ItemArticle

All-Optical Plasmonic Neurosensor for Self-Learning Anomaly Detection in Smart IoT Systems

Title
All-Optical Plasmonic Neurosensor for Self-Learning Anomaly Detection in Smart IoT Systems
Creator
Shrichandran, G.V.; Warrier, Gayathry S.; Vignesh, K.; Rajendran, A.; Qamar, Shamimul; Shuaib, Mohammed; Rajaram, A.
Description
An integrated plasmonic neurosensing platform is introduced to enable ultrafast, self-learning anomaly detection within next-generation Internet of Things (IoT) environments. The research attempts to design an all-optical plasmonic neurosensor that can monitor irregularities as well as at the same time learns in hardware without the aid of electronics. The big picture is to develop an ultra-fast energy-saving sensorial unit that can scale to large tissues of IoT network applications and, autonomously, adjusts to varying conditions. The most significant invention of the paper is that localized surface plasmon resonance (LSPR) nanostructures are proposed to combine both nonlinear optical memory-effect and physical learning in sensor plasmonic gap. The technique is a hybrid between FDTD/FEM electromagnetic modelling, nanoimprint based production of sub-20-nm bow-tie antennas, nonlinear optical modulation experimental studies, and scalability analysis on the network level. A simulated system determined the optimal bow-tie configuration that resonated at 817nm with a field enhancement of approximately 28x with gap dimensions of 10nm long. Fabricated devices attained resonance of 823nm with Q-factor of 18.7. A refractive-index modulation was achieved of 3.1 10? and overall shift of the resonance at 51nm of 50 cycles in optical learning. The IoT level testing had 94.6% anomaly-detection errors and 47 ps response time, whereas the scalability experiment enabled the growth of bandwidth linearly with WDM and 92% fabrication yield. These findings provide an answer to the consequences that will lead to ultra-dense self-learning photonic IoT designs. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2026.
Source
Plasmonics;Volume;21;Issue;2;pp.1683-1700
Date
01-01-2026
Publisher
Springer
Subject
All-optical computation; Distributed IoT sensing; LSPR resonance tuning; Neuromorphic photonics; Photonic edge intelligence; Plasmonic neurosensor
Coverage
Shrichandran G.V., Department of computer science and engineering, School of computer science engineering, SRM Institute of science and technology, Ramapuram, Tamil Nadu, Chennai, 600089, India; Warrier G.S., Department of Computer Science, Christ (Deemed to be University), Karnataka, Bangalore, 560073, India; Vignesh K., Kalasalingam Academy of Research and Education, Krishnankoil, Tamil Nadu, 626126, India; Rajendran A., Department of ECE, Karpagam College of Engineering, Tamil Nadu, India; Qamar S., Computer Science & Engineering, Applied College, Dhahran Al Janoub Campus, King Khalid University, Abha, Saudi Arabia; Shuaib M., Department of Computer Science, College of Engineering and Computer Science, Jazan University, Jazan, Saudi Arabia; Rajaram A., Department of Electronics and Communication Engineering, E.G.S Pillay Engineering College, Tamilnadu, Nagapattinam, 611002, India
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 15571955;
Format
online
Language
English
Type
Article

Citation

Shrichandran, G.V.; Warrier, Gayathry S.; Vignesh, K.; Rajendran, A.; Qamar, Shamimul; Shuaib, Mohammed; Rajaram, A., “All-Optical Plasmonic Neurosensor for Self-Learning Anomaly Detection in Smart IoT Systems,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 19, 2026, https://archives.christuniversity.in/items/show/21973.

Output Formats