Modelling conditional probability distributions for periodic variables

Christopher M. Bishop, Ian T. Nabney

Research output: Contribution to journalArticle

Abstract

Most conventional techniques for estimating conditional probability densities are inappropriate for applications involving periodic variables. In this paper we introduce three related techniques for tackling such problems, and investigate their performance using synthetic data. We then apply these techniques to the problem of extracting the distribution of wind vector directions from radar scatterometer data gathered by a remote-sensing satellite.
Original languageEnglish
Pages (from-to)209-214
Number of pages6
JournalNeural Computation
Volume8
Issue number5
DOIs
Publication statusPublished - 1 Jul 1996
EventInternational Conference on Artificial Neural Networks - Paris
Duration: 1 Oct 1995 → …

Fingerprint

Radar
Direction compound
Conditional Probability
Modeling

Bibliographical note

@ 1996 Massachusetts Institute of Technology

Keywords

  • conditional probability densities
  • periodic variables
  • synthetic data
  • wind vector
  • radar scatterometer data
  • remote-sensing
  • satellite.

Cite this

Bishop, Christopher M. ; Nabney, Ian T. / Modelling conditional probability distributions for periodic variables. In: Neural Computation. 1996 ; Vol. 8, No. 5. pp. 209-214.
@article{f42e78e6f338479884856d63189e2425,
title = "Modelling conditional probability distributions for periodic variables",
abstract = "Most conventional techniques for estimating conditional probability densities are inappropriate for applications involving periodic variables. In this paper we introduce three related techniques for tackling such problems, and investigate their performance using synthetic data. We then apply these techniques to the problem of extracting the distribution of wind vector directions from radar scatterometer data gathered by a remote-sensing satellite.",
keywords = "conditional probability densities, periodic variables, synthetic data, wind vector, radar scatterometer data, remote-sensing, satellite.",
author = "Bishop, {Christopher M.} and Nabney, {Ian T.}",
note = "@ 1996 Massachusetts Institute of Technology",
year = "1996",
month = "7",
day = "1",
doi = "10.1162/neco.1996.8.5.1123",
language = "English",
volume = "8",
pages = "209--214",
journal = "Neural Computation",
issn = "0899-7667",
publisher = "MIT Press Journals",
number = "5",

}

Modelling conditional probability distributions for periodic variables. / Bishop, Christopher M.; Nabney, Ian T.

In: Neural Computation, Vol. 8, No. 5, 01.07.1996, p. 209-214.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Modelling conditional probability distributions for periodic variables

AU - Bishop, Christopher M.

AU - Nabney, Ian T.

N1 - @ 1996 Massachusetts Institute of Technology

PY - 1996/7/1

Y1 - 1996/7/1

N2 - Most conventional techniques for estimating conditional probability densities are inappropriate for applications involving periodic variables. In this paper we introduce three related techniques for tackling such problems, and investigate their performance using synthetic data. We then apply these techniques to the problem of extracting the distribution of wind vector directions from radar scatterometer data gathered by a remote-sensing satellite.

AB - Most conventional techniques for estimating conditional probability densities are inappropriate for applications involving periodic variables. In this paper we introduce three related techniques for tackling such problems, and investigate their performance using synthetic data. We then apply these techniques to the problem of extracting the distribution of wind vector directions from radar scatterometer data gathered by a remote-sensing satellite.

KW - conditional probability densities

KW - periodic variables

KW - synthetic data

KW - wind vector

KW - radar scatterometer data

KW - remote-sensing

KW - satellite.

U2 - 10.1162/neco.1996.8.5.1123

DO - 10.1162/neco.1996.8.5.1123

M3 - Article

VL - 8

SP - 209

EP - 214

JO - Neural Computation

JF - Neural Computation

SN - 0899-7667

IS - 5

ER -