CoChat

MBOSS: A Symbolic Representation of Human Activity Recognition Using Mobile Sensors

Open access
Montero Quispe, Kevin G., Sousa Lima, Wesllen, Macêdo Batista, Daniel, Souto, Eduardo · 2018 · Sensors

The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.

Abstract

Human activity recognition (HAR) through sensors embedded in smartphones has allowed for the development of systems that are capable of detecting and monitoring human behavior. However, such systems have been affected by the high consumption of computational resources (e.g., memory and processing) needed to effectively recognize activities. In addition, existing HAR systems are mostly based on supervised classification techniques, in which the feature extraction process is done manually, and depends on the knowledge of a specialist. To overcome these limitations, this paper proposes a new method for recognizing human activities based on symbolic representation algorithms. The method, called “Multivariate Bag-Of-SFA-Symbols” (MBOSS), aims to increase the efficiency of HAR systems and maintain accuracy levels similar to those of conventional systems based on time and frequency domain features. The experiments conducted on three public datasets showed that MBOSS performed the best in terms of accuracy, processing time, and memory consumption.

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/s18124354

Cites

30 of 30 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 SFA Transform: A time series T is estimated using Fourier Transform and quantized using MCB lookup table. The result is a SFA word “DAAC” of length 4 and alphabet of size 6 [14].
Figure 1 SFA Transform: A time series T is estimated using Fourier Transform and quantized using MCB lookup table. The result is a SFA word “DAAC” of length 4 and alphabet of size 6 [14].CC BY · PubMed Central
Figure 2 A set of time series is used to generate the bins and breakpoints in MCB. First, Fourier transform is applied and later is applied equi-depth binning for each i-th columns.
Figure 2 A set of time series is used to generate the bins and breakpoints in MCB. First, Fourier transform is applied and later is applied equi-depth binning for each i-th columns.CC BY · PubMed Central
Figure 3 Example of the BOSS model construction: (a) a normalized time series; (b) windowing process to extract subseries; (c) symbolic transformation of SFA with numerosity reduction; and (d) histogram construction based on the repetition frequency of the SFA words.
Figure 3 Example of the BOSS model construction: (a) a normalized time series; (b) windowing process to extract subseries; (c) symbolic transformation of SFA with numerosity reduction; and (d) histogram construction based on the repetition frequency of the SFA words.CC BY · PubMed Central
Figure 4 Data fusion at the features level: Example of concatenation of histograms (Feature Stacking).
Figure 4 Data fusion at the features level: Example of concatenation of histograms (Feature Stacking).CC BY · PubMed Central
Figure 5 MBOSS VS classifier based on the vector space model to classify human activities.
Figure 5 MBOSS VS classifier based on the vector space model to classify human activities.CC BY · PubMed Central
Figure 6 Accuracy results for all classifiers evaluated based on personalized model.
Figure 6 Accuracy results for all classifiers evaluated based on personalized model.CC BY · PubMed Central
Figure 7 Confusion matrices for (a) MBOSS and (b) KNN classifiers for the WISDM dataset.
Figure 7 Confusion matrices for (a) MBOSS and (b) KNN classifiers for the WISDM dataset.CC BY · PubMed Central
Figure 8 Accuracy results for all classifiers evaluated based on generalized model.
Figure 8 Accuracy results for all classifiers evaluated based on generalized model.CC BY · PubMed Central
Figure 9 Confusion matrices for (a) MBOSS and (b) SVM classifiers for the UCI HAR dataset.
Figure 9 Confusion matrices for (a) MBOSS and (b) SVM classifiers for the UCI HAR dataset.CC BY · PubMed Central
Figure 10 Classification results of (a) the personalized model and (b) the generalized model.
Figure 10 Classification results of (a) the personalized model and (b) the generalized model.CC BY · PubMed Central
Figure 11 Comparison of computation time for extraction features.
Figure 11 Comparison of computation time for extraction features.CC BY · PubMed Central
Figure 12 Comparative computational time for the training and classification of human activities.
Figure 12 Comparative computational time for the training and classification of human activities.CC BY · PubMed Central
Figure 13 Comparison of the cost of memory space required for the processing of time series.
Figure 13 Comparison of the cost of memory space required for the processing of time series.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 30 references

Research works printed but not linked: 6

  1. Cook, D.J., and Krishnan, N.C. (2015). Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data, John Wiley & Sons. · doi:10.1002/9781119010258
  2. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (arXiv, 2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv.
  3. Schäfer, P., and Högqvist, M. (2012, January 27–30). SFA: A symbolic fourier approximation and index for similarity search in high dimensional datasets. Proceedings of the 15th International Conference on Extending Database Technology, Berlin, Germany.
  4. Phillips, C.L., Parr, J.M., and Riskin, E.A. (2013). Signals, Systems, and Transforms, Prentice Hall.
  5. Tabachnick, B., and Fidell, L. (2012). Using Multivariate Statistics, Pearson Education.
  6. Witten, I.H., Frank, E., Hall, M.A., and Pal, C.J. (2016). Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann.

Cited by

See all 24

Metadata

Authors
Montero Quispe, K. G., Sousa Lima, W., Macêdo Batista, D., & Souto, E.
Affiliations
  • Computer Institute, Federal University of Amazonas, Manaus 69080-900, Brazil
  • Department of Computer Science, University of São Paulo, São Paulo 05508-090, Brazil
  • Universidade Federal do Amazonas (BR)
Venue
Sensors
Publisher
MDPI AG
Published
2018-12-10
Volume
18
Issue
12
Pages
4354
ISSN
1424-8220 (ISSN-L)
OpenAlex
W2904478006
Cited by
24
References
28
Citations by year
2025: 3 · 2024: 1 · 2023: 1 · 2022: 6 · 2021: 5 · 2020: 6 · 2019: 2
FWCI
1.63
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, other-oa)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Fundação de Amparo à Pesquisa do Estado do Amazonas (009/2017)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
  • Social Sciences › Transportation › Human Mobility and Location-Based Analysis
Keywords
human activity recognition, symbolic representation, smartphones, mobile sensors, feature extraction, computational efficiency, memory usage, processing time
MeSH terms
Smartphone, Algorithms, Humans, Human Activities, Monitoring, Physiologic, Pattern Recognition, Automated, 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: MBOSS: A Symbolic Representation of Human Activity Recognition Using Mobile Sensors. https://app.cochat.ai/papers/10.3390/s18124354
The paper
Montero Quispe, K. G., Sousa Lima, W., Macêdo Batista, D., & Souto, E. (2018). MBOSS: A Symbolic Representation of Human Activity Recognition Using Mobile Sensors. Sensors. https://doi.org/10.3390/s18124354

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.