PANTHER. Trajectory Analysis

Rintoul, Mark Daniel; Wilson, Andrew T.; Valicka, Christopher G.; Kegelmeyer, W. Philip; Shead, Timothy M.; Newton, Benjamin D.; Czuchlewski, Kristina Rodriguez

doi:10.2172/1221864

Title: PANTHER. Trajectory Analysis

Full Record
Other Related Research

Abstract

We want to organize a body of trajectories in order to identify, search for, classify and predict behavior among objects such as aircraft and ships. Existing compari- son functions such as the Fr'echet distance are computationally expensive and yield counterintuitive results in some cases. We propose an approach using feature vectors whose components represent succinctly the salient information in trajectories. These features incorporate basic information such as total distance traveled and distance be- tween start/stop points as well as geometric features related to the properties of the convex hull, trajectory curvature and general distance geometry. Additionally, these features can generally be mapped easily to behaviors of interest to humans that are searching large databases. Most of these geometric features are invariant under rigid transformation. We demonstrate the use of different subsets of these features to iden- tify trajectories similar to an exemplar, cluster a database of several hundred thousand trajectories, predict destination and apply unsupervised machine learning algorithms.

Authors:

Rintoul, Mark Daniel ^[1]; Wilson, Andrew T. ^[1]; Valicka, Christopher G. ^[1]; Kegelmeyer, W. Philip ^[1]; Shead, Timothy M. ^[1]; Newton, Benjamin D. ^[1]; Czuchlewski, Kristina Rodriguez ^[1]

Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Publication Date:: Tue Sep 01 00:00:00 EDT 2015

Research Org.:: Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Sandia National Lab. (SNL-CA), Livermore, CA (United States)

Sponsoring Org.:: USDOE National Nuclear Security Administration (NNSA)

OSTI Identifier:: 1221864

Report Number(s):: SAND2015-8120
604041

DOE Contract Number:: AC04-94AL85000

Resource Type:: Technical Report

Country of Publication:: United States

Language:: English

Citation Formats


                    Rintoul, Mark Daniel, Wilson, Andrew T., Valicka, Christopher G., Kegelmeyer, W. Philip, Shead, Timothy M., Newton, Benjamin D., and Czuchlewski, Kristina Rodriguez. PANTHER. Trajectory Analysis.  United States: N. p., 2015. 
        Web.  doi:10.2172/1221864.

Copy to clipboard


                    Rintoul, Mark Daniel, Wilson, Andrew T., Valicka, Christopher G., Kegelmeyer, W. Philip, Shead, Timothy M., Newton, Benjamin D., & Czuchlewski, Kristina Rodriguez. PANTHER. Trajectory Analysis.  United States.  https://doi.org/10.2172/1221864

Copy to clipboard


                    Rintoul, Mark Daniel, Wilson, Andrew T., Valicka, Christopher G., Kegelmeyer, W. Philip, Shead, Timothy M., Newton, Benjamin D., and Czuchlewski, Kristina Rodriguez. 2015.  
        "PANTHER. Trajectory Analysis".  United States.  https://doi.org/10.2172/1221864.  https://www.osti.gov/servlets/purl/1221864.

Copy to clipboard


                    
@article{osti_1221864,

  title        = {PANTHER. Trajectory Analysis},

  author       = {Rintoul, Mark Daniel and Wilson, Andrew T. and Valicka, Christopher G. and Kegelmeyer, W. Philip and Shead, Timothy M. and Newton, Benjamin D. and Czuchlewski, Kristina Rodriguez},

  abstractNote = {We want to organize a body of trajectories in order to identify, search for, classify and predict behavior among objects such as aircraft and ships. Existing compari- son functions such as the Fr'echet distance are computationally expensive and yield counterintuitive results in some cases. We propose an approach using feature vectors whose components represent succinctly the salient information in trajectories. These features incorporate basic information such as total distance traveled and distance be- tween start/stop points as well as geometric features related to the properties of the convex hull, trajectory curvature and general distance geometry. Additionally, these features can generally be mapped easily to behaviors of interest to humans that are searching large databases. Most of these geometric features are invariant under rigid transformation. We demonstrate the use of different subsets of these features to iden- tify trajectories similar to an exemplar, cluster a database of several hundred thousand trajectories, predict destination and apply unsupervised machine learning algorithms.},

  doi          = {10.2172/1221864},

  url          = {https://www.osti.gov/biblio/1221864},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {Tue Sep 01 00:00:00 EDT 2015},

  month        = {Tue Sep 01 00:00:00 EDT 2015}

}

Copy to clipboard

Technical Report:

View Technical Report (14.12 MB)

https://doi.org/10.2172/1221864

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Trajectory analysis via a geometric feature space approach

Journal Article Rintoul, Mark; Wilson, Andrew - Statistical Analysis and Data Mining

This study aimed to organize a body of trajectories in order to identify, search for and classify both common and uncommon behaviors among objects such as aircraft and ships. Existing comparison functions such as the Fréchet distance are computationally expensive and yield counterintuitive results in some cases. We propose an approach using feature vectors whose components represent succinctly the salient information in trajectories. These features incorporate basic information such as the total distance traveled and the distance between start/stop points as well as geometric features related to the properties of the convex hull, trajectory curvature and general distance geometry. Additionally,more »« less
Cited by 6
https://doi.org/10.1002/sam.11287

Full Text Available
Numerical and semiclassical analysis of some generalized Casimir pistons

Journal Article Schaden, M - Physical Review. A

The Casimir force due to a scalar field in a cylinder of radius r with a spherical cap of radius R>r is computed numerically in the world-line approach. A geometrical subtraction scheme gives the finite interaction energy that determines the Casimir force. The spectral function of convex domains is obtained from a probability measure on convex surfaces that is induced by the Wiener measure on Brownian bridges the convex surfaces are the hulls of. Due to reflection positivity, the vacuum force on the piston by a scalar field satisfying Dirichlet boundary conditions is attractive in these geometries, but the strengthmore »« less
https://doi.org/10.1103/PHYSREVA.79.052105
PANTHER. Pattern ANalytics To support High-performance Exploitation and Reasoning.

Technical Report Czuchlewski, Kristina; Hart, William

Sandia has approached the analysis of big datasets with an integrated methodology that uses computer science, image processing, and human factors to exploit critical patterns and relationships in large datasets despite the variety and rapidity of information. The work is part of a three-year LDRD Grand Challenge called PANTHER (Pattern ANalytics To support High-performance Exploitation and Reasoning). To maximize data analysis capability, Sandia pursued scientific advances across three key technical domains: (1) geospatial-temporal feature extraction via image segmentation and classification; (2) geospatial-temporal analysis capabilities tailored to identify and process new signatures more efficiently; and (3) domain- relevant models of humanmore »« less
https://doi.org/10.2172/1228822

Full Text Available
Optimizing training trajectories in variational autoencoders via latent Bayesian optimization approach^*

Journal Article Biswas, Arpan; Vasudevan, Rama; Ziatdinov, Maxim; ... - Machine Learning: Science and Technology

Unsupervised and semi-supervised ML methods such as variational autoencoders (VAE) have become widely adopted across multiple areas of physics, chemistry, and materials sciences due to their capability in disentangling representations and ability to find latent manifolds for classification and/or regression of complex experimental data. Like other ML problems, VAEs require hyperparameter tuning, e.g. balancing the Kullback–Leibler and reconstruction terms. However, the training process and resulting manifold topology and connectivity depend not only on hyperparameters, but also their evolution during training. Because of the inefficiency of exhaustive search in a high-dimensional hyperparameter space for the expensive-to-train models, here we have exploredmore »« less
https://doi.org/10.1088/2632-2153/acb316

Full Text Available
Computational investigation of half-Heusler compounds for spintronics applications

Journal Article Ma, Jianhua; Hegde, Vinay; Munira, Kamaram; ... - Physical Review B

We present first-principles density functional calculations of the electronic structure, magnetism, and structural stability of 378 XYZ half-Heusler compounds (with X= Cr, Mn, Fe, Co, Ni, Ru, Rh; Y=Ti, V, Cr, Mn, Fe, Ni; Z= Al, Ga, In, Si, Ge, Sn, P, As, Sb). We find that a “Slater-Pauling gap” in the density of states (i.e., a gap or pseudogap after nine states in the three atom primitive cell) in at least one spin channel is a common feature in half-Heusler compounds. We find that the presence of such a gap at the Fermi energy in one or both spinmore »« less
Cited by 97
https://doi.org/10.1103/PhysRevB.95.024411

Full Text Available

Similar Records