Interaction with a mixed-initiative system for exploratory data analysis

被引：0

作者：

St Amant, R

Cohen, PR

机构：

[1] N Carolina State Univ, Dept Comp Sci, Raleigh, NC 27695 USA

[2] Univ Massachusetts, Dept Comp Sci, LGRC, Amherst, MA 01003 USA

来源：

KNOWLEDGE-BASED SYSTEMS | 1998年 / 10卷 / 05期

关键词：

artificial intelligence; planning; data exploration;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Exploratory data analysis (EDA) plays an increasingly important role in statistical analysis. EDA is difficult, however, even with the help of modern statistical software. We have developed an assistant for data exploration, based on Al planning techniques, that addresses some of the strategic shortcomings of conventional software. This paper describes the design and behavior of the system and discusses an experimental evaluation that demonstrates the effectiveness of our approach. (C) 1998 Elsevier Science B.V. All rights reserved.

引用

页码：265 / 273

页数：9

共 25 条

[11] HAND DJ, 1986, ARTIF INTELL, V1, P355
[12] HUBER PJ, 1986, FDN HUMAN COMPUTER C
[13] HUBER PJ, 1994, COMPUTATIONAL STAT
[14] PLANNING AS SEARCH - A QUANTITATIVE APPROACH
KORF, RE
[J]. ARTIFICIAL INTELLIGENCE, 1987, 33 (01) : 65 - 88
[15] DATA-ANALYSIS AS SEARCH
LUBINSKY, D
PREGIBON, D
[J]. JOURNAL OF ECONOMETRICS, 1988, 38 (1-2) : 247 - 268
[16] NIELSEN J, 1990, HYPERTEXT HYPERMEDIA
[17] NIEVERGELT J, 1987, READINGS HUMAN COMPU, P438
[18] OBRIEN CM, 1994, AI COMPUTING POWER, P53
[19] PREGIBON D, 1986, ARTIF INTELL, V1, P389
[20] PREGIBON D, 1991, INCORPORATING STAT E, P51

← 1 2 3 →