Discover unknown causes from inferred and visualized Co-occurring events

Y Ohsawa, M Yachida - New Generation Computing, 2000 - Springer
Y Ohsawa, M Yachida
New Generation Computing, 2000Springer
It is hard to have knowledge including all events which may have caused observed events.
This makes it difficult to infer significant causes of observed events. However, unexpected
relations detected between known events by a computer suggest unknown events to
humans, being combined with the vast human knowledge acquired by rich experience. This
paper presents a method to have a computer express “unknown” hidden causes, ie not
included in the given knowledge. The inference method of the computer, for inferring known …
Abstract
It is hard to have knowledge including all events which may have caused observed events. This makes it difficult to infer significant causes of observed events. However, unexpected relations detected between known events by a computer suggest unknown events to humans, being combined with the vast human knowledge acquired by rich experience. This paper presents a method to have a computer express “unknown” hidden causes, i.e. not included in the given knowledge. The inference method of the computer, for inferring known causes of observed time-series events, is Cost-based Cooperation of Multi-Abducers (CCMA) here aiming at detecting unexpectedly strong co-occurrences among known events. The detected relations are expressed to user, which makes significant unknown causal events easily understood. The empirical results encourages that the presented method helps in discovering significant unknown events.
Springer
Showing the best result for this search. See all results