Strain FBG-Based Sensor for Detecting Fence Intruders Using Machine Learning and Adaptive Thresholding
Ahmad Elleathy,
Faris Alhumaidan,
Mohammed Alqahtani,
Ahmed S. Almaiman,
Amr M. Ragheb,
Ahmed B. Ibrahim,
Jameel Ali,
Maged A. Esmail,
Saleh A. Alshebeili
Affiliations
Ahmad Elleathy
Electrical Engineering Department, King Saud University, Riyadh 11421, Saudi Arabia
Faris Alhumaidan
Electrical Engineering Department, King Saud University, Riyadh 11421, Saudi Arabia
Mohammed Alqahtani
Electrical Engineering Department, King Saud University, Riyadh 11421, Saudi Arabia
Ahmed S. Almaiman
Electrical Engineering Department, King Saud University, Riyadh 11421, Saudi Arabia
Amr M. Ragheb
Electrical Engineering Department, King Saud University, Riyadh 11421, Saudi Arabia
Ahmed B. Ibrahim
KACST-TIC in Radio Frequency and Photonics (RFTONICS), King Saud University, Riyadh 11421, Saudi Arabia
Jameel Ali
Electrical Engineering Department, King Saud University, Riyadh 11421, Saudi Arabia
Maged A. Esmail
Smart Systems Engineering Laboratory, Communications and Networks Engineering Department, Faculty of Engineering, Prince Sultan University, Riyadh 11586, Saudi Arabia
Saleh A. Alshebeili
Electrical Engineering Department, King Saud University, Riyadh 11421, Saudi Arabia
This paper demonstrates an intruder detection system using a strain-based optical fiber Bragg grating (FBG), machine learning (ML), and adaptive thresholding to classify the intruder as no intruder, intruder, or wind at low levels of signal-to-noise ratio. We demonstrate the intruder detection system using a portion of a real fence manufactured and installed around one of the engineering college’s gardens at King Saud University. The experimental results show that adaptive thresholding can help improve the performance of machine learning classifiers, such as linear discriminant analysis (LDA) or logistic regression algorithms in identifying an intruder’s existence at low optical signal-to-noise ratio (OSNR) scenarios. The proposed method can achieve an average accuracy of 99.17% when the OSNR level is <0.5 dB.
