EUVIMEDEUVIMED entdecken
Crossref

E-M 2 : Efficient Multimodal Sensing via Adaptive Sensor-Computation Activation

Jinyi Cui, Tianyue Zheng

IEEE Transactions on Mobile Computing · 2026-04 · 25 (4) · 4551-4565

DOI: 10.1109/tmc.2025.3623296 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-04. Verfasst von Jinyi Cui und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Shenzhen Science and Technology Program, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal sensing systems have gained widespread adoption in IoT and edge intelligence, due to their ability to collect more comprehensive information of the target, thus improving sensing accuracy. However, this improved accuracy often comes at the cost of increased power consumption and computational overhead. Specifically, sensors require continuous power to collect data, and data processing algorithms not only demand intensive computational resources, but also consume significant energy to analyze the data, hindering the deployment of such systems on the edge. To address this issue, we propose E-M $^{2}$ 2 , a framework for efficient multimodal sensing by adaptive sensor-computation activation. First, E-M $^{2}$ 2 selectively disables redundant modalities and corresponding data processing modules, effectively reducing unnecessary power consumption and computational overhead. Second, E-M $^{2}$ 2 employs an exploration mechanism to reactivate disabled modalities, thus preventing “dead” modalities and enhancing overall system utilization. Finally, E-M $^{2}$ 2 conditions the data processing algorithms on the on/standby states of the modalities, thus alleviating the negative impacts of sensor deactivation. Extensive evaluations demonstrate that E-M $^{2}$ 2 reduces average power consumption by 40.75% and computational overhead by 48.84% across various sensing tasks, all while maintaining the sensing performance.

Förderung

  • Shenzhen Science and Technology Program
  • National Natural Science Foundation of China

Zitieren

APA

Cui, J., & Zheng, T. (2026). E-M 2 : Efficient Multimodal Sensing via Adaptive Sensor-Computation Activation. IEEE Transactions on Mobile Computing, 25(4), 4551-4565. https://doi.org/10.1109/tmc.2025.3623296

Vancouver

Cui J, Zheng T. E-M 2 : Efficient Multimodal Sensing via Adaptive Sensor-Computation Activation. IEEE Transactions on Mobile Computing. 2026;25(4):4551-4565. doi:10.1109/tmc.2025.3623296

BibTeX
@article{Cui2026,
  author = {Cui, Jinyi and Zheng, Tianyue},
  title = {E-M 2 : Efficient Multimodal Sensing via Adaptive Sensor-Computation Activation},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {4},
  pages = {4551--4565},
  doi = {10.1109/tmc.2025.3623296}
}
Kostenlos starten →