Multispectral and LiDAR data fusion for fuel type mapping using Support Vector Machine and decision rules

2011 ◽  
Vol 115 (6) ◽  
pp. 1369-1379 ◽  
Author(s):  
Mariano García ◽  
David Riaño ◽  
Emilio Chuvieco ◽  
Javier Salas ◽  
F. Mark Danson
Keyword(s):  
Support Vector Machine ◽  
Data Fusion ◽  
Decision Rules ◽  
Support Vector ◽  
Lidar Data ◽  
Fuel Type ◽  
Type Mapping

scholarly journals Roof Shape Classification from LiDAR and Satellite Image Data Fusion Using Supervised Learning

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3960 ◽  
Author(s):  
Jeremy Castagno ◽  
Ella Atkins
Keyword(s):  
Data Fusion ◽  
Satellite Image ◽  
Image Data ◽  
Unmanned Aircraft ◽  
Airborne Lidar ◽  
Support Vector ◽  
Lidar Data ◽  
Building Roof ◽  
Roof Structure ◽  
Roof Shape

Geographic information systems (GIS) provide accurate maps of terrain, roads, waterways, and building footprints and heights. Aircraft, particularly small unmanned aircraft systems (UAS), can exploit this and additional information such as building roof structure to improve navigation accuracy and safely perform contingency landings particularly in urban regions. However, building roof structure is not fully provided in maps. This paper proposes a method to automatically label building roof shape from publicly available GIS data. Satellite imagery and airborne LiDAR data are processed and manually labeled to create a diverse annotated roof image dataset for small to large urban cities. Multiple convolutional neural network (CNN) architectures are trained and tested, with the best performing networks providing a condensed feature set for support vector machine and decision tree classifiers. Satellite image and LiDAR data fusion is shown to provide greater classification accuracy than using either data type alone. Model confidence thresholds are adjusted leading to significant increases in models precision. Networks trained from roof data in Witten, Germany and Manhattan (New York City) are evaluated on independent data from these cities and Ann Arbor, Michigan.

Data fusion of several support-vector-machine breast-cancer diagnostic paradigms using a GRNN oracle

2004 ◽  
Author(s):  
Walker H. Land, Jr. ◽  
Lut Wong ◽  
Dan McKee ◽  
Timothy Masters ◽  
Frances Anderson ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Support Vector Machine ◽  
Data Fusion ◽  
Support Vector ◽  
Cancer Diagnostic

scholarly journals Optimasi Klasifikasi Jenis Hutan Menggunakan Deep Learning Berbasis Optimize Selection

2019 ◽  
Vol 6 (1) ◽  
pp. 100-106
Author(s):  
Rizki Tri Prasetio ◽  
Endang Ripandi
Keyword(s):  
Support Vector Machine ◽  
Deep Learning ◽  
Forest Type ◽  
Support Vector ◽  
Type Mapping

AbstrakHutan adalah paru-paru dunia, maka menjaga kelestarian hutan merupakan suatu keharusan. Menurut WWF (2015) bahwa lebih dari 170 hektar hutan di seluruh dunia akan menghilang secara pesat hingga tahun 2030 mendatang. Brian Johnson, Ryutaro Tateishi, dan Zhixiao Xie (2010) melakukan penelitian untuk mengklasifikasikan jenis populasi tumbuhan hutan pada hutan Ibraki, Jepang. Algoritma SVM (Support Vector Machine) dan MLP (Multy Layer Perceptron) diterapkan untuk mengklasifikasikan jenis populasi tumbuhan hutan di hutan Ibraki dengan hasil akurasi 85.9%. Hasil Penelitian Brian Johnson dkk, diberi nama Forest Type Mapping Datasets.  Hasil akurasi yang diperoleh dari penerapan algoritma SVM dan MLP masih belum mencapai hasil akurasi yang optimal dan masih mungkin untuk ditingkatkan. Untuk dapat meningkatkan hasil akurasi yang optimal terhadap klasifikasi jenis populasi tumbuhan hutan pada Forest Type Mapping Datasets, maka pada penelitian ini diusulkan untuk menerapkan algoritma optimasi fitur Optimize Selection pada algoritma Deep Learning. Hasil penelitian menunjukan bahwa metode yang diusulkan membuat peningkatan akurasi yang signifikan. Nilai akurasi klasifikasi pada jenis populasi tumbuhan hutan yang dihasilkan algoritma Deep Learning dengan optimasi fitur Optimize Selection berhasil meningkat menjadi  96.46%.

Sign in / Sign up

Export Citation Format

Share Document