Title :
Classification by attribute evaluation
Author_Institution :
US Army Res. Lab., Aberdeen Proving Ground, MD, USA
Abstract :
We consider a classification of objects by combining classification estimates that are derived from attributes of each object. These estimates are modelled as fuzzy sets and are combined with the help of a decision function into an output fuzzy set that represents the overall assessment of the object. A final linguistic classification is obtained by comparing the output of the decision function with target classes. Possible applications of the described classification procedure include target recognition from approximate sensor inputs, triage procedures and diagnostics in medical praxis, risk assessments, foreign document classification, and other problems where classification requires a combination of uncertain judgements from heterogeneous sources
Keywords :
fuzzy set theory; pattern classification; classification by attribute evaluation; classification estimates; decision function; foreign document classification; fuzzy sets; linguistic classification; medical diagnostics; object classification; risk assessment; sensor inputs; target recognition; triage procedures; uncertain judgements; Additives; Electronic mail; Fuzzy sets; Keyword search; Laboratories; Medical diagnostic imaging; Risk management; Sensor phenomena and characterization; State estimation; Target recognition;
Conference_Titel :
Fuzzy Information Processing Society, 2000. NAFIPS. 19th International Conference of the North American
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-6274-8
DOI :
10.1109/NAFIPS.2000.877402