A Multiobjective Observation Network Design Procedure and its Application in Hydrology and Mining

1984 ◽  
pp. 210-217
Author(s):  
Ferenc Szidarovszky
Keyword(s):  
Network Design ◽  
Design Procedure ◽  
Observation Network

scholarly journals Greenhouse gas observation network design for Africa

Tellus B ◽  
2020 ◽  
Vol 72 (1) ◽  
pp. 1-30
Author(s):  
Alecia Nickless ◽  
Robert J. Scholes ◽  
Alex Vermeulen ◽  
Johannes Beck ◽  
Ana López-Ballesteros ◽  
...  
Keyword(s):  
Network Design ◽  
Greenhouse Gas ◽  
Observation Network

Illinois ground-water observation network; a preliminary planning document for network design

1984 ◽  
Author(s):  
L.R. Frost ◽  
Michael O'Hearn ◽  
J.P. Gibb ◽  
M.G. Sherrill
Keyword(s):  
Network Design ◽  
Ground Water ◽  
Observation Network ◽  
Preliminary Planning

A bus network design procedure with elastic demand for large urban areas

2012 ◽  
Vol 4 (1) ◽  
pp. 57-76 ◽  
Author(s):  
Ernesto Cipriani ◽  
Stefano Gori ◽  
Marco Petrelli
Keyword(s):  
Network Design ◽  
Urban Areas ◽  
Design Procedure ◽  
Elastic Demand ◽  
Bus Network

scholarly journals AUTOMATED AND LIGHTWEIGHT NETWORK DESIGN VIA RANDOM SEARCH FOR REMOTE SENSING IMAGE SCENE CLASSIFICATION

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 1217-1224
Author(s):  
J. Li ◽  
W. Diao ◽  
X. Sun ◽  
Y. Feng ◽  
W. Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Network Design ◽  
Random Search ◽  
Design Procedure ◽  
Semantic Segmentation ◽  
Remote Sensing Image ◽  
Labor Cost ◽  
Scene Classification ◽  
Convolutional Network ◽  
Segmentation Task

Abstract. With the development of deep learning, remote sensing image scene classification technology has been greatly improved. However, current deep networks used for scene classification usually introduce ingenious extra modules to fit the characteristics of remote sensing images. It causes a high labor cost and brings more parameters, which makes the network more complicated and poses new intractable problems. In this paper, we rethink this popular “add module” pattern and propose a more lightweight model, called ProbDenseNet (PDN). PDN is obtained via a random search strategy in Neural Architecture Search (NAS) which is an automated network design manner. In our method, all topological connections are assigned importance degrees which subject to a uniform distribution. And we set a regulator to adjust the sparsity of the network. By this way, the design procedure is more automated and the network structure becomes more lightweight. Experimental results on AID benchmark demonstrate that the proposed PDN model can achieve competitive performance even with much fewer parameters. And we also find that excessive connections do not always improve the network’s performance while they can drag down the network’s behavior as well. Furthermore, we conduct experiments on Vaihingen dataset with classical Fully Convolutional Network (FCN) framework. Quantitative and qualitative results both indicate that the features learned by PDN can also transfer in semantic segmentation task.

Observation network design for selecting locations for water supply wells

1994 ◽  
Vol 5 (2) ◽  
pp. 91-110 ◽  
Author(s):  
Geza Pesti ◽  
William E. Kelly ◽  
Istvan Bogardi
Keyword(s):  
Water Supply ◽  
Network Design ◽  
Observation Network
Sign in / Sign up

Export Citation Format

Share Document