東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

The effect of adding domain knowledg...

Ambrosino, Richard.

Linked to FindBook

Google Book

Amazon

博客來

The effect of adding domain knowledge on the learning of rule-based models for decision-support.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	The effect of adding domain knowledge on the learning of rule-based models for decision-support./
Author:	Ambrosino, Richard.
Description:	374 p.
Notes:	Adviser: Bruce G. Buchanan.
Contained By:	Dissertation Abstracts International61-12B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9998572
ISBN:	0493068457

The effect of adding domain knowledge on the learning of rule-based models for decision-support.
Ambrosino, Richard.

The effect of adding domain knowledge on the learning of rule-based models for decision-support. - 374 p.

Adviser: Bruce G. Buchanan.

Thesis (Ph.D.)--University of Pittsburgh, 2000.

Historically, medical decision-support systems have either been <italic> engineered</italic> from knowledge acquired from domain experts, or learned from clinical databases using computer learning algorithms. The amount of expert domain knowledge used in building models can be considered as a continuous spectrum: at one end of this spectrum are models which are built almost exclusively from expert knowledge (e.g., QMR); at the other end, are models generated from clinical data by statistical or machine learning algorithms (e.g., the pre-operative cardiac risk-assessment scale of Goldman et al. [1977.]) Very little research has focused on combining these two approaches.

ISBN: 0493068457Subjects--Topical Terms:

626642
Computer Science.

The effect of adding domain knowledge on the learning of rule-based models for decision-support.
LDR:02694nam 2200325 a 45 001 936333
005 20110510
008 110510s2000 eng d
020 $a 0493068457
035 $a (UnM)AAI9998572
035 $a AAI9998572
040 $a UnM $c UnM
100 1 $a Ambrosino, Richard. $3 1260023
245 1 0 $a The effect of adding domain knowledge on the learning of rule-based models for decision-support.
300 $a 374 p.
500 $a Adviser: Bruce G. Buchanan.
500 $a Source: Dissertation Abstracts International, Volume: 61-12, Section: B, page: 6553.
502 $a Thesis (Ph.D.)--University of Pittsburgh, 2000.
520 $a Historically, medical decision-support systems have either been <italic> engineered</italic> from knowledge acquired from domain experts, or learned from clinical databases using computer learning algorithms. The amount of expert domain knowledge used in building models can be considered as a continuous spectrum: at one end of this spectrum are models which are built almost exclusively from expert knowledge (e.g., QMR); at the other end, are models generated from clinical data by statistical or machine learning algorithms (e.g., the pre-operative cardiac risk-assessment scale of Goldman et al. [1977.]) Very little research has focused on combining these two approaches.
520 $a This thesis completely describes a study designed to test the hypothesis that the learning of a decision-support model by a computer learning algorithm from clinical data can be improved by the addition of domain knowledge from practicing physicians. The domain of the experiment is community-acquired pneumonia. The overall design of the study presented in this thesis compares a computer learning algorithm given clinical data to one given clinical data plus domain knowledge added by physician subjects.
520 $a The results reported in this thesis show that the performance of the computer-generated models augmented with knowledge added by physician subjects were significantly better than the computer-generated models generated without added knowledge using a two-stage rule induction algorithm in the domain of community-acquired pneumonia. This result was highly significant and shows that the addition of domain knowledge may be beneficial to the learning of clinical decision-support models, especially in domains where data is limited.
590 $a School code: 0178.
650 4 $a Computer Science. $3 626642
650 4 $a Engineering, System Science. $3 1018128
650 4 $a Health Sciences, Medicine and Surgery. $3 1017756
650 4 $a Operations Research. $3 626629
690 $a 0564
690 $a 0790
690 $a 0796
690 $a 0984
710 2 0 $a University of Pittsburgh. $3 958527
773 0 $t Dissertation Abstracts International $g 61-12B.
790 $a 0178
790 1 0 $a Buchanan, Bruce G., $e advisor
791 $a Ph.D.
792 $a 2000
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9998572