-
Article
Identifying priority air pollution management areas during the burning season in Nan Province, Northern Thailand
In northern Thailand, biomass burning is a major source of high concentrations of particulate matter with a diameter < 10 μm (PM10) during the burning season (January to May), leading to health concerns related t...
-
Article
DropCircuit : A Modular Regularizer for Parallel Circuit Networks
How to design and train increasingly large neural network models is a topic that has been actively researched for several years. However, while there exists a large number of studies on training deeper and/or ...
-
Article
An Empirical Study on Improving the Speed and Generalization of Neural Networks Using a Parallel Circuit Approach
One of the common problems of neural networks, especially those with many layers, consists of their lengthy training time. We attempt to solve this problem at the algorithmic level, proposing a simple parallel...
-
Chapter
Monitoring Long-Term Disaster Recovery – Space and Ground Views
Remote sensing plays a crucial role in post-disaster and emergency responses. For years, it has been a key player in providing invaluable multi-temporal synoptic data for landuse and landcover change detection...
-
Chapter and Conference Paper
Improving Neural Network Generalization by Combining Parallel Circuits with Dropout
In an attempt to solve the lengthy training times of neural networks, we proposed Parallel Circuits (PCs), a biologically inspired architecture. Previous work has shown that this approach fails to maintain gen...
-
Chapter
Ushahidi and Sahana Eden Open-Source Platforms to Assist Disaster Relief: Geospatial Components and Capabilities
In responses to recent large-scale disaster events, huge amount of ground information have been collected in addition to the synoptic views from satellite images. Different platforms have been in place to faci...
-
Article
Building extraction from high-resolution satellite image for tsunami early damage estimation
This paper introduced a developed object-based extraction tool for delineating the building footprints from high-resolution satellite image. The foundation of the algorithm is a scale-space analysis based on l...
-
Chapter
Towards a Quick Damage Detection System Based on Grid Computing
This chapter develops a quick system prototype, which produces reasonably detailed information of damaged buildings and accommodates high spatial resolution data. Parallel processing based on is chosen to ...
