PUBLICATION DATE

2015-12-04

TITLE

Combining domain knowledge and machine learning for robust fall detection

ISSUE

7

VOLUME

66

ISSN (print)

0020-580X

ISSN (electronic)

1476-9352

ABSTRACT

This paper presents a method for combining domain knowledge and machine learning (CDKML) for classifier generation and online adaptation. The method exploits advantages in domain knowledge and machine learning as complementary information sources. Whereas machine learning may discover patterns in interest domains that are too subtle for humans to detect, domain knowledge may contain information on a domain not present in the available domain dataset. CDKML has three steps. First, prior domain knowledge is enriched with relevant patterns obtained by machine learning to create an initial classifier. Second, genetic algorithms refine the classifier. Third, the classifier is adapted online on the basis of user feedback using the Markov decision process. CDKML was applied in fall detection. Tests showed that the classifiers developed by CDKML have better performance than machine‐learning classifiers generated on a training dataset that does not adequately represent all real‐life cases of the learned concept. The accuracy of the initial classifier was 10 percentage points higher than the best machine‐learning classifier and the refinement added 3 percentage points. The online adaptation improved the accuracy of the refined classifier by an additional 15 percentage points.

How to use: Click on a object to move its position. Double click to open its homepage. Right click to preview its contents.

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


25 TRIPLES      23 PREDICATES      25 URIs      15 LITERALS

Subject Predicate Object
1 articles:5197e35d3f6ad8be8aee5785bbf7c33d sg:abstract This paper presents a method for combining domain knowledge and machine learning (CDKML) for classifier generation and online adaptation. The method exploits advantages in domain knowledge and machine learning as complementary information sources. Whereas machine learning may discover patterns in interest domains that are too subtle for humans to detect, domain knowledge may contain information on a domain not present in the available domain dataset. CDKML has three steps. First, prior domain knowledge is enriched with relevant patterns obtained by machine learning to create an initial classifier. Second, genetic algorithms refine the classifier. Third, the classifier is adapted online on the basis of user feedback using the Markov decision process. CDKML was applied in fall detection. Tests showed that the classifiers developed by CDKML have better performance than machine‐learning classifiers generated on a training dataset that does not adequately represent all real‐life cases of the learned concept. The accuracy of the initial classifier was 10 percentage points higher than the best machine‐learning classifier and the refinement added 3 percentage points. The online adaptation improved the accuracy of the refined classifier by an additional 15 percentage points.
2 sg:ddsIdJournalBrand iaor
3 sg:doi 10.1057/iaor.2015.74819
4 sg:doiLink http://dx.doi.org/10.1057/iaor.2015.74819
5 sg:hasArticleType article-types:research
6 sg:hasFieldOfResearchCode anzsrc-for:08
7 anzsrc-for:0801
8 sg:hasJournal journals:1587f0c23f6d790a0b249e0af78a213d
9 journals:d654b82ffa89697399434ee935ac5bbb
10 sg:hasJournalBrand journal-brands:11eaa1206191d0347361452c8e00709c
11 sg:issnElectronic 1476-9352
12 sg:issnPrint 0020-580X
13 sg:issue 7
14 sg:license http://scigraph.springernature.com/explorer/license/
15 sg:npgId iaor201522545
16 sg:pageEnd
17 sg:pageStart
18 sg:publicationDate 2015-12-04
19 sg:publicationYear 2015
20 sg:publicationYearMonth 2015-12
21 sg:scigraphId 5197e35d3f6ad8be8aee5785bbf7c33d
22 sg:title Combining domain knowledge and machine learning for robust fall detection
23 sg:volume 66
24 rdf:type sg:Article
25 rdfs:label Article: Combining domain knowledge and machine learning for robust fall detection
HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular JSON format for linked data.

curl -H 'Accept: application/ld+json' 'http://scigraph.springernature.com/things/articles/5197e35d3f6ad8be8aee5785bbf7c33d'

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

curl -H 'Accept: application/n-triples' 'http://scigraph.springernature.com/things/articles/5197e35d3f6ad8be8aee5785bbf7c33d'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'http://scigraph.springernature.com/things/articles/5197e35d3f6ad8be8aee5785bbf7c33d'

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

curl -H 'Accept: application/rdf+xml' 'http://scigraph.springernature.com/things/articles/5197e35d3f6ad8be8aee5785bbf7c33d'






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


...