Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction
Abstract
This paper proposes to use autoencoders with nonlinear dimensionality reduction in the anomaly detection task. The authors apply dimensionality reduction by using an autoencoder onto both artificial data and real data, and compare it with linear PCA and kernel PCA to clarify its property. The artificial data is generated from Lorenz system, and the real data is the spacecrafts' telemetry data. This paper demonstrates that autoencoders are able to detect subtle anomalies which linear PCA fails. Also, autoencoders can increase their accuracy by extending them to denoising autoenconders. Moreover, autoencoders can be useful as nonlinear techniques without complex computation as kernel PCA requires. Finaly, the authors examine the learned features in the hidden layer of autoencoders, and present that autoencoders learn the normal state properly and activate differently with anomalous input.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Autoencoders have been successfully applied across various domains, including robust feature learning, generative modeling, and anomaly detection.
“Vincent et al. [41] used denoising autoencoders for robust feature learning, Kingma and Welling [42] introduced variational autoencoders for generative modeling, and Sakurada and Yairi [43] employed autoencoders for anomaly detection in time-series data.”
From Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches (2025) · cites this paper as [43]
Cites
Lecture Notes in Computer Science 1205
(1999) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir.1999.04926fae.001 · Cited by 39,228 · see citing works
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928 · see citing works
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · see citing works
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436 · see citing works
Proceedings of the 19th International Joint Conference on Artificial Intelligence
Pujol, J. M., Delgado, J., Ramon Sangüesa, A., & Flache, A. (2005) · International Joint Conference on Artificial Intelligence · Cited by 5,771 · see citing works
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051 · see citing works
Nonlinear principal component analysis using autoassociative neural networks
Kramer, M. A. (1991) · AIChE Journal · doi:10.1002/aic.690370209 · Cited by 3,037 · see citing works
Proceedings of the International Joint Conference on Neural Networks, 2003.
(2003) · doi:10.1109/ijcnn.2003 · Cited by 1,673 · see citing works
Kernel PCA for novelty detection
Hoffmann, H. (2006) · Pattern Recognition · doi:10.1016/j.patcog.2006.07.009 · Cited by 776 · see citing works
Outlier Detection Using Replicator Neural Networks
Hawkins, S., He, H., Williams, G., & Baxter, R. A. (2002) · Lecture notes in computer science · doi:10.1007/3-540-46145-0_17 · Cited by 735 · see citing works
A novelty detection approach to classification
Japkowicz, N., Myers, C. E., & Gluck, M. A. (1995) · Cited by 392 · see citing works
A comparative study of RNN for outlier detection in data mining
Williams, G., Baxter, R. A., He, H., Hawkins, S., & Gu, L. (2003) · Proceedings · doi:10.1109/icdm.2002.1184035 · Cited by 281 · see citing works
Implicit learning in autoencoder novelty assessment
Thompson, B. B., Marks, R. J., Choi, J. J., El-Sharkawi, M. A., Huang, M.-Y., & Bunje, C. (2003) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2002.1007605 · Cited by 58 · see citing works
Electric Power System Anomaly Detection Using Neural Networks
Martinelli, M., Tronci, E., Dipoppa, G., et al. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-30132-5_168 · Cited by 39 · see citing works
Characteristics of auto-associative MLP as a novelty detector
Hwang, B.-H., & Cho, S. (2003) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1999.836051 · Cited by 20 · see citing works
A Novelty Detection Approach To Diagnose Damage In A Cracked Beam
Surace, C., Worden, K., & Tomlinson, G. R. (1997) · Cited by 19 · see citing works
Spacecraft telemetry data monitoring by dimensionality reduction techniques
Yairi, T., Kawahara, Y., & Takata, N. (2010) · Society of Instrument and Control Engineers of Japan · Cited by 15 · see citing works
Self-citationAnalysis of Novelty Detection Properties of Autoassociators
Song, S. O., Shin, D. P., & Yoon, E. S. (2001) · Elsevier eBooks · doi:10.1016/b978-008044036-1/50068-8 · Cited by 9 · see citing works
Spacecraft telemetry data monitoring by dimensionality reduction techniques
Yairi, Inui, Yoshiki, et al. (2010) · Society of Instrument and Control Engineers of Japan · Cited by 6 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Towards Total Recall in Industrial Anomaly Detection
Roth, K., Pemula, L., Zepeda, J., Scholkopf, B., Brox, T., & Gehler, P. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01392 · Cited by 1,810 · see citing works
“Existing work on cold-start, industrial visual anomaly detection relies on learning a model of the nominal distribution via autoencoding methods [12, 36, 44], GANs [2, 39, 43], or other unsupervised adaptation methods [42, 56].”
BackgroundA Review on Outlier/Anomaly Detection in Time Series Data
Blázquez-García, A., Conde, A., Mori, U., & Lozano, J. A. (2022) · ACM Computing Surveys · doi:10.1145/3444690 · Cited by 1,102 · see citing works
OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations
Perera, P., Nallapati, R., & Xiang, B. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00301 · Cited by 608 · see citing works
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection
Yang, Y., Zhang, C., Zhou, T., Wen, Q., & Sun, L. (2023) · Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3580305.3599295 · Cited by 387 · see citing works
Sub-Image Anomaly Detection with Deep Pyramid Correspondences
Cohen, N., & Hoshen, Y. (2020) · arXiv · doi:10.48550/arxiv.2005.02357 · Cited by 372 · see citing works
Generative Probabilistic Novelty Detection with Adversarial Autoencoders
Pidhorskyi, S., Almohsen, R., Adjeroh, D. A., & Doretto, G. (2018) · arXiv · doi:10.48550/arxiv.1807.02588 · Cited by 255 · see citing works
Inpainting transformer for anomaly detection
Pirnay, J., & Chai, K. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-06430-2_33 · Cited by 227 · see citing works
Kravchik, M., & Shabtai, A. (2022) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2021.3050101 · Cited by 224 · see citing works
Free-riders in Federated Learning: Attacks and Defenses
Lin, J., Du, M., & Liu, J. (2019) · arXiv · doi:10.48550/arxiv.1911.12560 · Cited by 76 · see citing works
Seal, D. B., Das, V., Goswami, S., & De, R. K. (2020) · Genomics · doi:10.1016/j.ygeno.2020.03.021 · Cited by 69 · see citing works
FAPM: Fast Adaptive Patch Memory for Real-Time Industrial Anomaly Detection
Kim, D., Park, C., Cho, S., & Lee, S. (2023) · ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49357.2023.10096400 · Cited by 56 · see citing works
Tu, S., Waqas, M., Badshah, A., Yin, M., & Abbas, G. (2023) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2023.3319953 · Cited by 22 · see citing works
Xing, S., Wang, Y., & Liu, W. (2025) · Sensors · doi:10.3390/s25113396 · Cited by 23 · see citing works
Sheng, T., & Huber, M. (2025) · Sensors · doi:10.3390/s25134032 · Cited by 5 · see citing works
- Authors
- Sakurada, M., & Yairi, T.
- Affiliations
- The University of Tokyo (JP)
- Research Center for Advanced Science and Technology, The University of Tokyo (JP)
- ORCID
- Yairi, Takehisa
- Venue
- Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis
- Publisher
- ACM
- Published
- 2014-12-02
- Pages
- 4-11
- OpenAlex
- W2127979711
- Cited by
- 1,438
- References
- 19
- Citations by year
- 2026: 203 · 2025: 198 · 2024: 170 · 2023: 159 · 2022: 174 · 2021: 178 · 2020: 165 · 2019: 109 · 2018: 44 · 2017: 27 · 2016: 9 · 2015: 2
- FWCI
- 7.39
- Type
- conference paper
- Language
- en
- Open access
- closed
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- anomaly detection, autoencoder, nonlinear dimensionality reduction, denoising autoencoder, kernel principal component analysis, principal component analysis, Lorenz system, spacecraft telemetry
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
