Incremental data fusion and decision making system and associated method
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06E-001/00
G06E-003/00
G06F-015/18
G06G-007/00
출원번호
US-0230932
(2005-09-19)
등록번호
US-7467116
(2008-12-16)
발명자
/ 주소
Wang,Yuan Fang
출원인 / 주소
Proximex Corporation
대리인 / 주소
Durant,Stephen C.
인용정보
피인용 횟수 :
3인용 특허 :
32
초록▼
A computer implemented adaptive ensemble classifier is provided which includes: a plurality of classifiers; a decision structure that maps respective classifier combinations to respective classification decision results; and a plurality of respective sets of weights associated with respective classi
A computer implemented adaptive ensemble classifier is provided which includes: a plurality of classifiers; a decision structure that maps respective classifier combinations to respective classification decision results; and a plurality of respective sets of weights associated with respective classifier combinations.
대표청구항▼
What is claimed is: 1. A computer implemented adaptive classification method comprising: receiving information from one or more first data sources; producing at least one first classification result using a processor programmed with one or more first classifiers and the information received from th
What is claimed is: 1. A computer implemented adaptive classification method comprising: receiving information from one or more first data sources; producing at least one first classification result using a processor programmed with one or more first classifiers and the information received from the one or more first data sources; producing a first decision using the processor programmed with the at least one first classification result and a first set of one or more respective weights respectively associated with the one or more first classifiers; selecting at least one second classifier if the first decision has a first prescribed value; receiving information from one or more second data sources; producing at least one second classification result using the processor programmed with one or more first classifiers and the at least one second classifier and the information received from the one or more first data sources and the information received from the at least one second data source; producing a second decision using the processor programmed with the at least one second classification result and a second set of one or more respective weights respectively associated with the one or more first classifiers and with the at least one second classifier; and outputting an indication of the second decision from the processor. 2. The method of claim 1 further including: terminating the classification process if the first decision has a second prescribed value. 3. The method of claim 1 further including: selecting at least one third classifier if the first decision has a second prescribed value; producing at least one third classification result using the one or more first classifiers and the at least one third classifier and the one or more first data sources and at least one third data source; and producing a third decision using the at least one second classification result and a third set of one or more respective weights respectively associated with the one or more first classifiers and with the at least one third classifier. 4. The method of claim 3 further including: selecting at least one fourth classifier if the third decision has a first prescribed value; producing at least one fourth classification result using the one or more first classifiers, the at least one third and the at least one fourth classifiers and the one or more first and third data sources and at least one fourth data source; producing a fourth decision using the at least one fourth classification result and a fourth set of one or more respective weights respectively associated with the one or more first classifiers and with the at least one third and the at least one fourth classifiers. 5. The method of claim 3 further including: terminating the classification process if the third decision has a second prescribed value. 6. A computer implemented adaptive ensemble object classifier comprising: a plurality of classifiers, each of the classifiers operable to input data from one or data sources concerning characteristics of an object to be classified, and to produce respective classification outputs; a plurality of sets of weights associated with the classification outputs to produce object classification decisions from weighted combinations of outputs from the classifiers; a decision structure that specifies, based on a given object classification decision of one of the weighted combinations of the classifiers, a further classifier combination for producing a further object classification decision, the further classifier combination involving an additional classifier, an additional data source, and a set of weights including weights additional to or different from the set of weights used to produce the given object classification decision; an interface operable for outputting the further object classification decision as a decision concerning classification of the object. 7. The adaptive ensemble classifier of claim 6, wherein the decision structure maps respective classifier combinations to respective sequences of classification decision results. 8. The adaptive ensemble classifier of claim 6, wherein the decision structure comprises a tree-structure. 9. The adaptive ensemble classifier of claim 6, wherein the decision structure comprises a tree-structure; and wherein each respective classifier combination is associated with one or more branches of the tree structure. 10. The adaptive ensemble classifier of claim 6, wherein the decision structure comprises a tree-structure; and wherein respective sets of weights are associated with respective branches of the tree structure. 11. An adaptive object classification method to produce a classification of an object, comprising: receiving first information concerning one or more characteristics of an object to be classified; producing at least one first classification result with one or more first classifiers using the first information; producing a first object classification decision using the at least one first classification result and a first set of weights respectively associated with the one or more first classifiers; and in response to the first object classification decision having a first prescribed value, selecting one or more second classifiers that use second information concerning one or more further characteristics of the object to be classified, producing at least one second object classification result using the one or more first classifiers, the first information, the one or more second classifiers, and the second information, producing a second object classification decision using the second object classification result and a second set of weights, differing from the first set of weights, the weights of the second set respectively associated with classifiers from both the one or more first classifiers and the one or more second classifiers, and outputting the second object classification decision as an indication of classification of the object. 12. An adaptive network intrusion detection method, comprising: receiving first input from a first set of network surveillance modules; producing at least one first classification result with one or more first classifiers using the first input; producing a first network intrusion decision using the at least one first classification result and a first set of weights respectively associated with the one or more first classifiers; and in response to the first network intrusion decision having a first prescribed value, selecting one or more second classifiers that use second input from a second set of network surveillance modules, producing at least one second classification result using the one or more first classifiers, the first information, the one or more second classifiers, and the second input, producing a second network intrusion decision using the second classification result and a second set of weights, differing from the first set of weights, the weights of the second set respectively associated with classifiers from both the one or more first classifiers and the one or more second classifiers, and outputting the second network intrusion decision as an indication of a detected network intrusion. 13. An adaptive method for approving extension of credit, comprising: receiving first input concerning first credit worthiness criteria of an entity or a person; producing at least one first credit classification result with one or more first classifiers using the first input; producing a first credit extension decision using the at least one first classification result and a first set of one or more weights respectively associated with the one or more first classifiers; and in response to the first credit approval decision having a first prescribed value, selecting one or more second classifiers that use second input concerning second credit worthiness criteria, producing at least one second classification result using the one or more first classifiers, the first information, the one or more second classifiers, and the second input, producing a second credit approval decision using the second classification result and a second set of weights, differing from the first set of weights, the weights of the second set respectively associated with classifiers from both the one or more first classifiers and the one or more second classifiers, and outputting an indication of the second credit approval decision as an indication of whether to extend credit to the entity or the person.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (32)
MacFaden,Michael R.; Calato,Paul, Adaptive classification of network traffic.
Eger, Horst; Haagensen, Annett; Koohmaraie, Mohammed; Shackelford, Steven D.; Wheeler, Tommy L., Image analysis systems for grading of meat, predicting quality of meat and/or predicting meat yield of an animal carcass.
Haagensen, Peter; Annett Haagensen,; Eger, Horst; Koohmaraie, Mohammed; Shackelford, Steven D.; Wheeler, Tommy L., Image analysis systems for grading of meat, predicting quality of meat and/or predicting meat yield of an animal carcass.
Glier Michael T. (Chepachet RI) Nunez Linda I. Mensinger (North Kingstown RI) Scofield Christopher L. (Providence RI), Method and apparatus for adaptive classification.
Gallo Girolamo,ITX, Method for speeding up the convergence of the back-propagation algorithm applied to realize the learning process in a neural network of the multilayer perceptron type.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.