東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Infant Breath Sound Classification a...

Jiang, Chao.

Linked to FindBook

Google Book

Amazon

博客來

Infant Breath Sound Classification and Recognition.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Infant Breath Sound Classification and Recognition./
Author:	Jiang, Chao.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
Description:	59 p.
Notes:	Source: Masters Abstracts International, Volume: 57-04.
Contained By:	Masters Abstracts International57-04(E).
Subject:	Electrical engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10639856
ISBN:	9780355628654

Infant Breath Sound Classification and Recognition.
Jiang, Chao.

Infant Breath Sound Classification and Recognition. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 59 p.

Source: Masters Abstracts International, Volume: 57-04.

Thesis (M.S.)--Northern Illinois University, 2017.

It is well known that infants' breath sounds can indicate their different healthy conditions. It is possible for experts to distinguish infants' breath sounds through training and experience. These different breath sounds have different features. In this thesis we modify signal recognition techniques which are widely used for speech signal processing to process breath sound signal. Then we find out the relationship between breath sounds and some common diseases. Different breath sound are detected by Short Time Energy (STE) method. Then four feature extraction methods which include Linear Predictive Coding (LPC), Linear Predictive Cepstral Coefficients (LPCC), Mel Frequency Cepstral Coefficients (MFCC) and Time-Varying LPC are used to extract the features of those breath sounds. Infant breath sound recognition is processed by three most popular signal classification methods: Nearest Neighbor (NN), Hidden Markov Model (HMM), and Artificial Neural Network (ANN). The simulation and experiment results show that the proposed recognition algorithm offer a feasible solution for classifying infant breath sound in order to help with the diagnose and monitor/screen infant healthy condition.

ISBN: 9780355628654Subjects--Topical Terms:

649834
Electrical engineering.

Infant Breath Sound Classification and Recognition.
LDR:02128nmm a2200301 4500 001 2165091
005 20181129115239.5
008 190424s2017 ||||||||||||||||| ||eng d
020 $a 9780355628654
035 $a (MiAaPQ)AAI10639856
035 $a (MiAaPQ)niu:13045
035 $a AAI10639856
040 $a MiAaPQ $c MiAaPQ
100 1 $a Jiang, Chao. $3 3344261
245 1 0 $a Infant Breath Sound Classification and Recognition.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 59 p.
500 $a Source: Masters Abstracts International, Volume: 57-04.
500 $a Includes supplementary digital materials.
500 $a Adviser: Lichuan Liu.
502 $a Thesis (M.S.)--Northern Illinois University, 2017.
520 $a It is well known that infants' breath sounds can indicate their different healthy conditions. It is possible for experts to distinguish infants' breath sounds through training and experience. These different breath sounds have different features. In this thesis we modify signal recognition techniques which are widely used for speech signal processing to process breath sound signal. Then we find out the relationship between breath sounds and some common diseases. Different breath sound are detected by Short Time Energy (STE) method. Then four feature extraction methods which include Linear Predictive Coding (LPC), Linear Predictive Cepstral Coefficients (LPCC), Mel Frequency Cepstral Coefficients (MFCC) and Time-Varying LPC are used to extract the features of those breath sounds. Infant breath sound recognition is processed by three most popular signal classification methods: Nearest Neighbor (NN), Hidden Markov Model (HMM), and Artificial Neural Network (ANN). The simulation and experiment results show that the proposed recognition algorithm offer a feasible solution for classifying infant breath sound in order to help with the diagnose and monitor/screen infant healthy condition.
590 $a School code: 0162.
650 4 $a Electrical engineering. $3 649834
690 $a 0544
710 2 $a Northern Illinois University. $b Electrical Engineering. $3 1030613
773 0 $t Masters Abstracts International $g 57-04(E).
790 $a 0162
791 $a M.S.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10639856