R
Reid B. Porter
Researcher at Los Alamos National Laboratory
Publications - 66
Citations - 2821
Reid B. Porter is an academic researcher from Los Alamos National Laboratory. The author has contributed to research in topics: Image processing & Feature extraction. The author has an hindex of 18, co-authored 66 publications receiving 2570 citations. Previous affiliations of Reid B. Porter include Queensland University of Technology & University of Cambridge.
Papers
More filters
Proceedings Article
Knowledge-based probabilistic logic learning
TL;DR: The empirical evidence proves that human advice can effectively accelerate learning in noisy structured domains where so far humans have been merely used as labelers or as designers of initial structure of the model.
Proceedings ArticleDOI
Geospatial image mining for nuclear proliferation detection: Challenges and new opportunities
Ranga Raju Vatsavai,Budhendra L. Bhaduri,Anil Cheriyadat,Lloyd F. Arrowood,Eddie A Bright,Shaun S. Gleason,Carl F. Diegert,Aggelos K. Katsaggelos,Thrasos Pappas,Reid B. Porter,James S. Bollinger,Barry Chen,Ryan E. Hohimer +12 more
TL;DR: The current understanding of geospatial image mining techniques is described and key gaps are enumerated and future research needs in the context of nuclear proliferation are identified.
Proceedings ArticleDOI
Feature extraction from multiple data sources using genetic programming
John J. Szymanski,Steven P. Brumby,Paul A. Pope,Damian Eads,Diana M. Esch-Mosher,M. Galassi,Neal R. Harvey,Hersey D.W. McCulloch,Simon Perkins,Reid B. Porter,James Theiler,Aaron Cody Young,Jeffrey J. Bloch,Nancy A. David +13 more
TL;DR: In this paper, the authors used genetic programming to perform feature extraction simultaneously from multispectral and digital elevation model (DEM) data, which is an important and long-standing problem in remote sensing.
Book ChapterDOI
Everything on the Chip: A Hardware-Based Self-Contained Spatially-Structured Genetic Algorithm for Signal Processing
TL;DR: A self-contained FPGA-based implementation of a spatially-structured evolutionary algorithm that provides significant speedup over conventional serial processing in three ways: eficient hardware-pipelined fitness evaluation of individuals, evaluation of an entire population of individuals in parallel, and elimination of slow off-chip communication.
Journal ArticleDOI
A new approach for quantifying morphological features of U3O8 for nuclear forensics using a deep learning model
Cuong Ly,Cuong Ly,Adam M. Olsen,Ian J. Schwerdt,Reid B. Porter,Kari Sentz,Luther W. McDonald,Tolga Tasdizen,Tolga Tasdizen +8 more
TL;DR: The deep learning model used in this study is a modified version of a well-known segmentation model in the computer vision community referred to as U-net, and was able to produce the segmentation results similar to manual segmentation Results obtained using MAMA with at least 85% accuracy in intersection over union metric.