COBBIT—A control procedure for COBWEB in the presence of concept drift View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

1993

AUTHORS

Fredrik Kilander , Carl Gustaf Jansson

ABSTRACT

This paper is concerned with the robustness of concept formation systems in the presence of concept drift. By concept drift is meant that the intension of a concept is not stable during the period of learning, a restriction which is otherwise often imposed. The work is based upon the architecture of Cobweb, an incremental, probabilistic conceptual clustering system. When incrementally and sequentially exposed to the extensions of a set of concepts, Cobweb retains all examples, disregards the age of a concept and may create different conceptual structures dependent on the order of examples. These three characteristics make Cobweb sensitive to the effects of concept drift. Six mechanisms that can detect concept drift and adjust the conceptual structure are proposed. A variant of one of these mechanisms: dynamic deletion of old examples, is implemented in a modified Cobweb system called Cobbit. The relative performance of Cobweb and Cobbit in the presence of concept drift is evaluated. In the experiment the error index, i.e. the average of the ability to predict each attribute is used as the major instrument. The experiment is performed in a synthetical domain and indicates that Cobbit regain performance faster after a discrete concept shift. More... »

PAGES

244-261

Book

TITLE

Machine Learning: ECML-93

ISBN

978-3-540-56602-1
978-3-540-47597-2

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/3-540-56602-3_140

DOI

http://dx.doi.org/10.1007/3-540-56602-3_140

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1019860602


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/2008/17", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology and Cognitive Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Department of Computer and Systems Sciences, Royal Institute of Technology and Stockholm University, Sweden", 
          "id": "http://www.grid.ac/institutes/grid.10548.38", 
          "name": [
            "Department of Computer and Systems Sciences, Royal Institute of Technology and Stockholm University, Sweden"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kilander", 
        "givenName": "Fredrik", 
        "id": "sg:person.012503334701.01", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012503334701.01"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer and Systems Sciences, Royal Institute of Technology and Stockholm University, Sweden", 
          "id": "http://www.grid.ac/institutes/grid.10548.38", 
          "name": [
            "Department of Computer and Systems Sciences, Royal Institute of Technology and Stockholm University, Sweden"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jansson", 
        "givenName": "Carl Gustaf", 
        "id": "sg:person.016263216701.04", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016263216701.04"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "1993", 
    "datePublishedReg": "1993-01-01", 
    "description": "This paper is concerned with the robustness of concept formation systems in the presence of concept drift. By concept drift is meant that the intension of a concept is not stable during the period of learning, a restriction which is otherwise often imposed. The work is based upon the architecture of Cobweb, an incremental, probabilistic conceptual clustering system. When incrementally and sequentially exposed to the extensions of a set of concepts, Cobweb retains all examples, disregards the age of a concept and may create different conceptual structures dependent on the order of examples. These three characteristics make Cobweb sensitive to the effects of concept drift. Six mechanisms that can detect concept drift and adjust the conceptual structure are proposed. A variant of one of these mechanisms: dynamic deletion of old examples, is implemented in a modified Cobweb system called Cobbit. The relative performance of Cobweb and Cobbit in the presence of concept drift is evaluated. In the experiment the error index, i.e. the average of the ability to predict each attribute is used as the major instrument. The experiment is performed in a synthetical domain and indicates that Cobbit regain performance faster after a discrete concept shift.", 
    "editor": [
      {
        "familyName": "Brazdil", 
        "givenName": "Pavel B.", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/3-540-56602-3_140", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-56602-1", 
        "978-3-540-47597-2"
      ], 
      "name": "Machine Learning: ECML-93", 
      "type": "Book"
    }, 
    "keywords": [
      "concept drift", 
      "concept formation system", 
      "conceptual clustering system", 
      "clustering system", 
      "set of concepts", 
      "order of examples", 
      "conceptual structure", 
      "dynamic deletion", 
      "concept shift", 
      "cobweb", 
      "error index", 
      "formation system", 
      "different conceptual structures", 
      "system", 
      "period of learning", 
      "architecture", 
      "relative performance", 
      "performance", 
      "robustness", 
      "concept", 
      "learning", 
      "example", 
      "control procedures", 
      "set", 
      "intension", 
      "experiments", 
      "attributes", 
      "extension", 
      "domain", 
      "work", 
      "order", 
      "drift", 
      "major instrument", 
      "ability", 
      "restriction", 
      "structure", 
      "variants", 
      "oldest examples", 
      "age", 
      "characteristics", 
      "mechanism", 
      "instrument", 
      "procedure", 
      "effect", 
      "shift", 
      "index", 
      "average", 
      "paper", 
      "period", 
      "presence", 
      "deletion", 
      "architecture of Cobweb", 
      "probabilistic conceptual clustering system", 
      "Cobweb system", 
      "Cobbit", 
      "synthetical domain", 
      "discrete concept shift"
    ], 
    "name": "COBBIT\u2014A control procedure for COBWEB in the presence of concept drift", 
    "pagination": "244-261", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1019860602"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/3-540-56602-3_140"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/3-540-56602-3_140", 
      "https://app.dimensions.ai/details/publication/pub.1019860602"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-12-01T20:00", 
    "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_218.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/3-540-56602-3_140"
  }
]
 

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.10.1007/3-540-56602-3_140'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/3-540-56602-3_140'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/3-540-56602-3_140'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/3-540-56602-3_140'


 

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

124 TRIPLES      23 PREDICATES      83 URIs      76 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/3-540-56602-3_140 schema:about anzsrc-for:17
2 anzsrc-for:1701
3 schema:author Ncbc9dd30f37c44e2993260df8ffcd6ba
4 schema:datePublished 1993
5 schema:datePublishedReg 1993-01-01
6 schema:description This paper is concerned with the robustness of concept formation systems in the presence of concept drift. By concept drift is meant that the intension of a concept is not stable during the period of learning, a restriction which is otherwise often imposed. The work is based upon the architecture of Cobweb, an incremental, probabilistic conceptual clustering system. When incrementally and sequentially exposed to the extensions of a set of concepts, Cobweb retains all examples, disregards the age of a concept and may create different conceptual structures dependent on the order of examples. These three characteristics make Cobweb sensitive to the effects of concept drift. Six mechanisms that can detect concept drift and adjust the conceptual structure are proposed. A variant of one of these mechanisms: dynamic deletion of old examples, is implemented in a modified Cobweb system called Cobbit. The relative performance of Cobweb and Cobbit in the presence of concept drift is evaluated. In the experiment the error index, i.e. the average of the ability to predict each attribute is used as the major instrument. The experiment is performed in a synthetical domain and indicates that Cobbit regain performance faster after a discrete concept shift.
7 schema:editor N7521fdd56d334c24b35272e101af46bf
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf N05200b996e294abdacb1bf3a3884d3b5
12 schema:keywords Cobbit
13 Cobweb system
14 ability
15 age
16 architecture
17 architecture of Cobweb
18 attributes
19 average
20 characteristics
21 clustering system
22 cobweb
23 concept
24 concept drift
25 concept formation system
26 concept shift
27 conceptual clustering system
28 conceptual structure
29 control procedures
30 deletion
31 different conceptual structures
32 discrete concept shift
33 domain
34 drift
35 dynamic deletion
36 effect
37 error index
38 example
39 experiments
40 extension
41 formation system
42 index
43 instrument
44 intension
45 learning
46 major instrument
47 mechanism
48 oldest examples
49 order
50 order of examples
51 paper
52 performance
53 period
54 period of learning
55 presence
56 probabilistic conceptual clustering system
57 procedure
58 relative performance
59 restriction
60 robustness
61 set
62 set of concepts
63 shift
64 structure
65 synthetical domain
66 system
67 variants
68 work
69 schema:name COBBIT—A control procedure for COBWEB in the presence of concept drift
70 schema:pagination 244-261
71 schema:productId N7c3cb559e1354a5cbff59a54903f36b8
72 Nf606f48a63324ac5acf7e07212de41c7
73 schema:publisher Ndd12ebce44b7475a9888115dd2dc51fb
74 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019860602
75 https://doi.org/10.1007/3-540-56602-3_140
76 schema:sdDatePublished 2021-12-01T20:00
77 schema:sdLicense https://scigraph.springernature.com/explorer/license/
78 schema:sdPublisher N28cae35a3773476dbc74598207ddda40
79 schema:url https://doi.org/10.1007/3-540-56602-3_140
80 sgo:license sg:explorer/license/
81 sgo:sdDataset chapters
82 rdf:type schema:Chapter
83 N05200b996e294abdacb1bf3a3884d3b5 schema:isbn 978-3-540-47597-2
84 978-3-540-56602-1
85 schema:name Machine Learning: ECML-93
86 rdf:type schema:Book
87 N28cae35a3773476dbc74598207ddda40 schema:name Springer Nature - SN SciGraph project
88 rdf:type schema:Organization
89 N5438ffc9ca2b4f2c90df8094acaf6e7f rdf:first sg:person.016263216701.04
90 rdf:rest rdf:nil
91 N7521fdd56d334c24b35272e101af46bf rdf:first Nb321525895a64360a2a85ae40573912d
92 rdf:rest rdf:nil
93 N7c3cb559e1354a5cbff59a54903f36b8 schema:name dimensions_id
94 schema:value pub.1019860602
95 rdf:type schema:PropertyValue
96 Nb321525895a64360a2a85ae40573912d schema:familyName Brazdil
97 schema:givenName Pavel B.
98 rdf:type schema:Person
99 Ncbc9dd30f37c44e2993260df8ffcd6ba rdf:first sg:person.012503334701.01
100 rdf:rest N5438ffc9ca2b4f2c90df8094acaf6e7f
101 Ndd12ebce44b7475a9888115dd2dc51fb schema:name Springer Nature
102 rdf:type schema:Organisation
103 Nf606f48a63324ac5acf7e07212de41c7 schema:name doi
104 schema:value 10.1007/3-540-56602-3_140
105 rdf:type schema:PropertyValue
106 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
107 schema:name Psychology and Cognitive Sciences
108 rdf:type schema:DefinedTerm
109 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
110 schema:name Psychology
111 rdf:type schema:DefinedTerm
112 sg:person.012503334701.01 schema:affiliation grid-institutes:grid.10548.38
113 schema:familyName Kilander
114 schema:givenName Fredrik
115 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012503334701.01
116 rdf:type schema:Person
117 sg:person.016263216701.04 schema:affiliation grid-institutes:grid.10548.38
118 schema:familyName Jansson
119 schema:givenName Carl Gustaf
120 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016263216701.04
121 rdf:type schema:Person
122 grid-institutes:grid.10548.38 schema:alternateName Department of Computer and Systems Sciences, Royal Institute of Technology and Stockholm University, Sweden
123 schema:name Department of Computer and Systems Sciences, Royal Institute of Technology and Stockholm University, Sweden
124 rdf:type schema:Organization
 




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


...