Rule Extraction from Random Forest: the RF+HC Methods View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2015-04-29

AUTHORS

Morteza Mashayekhi , Robin Gras

ABSTRACT

Random forest (RF) is a tree-based learning method, which exhibits a high ability to generalize on real data sets. Nevertheless, a possible limitation of RF is that it generates a forest consisting of many trees and rules, thus it is viewed as a black box model. In this paper, the RF+HC methods for rule extraction from RF are proposed. Once the RF is built, a hill climbing algorithm is used to search for a rule set such that it reduces the number of rules dramatically, which significantly improves comprehensibility of the underlying model built by RF. The proposed methods are evaluated on eighteen UCI and four microarray data sets. Our experimental results show that the proposed methods outperform one of the state-of-the-art methods in terms of scalability and comprehensibility while preserving the same level of accuracy. More... »

PAGES

223-237

Book

TITLE

Advances in Artificial Intelligence

ISBN

978-3-319-18355-8
978-3-319-18356-5

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-18356-5_20

DOI

http://dx.doi.org/10.1007/978-3-319-18356-5_20

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1039448237


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "School of Computer Science, University of Windsor, Windsor, ON, Canada", 
          "id": "http://www.grid.ac/institutes/grid.267455.7", 
          "name": [
            "School of Computer Science, University of Windsor, Windsor, ON, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Mashayekhi", 
        "givenName": "Morteza", 
        "id": "sg:person.07552175653.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07552175653.46"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Computer Science, University of Windsor, Windsor, ON, Canada", 
          "id": "http://www.grid.ac/institutes/grid.267455.7", 
          "name": [
            "School of Computer Science, University of Windsor, Windsor, ON, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Gras", 
        "givenName": "Robin", 
        "id": "sg:person.0712313416.43", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0712313416.43"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2015-04-29", 
    "datePublishedReg": "2015-04-29", 
    "description": "Random forest (RF) is a tree-based learning method, which exhibits a high ability to generalize on real data sets. Nevertheless, a possible limitation of RF is that it generates a forest consisting of many trees and rules, thus it is viewed as a black box model. In this paper, the RF+HC methods for rule extraction from RF are proposed. Once the RF is built, a hill climbing algorithm is used to search for a rule set such that it reduces the number of rules dramatically, which significantly improves comprehensibility of the underlying model built by RF. The proposed methods are evaluated on eighteen UCI and four microarray data sets. Our experimental results show that the proposed methods outperform one of the state-of-the-art methods in terms of scalability and comprehensibility while preserving the same level of accuracy.", 
    "editor": [
      {
        "familyName": "Barbosa", 
        "givenName": "Denilson", 
        "type": "Person"
      }, 
      {
        "familyName": "Milios", 
        "givenName": "Evangelos", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-18356-5_20", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-18355-8", 
        "978-3-319-18356-5"
      ], 
      "name": "Advances in Artificial Intelligence", 
      "type": "Book"
    }, 
    "keywords": [
      "random forest", 
      "terms of scalability", 
      "number of rules", 
      "data sets", 
      "real data sets", 
      "rule extraction", 
      "art methods", 
      "learning method", 
      "tree-based learning method", 
      "black box model", 
      "microarray data sets", 
      "experimental results", 
      "comprehensibility", 
      "rules", 
      "scalability", 
      "UCI", 
      "set", 
      "algorithm", 
      "extraction", 
      "method", 
      "accuracy", 
      "model", 
      "trees", 
      "possible limitations", 
      "same level", 
      "limitations", 
      "box model", 
      "terms", 
      "number", 
      "results", 
      "high ability", 
      "ability", 
      "state", 
      "forest", 
      "levels", 
      "Hill", 
      "paper"
    ], 
    "name": "Rule Extraction from Random Forest: the RF+HC Methods", 
    "pagination": "223-237", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1039448237"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-18356-5_20"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-18356-5_20", 
      "https://app.dimensions.ai/details/publication/pub.1039448237"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-12-01T20:01", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211201/entities/gbq_results/chapter/chapter_245.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-18356-5_20"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-18356-5_20'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-18356-5_20'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-18356-5_20'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-18356-5_20'


 

This table displays all metadata directly associated to this object as RDF triples.

109 TRIPLES      23 PREDICATES      62 URIs      55 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-18356-5_20 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N0e535eb3c87b4129b4c84bae5d0f9fa2
4 schema:datePublished 2015-04-29
5 schema:datePublishedReg 2015-04-29
6 schema:description Random forest (RF) is a tree-based learning method, which exhibits a high ability to generalize on real data sets. Nevertheless, a possible limitation of RF is that it generates a forest consisting of many trees and rules, thus it is viewed as a black box model. In this paper, the RF+HC methods for rule extraction from RF are proposed. Once the RF is built, a hill climbing algorithm is used to search for a rule set such that it reduces the number of rules dramatically, which significantly improves comprehensibility of the underlying model built by RF. The proposed methods are evaluated on eighteen UCI and four microarray data sets. Our experimental results show that the proposed methods outperform one of the state-of-the-art methods in terms of scalability and comprehensibility while preserving the same level of accuracy.
7 schema:editor N261988c0e84e4e648a262a4eb4847f40
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf Nf4c6524665d6440998cc5c12cc52897a
12 schema:keywords Hill
13 UCI
14 ability
15 accuracy
16 algorithm
17 art methods
18 black box model
19 box model
20 comprehensibility
21 data sets
22 experimental results
23 extraction
24 forest
25 high ability
26 learning method
27 levels
28 limitations
29 method
30 microarray data sets
31 model
32 number
33 number of rules
34 paper
35 possible limitations
36 random forest
37 real data sets
38 results
39 rule extraction
40 rules
41 same level
42 scalability
43 set
44 state
45 terms
46 terms of scalability
47 tree-based learning method
48 trees
49 schema:name Rule Extraction from Random Forest: the RF+HC Methods
50 schema:pagination 223-237
51 schema:productId N768c9b30a4d7444e8ae8252943c7b48a
52 N8ca3ec8fb38942e69a2f4ba2a3e566d1
53 schema:publisher N946a2925536e4bd89a5aec1d5e576a88
54 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039448237
55 https://doi.org/10.1007/978-3-319-18356-5_20
56 schema:sdDatePublished 2021-12-01T20:01
57 schema:sdLicense https://scigraph.springernature.com/explorer/license/
58 schema:sdPublisher N87088842dbe94a68a9e4fe20b28827e1
59 schema:url https://doi.org/10.1007/978-3-319-18356-5_20
60 sgo:license sg:explorer/license/
61 sgo:sdDataset chapters
62 rdf:type schema:Chapter
63 N0e535eb3c87b4129b4c84bae5d0f9fa2 rdf:first sg:person.07552175653.46
64 rdf:rest N63767f5c81174d8c89aac5d8a8509253
65 N261988c0e84e4e648a262a4eb4847f40 rdf:first Ne5751a412f304ba7ba535fd8b9ecab23
66 rdf:rest N8b01efa725ee43f8be95b187fbeac881
67 N2e9e401ff5e145cf8f57dc87989c5143 schema:familyName Milios
68 schema:givenName Evangelos
69 rdf:type schema:Person
70 N63767f5c81174d8c89aac5d8a8509253 rdf:first sg:person.0712313416.43
71 rdf:rest rdf:nil
72 N768c9b30a4d7444e8ae8252943c7b48a schema:name doi
73 schema:value 10.1007/978-3-319-18356-5_20
74 rdf:type schema:PropertyValue
75 N87088842dbe94a68a9e4fe20b28827e1 schema:name Springer Nature - SN SciGraph project
76 rdf:type schema:Organization
77 N8b01efa725ee43f8be95b187fbeac881 rdf:first N2e9e401ff5e145cf8f57dc87989c5143
78 rdf:rest rdf:nil
79 N8ca3ec8fb38942e69a2f4ba2a3e566d1 schema:name dimensions_id
80 schema:value pub.1039448237
81 rdf:type schema:PropertyValue
82 N946a2925536e4bd89a5aec1d5e576a88 schema:name Springer Nature
83 rdf:type schema:Organisation
84 Ne5751a412f304ba7ba535fd8b9ecab23 schema:familyName Barbosa
85 schema:givenName Denilson
86 rdf:type schema:Person
87 Nf4c6524665d6440998cc5c12cc52897a schema:isbn 978-3-319-18355-8
88 978-3-319-18356-5
89 schema:name Advances in Artificial Intelligence
90 rdf:type schema:Book
91 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
92 schema:name Information and Computing Sciences
93 rdf:type schema:DefinedTerm
94 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
95 schema:name Artificial Intelligence and Image Processing
96 rdf:type schema:DefinedTerm
97 sg:person.0712313416.43 schema:affiliation grid-institutes:grid.267455.7
98 schema:familyName Gras
99 schema:givenName Robin
100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0712313416.43
101 rdf:type schema:Person
102 sg:person.07552175653.46 schema:affiliation grid-institutes:grid.267455.7
103 schema:familyName Mashayekhi
104 schema:givenName Morteza
105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07552175653.46
106 rdf:type schema:Person
107 grid-institutes:grid.267455.7 schema:alternateName School of Computer Science, University of Windsor, Windsor, ON, Canada
108 schema:name School of Computer Science, University of Windsor, Windsor, ON, Canada
109 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...