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

Linked to FindBook

Google Book

Amazon

博客來

Optimizing Flight Control Sensors Through the Effective Classification of Emissions & Absorption Spectroscopy Data Using Denoising & Deep Learning Algorithms.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Optimizing Flight Control Sensors Through the Effective Classification of Emissions & Absorption Spectroscopy Data Using Denoising & Deep Learning Algorithms./
Author:	Hunt, Darrien.
Description:	1 online resource (92 pages)
Notes:	Source: Masters Abstracts International, Volume: 84-10.
Contained By:	Masters Abstracts International84-10.
Subject:	Computer science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30417519click for full text (PQDT)
ISBN:	9798379412296

Optimizing Flight Control Sensors Through the Effective Classification of Emissions & Absorption Spectroscopy Data Using Denoising & Deep Learning Algorithms.
Hunt, Darrien.

Optimizing Flight Control Sensors Through the Effective Classification of Emissions & Absorption Spectroscopy Data Using Denoising & Deep Learning Algorithms. - 1 online resource (92 pages)

Source: Masters Abstracts International, Volume: 84-10.

Thesis (M.S.)--Hampton University, 2023.

Includes bibliographical references

Denoising filters are used to remove various types of noise from images, signals, and time-series data for the purpose of preserving relevant data. One-dimensional signals benefit from denoising filters which enhance their quality by applying a numerical computation to segments of the signals. A variety of denoising filters exist, such as the median filter, moving average filter, Savitzky-Golay filter, and wavelet transform, which all provide a unique approach to signal-to-noise ratio improvement. This paper provides a direct comparative analysis of these filters' conceptual and practical applications determining which technique will produce the most effective results in signal denoising. Research was conducted using an experimental dataset based on dual-mode scramjet (DMSJ) emissions with the goal of improving engine efficiency at high speeds and preventing harmful events like "unstart."To evaluate the filters' effectiveness a comparison was conducted on the basis of the statistical parameters of Signal to Noise Ratio (SNR) and Mean Square Error (MSE). This showed the moving-average filter and the wavelet transform method served as the top performing. Further evaluation was conducted to distinguish between the steady states and transition states of our denoised signals for DMSJ engine improvement using machine learning classifiers. Wavelet transform and the median filter proved to be the most effective in measuring model accuracy and the classification rate of the various classes within our single-step transient data. Our CNN-LSTM hybrid model was also successful in performing classification for our multi-step transient data, resulting in high model accuracy and precision.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798379412296Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Denoising algorithmsIndex Terms--Genre/Form:

542853
Electronic books.

Optimizing Flight Control Sensors Through the Effective Classification of Emissions & Absorption Spectroscopy Data Using Denoising & Deep Learning Algorithms.
LDR:03121nmm a2200385K 4500 001 2362696
005 20231102122802.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798379412296
035 $a (MiAaPQ)AAI30417519
035 $a AAI30417519
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Hunt, Darrien. $3 3703436
245 1 0 $a Optimizing Flight Control Sensors Through the Effective Classification of Emissions & Absorption Spectroscopy Data Using Denoising & Deep Learning Algorithms.
264 0 $c 2023
300 $a 1 online resource (92 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 84-10.
500 $a Advisor: Walters-Willliams, Janett.
502 $a Thesis (M.S.)--Hampton University, 2023.
504 $a Includes bibliographical references
520 $a Denoising filters are used to remove various types of noise from images, signals, and time-series data for the purpose of preserving relevant data. One-dimensional signals benefit from denoising filters which enhance their quality by applying a numerical computation to segments of the signals. A variety of denoising filters exist, such as the median filter, moving average filter, Savitzky-Golay filter, and wavelet transform, which all provide a unique approach to signal-to-noise ratio improvement. This paper provides a direct comparative analysis of these filters' conceptual and practical applications determining which technique will produce the most effective results in signal denoising. Research was conducted using an experimental dataset based on dual-mode scramjet (DMSJ) emissions with the goal of improving engine efficiency at high speeds and preventing harmful events like "unstart."To evaluate the filters' effectiveness a comparison was conducted on the basis of the statistical parameters of Signal to Noise Ratio (SNR) and Mean Square Error (MSE). This showed the moving-average filter and the wavelet transform method served as the top performing. Further evaluation was conducted to distinguish between the steady states and transition states of our denoised signals for DMSJ engine improvement using machine learning classifiers. Wavelet transform and the median filter proved to be the most effective in measuring model accuracy and the classification rate of the various classes within our single-step transient data. Our CNN-LSTM hybrid model was also successful in performing classification for our multi-step transient data, resulting in high model accuracy and precision.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 523869
650 4 $a Remote sensing. $3 535394
653 $a Denoising algorithms
653 $a Dual scramjets
653 $a Hypersonic engine
653 $a Machine learning
653 $a Signal processing
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0984
690 $a 0799
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Hampton University. $b Computer Science. $3 2102351
773 0 $t Masters Abstracts International $g 84-10.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30417519 $z click for full text (PQDT)