scholarly journals Reconstructive Reservoir Computing to Detect Anomaly in Time-series Signals

2022 ◽  
Author(s):  
Junya Kato ◽  
Gouhei Tanaka ◽  
Ryosho Nakane ◽  
Akira Hirose
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Large Range ◽  
Reconstruction Error ◽  
Time Shift ◽  
Reservoir Computing ◽  
Fundamental Properties ◽  
Echo State Networks ◽  
The Difference ◽  
Normal Input

We propose reconstructive reservoir computing (RRC) for anomaly detection working for time-series signals. This paper investigates its fundamental properties with experiments employing echo state networks (ESNs). The RRC model is a reconstructor to replicate a normal input time-series signal with no delay or a certain delay (delay ≥ 0). In its anomaly detection process, we evaluate instantaneous reconstruction error defined as the difference between input and output signals at each time. Experiments with a sound dataset from industrial machines demonstrate that the error is low for normal signals while it becomes higher for abnormal ones, showing successful anomaly detection. It is notable that the RRC models’ behavior is very different from that of conventional anomaly detection models, that is, those based on forecasting (delay < 0). The error of the proposed reconstructor is explicitly lower than that of a forecaster, resulting in superior distinction between normal and abnormal states. We show that the RRC model is effective over a large range of reservoir parameters. We also illustrate the distribution of the output weights optimized through a training to discuss their roles in the reconstruction. Then, we investigate the influence of the neuronal leaking rate and the delay time shift amount on the transient response and the reconstruction error, showing high effectiveness of the reconstructor in anomaly detection. The proposed RRC will play a significant role for anomaly detection in the present and future sensor network society

scholarly journals Reconstructive Reservoir Computing to Detect Anomaly in Time-series Signals

2022 ◽  
Author(s):  
Junya Kato ◽  
Gouhei Tanaka ◽  
Ryosho Nakane ◽  
Akira Hirose
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Large Range ◽  
Reconstruction Error ◽  
Time Shift ◽  
Reservoir Computing ◽  
Fundamental Properties ◽  
Echo State Networks ◽  
The Difference ◽  
Normal Input

We propose reconstructive reservoir computing (RRC) for anomaly detection working for time-series signals. This paper investigates its fundamental properties with experiments employing echo state networks (ESNs). The RRC model is a reconstructor to replicate a normal input time-series signal with no delay or a certain delay (delay ≥ 0). In its anomaly detection process, we evaluate instantaneous reconstruction error defined as the difference between input and output signals at each time. Experiments with a sound dataset from industrial machines demonstrate that the error is low for normal signals while it becomes higher for abnormal ones, showing successful anomaly detection. It is notable that the RRC models’ behavior is very different from that of conventional anomaly detection models, that is, those based on forecasting (delay < 0). The error of the proposed reconstructor is explicitly lower than that of a forecaster, resulting in superior distinction between normal and abnormal states. We show that the RRC model is effective over a large range of reservoir parameters. We also illustrate the distribution of the output weights optimized through a training to discuss their roles in the reconstruction. Then, we investigate the influence of the neuronal leaking rate and the delay time shift amount on the transient response and the reconstruction error, showing high effectiveness of the reconstructor in anomaly detection. The proposed RRC will play a significant role for anomaly detection in the present and future sensor network society

scholarly journals FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting

2016 ◽  
Vol 2016 ◽  
pp. 1-14 ◽  
Author(s):  
Miquel L. Alomar ◽  
Vincent Canals ◽  
Nicolas Perez-Mora ◽  
Víctor Martínez-Moll ◽  
Josep L. Rosselló
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Power Dissipation ◽  
Hardware Implementation ◽  
Functional System ◽  
Time Series Forecasting ◽  
Reservoir Computing ◽  
New Approach ◽  
Echo State Networks ◽  
Learning Capabilities

Hardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a strategic technique to design recurrent neural networks (RNNs) with simple learning capabilities. In this work, we show a new approach to implement RC systems with digital gates. The proposed method is based on the use of probabilistic computing concepts to reduce the hardware required to implement different arithmetic operations. The result is the development of a highly functional system with low hardware resources. The presented methodology is applied to chaotic time-series forecasting.

Variance error of multi-classification based anomaly detection for time series data

2020 ◽  
pp. 1-16
Author(s):  
Baoquan Wang ◽  
Tonghai Jiang ◽  
Xi Zhou ◽  
Bo Ma ◽  
Fan Zhao ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Short Term Memory ◽  
Computational Cost ◽  
Reconstruction Error ◽  
Detection Methods ◽  
Series Data ◽  
Data Set

For abnormal detection of time series data, the supervised anomaly detection methods require labeled data. While the range of outlier factors used by the existing semi-supervised methods varies with data, model and time, the threshold for determining abnormality is difficult to obtain, in addition, the computational cost of the way to calculate outlier factors from other data points in the data set is also very large. These make such methods difficult to practically apply. This paper proposes a framework named LSTM-VE which uses clustering combined with visualization method to roughly label normal data, and then uses the normal data to train long short-term memory (LSTM) neural network for semi-supervised anomaly detection. The variance error (VE) of the normal data category classification probability sequence is used as outlier factor. The framework enables anomaly detection based on deep learning to be practically applied and using VE avoids the shortcomings of existing outlier factors and gains a better performance. In addition, the framework is easy to expand because the LSTM neural network can be replaced with other classification models. Experiments on the labeled and real unlabeled data sets prove that the framework is better than replicator neural networks with reconstruction error (RNN-RS) and has good scalability as well as practicability.

scholarly journals Unsupervised Anomaly Detection Approach for Time-Series in Multi-Domains Using Deep Reconstruction Error

Symmetry ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 1251 ◽  
Author(s):  
Tsatsral Amarbayasgalan ◽  
Van Huy Pham ◽  
Nipon Theera-Umpon ◽  
Keun Ho Ryu
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Real Time ◽  
Reconstruction Error ◽  
Ar Model ◽  
Detection Methods ◽  
Series Data ◽  
Detection Approach ◽  
Unsupervised Anomaly Detection ◽  
Anomaly Detector

Automatic anomaly detection for time-series is critical in a variety of real-world domains such as fraud detection, fault diagnosis, and patient monitoring. Current anomaly detection methods detect the remarkably low proportion of the actual abnormalities correctly. Furthermore, most of the datasets do not provide data labels, and require unsupervised approaches. By focusing on these problems, we propose a novel deep learning-based unsupervised anomaly detection approach (RE-ADTS) for time-series data, which can be applicable to batch and real-time anomaly detections. RE-ADTS consists of two modules including the time-series reconstructor and anomaly detector. The time-series reconstructor module uses the autoregressive (AR) model to find an optimal window width and prepares the subsequences for further analysis according to the width. Then, it uses a deep autoencoder (AE) model to learn the data distribution, which is then used to reconstruct a time-series close to the normal. For anomalies, their reconstruction error (RE) was higher than that of the normal data. As a result of this module, RE and compressed representation of the subsequences were estimated. Later, the anomaly detector module defines the corresponding time-series as normal or an anomaly using a RE based anomaly threshold. For batch anomaly detection, the combination of the density-based clustering technique and anomaly threshold is employed. In the case of real-time anomaly detection, only the anomaly threshold is used without the clustering process. We conducted two types of experiments on a total of 52 publicly available time-series benchmark datasets for the batch and real-time anomaly detections. Experimental results show that the proposed RE-ADTS outperformed the state-of-the-art publicly available anomaly detection methods in most cases.

scholarly journals BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series

2019 ◽  
Author(s):  
Bin Zhou ◽  
Shenghua Liu ◽  
Bryan Hooi ◽  
Xueqi Cheng ◽  
Jing Ye
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Large Scale ◽  
Data Augmentation ◽  
Time Series Data ◽  
Detection Algorithm ◽  
Reconstruction Error ◽  
Series Data ◽  
Lower Accuracy ◽  
Unsupervised Anomaly Detection

Given a large-scale rhythmic time series containing mostly normal data segments (or `beats'), can we learn how to detect anomalous beats in an effective yet efficient way? For example, how can we detect anomalous beats from electrocardiogram (ECG) readings? Existing approaches either require excessively high amounts of labeled and balanced data for classification, or rely on less regularized reconstructions, resulting in lower accuracy in anomaly detection. Therefore, we propose BeatGAN, an unsupervised anomaly detection algorithm for time series data. BeatGAN outputs explainable results to pinpoint the anomalous time ticks of an input beat, by comparing them to adversarially generated beats. Its robustness is guaranteed by its regularization of reconstruction error using an adversarial generation approach, as well as data augmentation using time series warping. Experiments show that BeatGAN accurately and efficiently detects anomalous beats in ECG time series, and routes doctors' attention to anomalous time ticks, achieving accuracy of nearly 0.95 AUC, and very fast inference (2.6 ms per beat). In addition, we show that BeatGAN accurately detects unusual motions from multivariate motion-capture time series data, illustrating its generality.

HAAR WAVELET ANALYSIS OF CLIMATIC TIME SERIES

2014 ◽  
Vol 12 (02) ◽  
pp. 1450020 ◽  
Author(s):  
ZHIHUA ZHANG ◽  
JOHN C. MOORE ◽  
ASLAK GRINSTED
Keyword(s):  
Time Series ◽  
Arctic Oscillation ◽  
Regime Shift ◽  
Power Spectra ◽  
Haar Wavelet ◽  
Analytic Formula ◽  
Fundamental Properties ◽  
Statistical Framework ◽  
The Difference ◽  
Climatic Time Series

In order to extract the intrinsic information of climatic time series from background red noise, in this paper, we will first give an analytic formula on the distribution of Haar wavelet power spectra of red noise in a rigorous statistical framework. After that, by comparing the difference of wavelet power spectra of real climatic time series and red noise, we can extract intrinsic features of climatic time series. Finally, we use our method to analyze Arctic Oscillation (AO) which is a key aspect of climate variability in the Northern Hemisphere, and discover a great change in fundamental properties of the AO, commonly called a regime shift or tripping point.

An Anomaly Detection Method with Exemplar Subsequence for Time Series Data

2016 ◽  
Vol 136 (3) ◽  
pp. 363-372
Author(s):  
Takaaki Nakamura ◽  
Makoto Imamura ◽  
Masashi Tatedoko ◽  
Norio Hirai
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Detection Method ◽  
Series Data

EVALUASI PROYEKSI DEMAND BARANG DAN PENUMPANG PELABUHAN DI PROVINSI MALUKU

2019 ◽  
Vol 19 (2) ◽  
pp. 101-110
Author(s):  
Adrian Firdaus ◽  
M. Dwi Yoga Sutanto ◽  
Rajin Sihombing ◽  
M. Weldy Hermawan
Keyword(s):  
Time Series ◽  
Projection Method ◽  
Development Plan ◽  
Master Plan ◽  
Port Development ◽  
Loading And Unloading ◽  
The Difference ◽  
Existing Data

Abstract Every port in Indonesia must have a Port Master Plan that contains an integrated port development plan. This study discusses one important aspect in the preparation of the Port Master Plan, namely the projected movement of goods and passengers, which can be used as a reference in determining the need for facilities at each stage of port development. The case study was conducted at a port located in a district in Maluku Province and aims to evaluate the analysis of projected demand for goods and passengers occurring at the port. The projection method used is time series and econometric projection. The projection results are then compared with the existing data in 2018. The results of this study show that the econometric projection gives adequate results in predicting loading and unloading activities as well as the number of passenger arrival and departure in 2018. This is indicated by the difference in the percentage of projection results towards the existing data, which is smaller than 10%. Whereas for loading and unloading activities, time series projections with logarithmic trends give better results than econometric projections. Keywords: port, port master plan, port development, unloading activities  Abstrak Setiap pelabuhan di Indonesia harus memiliki sebuah Rencana Induk Pelabuhan yang memuat rencana pengem-bangan pelabuhan secara terpadu. Studi ini membahas salah satu aspek penting dalam penyusunan Rencana Induk Pelabuhan, yaitu proyeksi pergerakan barang dan penumpang, yang dapat dipakai sebagai acuan dalam penentuan kebutuhan fasilitas di setiap tahap pengembangan pelabuhan. Studi kasus dilakukan pada sebuah pelabuhan yang terletak di sebuah kabupaten di Provinsi Maluku dan bertujuan untuk melakukan evaluasi ter-hadap analisis proyeksi demand barang dan penumpang yang terjadi di pelabuhan tersebut. Metode proyeksi yang dipakai adalah proyeksi deret waktu dan ekonometrik. Hasil proyeksi selanjutnya dibandingkan dengan data eksisting tahun 2018. Hasil studi ini menunjukkan bahwa proyeksi ekonometrik memberikan hasil yang cukup baik dalam memprediksi aktivitas bongkar barang serta jumlah penumpang naik dan turun di tahun 2018. Hal ini diindikasikan dengan selisih persentase hasil proyeksi terhadap data eksisting yang lebih kecil dari 10%. Sedangkan untuk aktivitas muat barang, proyeksi deret waktu dengan tren logaritmik memberikan hasil yang lebih baik daripada proyeksi ekonometrik. Kata-kata kunci: pelabuhan, rencana induk pelabuhan, pengembangan pelauhan, aktivitas bongkar barang

Sign in / Sign up

Export Citation Format

Share Document