2,257 Hits in 4.1 sec

Deep Federated Anomaly Detection for Multivariate Time Series Data [article]

Wei Zhu, Dongjin Song, Yuncong Chen, Wei Cheng, Bo Zong, Takehiko Mizoguchi, Cristian Lumezanu, Haifeng Chen, Jiebo Luo
2022 arXiv   pre-print
Despite the fact that many anomaly detection approaches have been developed for multivariate time series data, limited effort has been made on federated settings in which multivariate time series data  ...  In this paper, we investigate the problem of federated unsupervised anomaly detection and present a Federated Exemplar-based Deep Neural Network (Fed-ExDNN) to conduct anomaly detection for multivariate  ...  Introduction Anomaly detection in multivariate time series refers to identifying abnormal status in certain time steps of the time series data [1, 2] .  ... 
arXiv:2205.04041v1 fatcat:aeuvv3tqk5e6bbh3sddx6ctu5a

Federated Variational Learning for Anomaly Detection in Multivariate Time Series [article]

Kai Zhang, Yushan Jiang, Lee Seversky, Chengtao Xu, Dahai Liu, Houbing Song
2021 arXiv   pre-print
and temporal dependencies in the multivariate time series data for representation learning and downstream anomaly detection tasks.  ...  Anomaly detection has been a challenging task given high-dimensional multivariate time series data generated by networked sensors and actuators in Cyber-Physical Systems (CPS).  ...  In the future, we plan to investigate solutions to tackle the data heterogeneity problem in the federated deep generative model for time series anomaly detection.  ... 
arXiv:2108.08404v2 fatcat:jq2liwv24fhn7hkvgwbv667n5u

A Comprehensive Study of Anomaly Detection Schemes in IoT Networks Using Machine Learning Algorithms

Abebe Diro, Naveen Chilamkurti, Van-Doan Nguyen, Will Heyne
2021 Sensors  
In this paper, we aim to provide an in-depth review of existing works in developing anomaly detection solutions using machine learning for protecting an IoT system.  ...  We also indicate that blockchain-based anomaly detection systems can collaboratively learn effective machine learning models to detect anomalies.  ...  The IoT anomaly detection using univariate series compares current data against historical time series.  ... 
doi:10.3390/s21248320 pmid:34960414 pmcid:PMC8708212 fatcat:vogif3xvhbdvvb324iwpyq5vkm

DeepFIB: Self-Imputation for Time Series Anomaly Detection [article]

Minhao Liu, Zhijian Xu, Qiang Xu
2021 arXiv   pre-print
Time series (TS) anomaly detection (AD) plays an essential role in various applications, e.g., fraud detection in finance and healthcare monitoring.  ...  To tackle this problem, we propose a novel self-supervised learning technique for AD in time series, namely DeepFIB.  ...  A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data. AAAI, abs/1811.08055, 2019. R. Zhang, P. Isola, and A.A. Efros.  ... 
arXiv:2112.06247v1 fatcat:k7gmfcsnajafdp5qgwq4iuq4f4

TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data [article]

Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
2022 arXiv   pre-print
Efficient anomaly detection and diagnosis in multivariate time-series data is of great importance for modern industrial applications.  ...  Despite the recent developments of deep learning approaches for anomaly detection, only a few of them can address all of these challenges.  ...  We thank Kate Highnam for constructive comments on improving the manuscript writing. We thank the providers of all datasets used in this work.  ... 
arXiv:2201.07284v6 fatcat:eenjcq4u6bd6rk4vwxkts2gokm

Unsupervised Anomaly Detection in Flight Data Using Convolutional Variational Auto-Encoder

Milad Memarzadeh, Bryan Matthews, Ilya Avrekh
2020 Aerospace (Basel)  
To address this challenge, we develop a Convolutional Variational Auto-Encoder (CVAE), an unsupervised deep generative model for anomaly detection in high-dimensional time-series data.  ...  precision and recall of detecting anomalies.  ...  We would also like to thank Hamed Valizadegan, Thomas Templin, Daniel Weckler, and Marc-Henri Bleu-Laine for their insights and comments in developing and testing the algorithm.  ... 
doi:10.3390/aerospace7080115 fatcat:4a2pwunjijckzptfzm3bcbnm7m

Data science and AI in FinTech: An overview [article]

Longbing Cao, Qiang Yang, Philip S. Yu
2021 arXiv   pre-print
blockchain, and the DSAI techniques including complex system methods, quantitative methods, intelligent interactions, recognition and responses, data analytics, deep learning, federated learning, privacy-preserving  ...  The research on data science and AI in FinTech involves many latest progress made in smart FinTech for BankingTech, TradeTech, LendTech, InsurTech, WealthTech, PayTech, RiskTech, cryptocurrencies, and  ...  frequency and wavelet and Fourier transform for audio and time-series data.  ... 
arXiv:2007.12681v2 fatcat:jntzuwaktjg2hmmjypi5lvyht4

IoTSDA: IoT-Edge analytics architecture for anomaly detection of univariate health data

2021 Turkish Journal of Electrical Engineering and Computer Sciences  
Presence of abnormal data points can create noise in a time series data set.  ...  This article aims at detection of anomalies from a time series 7 health data set collected from a pulse sensor integrated IoT-based device. We use the seasonal-decomposition by Loess 8 i.e.  ...  Deep anomaly detection for time-series data in 24 industrial iot: a communication-efficient on-device federated learning approach.  ... 
doi:10.3906/elk-2106-87 fatcat:lg5ijzqzfza2loyghh4vxd5vxm

Double deep q-learning with prioritized experience replay for anomaly detection in smart environments

Daniel Fahrmann, Nils Jorek, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
2022 IEEE Access  
Our proposed anomaly detector directly learns a decision-making function, which can classify rare events based on multivariate sequential time series data.  ...  In this work, we propose the adaption of a deep reinforcement learning algorithm, namely double deep q-learning (DDQN), for anomaly detection in smart environments.  ...  support of the National Research Center for Applied Cybersecurity ATHENE.  ... 
doi:10.1109/access.2022.3179720 fatcat:2qbap4vggbfj7jslhldq6zuiem

Table of Contents

2020 2020 International Conference on Data Mining Workshops (ICDMW)  
Time Evolving Data (CLEATED 2020) An Unsupervised Methodology for Online Drift Detection in Multivariate Industrial Datasets 392 Sarah Klein (Data and AI Competence Lab (EluciDATA Lab), Sirris) and  ...  Detection of Periodic Multivariate Time Series Under High Acquisition Frequency Scene in IoT 543 Shuo Zhang (Harbin Institute of Technology, China), XiaoFei Chen (Harbin Institute of Technology, China  ... 
doi:10.1109/icdmw51313.2020.00004 fatcat:ykrkkp5hx5asrpvw6r3oo4rwcq

Unsupervised Anomaly Detection of Industrial Robots using Sliding-Window Convolutional Variational Autoencoder

Tingting Chen, Xueping Liu, Bizhong Xia, Wei Wang, Yongzhi Lai
2020 IEEE Access  
and temporally by coping with multivariate time series data.  ...  Besides, the used technique for anomaly detection of robots should be required to not only capture the temporal dependency in collected time series data, but also the inter-correlations between different  ...  Since multivariate time series have the same 2-dimensional data structures as image, CNN for analyzing images is suitable for handling multivariate time series as well. IV.  ... 
doi:10.1109/access.2020.2977892 fatcat:5a74eirhvfdkdho2mb7uzz7ehy

TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks [article]

Alexander Geiger, Dongyu Liu, Sarah Alnegheimish, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
2020 arXiv   pre-print
TadGAN is trained with cycle consistency loss to allow for effective time-series data reconstruction.  ...  However, detecting anomalies in time series data is particularly challenging due to the vague definition of anomalies and said data's frequent lack of labels and highly complex temporal correlations.  ...  Cuesta-Infante is funded by the Spanish Government research fundings RTI2018-098743-B-I00 (MICINN/FEDER) and Y2018/EMT-5062 (Comunidad de Madrid).  ... 
arXiv:2009.07769v3 fatcat:6grbkqexcvehzbpt6vh5bedkpq

A Federated Learning Approach to Anomaly Detection in Smart Buildings [article]

Raed Abdel Sater, A. Ben Hamza
2021 arXiv   pre-print
These devices sense the environment and generate multivariate temporal data of paramount importance for detecting anomalies and improving the prediction of energy usage in smart buildings.  ...  However, detecting these anomalies in centralized systems is often plagued by a huge delay in response time.  ...  Detecting anomalies has become a central research question in IoT applications, particularly from IoT time-series data [10, 20, 34] .  ... 
arXiv:2010.10293v3 fatcat:zmwqhebvrbgcrgc3pjr6eqchcu

Privacy reinforcement learning for faults detection in the smart grid

Asma Belhadi, Youcef Djenouri, Gautam Srivastava, Alireza Jolfaei, Jerry Chun-Wei Lin
2021 Ad hoc networks  
Fault detection in these types of energy systems has recently shown lots of interest in the data science community, where anomalous behavior from energy platforms is identified.  ...  A B S T R A C T Recent anticipated advancements in ad hoc Wireless Mesh Networks (WMN) have made them strong natural candidates for Smart Grid's Neighborhood Area Network (NAN) and the ongoing work on  ...  [13] developed an anomaly detection approach for mixed-type time series data.  ... 
doi:10.1016/j.adhoc.2021.102541 fatcat:e3y7ugsccnhhxiewjyu4y5ckby

Smart anomaly detection in sensor systems: A multi-perspective review

L. Erhan, M. Ndubuaku, M. Di Mauro, W. Song, M. Chen, G. Fortino, O. Bagdasar, A. Liotta
2020 Information Fusion  
We taxonomize methods ranging from conventional techniques (statistical methods, time-series analysis, signal processing, etc.) to data-driven techniques (supervised learning, reinforcement learning, deep  ...  Anomaly detection is concerned with identifying data patterns that deviate remarkably from the expected behaviour.  ...  RNN and LSTM have been demonstrated to perform well in detecting anomalies in multivariate time series sensor data [60] . Goh et al.  ... 
doi:10.1016/j.inffus.2020.10.001 fatcat:r65qp56ipzebnasd33o3wxkfo4
« Previous Showing results 1 — 15 out of 2,257 results