Computer Vision and Bi-directional Neural Network for Extraction of Communications Signal from Noisy Spectrogram

Seksan Phonsri; Sankha Subhra Mukherjee; Mathini Sellathurai

doi:10.1109/CAMA.2015.7428185

Computer Vision and Bi-directional Neural Network for Extraction of Communications Signal from Noisy Spectrogram

Seksan Phonsri, Sankha Subhra Mukherjee, Mathini Sellathurai

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

Extraction of communication signals from noisy spectrograms is a challenging problem which has not been explored extensively from an intelligent signal processing and computer vision based perspective. In this paper we propose a novel technique of extracting the communications signal from a noisy spectrogram using a combination of fuzzy neighborhood thresholding based self organizing neural network and morphological operations. We show that about 98% detection is achieved at 5% false alarm of a particular scenario outperforming traditional energy detection.

Original language	English
Title of host publication	2015 IEEE Conference on Antenna Measurements & Applications (CAMA)
Publisher	IEEE
Number of pages	4
ISBN (Electronic)	9781467391498
DOIs	https://doi.org/10.1109/CAMA.2015.7428185
Publication status	Published - 10 Mar 2015
Event	IEEE Conference on Antenna Measurements 2015 - Chiang Mai, Thailand Duration: 30 Nov 2015 → 2 Dec 2015

Conference

Conference	IEEE Conference on Antenna Measurements 2015
Country	Thailand
City	Chiang Mai
Period	30/11/15 → 2/12/15

Keywords

Computer Vision
Spectrogram
Bi-directional Self-organizing Neural Networks
Fuzzy Hostility Index
Morphological Filtering
Blob Detection

Access to Document

10.1109/CAMA.2015.7428185

Cite this

@inproceedings{6e63e1e95cf14f7bbd28f9c9647658a5,

title = "Computer Vision and Bi-directional Neural Network for Extraction of Communications Signal from Noisy Spectrogram",

abstract = "Extraction of communication signals from noisy spectrograms is a challenging problem which has not been explored extensively from an intelligent signal processing and computer vision based perspective. In this paper we propose a novel technique of extracting the communications signal from a noisy spectrogram using a combination of fuzzy neighborhood thresholding based self organizing neural network and morphological operations. We show that about 98% detection is achieved at 5% false alarm of a particular scenario outperforming traditional energy detection.",

keywords = "Computer Vision, Spectrogram, Bi-directional Self-organizing Neural Networks, Fuzzy Hostility Index, Morphological Filtering, Blob Detection",

author = "Seksan Phonsri and Mukherjee, {Sankha Subhra} and Mathini Sellathurai",

year = "2015",

month = mar,

day = "10",

doi = "10.1109/CAMA.2015.7428185",

language = "English",

booktitle = "2015 IEEE Conference on Antenna Measurements & Applications (CAMA)",

publisher = "IEEE",

address = "United States",

note = "IEEE Conference on Antenna Measurements 2015 ; Conference date: 30-11-2015 Through 02-12-2015",

}

TY - GEN

T1 - Computer Vision and Bi-directional Neural Network for Extraction of Communications Signal from Noisy Spectrogram

AU - Phonsri, Seksan

AU - Mukherjee, Sankha Subhra

AU - Sellathurai, Mathini

PY - 2015/3/10

Y1 - 2015/3/10

N2 - Extraction of communication signals from noisy spectrograms is a challenging problem which has not been explored extensively from an intelligent signal processing and computer vision based perspective. In this paper we propose a novel technique of extracting the communications signal from a noisy spectrogram using a combination of fuzzy neighborhood thresholding based self organizing neural network and morphological operations. We show that about 98% detection is achieved at 5% false alarm of a particular scenario outperforming traditional energy detection.

AB - Extraction of communication signals from noisy spectrograms is a challenging problem which has not been explored extensively from an intelligent signal processing and computer vision based perspective. In this paper we propose a novel technique of extracting the communications signal from a noisy spectrogram using a combination of fuzzy neighborhood thresholding based self organizing neural network and morphological operations. We show that about 98% detection is achieved at 5% false alarm of a particular scenario outperforming traditional energy detection.

KW - Computer Vision

KW - Spectrogram

KW - Bi-directional Self-organizing Neural Networks

KW - Fuzzy Hostility Index

KW - Morphological Filtering

KW - Blob Detection

U2 - 10.1109/CAMA.2015.7428185

DO - 10.1109/CAMA.2015.7428185

M3 - Conference contribution

BT - 2015 IEEE Conference on Antenna Measurements & Applications (CAMA)

PB - IEEE

T2 - IEEE Conference on Antenna Measurements 2015

Y2 - 30 November 2015 through 2 December 2015

ER -