LSTM-Based Anomaly Detection for Non-Linear Dynamical System

Tan, Yue; Hu, Chunjing; Zheng, Kan; Davis, Ethan; Park, Jae Sung

doi:10.1109/access.2020.2999065

Cited by 19 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RAE and MRAE model may be useful for applications such as filling in missing measurements (data completion) or predicting future neural activity (forecasting). Reconstruction with MRAE is also a possible means of anomaly detection, where out-of-distribution neural recordings may be detected by their poor reconstruction accuracy [32]. Accurate dynamical models of neural signals also enable analysis of neural dynamics using nonlinear systems analysis, which has shed light on many complex cognitive processes [33].…”

Section: Discussionmentioning

confidence: 99%

Multi-block RNN Autoencoders Enable Broadband ECoG Signal Reconstruction

Nolan

Pesaran

Shlizerman

et al. 2022

Preprint

View full text Add to dashboard Cite

Objective: Neural dynamical models reconstruct neural data using dynamical systems. These models enable direct reconstruction and estimation of neural time-series data as well as estimation of neural latent states. Nonlinear neural dynamical models using recurrent neural networks in an encoder-decoder architecture have recently enabled accurate single-trial reconstructions of neural activity for neuronal spiking data. While these models have been applied to neural field potential data, they have only so far been applied to signal feature reconstruction (e.g. frequency band power), and have not yet produced direct reconstructions of broadband time-series data preserving signal phase and temporal resolution. Approach: Here we present two encoder-decoder model architectures - the RNN autoencoder (RAE) and multi-block RAE (MRAE) for direct time-series reconstruction of broadband neural data. We trained and tested models on multi-channel micro-Electrocorticography (μECoG) recordings from non-human primate motor corticies during unconstrained behavior. Main Results: We show that RAE reconstructs micro-electrocorticography recordings, but has reconstruction accuracy that is band-limited to model scale. The MRAE architecture overcomes these time-bandwidth restrictions, yielding broadband (0-100 Hz), accurate reconstructions of μECoG data. Significance: RAE and MRAE reconstruct broadband μECoG data through multiblock dynamical modeling. The MRAE overcomes time-bandwitdh restrictions to provide improved accuracy for long time duration signals. The reconstruction capabilities provided by these models for broadband neural signals like μECoG may enable the development of improved tools and analysis for basic scientific research and applications like brain-computer interfaces.

show abstract

Section: Discussionmentioning

confidence: 99%

Multi-block RNN Autoencoders Enable Broadband ECoG Signal Reconstruction

Nolan

Pesaran

Shlizerman

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Markov models can predict future states using previous information. It can establish transfer probability relationships between states [9,10]. Gu et al propose a stream-based mining algorithm combining Markov models and Bayesian classification methods, used for online anomaly prediction [11].…”

Section: Time Series Anomaly Detection Methodsmentioning

confidence: 99%

AC-LSTM: Anomaly State Perception of Infrared Point Targets Based on CNN+LSTM

et al. 2022

View full text Add to dashboard Cite

Anomaly perception of infrared point targets has high application value in many fields, such as maritime surveillance, airspace surveillance, and early warning systems. This kind of abnormality includes the explosion of the target, the separation between stages, the disintegration caused by the abnormal strike, etc. By extracting the radiation characteristics of continuous frame targets, it is possible to analyze and warn the target state in time. Most anomaly detection methods adopt traditional outlier detection, which has the problems of poor accuracy and a high false alarm rate. Driven by data, this paper proposes a new network structure, called AC-LSTM, which combines Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM), and embeds the Periodic Time Series Data Attention module (PTSA). The network can better extract the spatial and temporal characteristics of one-dimensional time series data, and the PTSA module can consider the periodic characteristics of the target in the process of continuous movement, and focus on abnormal data. In addition, this paper also proposes a new time series data enhancement method, which slices and re-amplifies the long time series data. This method significantly improves the accuracy of anomaly detection. Through a large number of experiments, AC-LSTM has achieved higher scores on our collected datasets than other methods.

show abstract

“…The LSTM-based method delivers higher prediction accuracy for distinct zones of the time series than standard prediction methods and has been widely applied in the anomaly detection research field [32]. The LSTM design is based on a memory cell that can preserve its state over time and nonlinear gating devices that control the flow of information into and out of the cell.…”

Section: Long-short Term Memory (Lstm)mentioning

confidence: 99%

Machine Learning Techniques for Detecting Attackers During Quantum Key Distribution in IoT Networks With Application to Railway Scenarios

Al-Mohammed

Al-Ali

Yaacoub³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Internet of Things (IoT) deployments face significant security challenges due to the limited energy and computational power of IoT devices. These challenges are more serious in the quantum communications era, where certain attackers might have quantum computing capabilities, which renders IoT devices more vulnerable. This paper addresses the problem of IoT security by investigating quantum key distribution (QKD) in beyond 5G networks. An algorithm for detecting an attacker between a transmitter and receiver is proposed, with the side effect of interrupting the QKD process while detecting the attacker. Afterwards, Artificial neural network (ANN) and deep learning (DL) techniques are proposed in order to detect the presence of an attacker during QKD without the need to disrupt the key distribution process. An architecture for implementing QKD in beyond 5G IoT networks is proposed, offloading the heavy computational tasks to IoT controllers. In addition, an implementation scenario for securing IoT communications for sensors deployed in railroad networks is described. The results show that the proposed ML techniques can reach 99% accuracy in detecting attackers.INDEX TERMS 5G and beyond, IoT security, Quantum key distribution, Machine Learning, railway communications.

show abstract

LSTM-Based Anomaly Detection for Non-Linear Dynamical System

Cited by 19 publications

References 27 publications

Multi-block RNN Autoencoders Enable Broadband ECoG Signal Reconstruction

Multi-block RNN Autoencoders Enable Broadband ECoG Signal Reconstruction

AC-LSTM: Anomaly State Perception of Infrared Point Targets Based on CNN+LSTM

Machine Learning Techniques for Detecting Attackers During Quantum Key Distribution in IoT Networks With Application to Railway Scenarios

Contact Info

Product

Resources

About