Home // AICT 2019, The Fifteenth Advanced International Conference on Telecommunications // View article

Interference Classification in a Factory Environment Based on Semi-supervised Deep Learning

Authors:
Su Yi
Hao Wang
Wenqian Xue
Leifei Wang

Keywords: Interference classification; Semi-supervised deep learning; RSSI sampling

Abstract:
The steadily growing use of license-free frequency bands requires reliable coexistence management and therefore proper wireless interference identification. This paper provides a realtime interference source classification method based on semi-supervised deep learning. It uses Received Signal Strength Indicator (RSSI) samples collected by an 802.15.4-based wireless sensor for formulating training data as well as online test data in a factory environment. To address the issue of laborious process on labeling the training data, a Fast Fourier Transform (FFT)-based algorithm is used to help labeling the sample data. We have trained a deep neural network with two hidden convolutional layers using raw RSSI samples as inputs. The whole realtime management system with the classifier is implemented on IEEE 802.15.4 System on Chip (SoC) and Linux-based system.

Pages: 39 to 45

Copyright: Copyright (c) IARIA, 2019

Publication date: July 28, 2019

Published in: conference

ISSN: 2308-4030

ISBN: 978-1-61208-727-6

Location: Nice, France

Dates: from July 28, 2019 to August 2, 2019