Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Push-up Tracking through Smartphone Sensors
KTH, School of Engineering Sciences (SCI).
KTH, School of Engineering Sciences (SCI).
2016 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Fitness tracking using machine learning algorithms is a new and widely unex-plored field. In most reports on fitness tracking, multiple accelerometers and other sensors are attached to the subject preforming exercises. This approach is not suitable for everyday usage. The last decade have seen a growing trend to- wards using smartphones for everyday applications. This offers a new possibility of collecting data for fitness tracking.This report investigates to what extent accelerometer and gyroscope data from a smartphone attached to an arm can be used to detect and separate push-ups from other workout exercises. A complete workout performed by two subjects have been recorded and analysed. A window based pre-processing technique was applied to extract features of the workout data. Support vector machines (SVM) and multi layer perceptrons (MLP) have been used to classify the data based on the feature extraction.Dips was the exercise easiest confused as push-ups. When a sample containing push-ups and dips was tested by a two layer perceptron trained on a variety of exercises not including dips, more false positives than true positives was acquired.A total of 87.5% correct classifications was obtained when the training data consisted of an entire workout by the first subject and the test data consisted of the same workout by the second subject. In the opposite case a total of 95.6% correct classifications were acquired.The results of this research support the idea that one smartphone attatched to the upper arm of a subject is sufficient to perform the distinction of push-ups and non push-ups.

Place, publisher, year, edition, pages
2016. , p. 23
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-201035OAI: oai:DiVA.org:kth-201035DiVA, id: diva2:1072495
Educational program
Master of Science in Engineering -Engineering Physics
Available from: 2017-02-08 Created: 2017-02-08Bibliographically approved

Open Access in DiVA

fulltext(729 kB)373 downloads
File information
File name FULLTEXT01.pdfFile size 729 kBChecksum SHA-512
3ef5c125f718f27a574c4862015ff3eaf02e60ccff4db63afcfa50f8a4e4db7ed589e353820ec2f7a96c797598624d4c7a35eab43e92e1a8169d53bb128d6202
Type fulltextMimetype application/pdf

By organisation
School of Engineering Sciences (SCI)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 373 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 121 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf