2020/06/30 by Robert Müller, Fabian Ritz, Steffen Illium +2 · 60 citations
Computer Science · Engineering · #Anomaly (physics) #Anomaly Detection Techniques and Applications #Anomaly detection #Artificial intelligence #Computer science #Computer vision #Image (mathematics) #Music and Audio Processing #Pattern recognition (psychology) #Physics #Speech recognition #Time Series Analysis and Forecasting #Transfer of learning #cs.CV #cs.LG #cs.SD #eess.AS
paper · pdf · open access · doi:10.5220/0010185800490056
ICAART 2021, 8 pages, 2 figures, 1 table
arxiv created 2020/12/11 · openalex publication_date 2021/01/01 · arxiv updated 2021/02/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
In industrial applications, the early detection of malfunctioning factory machinery is crucial. In this paper, we consider acoustic malfunction detection via transfer learning. Contrary to the majority of current approaches which are based on deep autoencoders, we propose to extract features using neural networks that were pretrained on the task of image classification. We then use these features to train a variety of anomaly detection models and show that this improves results compared to convolutional autoencoders in recordings of four different factory machines in noisy environments. Moreover, we find that features extracted from ResNet based networks yield better results than those from AlexNet and Squeezenet. In our setting, Gaussian Mixture Models and One-Class Support Vector Machines achieve the best anomaly detection performance.