018EDL8004},
ISSN={1745-1361},
month={August},}
Copy
TY - JOUR
TI - Multi-Channels LSTM Networks for Fence Activity Classification
T2 - IEICE TRANSACTIONS on Information
SP - 2173
EP - 2177
AU - Kelu HU
AU - Chunlei ZHENG
AU - Wei HE
AU - Xinghe BAO
AU - Yingguan WANG
PY - 2018
DO - 10.1587/transinf.2018EDL8004
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2018
AB - We propose a novel neural networks model based on LSTM which is used to solve the task of classifying inertial sensor data attached to a fence with the goal of detecting security relevant incidents. To evaluate it we deployed an experimental fence surveillance system. By comparing experimental data of different approaches we find out that the neural network outperforms the baseline approach.
ER -
English
