20.500.12556/DKUM-86403 Accuracy is not enough: optimizing for a fault detection delay This paper assesses the fault-detection capabilities of modern deep-learning models. It highlights that a naive deep-learning approach optimized for accuracy is unsuitable for learning fault-detection models from time-series data. Consequently, out-of-the-box deep-learning strategies may yield impressive accuracy results but are ill-equipped for real-world applications. The paper introduces a methodology for estimating fault-detection delays when no oracle information on fault occurrence time is available. Moreover, the paper presents a straightforward approach to implicitly achieve the objective of minimizing fault-detection delays. This approach involves using pseudo-multi-objective deep optimization with data windowing, which enables the utilization of standard deep-learning methods for fault detection and expanding their applicability. However, it does introduce an additional hyperparameter that needs careful tuning. The paper employs the Tennessee Eastman Process dataset as a case study to demonstrate its findings. The results effectively highlight the limitations of standard loss functions and emphasize the importance of incorporating fault-detection delays in evaluating and reporting performance. In our study, the pseudo-multi-objective optimization could reach a fault-detection accuracy of 95% in just a fifth of the time it takes the best naive approach to do so. artificial neural networks deep learning fault detection accuracy multi-objective optimization umetna inteligenca globoko učenje multi-objektna optimizacija true false true MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/ © 2023 by the authors Članek v reviji 2023-11-27 14:27:05 2023-11-30 11:21:53 2024-05-22 14:17:53 0000-00-00 00:00:00 2023 0 0 18 str. no. 15, [Article no.] 3396 Vol. 11 2023 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2023-06-29 2023-07-31 2023-08-01 004.8 160904707 10.3390/math11153369 2227-7390 AccuracyIsNotEnough23.pdf AccuracyIsNotEnough23.pdf 1 B863E205A9C82F493381E08681CF63A7 abc6604f0613e7895f541f590359696e4d480cdaf4a289100e301b68a8d1921c b2197ad2-8d28-11ee-88ec-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=174348 https://www.mdpi.com/2227-7390/11/15/3369 1 aba87264-8d28-11ee-88ec-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=174347 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0