Detection of left-sided and right-sided hearing loss via fractional Fourier transform

Shuihua Wang; Ming Yang; Yin Zhang; Jianwu Li; Ling Zou; Siyuan Lu; Bin Liu; Jiquan Yang; Yudong Zhang

doi:10.3390/e18050194

Detection of left-sided and right-sided hearing loss via fractional Fourier transform

Shuihua Wang, Ming Yang, Yin Zhang, Jianwu Li, Ling Zou, Siyuan Lu, Bin Liu, Jiquan Yang, Yudong Zhang^*

^*Corresponding author for this work

School of Computer Science and Technology

Research output: Contribution to journal › Article › peer-review

45 Citations (Scopus)

Abstract

In order to detect hearing loss more efficiently and accurately, this study proposed a new method based on fractional Fourier transform (FRFT). Three-dimensional volumetric magnetic resonance images were obtained from 15 patients with left-sided hearing loss (LHL), 20 healthy controls (HC), and 14 patients with right-sided hearing loss (RHL). Twenty-five FRFT spectrums were reduced by principal component analysis with thresholds of 90%, 95%, and 98%, respectively. The classifier is the single-hidden-layer feed-forward neural network (SFN) trained by the Levenberg–Marquardt algorithm. The results showed that the accuracies of all three classes are higher than 95%. In all, our method is promising and may raise interest from other researchers.

Original language	English
Article number	194
Journal	Entropy
Volume	18
Issue number	5
DOIs	https://doi.org/10.3390/e18050194
Publication status	Published - May 2016

Keywords

Artificial neural network
Computer-aided diagnosis
Fractional Fourier transform
Hearing loss
Levenberg–Marquardt algorithm
Principal component analysis
Unified time-frequency domain

Access to Document

10.3390/e18050194

Cite this

@article{83d67578e60e4a5e8deb60c245f497ed,

title = "Detection of left-sided and right-sided hearing loss via fractional Fourier transform",

abstract = "In order to detect hearing loss more efficiently and accurately, this study proposed a new method based on fractional Fourier transform (FRFT). Three-dimensional volumetric magnetic resonance images were obtained from 15 patients with left-sided hearing loss (LHL), 20 healthy controls (HC), and 14 patients with right-sided hearing loss (RHL). Twenty-five FRFT spectrums were reduced by principal component analysis with thresholds of 90%, 95%, and 98%, respectively. The classifier is the single-hidden-layer feed-forward neural network (SFN) trained by the Levenberg–Marquardt algorithm. The results showed that the accuracies of all three classes are higher than 95%. In all, our method is promising and may raise interest from other researchers.",

keywords = "Artificial neural network, Computer-aided diagnosis, Fractional Fourier transform, Hearing loss, Levenberg–Marquardt algorithm, Principal component analysis, Unified time-frequency domain",

author = "Shuihua Wang and Ming Yang and Yin Zhang and Jianwu Li and Ling Zou and Siyuan Lu and Bin Liu and Jiquan Yang and Yudong Zhang",

note = "Publisher Copyright: {\textcopyright} 2016 by the authors.",

year = "2016",

month = may,

doi = "10.3390/e18050194",

language = "English",

volume = "18",

journal = "Entropy",

issn = "1099-4300",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "5",

}

TY - JOUR

T1 - Detection of left-sided and right-sided hearing loss via fractional Fourier transform

AU - Wang, Shuihua

AU - Yang, Ming

AU - Zhang, Yin

AU - Li, Jianwu

AU - Zou, Ling

AU - Lu, Siyuan

AU - Liu, Bin

AU - Yang, Jiquan

AU - Zhang, Yudong

PY - 2016/5

Y1 - 2016/5

N2 - In order to detect hearing loss more efficiently and accurately, this study proposed a new method based on fractional Fourier transform (FRFT). Three-dimensional volumetric magnetic resonance images were obtained from 15 patients with left-sided hearing loss (LHL), 20 healthy controls (HC), and 14 patients with right-sided hearing loss (RHL). Twenty-five FRFT spectrums were reduced by principal component analysis with thresholds of 90%, 95%, and 98%, respectively. The classifier is the single-hidden-layer feed-forward neural network (SFN) trained by the Levenberg–Marquardt algorithm. The results showed that the accuracies of all three classes are higher than 95%. In all, our method is promising and may raise interest from other researchers.

AB - In order to detect hearing loss more efficiently and accurately, this study proposed a new method based on fractional Fourier transform (FRFT). Three-dimensional volumetric magnetic resonance images were obtained from 15 patients with left-sided hearing loss (LHL), 20 healthy controls (HC), and 14 patients with right-sided hearing loss (RHL). Twenty-five FRFT spectrums were reduced by principal component analysis with thresholds of 90%, 95%, and 98%, respectively. The classifier is the single-hidden-layer feed-forward neural network (SFN) trained by the Levenberg–Marquardt algorithm. The results showed that the accuracies of all three classes are higher than 95%. In all, our method is promising and may raise interest from other researchers.

KW - Artificial neural network

KW - Computer-aided diagnosis

KW - Fractional Fourier transform

KW - Hearing loss

KW - Levenberg–Marquardt algorithm

KW - Principal component analysis

KW - Unified time-frequency domain

UR - http://www.scopus.com/inward/record.url?scp=85011093743&partnerID=8YFLogxK

U2 - 10.3390/e18050194

DO - 10.3390/e18050194

M3 - Article

AN - SCOPUS:85011093743

SN - 1099-4300

VL - 18

JO - Entropy

JF - Entropy

IS - 5

M1 - 194

ER -

Detection of left-sided and right-sided hearing loss via fractional Fourier transform

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this