PUBLICATION DATE

2017-09-26

AUTHORS

Faisal K. Shaikh, Mohsin Bilal, Muhammad Arif, Mudasser F. Wyne

TITLE

A revised framework of machine learning application for optimal activity recognition

ISSUE

N/A

VOLUME

N/A

ISSN (print)

1386-7857

ISSN (electronic)

1573-7543

ABSTRACT

Data science augments manual data understanding with machine learning for potential performance increase. In this paper, data science methodology is examined to enhance machine learning application in smartphone based automatic human activity recognition (HAR). Eventually, a modified feature engineering and a novel post-learning data engineering are proposed in the machine learning framework as the alternate of data understanding for an effective HAR. The proposed framework is examined on two different HAR data sets demonstrating a possibility of data-driven machine learning for near an optimal classification of activities. The proposed framework exhibited effectiveness and efficiency when compared with the existing methods. The modified feature engineering resulted in 42% fewer features required by support vector machine to yield 97.3% correct recognition of human physical activities. However, the addition of post-learning data engineering further improved the model to perform 99% accurate classification, which is an almost optimal performance.

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


31 TRIPLES      25 PREDICATES      32 URIs      16 LITERALS

Subject Predicate Object
1 articles:4fb71752db5788db86cf80ad2293878f sg:abstract Abstract Data science augments manual data understanding with machine learning for potential performance increase. In this paper, data science methodology is examined to enhance machine learning application in smartphone based automatic human activity recognition (HAR). Eventually, a modified feature engineering and a novel post-learning data engineering are proposed in the machine learning framework as the alternate of data understanding for an effective HAR. The proposed framework is examined on two different HAR data sets demonstrating a possibility of data-driven machine learning for near an optimal classification of activities. The proposed framework exhibited effectiveness and efficiency when compared with the existing methods. The modified feature engineering resulted in 42% fewer features required by support vector machine to yield 97.3% correct recognition of human physical activities. However, the addition of post-learning data engineering further improved the model to perform 99% accurate classification, which is an almost optimal performance.
2 sg:articleType OriginalPaper
3 sg:ddsId s10586-017-1212-x
4 sg:ddsIdJournalBrand 10586
5 sg:doi 10.1007/s10586-017-1212-x
6 sg:doiLink http://dx.doi.org/10.1007/s10586-017-1212-x
7 sg:hasContributingOrganization grid-institutes:grid.412104.2
8 grid-institutes:grid.444814.9
9 sg:hasContribution contributions:4e59f717c5e96dcf69432d67d56713d6
10 contributions:72f1d9f20df7f89c10aa9b5a0a2ffd13
11 contributions:8c3c271c8fb2f7127bdaac6a54ad833e
12 contributions:90cf932f6ce1e1f4e7ae2fc8f7dc2111
13 sg:hasFieldOfResearchCode anzsrc-for:08
14 anzsrc-for:0801
15 sg:hasJournal journals:2aa13a9eefabd4e92548ba682e312d92
16 journals:daf64f08b18fc5381b7f76623e51dcc6
17 sg:hasJournalBrand journal-brands:e9e36ebee3cbdfd04b78e3cb22a028da
18 sg:issnElectronic 1573-7543
19 sg:issnPrint 1386-7857
20 sg:language English
21 sg:license http://scigraph.springernature.com/explorer/license/
22 sg:pageEnd 17
23 sg:pageStart 1
24 sg:publicationDate 2017-09-26
25 sg:publicationYear 2017
26 sg:publicationYearMonth 2017-09
27 sg:scigraphId 4fb71752db5788db86cf80ad2293878f
28 sg:title A revised framework of machine learning application for optimal activity recognition
29 sg:webpage https://link.springer.com/10.1007/s10586-017-1212-x
30 rdf:type sg:Article
31 rdfs:label Article: A revised framework of machine learning application for optimal activity recognition
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/4fb71752db5788db86cf80ad2293878f'

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/4fb71752db5788db86cf80ad2293878f'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'http://scigraph.springernature.com/things/articles/4fb71752db5788db86cf80ad2293878f'

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

curl -H 'Accept: application/rdf+xml' 'http://scigraph.springernature.com/things/articles/4fb71752db5788db86cf80ad2293878f'






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


...