TY - GEN
T1 - DETECTING ANOMALY IN CHEMICAL SENSORS VIA REGULARIZED CONTRASTIVE LEARNING
AU - Badawi, Diaa
AU - Bassi, Ishaan
AU - Ozev, Sule
AU - Cetin, Ahmet Enis
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - In this work, we present a method for detecting anomalous chemical sensors using contrastive learning-based framework. In many practical systems, an array of multiple chemical sensors are used. Some of the sensors may malfunction due to sensor drift and chemical poisoning. In standard contrastive learning, the aim is to learn representations that will have maximum agreement among data samples of the same concept while having a minimal agreement with data samples from other concepts. In this work, we adapt standard contrastive learning to learning useful representations for out-of-distribution sample detection. Furthermore, we compare the proposed framework with the cosine similarity measure and a novel similarity measure based on the 1 norm. Our experimental results show that our approach achieves higher AUC scores (93.6%) than baseline methods (90.1%).
AB - In this work, we present a method for detecting anomalous chemical sensors using contrastive learning-based framework. In many practical systems, an array of multiple chemical sensors are used. Some of the sensors may malfunction due to sensor drift and chemical poisoning. In standard contrastive learning, the aim is to learn representations that will have maximum agreement among data samples of the same concept while having a minimal agreement with data samples from other concepts. In this work, we adapt standard contrastive learning to learning useful representations for out-of-distribution sample detection. Furthermore, we compare the proposed framework with the cosine similarity measure and a novel similarity measure based on the 1 norm. Our experimental results show that our approach achieves higher AUC scores (93.6%) than baseline methods (90.1%).
KW - anomaly detection
KW - chemical sensors
KW - contrastive learning
KW - deep learning
KW - sensor signal processing
UR - http://www.scopus.com/inward/record.url?scp=85131236594&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85131236594&partnerID=8YFLogxK
U2 - 10.1109/ICASSP43922.2022.9746646
DO - 10.1109/ICASSP43922.2022.9746646
M3 - Conference contribution
AN - SCOPUS:85131236594
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 86
EP - 90
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Y2 - 23 May 2022 through 27 May 2022
ER -