EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Compact Tactile Representations in Texture Classification

Frederico Luiz Martins de Sousa iD, Aref Sayareh, Mateus Nazario Coelho iD, Mateus Coelho Silva iD, Thiago Eustaquio Alves de Oliveira iD, Amilcar Soares Junior iD, Vinicius Prado da Fonseca iD

Sensors · 07.11.2026 · 26 (21) · 7044

DOI: 10.3390/s26217044 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.11.2026. Verfasst von Frederico Luiz Martins de Sousa und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Memorial University of Newfoundland, St. John's, NL A1C 5S7, Canada. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, Mitacs, Mathematics of Information Technology and Complex Systems.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Robotic tactile perception benefits from short interactions and compact feature representations. This study investigates whether nine-channel magnetic, angular-rate, and gravity (MARG) signals can be fused for texture classification using shortened segments of a 12 s exploration. A dataset of 12 textures and 100 trials per texture was evaluated using principal component analysis (PCA), independent component analysis (ICA), and channel-wise temporal averaging (AVG), with segment lengths corresponding to nominal durations of 3, 6, and 9 s and four classifiers. All learned pipeline stages were fitted exclusively on training experiments within five-fold experiment-level cross-validation repeated with four predefined seeds. For the shortest evaluated segments (nominally 3 s), the best observed cross-validation (CV) estimates, averaged across four seeds for AVG, PCA, and ICA, were 99.41%, 99.09%, and 98.92%, respectively. At 9 s, the configurations selected by the highest observed CV means yielded for PCA, AVG, and ICA configurations that achieved 99.99%, 99.97%, and 99.98% with 126, 162, and 162 classifier input features, respectively. Separately, a compact PCA–Random Forest (RF) Pareto configuration achieved 99.99% with only 36 features. These results show that accurate texture classification is possible with substantially shorter tactile interactions under the evaluated protocol: AVG performs strongly at 3 s, whereas PCA offers compact representations at longer durations.

Schlagwörter

Stichwörter der Autor:innen

ICAPCArobotic manipulationsignal fusiontactile perceptiontexture classification

Autor:innen und Institutionen

  • Department of Computer Science, Memorial University of Newfoundland, St. John's, NL A1C 5S7, Canada.
  • Center for Mathematics, Computation and Cognition, Federal University of ABC, Santo André 09280-560, SP, Brazil.
  • Department of Computer Science, Lakehead University, Orillia, ON L3V 0B9, Canada.
  • Department of Engineering Mathematics and Technology, University of Bristol, Bristol BS8 1TW, UK.
  • Department of Computer Science and Media Technology, Linnaeus University, 351 95 Växjö, Sweden.

ORCID-Profile: Frederico Luiz Martins de Sousa, Mateus Nazario Coelho, Mateus Coelho Silva, Thiago Eustaquio Alves de Oliveira, Amilcar Soares Junior, Vinicius Prado da Fonseca

Förderung

  • Natural Sciences and Engineering Research Council of Canada
  • Mitacs
  • Mathematics of Information Technology and Complex Systems

Zitieren

APA

Martins de Sousa, F. L., Sayareh, A., Nazario Coelho, M., Coelho Silva, M., Alves de Oliveira, T. E., Soares Junior, A., & Prado da Fonseca, V. (2026). Compact Tactile Representations in Texture Classification. Sensors, 26(21), 7044. https://doi.org/10.3390/s26217044

Vancouver

Martins de Sousa FL, Sayareh A, Nazario Coelho M, Coelho Silva M, Alves de Oliveira TE, Soares Junior A, et al. Compact Tactile Representations in Texture Classification. Sensors. 2026;26(21):7044. doi:10.3390/s26217044

BibTeX
@article{MartinsdeSousa2026,
  author = {Martins de Sousa, Frederico Luiz and Sayareh, Aref and Nazario Coelho, Mateus and Coelho Silva, Mateus and Alves de Oliveira, Thiago Eustaquio and Soares Junior, Amilcar and Prado da Fonseca, Vinicius},
  title = {Compact Tactile Representations in Texture Classification},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {7044},
  doi = {10.3390/s26217044}
}
Kostenlos starten →