EUVIMEDEUVIMED entdecken
Crossref

A Machine Learning Driven Framework for High Capacity and Robust Chipless RFID Systems Integrating Electromagnetic Signature Intelligence and Distributed Edge Analytics

Rafael Monteiro

International Research Journal of Computer and Electronics Engineering · 01.06.2026 · 13 (01) · 15-22

DOI: 10.64917/ircee.v13.i01.a03 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Research Journal of Computer and Electronics Engineering, online erschienen am 01.06.2026. Verfasst von Rafael Monteiro.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid expansion of the Internet of Things and pervasive sensing technologies has led to unprecedented demand for ultra low cost, scalable, and maintenance free identification and sensing platforms. Chipless Radio Frequency Identification has emerged as a powerful alternative to conventional chipped RFID because it eliminates integrated circuits, thereby reducing cost, improving robustness, and enabling deployment in harsh environments. However, the absence of active electronic components also introduces significant technical challenges related to encoding capacity, electromagnetic signature discrimination, and reliable detection in cluttered and noisy environments. The present study develops a comprehensive machine learning driven framework for high capacity and robust chipless RFID systems by synthesizing advances in electromagnetic tag design, resonant frequency placement, polarization diversity, and intelligent signal interpretation techniques. Building on the foundational concepts of polarization based encoding introduced by Vena et al. in their compact chipless RFID tag design and the more recent resonant frequency placement strategies for capacity enhancement proposed by Le et al., this work integrates these electromagnetic innovations with advanced machine learning and deep learning methods for electromagnetic signature analysis as explored by Rather and colleagues. The theoretical and methodological approach is further extended by incorporating distributed and edge learning paradigms, inspired by recent developments in federated learning and edge based ensemble learning for critical sensing applications such as fire detection and healthcare monitoring. By mapping these ideas to chipless RFID networks, the article proposes a scalable and privacy preserving architecture in which local readers perform intelligent preprocessing and classification while collaboratively improving global detection models without centralized raw data aggregation. The methodology emphasizes descriptive modeling of electromagnetic responses, feature learning from frequency and polarization dependent signatures, and adaptive model updating across distributed nodes. The results section presents an extensive qualitative and conceptual analysis of how such a framework enhances tag readability, reduces false detections, and improves encoding density under real world multipath and interference conditions. The discussion critically examines theoretical implications, limitations related to dataset availability and generalization, and future directions for integrating chipless RFID with cyber twin and soft computing approaches used in smart grids, healthcare, and industrial automation. The study concludes that the convergence of chipless RFID engineering and machine learning based edge intelligence provides a viable pathway toward next generation identification and sensing infrastructures that are cost effective, resilient, and capable of supporting the data intensive demands of smart environments.

Zitieren

APA

Monteiro, R. (2026). A Machine Learning Driven Framework for High Capacity and Robust Chipless RFID Systems Integrating Electromagnetic Signature Intelligence and Distributed Edge Analytics. International Research Journal of Computer and Electronics Engineering, 13(01), 15-22. https://doi.org/10.64917/ircee.v13.i01.a03

Vancouver

Monteiro R. A Machine Learning Driven Framework for High Capacity and Robust Chipless RFID Systems Integrating Electromagnetic Signature Intelligence and Distributed Edge Analytics. International Research Journal of Computer and Electronics Engineering. 2026;13(01):15-22. doi:10.64917/ircee.v13.i01.a03

BibTeX
@article{Monteiro2026,
  author = {Monteiro, Rafael},
  title = {A Machine Learning Driven Framework for High Capacity and Robust Chipless RFID Systems Integrating Electromagnetic Signature Intelligence and Distributed Edge Analytics},
  journal = {International Research Journal of Computer and Electronics Engineering},
  year = {2026},
  volume = {13},
  number = {01},
  pages = {15--22},
  doi = {10.64917/ircee.v13.i01.a03}
}
Kostenlos starten →