A Study on Intrusion Detection Using Deep Learning-based Weight Measurement with Multimode Fiber Speckle Patterns

This paper presents a deep learning-based weight sensor, using optical speckle patterns of multimode fiber, designed for real-time intrusion detection. The weight sensor has been trained to identify 11 distinct speckle patterns, ranging in weight from 0.0 kg to 2.0 kg, with an interval of 200 g betw...

Full description

Saved in:
Bibliographic Details
Published in:Current optics and photonics 2024, 8(5), , pp.508-514
Main Author: Lee, Hyuek Jae
Format: Article
Language:English
Subjects:
Deep learning
Error analysis
Error detection
Internet of Things
Intrusion detection systems
Real time
Speckle patterns
Weight measurement
물리학
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a deep learning-based weight sensor, using optical speckle patterns of multimode fiber, designed for real-time intrusion detection. The weight sensor has been trained to identify 11 distinct speckle patterns, ranging in weight from 0.0 kg to 2.0 kg, with an interval of 200 g between each pattern. The estimation for untrained weights is based on the generalization capability of deep learning. This results in an average weight error of 243.8 g. Although this margin of error precludes accurate weight measurement, the system's ability to detect abrupt weight changes makes it a suitable choice for intrusion detection applications. The weight sensor is integrated with the Google Teachable Machine, and real-time intrusion notifications are facilitated by the ThingSpeakTM cloud platform, an open-source Internet of Things (IoT) application developed by MathWorks.
ISSN:2508-7266
2508-7274
DOI:10.3807/COPP.2024.8.5.508