國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Automated crater detection using mac...

Cohen, Joseph Paul.

Automated crater detection using machine learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Automated crater detection using machine learning.
作者:	Cohen, Joseph Paul.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, 2016
面頁冊數:	72 p.
附註:	Source: Dissertation Abstracts International, Volume: 77-11(E), Section: B.
附註:	Includes supplementary digital materials.
附註:	Adviser: Wei Ding.
Contained By:	Dissertation Abstracts International77-11B(E).
標題:	Computer science.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10118515
ISBN:	9781339798455

Automated crater detection using machine learning.
Cohen, Joseph Paul.

Automated crater detection using machine learning. - Ann Arbor : ProQuest Dissertations & Theses, 2016 - 72 p.

Source: Dissertation Abstracts International, Volume: 77-11(E), Section: B.

Thesis (Ph.D.)--University of Massachusetts Boston, 2016.

Craters are among the most studied geomorphic features in the Solar System because they yield important information about the past and present geological processes and provide information about the relative ages of observed geologic formations. This work focuses on improving the features extracted from satellite imagery in order to more accurately detect craters. The first focus is on improving the accuracy of methods based on semi-automatic Haar image features by only considering subsets of the features. Using feature selection methods for black-box optimization such as genetic algorithms and randomized variable elimination we are able to achieve better performance. The second focus was to learn the optimal filters and features based on training examples and replace the semi-automatic Haar features with full-automatic convolutional filters. For this a Convolutional Neural Network (CNN) called CraterCNN is designed which outperforms all existing methods and achieves up to 90% on the standard crater benchmark dataset. Then the GoogLeNet inception architecture is used to further improve the benchmark and achieve up to 93% F1-Score. In order to decrease the computational cost of CNN models to make global Martian analysis possible a convolutional feature selection method called RandomOut is proposed. This method identifies convolutional filters which have been abandoned by the network by using the convolutional gradient norm and reinitializes them during training. RandomOut method enables CNNs to increase their accuracy to that of a network containing more filters but without the computational cost of actually adding more filters. This dissertation showcases significant progress in the field of automated crater detection and provides methods that can be applied to many other areas of automated planetary science.

ISBN: 9781339798455Subjects--Topical Terms:

199325
Computer science.

Automated crater detection using machine learning.
LDR:02806nmm a2200313 4500 001 502068
005 20170619070722.5
008 170818s2016 ||||||||||||||||| ||eng d
020 $a 9781339798455
035 $a (MiAaPQ)AAI10118515
035 $a AAI10118515
040 $a MiAaPQ $c MiAaPQ
100 1 $a Cohen, Joseph Paul. $3 766044
245 1 0 $a Automated crater detection using machine learning.
260 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2016
300 $a 72 p.
500 $a Source: Dissertation Abstracts International, Volume: 77-11(E), Section: B.
500 $a Includes supplementary digital materials.
500 $a Adviser: Wei Ding.
502 $a Thesis (Ph.D.)--University of Massachusetts Boston, 2016.
520 $a Craters are among the most studied geomorphic features in the Solar System because they yield important information about the past and present geological processes and provide information about the relative ages of observed geologic formations. This work focuses on improving the features extracted from satellite imagery in order to more accurately detect craters. The first focus is on improving the accuracy of methods based on semi-automatic Haar image features by only considering subsets of the features. Using feature selection methods for black-box optimization such as genetic algorithms and randomized variable elimination we are able to achieve better performance. The second focus was to learn the optimal filters and features based on training examples and replace the semi-automatic Haar features with full-automatic convolutional filters. For this a Convolutional Neural Network (CNN) called CraterCNN is designed which outperforms all existing methods and achieves up to 90% on the standard crater benchmark dataset. Then the GoogLeNet inception architecture is used to further improve the benchmark and achieve up to 93% F1-Score. In order to decrease the computational cost of CNN models to make global Martian analysis possible a convolutional feature selection method called RandomOut is proposed. This method identifies convolutional filters which have been abandoned by the network by using the convolutional gradient norm and reinitializes them during training. RandomOut method enables CNNs to increase their accuracy to that of a network containing more filters but without the computational cost of actually adding more filters. This dissertation showcases significant progress in the field of automated crater detection and provides methods that can be applied to many other areas of automated planetary science.
590 $a School code: 1074.
650 4 $a Computer science. $3 199325
650 4 $a Artificial intelligence. $3 194058
650 4 $a Computer engineering. $3 212944
690 $a 0984
690 $a 0800
690 $a 0464
710 2 $a University of Massachusetts Boston. $b Computer Science. $3 766045
773 0 $t Dissertation Abstracts International $g 77-11B(E).
790 $a 1074
791 $a Ph.D.
792 $a 2016
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10118515