Presentation 2013/3/4
Topological Feature Extraction on Rambling Activities using Knot Theory
Masakatsu OHTA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recent advances in positioning technologies, such as global positioning systems, have accelerated trajectory analyses for space planning. A method for investigating rambling activities (multi-stop and multi-purpose trips) of moving objects is proposed. The goal is to construct common metrics used in various environments for characterizing the trajectory followed by rambling objects. Mathematical knot theory is introduced to examine the topological relation between intersections in each trajectory. The trajectories in an environment are represented in a vector space consisting of primitive knots. A primitive knot is universal for all environments and thus it is possible to compare the features of rambling activities across environments. An experiment using real-world taxi trajectories confirmed that our method effectively classifies rambling activities according to daytime, nighttime, and a special event.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) rambling activities / trajectory / knot theory / topology
Paper # AI2012-49
Date of Issue

Conference Information
Committee AI
Conference Date 2013/3/4(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Topological Feature Extraction on Rambling Activities using Knot Theory
Sub Title (in English)
Keyword(1) rambling activities
Keyword(2) trajectory
Keyword(3) knot theory
Keyword(4) topology
1st Author's Name Masakatsu OHTA
1st Author's Affiliation NTT Network Innovation Laboratories, NTT Corporation()
Date 2013/3/4
Paper # AI2012-49
Volume (vol) vol.112
Number (no) 477
Page pp.pp.-
#Pages 6
Date of Issue