Semi-Supervised Anomaly Detection for EEG Waveforms Using Deep Belief Nets
Abstract
Clinical electroencephalography (EEG) is routinely used to monitor brain function in critically ill patients, and specific EEG waveforms are recognized by clinicians as signatures of abnormal brain. These pathologic EEG waveforms, once detected, often necessitate accute clinincal interventions, but these events are typically rare, highly variable between patients, and often hard to separate from background, making them difficult to reliably detect. We show that Deep Belief Nets (DBNs), a type of multi-layer generative neural network, can be used effectively for such EEG anomaly detection. We compare this technique to the state-of-the-art, a one-class Support Vector Machine (SVM), showing that the DBN outperforms the SVM by the F1measure for our EEG dataset. We also show how the outputs of a DBN-based detector can be used to aid visualization of anomalies in large EEG data sets and propose a method for using DBNs to gain insight into which features of signals are characteristically anomalous. These findings show that Deep Belief Nets can facilitate human review of large amounts of clinical EEG as well as mining new EEG features that may be indicators of unusual activity.
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?
Most works try to learn the manifold of a single class representing normal data using an encoding-decoding scheme.
“Most of the works try to learn the manifold of a single class representing normal data[7], using an encoding-decoding scheme, and their output is a classification of the input image as either normal or anomaly, while fewer works deal with the task to segment the local anomalous region in an image[8].”
From VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization (2021) · cites this paper as [7]
Cites
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · 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
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · see citing works
Libsvm : A library for support vector machines
Ferrari, V. (2008) · Medical Entomology and Zoology · Cited by 10,124 · see citing works
Estimating the Support of a High-Dimensional Distribution
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001) · Neural Computation · doi:10.1162/089976601750264965 · Cited by 6,168 · see citing works
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 3× · see citing works
“Calculating the gradient of the log likelihood of v is intractable and so contrastive divergence with k iterations (often k = 1) [6] is usually used to approximate it”
BackgroundMethodA Survey of Outlier Detection Methodologies
Hodge, V., & Austin, J. (2004) · Artificial Intelligence Review · doi:10.1007/s10462-004-4304-y · Cited by 3,596 · see citing works
(2007) · Cited by 937 · see citing works
Current Practice of Clinical Electroencephalography.
(1980) · Annals of Internal Medicine · doi:10.7326/0003-4819-92-4-582_3 · Cited by 732 · see citing works
Chong, D. J., & Hirsch, L. J. (2005) · Journal of Clinical Neurophysiology · doi:10.1097/01.wnp.0000158699.78529.af · Cited by 501 · see citing works
Classifying Single Trial EEG: Towards Brain Computer Interfacing
Blankertz, B., Curio, G., & Müller, K. (2002) · The MIT Press eBooks · doi:10.7551/mitpress/1120.003.0025 · Cited by 473 · see citing works
One-Class Novelty Detection for Seizure Analysis from Intracranial EEG
Gardner, A. B., Krieger, A. Μ., Vachtsevanos, G., & Litt, B. (2006) · doi:10.5555/1248547.1248584 · Cited by 271 · see citing works
Self-citationGbureck, U., Lansnicker, L., Holste, T., & Thulĺ, R. (2004) · Biomedizinische Technik/Biomedical Engineering · doi:10.1515/bmt.2004.003 · Cited by 73 · see citing works
Current practice of clinical electroencephalography, 3rd edn
Ebersole, J. S., & Pedley, T. A. (2003) · European Journal of Neurology · doi:10.1046/j.1468-1331.2003.00643.x · Cited by 51 · see citing works
Machine learning techniques for Brain-Computer Interfaces
Müller, K.-R., Krauledat, M., Dornhege, G., Curio, G., & Blankertz, B. (2004) · Cited by 26 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Deep Learning for Health Informatics
Ravì, D., Wong, C., Deligianni, F., Berthelot, M., Andreu-Perez, J., Lo, B., & Yang, G.-Z. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2636665 · Cited by 2,000 · see citing works
“[89] proposed a DBN approach to detect anomalies in EEG waveforms.”
MethodMachine Learning for Anomaly Detection: A Systematic Review
Nassif, A. B., Talib, M. A., Nasir, Q., & Dakalbab, F. M. (2021) · IEEE Access · doi:10.1109/access.2021.3083060 · Cited by 748 · see citing works
VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization
Mishra, P., Verk, R., Fornasier, D., Piciarelli, C., & Foresti, G. L. (2021) · 2021 IEEE 30th International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie45552.2021.9576231 · Cited by 462 · see citing works
“Most of the works try to learn the manifold of a single class representing normal data[7], using an encoding-decoding scheme, and their output is a classification of the input image as either normal or anomaly, while fewer works deal with the task to segment the local anomalous region in an image[8].”
BackgroundImage-Based Surface Defect Detection Using Deep Learning: A Review
Bhatt, P. M., Malhan, R. K., Rajendran, P. S., Shah, B. C., Thakar, S., Yoon, Y. J., & Gupta, S. K. (2021) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4049535 · Cited by 381 · see citing works
Smart anomaly detection in sensor systems: A multi-perspective review
Erhan, L., Ndubuaku, M., Mauro, M. D., Song, W., Chen, M., Fortino, G., Bagdasar, O., & Liotta, A. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.10.001 · Cited by 340 · see citing works
“DBNs can scale to large datasets and can improve inter-pretability as demonstrated by Wulsin et al. in [82].”
BackgroundMethodUnsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals
Zhang, Y., Chen, Y., Wang, J., & Pan, Z. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3102110 · Cited by 322 · see citing works
“Others like Denoising AutoEncoders (DAEs) [22], Deep Belief Networks (DBNs) [39] and Robust Deep Autoencoder (RDA) [40] have also been reported good performance for anomaly detection.”
BackgroundDeep Learning in the Biomedical Applications: Recent and Future Status
Zemouri, R. M., Noureddine Zerhouni, A., & Racoceanu, D. (2019) · Applied Sciences · doi:10.3390/app9081526 · Cited by 194 · see citing works
Wulsin, D., Gupta, J. R., Mani, R., Blanco, J. A., & Litt, B. (2011) · Journal of Neural Engineering · doi:10.1088/1741-2560/8/3/036015 · Cited by 186 · see citing works
“In our previous work [38], we have shown that this DBN anomaly metric can be turned into a positive detection by learning an optimal threshold value.”
BackgroundSelf-citationAn analysis of process fault diagnosis methods from safety perspectives
Arunthavanathan, R., Khan, F. I., Ahmed, S., & Imtiaz, S. A. (2020) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2020.107197 · Cited by 173 · see citing works
A Survey on an Emerging Area: Deep Learning for Smart City Data
Chen, Q., Wang, W., Wu, F., De, S., Wang, R., Zhang, B., & Huang, X. (2019) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2019.2907718 · Cited by 167 · see citing works
“, xn] traffic flow (sensor) [17], [69] EEG signal (sensor) [88], [89]”
MethodInfluentialAutomatic ocular artifacts removal in EEG using deep learning
Yang, B., Duan, K., Fan, C., Hu, C., & Wang, J. (2018) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2018.02.021 · Cited by 151 · see citing works
The TUH EEG CORPUS: A big data resource for automated EEG interpretation
Harati, A., Lopez, S. M., Iyad Obeid, A., Picone, J., Jacobson, M. P., & Tobochnik, S. D. (2014) · IEEE Signal Processing in Medicine and Biology Symposium · doi:10.1109/spmb.2014.7002953 · Cited by 141 · see citing works
“A system with a low false alarm rate is much preferred over a high detection rate.”
BackgroundHyperspectral Anomaly Detection Using Deep Learning: A Review
Hu, X., Xie, C., Fan, Z., Duan, Q., Zhang, D., Jiang, L., Wei, X. H., Hong, D., Li, G., Zeng, X., et al. (2022) · Remote Sensing · doi:10.3390/rs14091973 · Cited by 140 · see citing works
Adaptive Memory Networks With Self-Supervised Learning for Unsupervised Anomaly Detection
Zhang, Y., Wang, J., Chen, Y., Yu, H., & Qin, T. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3139916 · Cited by 136 · see citing works
“Others like Variational Autoenocders (VAEs) [17], [18], De-noising AutoEncoders (DAEs) [19], Deep belief networks (DBNs) [20], Replicating neural network [21] and Robust Deep Autoencoder (RDA) [22] have also reported promising performance.”
BackgroundConvolutional deep belief networks for feature extraction of EEG signal
Ren, Y., & Wu, Y. X. (2014) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2014.6889383 · Cited by 130 · see citing works
“[12] applied DBN to model EEG waveforms for classification in a semi-supervised paradigm.”
MethodDeep learning for EEG data analytics: A survey
Li, G., Lee, C. H., Jung, J. J., Youn, Y. C., & Camacho, D. (2019) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5199 · Cited by 122 · see citing works
Jiang, K., Xie, W., Li, Y., Lei, J., He, G., & Du, Q. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2975295 · Cited by 103 · see citing works
A Novel Semi-Supervised Deep Learning Framework for Affective State Recognition on EEG Signals
Jia, X., Li, K., Li, X., & Zhang, A. (2014) · IEEE International Conference on Bioinformatics and Bioengineering (BIBE) · doi:10.1109/bibe.2014.26 · Cited by 100 · see citing works
“For instance, in [23], [24] DBN-based method is adopted as the reconstructor for anomaly detection in EEG signals.”
MethodDetecting anomalies in time series data from a manufacturing system using recurrent neural networks
Wang, Y., Perry, M., Whitlock, D., & Sutherland, J. W. (2020) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2020.12.007 · Cited by 94 · see citing works
Cognitive neuroscience and robotics: Advancements and future research directions
Liu, S., Wang, L., & Gao, R. X. (2023) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2023.102610 · Cited by 90 · see citing works
Zhang, J., Wu, Y. X., Bai, J., & Chen, F. (2015) · Transactions of the Institute of Measurement and Control · doi:10.1177/0142331215587568 · Cited by 77 · see citing works
“The definition of F1 score is as follows (Wulsin et al., 2010):”
BackgroundMethodInfluentialDeep unsupervised multi-modal fusion network for detecting driver distraction
Zhang, Y., Chen, Y., & Gao, C. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.09.023 · Cited by 76 · see citing works
Ensemble of Autoencoders for Anomaly Detection in Biomedical Data: A Narrative Review
Nawaz, A., Khan, S. S., & Ahmad, A. (2024) · IEEE Access · doi:10.1109/access.2024.3360691 · Cited by 68 · see citing works
“An EEG is often used to diagnose problems with the brain (e.g. epileptic seizures [34]) or to monitor brain activity [35].”
BackgroundAffective state recognition from EEG with deep belief networks
Li, K., Li, X., Zhang, Y., & Zhang, A. (2013) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2013.6732507 · Cited by 65 · see citing works
“For instances, semisupervised DBN is applied in [12], [13] for the task of anomaly detection.”
MethodStudies on the GAN-Based Anomaly Detection Methods for the Time Series Data
Lee, C., Cheon, Y.-J., & Hwang, W. (2021) · IEEE Access · doi:10.1109/access.2021.3078553 · Cited by 59 · see citing works
“A sufficiently trained AE would yield low reconstruction errors for normal instances compared to abnormal instances [27]–[29].”
BackgroundAutoEncoder and LightGBM for Credit Card Fraud Detection Problems
Du, H., Lv, L., Guo, A., & Wang, H. (2023) · Symmetry · doi:10.3390/sym15040870 · Cited by 57 · see citing works
A3D: Attention-based auto-encoder anomaly detector for false data injection attacks
Kundu, A., Sahu, A., Serpedin, E., & Davis, K. (2020) · Electric Power Systems Research · doi:10.1016/j.epsr.2020.106795 · Cited by 52 · see citing works
“Deep neural networks have been used in supervised [30], semi-supervised [31], and unsupervised settings [32] in the past for anomaly detection.”
MethodCheng, L., Li, D., Yu, G., Zhang, Z., li, X., & Yu, S. (2020) · IEEE Access · doi:10.1109/access.2020.2969054 · Cited by 50 · see citing works
“used DBN to detect the characteristics of abnormal EEG signals and got good results [17].”
MethodApplying Deep Learning to Individual and Community Health Monitoring Data: A Survey
Yao, Z., Bi, J., & Chen, Y. (2018) · Machine Intelligence Research · doi:10.1007/s11633-018-1136-9 · Cited by 49 · see citing works
Deep Multi-sphere Support Vector Data Description
Ghafoori, Z., & Leckie, C. A. (2020) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611976236.13 · Cited by 45 · see citing works
An IOT based smart grid system for advanced cooperative transmission and communication
Alomar, M. A. (2023) · Physical Communication · doi:10.1016/j.phycom.2023.102069 · Cited by 41 · see citing works
Seizure Onset Zone Identification From iEEG: A Review
Balaji, S. S., & Parhi, K. K. (2022) · IEEE Access · doi:10.1109/access.2022.3182716 · Cited by 38 · see citing works
“Semi-supervised algorithms that have shown to outperform unsupervised methods [115], [116] can be incorporated to improve the detection.”
BackgroundA privacy preserve big data analysis system for wearable wireless sensor network
Ge, C., Yin, C., Liu, Z., Fang, L., Zhu, J., & Ling, H. (2020) · Computers & Security · doi:10.1016/j.cose.2020.101887 · Cited by 35 · see citing works
A Novel Unsupervised Anomaly Detection Approach for Intrusion Detection System
Chen, W., Kong, F., Mei, F., Yuan, G., & Li, B. H. (2017) · IEEE International Conference on Big Data Security on Cloud, IEEE International Conference on High Performance and Smart Computing, and IEEE International Conference on Intelligent Data and Security (BigDataSecurity/HPSC/IDS) · doi:10.1109/bigdatasecurity.2017.56 · Cited by 34 · see citing works
“The semi-supervised anomaly detection[9][10] try to build a model based on normal data.”
BackgroundApplications of Deep Learning in Healthcare and Biomedicine
Mittal, S., & Hasija, Y. (2019) · Studies in big data · doi:10.1007/978-3-030-33966-1_4 · Cited by 33 · see citing works
A novel method for detecting credit card fraud problems
Du, H., Lv, L., Wang, H., & Guo, A. (2024) · PLoS ONE · doi:10.1371/journal.pone.0294537 · Cited by 33 · see citing works
Classification of ADHD and non-ADHD subjects using a universal background model
Marcano, J. L. L., Bell, M. A., & Beex, A. A. L. (2017) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2017.07.023 · Cited by 33 · see citing works
Dual Autoencoders Generative Adversarial Network for Imbalanced Classification Problem
Wu, E., Cui, H., & Welsch, R. E. (2020) · IEEE Access · doi:10.1109/access.2020.2994327 · Cited by 31 · see citing works
“In addition to balancing the majority and the minority classes by resampling, some researches proposed some semi-supervised methods based on autoencoders in anomaly detections [25]–[27].”
EXAD: A System for Explainable Anomaly Detection on Big Data Traces
Song, F., Diao, Y., Read, J., Stiegler, A., & Bifet, A. (2018) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2018.00204 · Cited by 29 · see citing works
“It has been applied to anomaly detection, though often with a focus on image data [10].”
MethodEEG-based affect states classification using Deep Belief Networks
Xu, H., & Plataniotis, K. N. (2016) · Digital Media Industry & Academic Forum (DMIAF) · doi:10.1109/dmiaf.2016.7574921 · Cited by 29 · see citing works
“In [9], DBNs was proposed in processing EEG signals for anomaly detection and classification on five clinically significant waves and in [10], DBNs were used as classifiers to determine sleep stages from EEG, EOG, and EMG signals.”
MethodSharma, P., Mirzan, S. R., Bhandari, A., Pimpley, A., Eswaran, A., Srinivasan, S., & Shao, L. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-65847-2_4 · Cited by 26 · see citing works
“Anomaly Detection (AD) [2] has been applied to various domains, such as tracking anomalous events in traffic surveillance videos [18] and tracking irregular patterns in electrocardiographs of a patient [20].”
BackgroundHuang, H., Zhao, B., Gao, F., Chen, P., Wang, J., & Hussain, A. (2023) · Sensors · doi:10.3390/s23104828 · Cited by 23 · see citing works
Wielgosz, M., Mertik, M., Skoczeń, A., & Matteis, E. D. (2018) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2018.06.012 · Cited by 23 · see citing works
“Besides a whole arena of fault detection and prediction systems, applications such as brain exploration and tracking extraordinary phenomena via ECG, EEG and fMRI signals (Chauhan and Vig, 2015; Wulsin et al., 2010; Dvornek et al., 2017) could benefit from the proposed system adoption.”
Network Anomaly Detection Using Transfer Learning Based on Auto-Encoders Loss Normalization
Yehezkel, A., Elyashiv, E., & Soffer, O. (2021) · ACM Workshop on Artificial Intelligence and Security (AISec) · doi:10.1145/3474369.3486869 · Cited by 21 · see citing works
“Having sufficient training samples of normal behaviour, auto-encoders would produce low reconstruction errors for normal instances, and high errors for unusual, anomalous, events ([23–25]).”
BackgroundLuo, X., Jiang, Y., Wang, E., & Men, X. (2022) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-022-00943-7 · Cited by 18 · see citing works
“Other AEs, such as variational AEs [24], denoising AEs [25], and deep faith networks [26], also show good performance.”
BackgroundDistributed detection of sequential anomalies in univariate time series
Schneider, J., Wenig, P., & Papenbrock, T. (2021) · The VLDB Journal · doi:10.1007/s00778-021-00657-6 · Cited by 16 · see citing works
“Although supervised and semi-supervised approaches are able to deliver competitive results in specific applications [17,32,50], they require labeled training data that are for many time series not or in not sufficient quantity available.”
BackgroundDevika, G., & Karegowda, A. G. (2020) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-7998-2108-3.ch001 · Cited by 15 · see citing works
Image Anomaly Detection by Aggregating Deep Pyramidal Representations
Mishra, P. K., Piciarelli, C., & Foresti, G. L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68799-1_51 · Cited by 15 · see citing works
A Study on Automatic Sleep Stage Classification Based on CNN-LSTM
Yang, Y., Zheng, X., & Yuan, F. (2018) · International Conference on Crowd Science and Engineering (ICCSE) · doi:10.1145/3265689.3265693 · Cited by 15 · see citing works
Neural Network Based Silent Error Detector
Wang, C., Dryden, N., Cappello, F., & Snir, M. (2018) · IEEE International Conference on Cluster Computing (CLUSTER) · doi:10.1109/cluster.2018.00035 · Cited by 13 · see citing works
“Deep neural networks have been used for anomaly detection in other fields such as network traffic inspection [48], particle physics [49], EEG waveforms [50], and videos [51].”
MethodThe Role of Deep Learning in Improving Healthcare
Thaler, S., & Menkovski, V. (2019) · Springer eBooks · doi:10.1007/978-3-030-05249-2_3 · Cited by 13 · see citing works
Image Anomaly Detection with Capsule Networks and Imbalanced Datasets
Piciarelli, C., Mishra, P., & Foresti, G. L. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-30642-7_23 · Cited by 10 · see citing works
“cessing step to make the dataset balanced before applying any classification algorithm [4]. Regardingsemi-supervised orunsupervisedapproaches,earlyworksadopted techniques such as Deep Belief Networks [20] for medical diagnosis on EEG waveforms or Restricted Boltzmann Machines [11] for network traffic analysis. Morerec…”
MethodAjidarma, P., Nof, S. Y., Pradana, R. A., Nugroho, W. A., & Halim, A. H. (2022) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2022.09.659 · Cited by 10 · see citing works
Bootstrap–CURE: A Novel Clustering Approach for Sensor Data—An Application to 3D Printing Industry
Suman, S., Karna, A., & Gibert, K. (2022) · Applied Sciences · doi:10.3390/app12042191 · Cited by 10 · see citing works
Nam, K. H., Song, Y. J., & Yun, I. D. (2021) · IEEE Access · doi:10.1109/access.2021.3112545 · Cited by 9 · see citing works
“In unsupervised learning, Auto-encoder [4], [5] models are first trained for reconstructing the normal data, abnormal data are then detected based on their reconstruction error [6].”
MethodSong, K., Liu, C., & Jiang, D. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130488 · Cited by 9 · see citing works
Online Location-based Detection of False Data Injection Attacks in Smart Grid Using Deep Learning
Hegazy, H. I., Eldien, A. S. T., Tantawy, M. M., Fouda, M. M., & TagElDien, H. A. (2022) · IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS) · doi:10.1109/iotais56727.2022.9975951 · Cited by 9 · see citing works
“Deep neural networks have demonstrated their ability to detect anomalies in supervised [24], semi-supervised [25], and unsupervised [26] domains.”
BackgroundLearning Discriminative Features for Semi-Supervised Anomaly Detection
Feng, Z., Tang, J., Dou, Y., & Wu, G. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414285 · Cited by 9 · see citing works
“Few approaches to anomaly detection have been proposed to make use of such labeled samples, and most of existing methods are domain-specific [1, 2].”
BackgroundAkamatsu, Y., Maeda, K., Ogawa, T., & Haseyama, M. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414361 · Cited by 9 · see citing works
Erkuş, E. C., & Purutçuoğlu, V. (2023) · Journal of Computational Science · doi:10.1016/j.jocs.2023.102084 · Cited by 8 · see citing works
FARMSAR: Fixing AgRicultural Mislabels Using Sentinel-1 Time Series and AutoencodeRs
Martino, T. D., Guinvarc’h, R., Thirion, L., & Colin‐Koeniguer, E. (2022) · Remote Sensing · doi:10.3390/rs15010035 · Cited by 8 · see citing works
EGDN-KL: Dynamic graph–deviation network for EEG anomaly detection
Naidji, I., Tibermacine, A., Tibermacine, I. E., Russo, S., & Napoli, C. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108597 · Cited by 7 · see citing works
Anomaly Detection through Grouping of SMD Machine Sounds Using Hierarchical Clustering
Song, Y. J., Nam, K. H., & Yun, I. D. (2023) · Applied Sciences · doi:10.3390/app13137569 · Cited by 7 · see citing works
An optimized deep belief network to detect anomalous behavior in social media
Sudha, M. S., & Valarmathi, K. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02708-2 · Cited by 7 · see citing works
Supervised Anomaly Detection with Highly Imbalanced Datasets Using Capsule Networks
Piciarelli, C., Mishra, P. K., & Foresti, G. L. (2021) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001421520108 · Cited by 6 · see citing works
Learning-Based Defense of False Data Injection Attacks in Power System State Estimation
Kundu, A., Sahu, A., Davis, K., & Serpedin, E. (2019) · North American Power Symposium (NAPS) · doi:10.1109/naps46351.2019.9000216 · Cited by 6 · see citing works
“Deep neural networks have been used in supervised [6], semi-supervised [7] and unsupervised setting [8] in the past for anomaly detection.”
MethodOutlier Detection via Deep Learning Architecture
Kakanakova, I., & Stoyanov, S. (2017) · International Conference on Computer Systems and Technologies (CompSysTech) · doi:10.1145/3134302.3134337 · Cited by 5 · see citing works
“In [17] one-class classification was used.”
Wu, D. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03049-4 · Cited by 5 · see citing works
Anomaly detection for internet surveillance
Bouma, H., Raaijmakers, S. A., Halma, A., & Wedemeijer, H. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.918573 · Cited by 4 · see citing works
“Applications of anomaly detection are widespread and vary from intrusion detection in computer networks [31], credit card fraud detection [30], medical applications such as EEG analysis [29], to forensic applications such as the detection of abnormal behavior in surveillance videos [2].”
A Survey on Different Techniques for Anomaly Detection
Pawar, P. P., & Phadke, A. C. (2023) · Algorithms for intelligent systems · doi:10.1007/978-981-99-2854-5_31 · Cited by 3 · see citing works
EEG Anomaly Detection using Generative Adversarial Networks (GANs)
Bidgoli, N. S., Kheradpisheh, S. R., & Farahani, H. (2024) · CSI International Symposium on Artificial Intelligence and Signal Processing · doi:10.1109/aisp61396.2024.10475243 · Cited by 3 · see citing works
“However, the brain waves of such patients have only occasional slips that are contrary to the background signal and are diagnostically significant [7].”
BackgroundRepresentation Learning With Autoencoders For Electronic Health Records
Sadatijafarkalaei, N. (2020) · Human Biology · Cited by 3 · see citing works
Anomaly Detection Based on PMF Encoding and Adversarially Learned Inference
Zhang, L., Yang, W., Gan, H., Li, M., Wang, X., & Liang, G. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1187/5/052037 · Cited by 2 · see citing works
“D WULSIN [16] used DBN as semi-supervised classification method to verify model performance on clinical medical image dataset.”
MethodMohandas, R. P., Elavarasi, M., Praveen, R., Chittapragada, H., Nithiya, C., & Prabagar, S. (2024) · International Conference on Mobile Networks and Wireless Communications (ICMNWC) · doi:10.1109/icmnwc63764.2024.10872058 · Cited by 2 · see citing works
“Class balancing strategies enhanced the identification of under-represented attack samples[17].”
Machine learning in translational bioinformatics
Ahmad, N., Mohanty, P., Kumar, N., & Gandotra, E. (2021) · Elsevier eBooks · doi:10.1016/b978-0-323-89824-9.00015-x · Cited by 2 · see citing works
Person-dependent seizure detection using statistical CUSUM detector: Preliminary results
Eldeeb, S. M., Sybeldon, M., Susam, B. T., Akcakaya, M., Wozny, T. A., Pan, J. W., Richardson, R. M., Bagic, A. I., & Antony, A. R. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115551 · Cited by 2 · see citing works
Introduction to Deep Learning in Health Informatics
Jyotiyana, M., & Kesswani, N. (2021) · doi:10.1002/9781119711278.ch9 · Cited by 2 · see citing works
Applications of AI and Deep Learning in Biomedicine and Healthcare
Pujahari, R. M., Khan, R., & Yadav, S. P. (2024) · Advances in bioinformatics and biomedical engineering book series · doi:10.4018/979-8-3693-2426-4.ch006 · Cited by 1 · see citing works
EEG anomaly detection using XGBoost and ConvLSTM model
Wu, W., Dai, J., Hasan, M., & Gu, X. (2026) · Annals of Operations Research · doi:10.1007/s10479-026-07248-0 · Cited by 1 · see citing works
Lu, K.-C., Wu, T.-W., & Cheng, C.-H. (2026) · doi:10.3390/engproc2026139004 · Cited by 1 · see citing works
Mining Neuroscience Data for Social Campaign Evaluation
Borawska, A. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.08.101 · Cited by 1 · see citing works
PASCL: Pathway-based Sparse Deep Clustering for Identifying Unknown Cancer Subtypes
Mallavarapu, T., Hao, J., Kim, Y. S., Oh, J. H., & Kang, M. (2018) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2018.8621387 · Cited by 1 · see citing works
“Consequently, personalized therapy may potentially lead to significantly different treatment outcomes for standardized treatment regimens [3], [4].”
BackgroundHybrid Stacking Model for Automatic Epileptic Seizure Detection Using Electroencephalogram Signals
Egorova, L. D., Kazakovtsev, L. A., STUPINA, A. A., Павлович, Р. И., & Savitskaya, T. N. (2024) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme62383.2024.10796593 · Cited by 1 · see citing works
“Specific EEG signal patterns allow clinicians to recognize signs of pathologies in the functioning of the brain [9].”
Advancing Spacecraft Security Through Anomaly Detection
Wiatrek, N., Burnett, K., Lin, S.-L., Liu, S., & Saenz, P. (2024) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa62245.2024.00077 · Cited by 1 · see citing works
APPLICATION OF DEEP LEARNING IN HEALTH INFORMATICS: A REVIEW
Mehta, V., & Shrivastava, N. (2021) · International Journal of Technical Research & Science · doi:10.30780/specialissue-icrdet-2021/002 · Cited by 1 · see citing works
“Wulsin et al. [17] proposed a DBN approach to detect anomalies in EEG waveforms.”
MethodImage anomaly detection with capsule networks and imbalanced datasetsPreprint
Piciarelli, C., Mishra, P. K., & Foresti, G. L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.02755 · Cited by 1 · see citing works
“cessing step to make the dataset balanced before applying any classification algorithm [4]. Regardingsemi-supervised orunsupervisedapproaches,earlyworksadopted techniques such as Deep Belief Networks [20] for medical diagnosis on EEG waveforms or Restricted Boltzmann Machines [11] for network traffic analysis. Morerec…”
MethodBrain Signals Analysis during Concentrated and Diluted Modes
AlHassan, H., & Gupta, N. (2025) · ASEE Northeast Section Meeting · doi:10.18260/1-2-1153-53374
Classifying single-trial event-related potentials using xDAWN and denoising auto-encoder
Cao, S., Wu, W., & Qi, F. (2017) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2017.8028248
“[8] have tried a novel attempt to utilize the Deep Belief Net (DBN) for the EEG classification and anomaly detection.”
MethodUnsupervised learning: application to epilepsy
Martínez-Toro, G. M., Rico-Bautista, D. W., Romero-Riaño, E., & Romero-Riaño, P. A. (2019) · Revista Colombiana de Computación · doi:10.29375/25392115.3718
IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite PropagationPreprint
Zhu, S., Zhao, H., & Liu, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.00360
“This idea is extended to the kernel version [16, 42], and deep representation [4, 9, 43, 47] as well.”
BackgroundDisease Diagnosis and Data Protection System for IoT-based Wearable Sensor Network
Khah, E. H., & Golsorkhtabaramiri, M. (2023) · International Conference on Technology and Energy Management (ICTEM) · doi:10.1109/ictem56862.2023.10083543
“Moreover, few studies have been performed on intraepithelial [6].”
BackgroundFDR Control for Online Anomaly DetectionPreprint
Krönert, E., Célisse, A., & Hattab, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.01969
Who is Legion?: Surfacing Demographic Voices in Large Language ModelsPreprint
Koehl, D. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4856328
Change Point Detection Based on Cluster Transition Distributions
Takahashi, S., Takeshita, K., Yamagishi, K., & Shiozu, A. (2024) · IEEE Access · doi:10.1109/access.2024.3455318
“…of normal data without any anomalies on the basis of its basic idea that a model of the normal class is learned first and anomalies can be detected afterwards by deviating from that model, and its well-known algorithms are One-class SVMs [20], Autoencoders (AEs) [21], and deep belief nets [22].”
MethodMa, H., Han, G., & Wang, J. (2025) · Mechanisms and machine science · doi:10.1007/978-3-031-81673-4_23
The Synergy of Autoencoders and Electronic Health Records for Improved Patient Care
Alkhawaji, R. N. (2025) · International Conference on Computing and Information Technology (ICCIT) · doi:10.1109/iccit63348.2025.10989336
“…the development of a general-purpose patient representation based on HER data, assessing and prioritizing risk factors for hypertension in African-Americans using EHRs, and assessment of clinical electroencephalography (EEG) in critically ill patients to detect anomalous brain activity [17-19].”
Deep Learning for Anomaly Detection: A Survey
Chalapathy, R., & Chawla, S. (2019) · arXiv · doi:10.48550/arxiv.1901.03407 · Cited by 1,240 · see citing works
“With sufficient training samples, of normal class autoencoders would produce low reconstruction errors for normal instances, over unusual events (Wulsin et al. [2010], Nadeem et al. [2016], Song et al. [2017]).”
BackgroundLSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection
Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., & Shroff, G. (2016) · arXiv · doi:10.48550/arxiv.1607.00148 · Cited by 819 · see citing works
“Non-temporal reconstruction models such as denoising au-toencoders for anomaly detection (Sakurada & Yairi, 2014) and Deep Belief Nets (Wulsin et al., 2010) have been proposed.”
Method
- Authors
- Wulsin, D., Blanco, J., Mani, R., & Litt, B.
- Affiliations
- University of Pennsylvania (US)
- Venue
- 2010 Ninth International Conference on Machine Learning and Applications
- Publisher
- IEEE
- Published
- 2010-12
- Pages
- 436-441
- OpenAlex
- W2171771147
- Cited by
- 98
- References
- 15
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 9 · 2023: 9 · 2022: 8 · 2021: 19 · 2020: 13 · 2019: 11 · 2018: 8 · 2017: 4 · 2016: 3 · 2015: 1 · 2014: 3 · 2013: 1 · 2012: 1
- FWCI
- 1.78
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Machine Learning and Applications (publishedVersion)
- Funders
- National Institutes of Health
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Keywords
- deep belief network, semi-supervised learning, one-class support vector machine, EEG feature extraction
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
