@inproceedings{ecf68e7949ab419d92f457ea7964acf6,
title = "Noise Reduction Caused by External Events in Wireless Sensor Network",
abstract = "Reliable communication always is an essential critical and challenging task in wireless sensor networks (WSNs). Despite this, WSNs models are prone to disrupting the normal working state because most WSN models are deployed in unattended hostile environments. To ensure secure data processing in a WSNs, many techniques have been proposed to protect data privacy when data are transferred from sensors to base stations. This article focuses on reducing noise, which occurs due to external events, such as harsh weather conditions. We reconstruct the data, which is affected by noise, by using a convolutional autoencoder network. The performance was evaluated in terms of error, and it was proven to be competitive.",
keywords = "CNN autoencoder, data reconstruction, noise reduction, weather effect, Wireless sensor network",
author = "Lai, \{Trinh Thuc\} and Jaehyuk Cho and Myungsik Yoo",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 37th International Conference on Information Networking, ICOIN 2023 ; Conference date: 11-01-2023 Through 14-01-2023",
year = "2023",
doi = "10.1109/ICOIN56518.2023.10049027",
language = "English",
series = "International Conference on Information Networking",
publisher = "IEEE Computer Society",
pages = "541--544",
booktitle = "37th International Conference on Information Networking, ICOIN 2023",
}