Anomaly detection for industrial quality assurance: A comparative evaluation of unsupervised deep learning models

Zipfel, Justus; Verworner, Felix; Fischer, Marco; Wieland, Uwe; Kraus, Mathias; Zschech, Patrick

doi:10.1016/j.cie.2023.109045

Cited by 27 publications

(11 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such an approach helps to improve the existing models with the update based on critical (boundary) samples [ 67 ]. Deep learning methods, on the other hand, try to build a model on unlabelled data on the basis of labelling provided by typical anomaly detection methods [ 68 , 69 ].…”

Section: Related Workmentioning

confidence: 99%

Anomaly Detection Module for Network Traffic Monitoring in Public Institutions

Wawrowski

Bialas

Kajzer

et al. 2023

Sensors

View full text Add to dashboard Cite

It seems to be a truism to say that we should pay more and more attention to network traffic safety. Such a goal may be achieved with many different approaches. In this paper, we put our attention on the increase in network traffic safety based on the continuous monitoring of network traffic statistics and detecting possible anomalies in the network traffic description. The developed solution, called the anomaly detection module, is mostly dedicated to public institutions as the additional component of the network security services. Despite the use of well-known anomaly detection methods, the novelty of the module is based on providing an exhaustive strategy of selecting the best combination of models as well as tuning the models in a much faster offline mode. It is worth emphasizing that combined models were able to achieve 100% balanced accuracy level of specific attack detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Anomaly Detection Module for Network Traffic Monitoring in Public Institutions

Wawrowski

Bialas

Kajzer

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Recently, many researches about anomaly detection have been based on self-supervised [7][8] or unsupervised [9][10] methods for constructing anomaly detectors. These methods typically aim to construct anomaly detectors by leveraging the unknown distribution of abnormal patterns.…”

Section: Introductionmentioning

confidence: 99%

STURM: exploiting swin transformer Unet with random masks for self-supervised anomaly detection

Liu,

Ma,

Gao

et al. 2024

Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023)

View full text Add to dashboard Cite

Anomaly detection is an essential task in industrial applications. Traditional anomaly detection algorithms based on convolutional neural networks (CNNs) struggle to extract global context information, resulting in poor anomaly detection performance. Moreover, the diversity and inherent uncertainty of anomalous samples present considerable constraints on the effectiveness of traditional anomaly detection algorithms. In this paper, a novel Swin Transformer Unet with Random Masks for self-supervised anomaly detection is proposed. First of all, a random mask strategy (RMS) is adopted to generate simulated anomalies in anomaly-free samples to solve the limited availability of abnormal samples during the training phase. Furthermore, to enhance the overall feature representation for anomaly detection tasks, the Swin Transformer Unet is utilized as the backbone network to extract local features and global contextual information from multi-scale feature maps. Experimental results on the industrial dataset MVTec AD demonstrate that our model achieves comparable performance in terms of anomaly detection.

show abstract

“…Each approach can be applied according to the research domain being worked on. The supervised learning approach is known as the machine learning development process, which requires labeled data [5][6][7], while unsupervised learning is without labeled data [8][9][10]. Supervised learning is applied to develop classification models and requires labeled data.…”

Section: Introductionmentioning

confidence: 99%

Labeling Consistency Test of Multi-Label Data for Aspect and Sentiment Classification Using the Cohen Kappa Method

Chamid,

Widowati,

Kusumaningrum

2024

ISI

View full text Add to dashboard Cite

Classification is part of machine learning, and developing it requires labeled data. Most data is available in an unlabeled form. Data labeling is a step that researchers must take. Good labeled data will produce a good classification model. The data labeling process cannot be ignored and needs to be done carefully and consistently. Because the classification process requires well-labeled data that can be accounted for. In addition, good labeled data will produce a good classification model. The role of an expert (rater) is needed to label the data and ideally at least two experts. However, involving two raters will become a new problem because it is likely that the results of the inter-rater labeling will be different. We propose the Cohen Kappa method to overcome this problem. We used data from scraping user reviews of the Indonesian marketplace, there were 4.307. Based on the calculation results, Kappa=0.909 for aspect detection, Kappa=0.893 for sentiment classification, and Kappa=0.971 for class aspect. Based on the kappa value, the labeling results for aspect detection, sentiment classification and aspect class were declared "almost perfect agreement", so that the results of this research obtained labeled data that can be used for classification tasks, especially for developing aspect-based sentiment analysis models.

show abstract

Anomaly detection for industrial quality assurance: A comparative evaluation of unsupervised deep learning models

Cited by 27 publications

References 46 publications

Anomaly Detection Module for Network Traffic Monitoring in Public Institutions

Anomaly Detection Module for Network Traffic Monitoring in Public Institutions

STURM: exploiting swin transformer Unet with random masks for self-supervised anomaly detection

Labeling Consistency Test of Multi-Label Data for Aspect and Sentiment Classification Using the Cohen Kappa Method

Contact Info

Product

Resources

About