Human–Computer Interactive Annealing for Discovering Invisible Dark Events
Maeno, Y.
Ohsawa, Y.
Graduate Sch. of Syst. Manage., Univ. of Tsukuba, Tokyo;
This paper appears in: Industrial Electronics, IEEE Transactions on
Publication Date: April 2007
Volume: 54,
Issue: 2
On page(s): 1184-1192
ISSN: 0278-0046
INSPEC Accession Number: 9400468
Digital Object Identifier: 10.1109/TIE.2007.891661
Current Version Published: 2007-03-26
Abstract
Experts of chance discovery have recognized a new class of problems where the previous methods fail to visualize a latent structure behind observation. There are invisible events that play an important role in the dynamics of visible events. An invisible leader in a communication network is a typical example. Such an event is named a dark event. A novel technique has been proposed to understand a dark event and to extend the process of chance discovery. This paper presents a new method named "human-computer interactive annealing" for revealing latent structures along with the algorithm for discovering dark events. Demonstration using test data generated from a scale-free network shows that the precision regarding the algorithm ranges from 80% to 90%. An experiment on discovering an invisible leader under an online collective decision-making circumstance is successful
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
