東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Deep Neural Network Architectures fo...

Liu, Xiaoyu.

FindBook

Google Book

Amazon

博客來

Deep Neural Network Architectures for Modulation Classification.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep Neural Network Architectures for Modulation Classification./
作者:	Liu, Xiaoyu.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
面頁冊數:	62 p.
附註:	Source: Masters Abstracts International, Volume: 79-12.
Contained By:	Masters Abstracts International79-12.
標題:	Computer Engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10793200
ISBN:	9780438012257

Deep Neural Network Architectures for Modulation Classification.
Liu, Xiaoyu.

Deep Neural Network Architectures for Modulation Classification. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 62 p.

Source: Masters Abstracts International, Volume: 79-12.

Thesis (M.S.E.C.E.)--Purdue University, 2018.

This item must not be sold to any third party vendors.

This thesis investigates the value of employing deep learning for the task of wireless signal modulation recognition. Recently in deep learning research on AMC, a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections in a real wireless channel, and uses 10 different modulation types. Further, a CNN architecture was developed and shown to deliver performance that exceeds that of expert-based approaches. Here, we follow the framework of O'shea [1] and find deep neural network architectures that deliver higher accuracy than the state of the art. We tested the architecture of O'shea [1] and found it to achieve an accuracy of approximately 75% of correctly recognizing the modulation type. We first tune the CNN architecture and find a design with four convolutional layers and two dense layers that gives an accuracy of approximately 83.8% at high SNR. We then develop architectures based on the recently introduced ideas of Residual Networks (ResNet) and Densely Connected Network (DenseNet) to achieve high SNR accuracies of approximately 83% and 86.6%, respectively. We also introduce a CLDNN to achieve an accuracy of approximately 88.5% at high SNR. To improve the classification accuracy of QAM, we calculate the high order cumulants of QAM16 and QAM64 as the expert feature and improve the total accuracy to approximately 90%. Finally, by preprocessing the input and send them into a LSTM model, we improve all classification success rates to 100% except the WBFM which is 46%. The average modulation classification accuracy got a improvement of roughly 22% in this thesis.

ISBN: 9780438012257Subjects--Topical Terms:

1567821
Computer Engineering.

Deep Neural Network Architectures for Modulation Classification.
LDR:02642nmm a2200313 4500 001 2265238
005 20200514111936.5
008 220629s2018 ||||||||||||||||| ||eng d
020 $a 9780438012257
035 $a (MiAaPQ)AAI10793200
035 $a (MiAaPQ)purdue:22599
035 $a AAI10793200
040 $a MiAaPQ $c MiAaPQ
100 1 $a Liu, Xiaoyu. $3 3185560
245 1 0 $a Deep Neural Network Architectures for Modulation Classification.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 62 p.
500 $a Source: Masters Abstracts International, Volume: 79-12.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Gamal, Aly El.
502 $a Thesis (M.S.E.C.E.)--Purdue University, 2018.
506 $a This item must not be sold to any third party vendors.
520 $a This thesis investigates the value of employing deep learning for the task of wireless signal modulation recognition. Recently in deep learning research on AMC, a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections in a real wireless channel, and uses 10 different modulation types. Further, a CNN architecture was developed and shown to deliver performance that exceeds that of expert-based approaches. Here, we follow the framework of O'shea [1] and find deep neural network architectures that deliver higher accuracy than the state of the art. We tested the architecture of O'shea [1] and found it to achieve an accuracy of approximately 75% of correctly recognizing the modulation type. We first tune the CNN architecture and find a design with four convolutional layers and two dense layers that gives an accuracy of approximately 83.8% at high SNR. We then develop architectures based on the recently introduced ideas of Residual Networks (ResNet) and Densely Connected Network (DenseNet) to achieve high SNR accuracies of approximately 83% and 86.6%, respectively. We also introduce a CLDNN to achieve an accuracy of approximately 88.5% at high SNR. To improve the classification accuracy of QAM, we calculate the high order cumulants of QAM16 and QAM64 as the expert feature and improve the total accuracy to approximately 90%. Finally, by preprocessing the input and send them into a LSTM model, we improve all classification success rates to 100% except the WBFM which is 46%. The average modulation classification accuracy got a improvement of roughly 22% in this thesis.
590 $a School code: 0183.
650 4 $a Computer Engineering. $3 1567821
690 $a 0464
710 2 $a Purdue University. $b Electrical and Computer Engineering. $3 1018497
773 0 $t Masters Abstracts International $g 79-12.
790 $a 0183
791 $a M.S.E.C.E.
792 $a 2018
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10793200