Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 40 of the 41 references it cites were found in a registry or an index.

Complex Human Activity Recognition Using Smartphone and Wrist-Worn Motion Sensors

Open access
Shoaib, Muhammad, Bosch, Stephan, Incel, Ozlem, Scholten, Hans, Havinga, Paul · 2016 · Sensors

Abstract

The position of on-body motion sensors plays an important role in human activity recognition. Most often, mobile phone sensors at the trouser pocket or an equivalent position are used for this purpose. However, this position is not suitable for recognizing activities that involve hand gestures, such as smoking, eating, drinking coffee and giving a talk. To recognize such activities, wrist-worn motion sensors are used. However, these two positions are mainly used in isolation. To use richer context information, we evaluate three motion sensors (accelerometer, gyroscope and linear acceleration sensor) at both wrist and pocket positions. Using three classifiers, we show that the combination of these two positions outperforms the wrist position alone, mainly at smaller segmentation windows. Another problem is that less-repetitive activities, such as smoking, eating, giving a talk and drinking coffee, cannot be recognized easily at smaller segmentation windows unlike repetitive activities, like walking, jogging and biking. For this purpose, we evaluate the effect of seven window sizes (2-30 s) on thirteen activities and show how increasing window size affects these various activities in different ways. We also propose various optimizations to further improve the recognition of these activities. For reproducibility, we make our dataset publicly available.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s16040426

Cites

40 of 40 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 F-measure difference with respect to the reference (WAG) for all activities using Naive Bayes classifier: (a) 2-s window; (b) 5-s window. The reference (WAG) F-measure is shown in the boxes.
Figure 1 F-measure difference with respect to the reference (WAG) for all activities using Naive Bayes classifier: (a) 2-s window; (b) 5-s window. The reference (WAG) F-measure is shown in the boxes.CC BY · PubMed Central
Figure 2 The confusion matrices of Naive Bayes classifier at a 5-s window size for; (a) WA (accelerometer at wrist); (b) WAG (accelerometer + gyroscope at wrist); (c) WPAG (accelerometer + gyroscope from both wrist and pocket). The major confused classes are shown in red.
Figure 2 The confusion matrices of Naive Bayes classifier at a 5-s window size for; (a) WA (accelerometer at wrist); (b) WAG (accelerometer + gyroscope at wrist); (c) WPAG (accelerometer + gyroscope from both wrist and pocket). The major confused classes are shown in red.CC BY · PubMed Central
Figure 3 F-measure difference with respect to the reference (WLG) for all activities using Naive Bayes classifier: (a) 2-s window; (b) 5-s window. The reference (WLG) F-measure is shown in the boxes.
Figure 3 F-measure difference with respect to the reference (WLG) for all activities using Naive Bayes classifier: (a) 2-s window; (b) 5-s window. The reference (WLG) F-measure is shown in the boxes.CC BY · PubMed Central
Figure 4 The effect of increasing window size on various activities using Naive Bayes classifier: (a) WA; (b) WG; (c) WAG; (d) WLG; (e) WPA; (f) WPAG.
Figure 4 The effect of increasing window size on various activities using Naive Bayes classifier: (a) WA; (b) WG; (c) WAG; (d) WLG; (e) WPA; (f) WPAG.CC BY · PubMed Central
Figure 5 The effect of increasing window size for WAG using the Naive Bayes classifier at; (a) 2-s window; (b) 15-s window; (c) 30-s window. The major confused classes with each actual class are highlighted in red in these confusion matrices.
Figure 5 The effect of increasing window size for WAG using the Naive Bayes classifier at; (a) 2-s window; (b) 15-s window; (c) 30-s window. The major confused classes with each actual class are highlighted in red in these confusion matrices.CC BY · PubMed Central
Figure 6 F-measure of various activities with Naive Bayes using only mean and standard deviation (MS) vs. our extended feature set (EFS) at 30-s window. (a) MS vs. EPS in WL; (b) MS vs. EPS WLG.
Figure 6 F-measure of various activities with Naive Bayes using only mean and standard deviation (MS) vs. our extended feature set (EFS) at 30-s window. (a) MS vs. EPS in WL; (b) MS vs. EPS WLG.CC BY · PubMed Central
Figure A1 F-measure difference with respect to the reference (WAG) for all activities using KNN: (a) 2-s window; (b) 5-s window. The reference F-measure is shown in the boxes.
Figure A1 F-measure difference with respect to the reference (WAG) for all activities using KNN: (a) 2-s window; (b) 5-s window. The reference F-measure is shown in the boxes.CC BY · PubMed Central
Figure A2 F-measure difference with respect to the reference (WLG) for all activities using KNN: (a) 2-s window; (b) 5-s window. The reference F-measure is shown in the boxes.
Figure A2 F-measure difference with respect to the reference (WLG) for all activities using KNN: (a) 2-s window; (b) 5-s window. The reference F-measure is shown in the boxes.CC BY · PubMed Central
Figure A3 F-measure difference with respect to the reference (WAG) for all activities using decision tree: (a) 2-s window; (b) 5-s window. The reference F-measure is shown in the boxes.
Figure A3 F-measure difference with respect to the reference (WAG) for all activities using decision tree: (a) 2-s window; (b) 5-s window. The reference F-measure is shown in the boxes.CC BY · PubMed Central
Figure A4 F-measure difference with respect to the reference (WLG) for all activities using decision tree: (a) 2-s window; (b) 5-s window. The reference F-measure is shown in the boxes.
Figure A4 F-measure difference with respect to the reference (WLG) for all activities using decision tree: (a) 2-s window; (b) 5-s window. The reference F-measure is shown in the boxes.CC BY · PubMed Central
Figure A5 The effect of increasing window size on various activities using KNN. (a) WA; (b) WG; (c) WAG; (d) WLG; (e) WPA; (f) WPAG.
Figure A5 The effect of increasing window size on various activities using KNN. (a) WA; (b) WG; (c) WAG; (d) WLG; (e) WPA; (f) WPAG.CC BY · PubMed Central
Figure A6 The effect of increasing window size on various activities using decision tree. (a) WA; (b) WG; (c) WAG; (d) WLG; (e) WPA; (f) WPAG.
Figure A6 The effect of increasing window size on various activities using decision tree. (a) WA; (b) WG; (c) WAG; (d) WLG; (e) WPA; (f) WPAG.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 41 references

Research works printed but not linked: 2

  1. Bieber, G., Fernholz, N., and Gaerber, M. (2013). HCI International 2013-Posters’ Extended Abstracts, Springer.
  2. Frank, J., Mannor, S., and Precup, D. (2011). Machine Learning and Knowledge Discovery in Databases, Springer.

Cited by

See all 424

Metadata

Authors
Shoaib, M., Bosch, S., Incel, O., Scholten, H., & Havinga, P.
Affiliations
  • University of Twente (NL)
  • Department of Computer Engineering, Galatasaray University, Ortakoy, 34349 Istanbul, Turkey
Corresponding author
Shoaib, Muhammad
Venue
Sensors
Publisher
MDPI AG
Published
2016-03-24
Volume
16
Issue
4
Pages
426
ISSN
1424-8220 (ISSN-L)
OpenAlex
W2304267454
Cited by
423
References
41
Citations by year
2026: 28 · 2025: 24 · 2024: 34 · 2023: 42 · 2022: 48 · 2021: 62 · 2020: 58 · 2019: 52 · 2018: 37 · 2017: 29 · 2016: 9
FWCI
28.79
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • University of Twente Research Information (publishedVersion, cc-by)
  • University of Twente Research Information (submittedVersion, cc-by)
Funders
Galatasaray Üniversitesi (13.401.002)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Social Sciences › Transportation › Human Mobility and Location-Based Analysis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
Keywords
human activity recognition, smartphone sensors, accelerometer, gyroscope, sensor placement, hand gestures, smoking detection, multimodal sensor fusion, activity recognition dataset
MeSH terms
Smartphone, Activities of Daily Living, Humans, Movement, Pattern Recognition, Automated, Smoking, Wrist, Walking, Accelerometry

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Complex Human Activity Recognition Using Smartphone and Wrist-Worn Motion Sensors. https://app.cochat.ai/papers/10.3390/s16040426
The paper
Shoaib, M., Bosch, S., Incel, O., Scholten, H., & Havinga, P. (2016). Complex Human Activity Recognition Using Smartphone and Wrist-Worn Motion Sensors. Sensors. https://doi.org/10.3390/s16040426

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.