{rfName}
Ef

Indexed in

License and Use

Icono OpenAccess

Citations

71

Altmetrics

Analysis of institutional authors

Jaén-Vargas MAuthorReyes Leiva, Karla MiriamAuthorSerrano Olmedo, José JavierCorresponding Author

Share

September 5, 2022
Publications
>
Article
Sí

Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models

Publicated to: PEERJ COMPUTER SCIENCE. 8 e1052- - 2022-08-08 8(), DOI: 10.7717/PEERJ-CS.1052

Authors:

Jaén-Vargas, M; Leiva, KMR; Fernandes, F; Gonçalves, SB; Silva, MT; Lopes, DS; Olmedo, JJS
[+]

Affiliations

Centro de Investigación Biomédica en Red de Bioingeniería, Biomateriales y Nanomedicina , Universidad Politécnica de Madrid - Author
Ctr Invest Biomed Red Bioingn Biomat & Nanomed, CIBER BBN, Madrid, Spain - Author
INESC ID, Lisbon, Portugal - Author
Instituto de Engenharia de Sistemas e Computadores Investigacao e Desenvolvimento em Lisboa - Author
Instituto Superior Tecnico - Author
Instituto Superior Técnico , Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa - Author
Univ Lisbon, Inst Super Tecn, IDMEC, Lisbon, Portugal - Author
Univ Lisbon, Inst Super Tecn, Lisbon, Portugal - Author
Univ Politecn Madrid, Ctr Biomed Technol, Bioinstrumentat & Nanomed Lab, Madrid, Spain - Author
Univ Tecnol Centroamer, Engn Fac, San Pedro Sula, Honduras - Author
Universidad Politécnica de Madrid - Author
Universidad Tecnológica Centroamericana , Universidad Politécnica de Madrid - Author
See more

Abstract

Deep learning (DL) models are very useful for human activity recognition (HAR); these methods present better accuracy for HAR when compared to traditional, among other advantages. DL learns from unlabeled data and extracts features from raw data, as for the case of time-series acceleration. Sliding windows is a feature extraction technique. When used for preprocessing time-series data, it provides an improvement in accuracy, latency, and cost of processing. The time and cost of preprocessing can be beneficial especially if the window size is small, but how small can this window be to keep good accuracy? The objective of this research was to analyze the performance of four DL models: a simple deep neural network (DNN); a convolutional neural network (CNN); a long short-term memory network (LSTM); and a hybrid model (CNN-LSTM), when variating the sliding window size using fixed overlapped windows to identify an optimal window size for HAR. We compare the effects in two acceleration sources': wearable inertial measurement unit sensors (IMU) and motion caption systems (MOCAP). Moreover, short sliding windows of sizes 5, 10, 15, 20, and 25 frames to long ones of sizes 50, 75, 100, and 200 frames were compared. The models were fed using raw acceleration data acquired in experimental conditions for three activities: walking, sit to stand, and squatting. Results show that the most optimal window is from 20-25 frames (0.20-0.25s) for both sources, providing an accuracy of 99,07% and F1-score of 87,08% in the (CNN-LSTM) using the wearable sensors data, and accuracy of 98,8% and F1-score of 82,80% using MOCAP data; similar accurate results were obtained with the LSTM model. There is almost no difference in accuracy in larger frames (100, 200). However, smaller windows present a decrease in the F1-score. In regard to inference time, data with a sliding window of 20 frames can be preprocessed around 4x (LSTM) and 2x (CNN-LSTM) times faster than data using 100 frames.
[+]

Keywords

deep learninghuman activity recognitionmotion capturepattern recognitionsensorssliding windowsAccelerometerDeep learningHuman activity recognitionMotion captureNetworksPattern recognitionSliding windows

Quality index

Bibliometric impact. Analysis of the contribution and dissemination channel

The work has been published in the journal PEERJ COMPUTER SCIENCE due to its progression and the good impact it has achieved in recent years, according to the agency WoS (JCR), it has become a reference in its field. In the year of publication of the work, 2022, it was in position 29/111, thus managing to position itself as a Q2 (Segundo Cuartil), in the category Computer Science, Theory & Methods. Notably, the journal is positioned en el Cuartil Q2 para la agencia Scopus (SJR) en la categoría Computer Science (Miscellaneous).

From a relative perspective, and based on the normalized impact indicator calculated from World Citations provided by WoS (ESI, Clarivate), it yields a value for the citation normalization relative to the expected citation rate of: 2.37. This indicates that, compared to works in the same discipline and in the same year of publication, it ranks as a work cited above average. (source consulted: ESI Nov 13, 2025)

This information is reinforced by other indicators of the same type, which, although dynamic over time and dependent on the set of average global citations at the time of their calculation, consistently position the work at some point among the top 50% most cited in its field:

  • Weighted Average of Normalized Impact by the Scopus agency: 4.35 (source consulted: FECYT Mar 2025)

Specifically, and according to different indexing agencies, this work has accumulated citations as of 2026-04-27, the following number of citations:

  • WoS: 31
  • Scopus: 40
  • Europe PMC: 3
  • Google Scholar: 37
[+]

Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2026-04-27:

  • The use, from an academic perspective evidenced by the Altmetric agency indicator referring to aggregations made by the personal bibliographic manager Mendeley, gives us a total of: 109.

With a more dissemination-oriented intent and targeting more general audiences, we can observe other more global scores such as:

  • The Total Score from Altmetric: 5.
  • The number of mentions on the social network Facebook: 1 (Altmetric).
  • The number of mentions on the social network X (formerly Twitter): 6 (Altmetric).

It is essential to present evidence supporting full alignment with institutional principles and guidelines on Open Science and the Conservation and Dissemination of Intellectual Heritage. A clear example of this is:

  • The work has been submitted to a journal whose editorial policy allows open Open Access publication.
  • Assignment of a Handle/URN as an identifier within the deposit in the Institutional Repository: https://oa.upm.es/85443/

As a result of the publication of the work in the institutional repository, statistical usage data has been obtained that reflects its impact. In terms of dissemination, we can state that, as of

  • Views: 226
  • Downloads: 19
[+]

Leadership analysis of institutional authors

This work has been carried out with international collaboration, specifically with researchers from: Honduras; Portugal.

There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: First Author (JAÉN VARGAS, MILAGROS QUILIMARA) and Last Author (SERRANO OLMEDO, JOSE JAVIER).

the authors responsible for correspondence tasks have been Olmedo JJS and SERRANO OLMEDO, JOSE JAVIER.

[+]