scholarly journals Semi-Supervised Time Series Anomaly Detection Based on Statistics and Deep Learning

2021 ◽  
Vol 11 (15) ◽  
pp. 6698
Author(s):  
Jehn-Ruey Jiang ◽  
Jian-Bin Kao ◽  
Yu-Lin Li
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Stationary Time Series ◽  
Test Time ◽  
Pearson Product Moment Correlation ◽  
Novel Technologies ◽  
Univariate Time Series ◽  
Comparison Results ◽  
Over Time

Thanks to the advance of novel technologies, such as sensors and Internet of Things (IoT) technologies, big amounts of data are continuously gathered over time, resulting in a variety of time series. A semi-supervised anomaly detection framework, called Tri-CAD, for univariate time series is proposed in this paper. Based on the Pearson product-moment correlation coefficient and Dickey–Fuller test, time series are first categorized into three classes: (i) periodic, (ii) stationary, and (iii) non-periodic and non-stationary time series. Afterwards, different mechanisms using statistics, wavelet transform, and deep learning autoencoder concepts are applied to different classes of time series for detecting anomalies. The performance of the proposed Tri-CAD framework is evaluated by experiments using three Numenta anomaly benchmark (NAB) datasets. The performance of Tri-CAD is compared with those of related methods, such as STL, SARIMA, LSTM, LSTM with STL, and ADSaS. The comparison results show that Tri-CAD outperforms the others in terms of the precision, recall, and F1-score.

scholarly journals An Enterprise Time Series Forecasting System for Cloud Applications Using Transfer Learning

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1590
Author(s):  
Arnak Poghosyan ◽  
Ashot Harutyunyan ◽  
Naira Grigoryan ◽  
Clement Pang ◽  
George Oganesyan ◽  
...  
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Transfer Learning ◽  
Performance Monitoring ◽  
Nonlinear Problems ◽  
Time Series Forecasting ◽  
Stationary Time Series ◽  
Learning Gain ◽  
Application Performance ◽  
Cloud Applications

The main purpose of an application performance monitoring/management (APM) software is to ensure the highest availability, efficiency and security of applications. An APM software accomplishes the main goals through automation, measurements, analysis and diagnostics. Gartner specifies the three crucial capabilities of APM softwares. The first is an end-user experience monitoring for revealing the interactions of users with application and infrastructure components. The second is application discovery, diagnostics and tracing. The third key component is machine learning (ML) and artificial intelligence (AI) powered data analytics for predictions, anomaly detection, event correlations and root cause analysis. Time series metrics, logs and traces are the three pillars of observability and the valuable source of information for IT operations. Accurate, scalable and robust time series forecasting and anomaly detection are the requested capabilities of the analytics. Approaches based on neural networks (NN) and deep learning gain an increasing popularity due to their flexibility and ability to tackle complex nonlinear problems. However, some of the disadvantages of NN-based models for distributed cloud applications mitigate expectations and require specific approaches. We demonstrate how NN-models, pretrained on a global time series database, can be applied to customer specific data using transfer learning. In general, NN-models adequately operate only on stationary time series. Application to nonstationary time series requires multilayer data processing including hypothesis testing for data categorization, category specific transformations into stationary data, forecasting and backward transformations. We present the mathematical background of this approach and discuss experimental results based on implementation for Wavefront by VMware (an APM software) while monitoring real customer cloud environments.

scholarly journals Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 120043-120065
Author(s):  
Kukjin Choi ◽  
Jihun Yi ◽  
Changhwa Park ◽  
Sungroh Yoon
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Series Data ◽  
Review Analysis

scholarly journals Anomaly detection in server metrics with use of one-sided median algorithm

2017 ◽  
Vol 9 (1) ◽  
pp. 5-22
Author(s):  
Szymon Zacher ◽  
Przemysław Ryba
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Detection Rate ◽  
Short Description ◽  
Algorithm Performance ◽  
Mail Service ◽  
Over Time ◽  
Simple Production ◽  
Good Detection

AbstractIn this paper we consider the problem of anomaly detection over time series metrics data took from one of corporate grade mail service cluster. We propose the algorithm based on one-sided median concept and present some results of experiments showing impact of parameters settings on algorithm performance. In addition we present short description of classes of anomalies discovered in monitored system. Proposed one-sided median based algorithm shows great robustness and good detection rate and can be considered as possible simple production ready solution.

Forecasting Areawide Hospital Utilization: A Comparison of Five Univariate Time Series Techniques

1993 ◽  
Vol 6 (3) ◽  
pp. 178-190 ◽  
Author(s):  
Thomas W. Weiss ◽  
Carol M. Ashton ◽  
Nelda P. Wray
Keyword(s):  
Time Series ◽  
Average Length ◽  
Discharge Rate ◽  
Veterans Affairs ◽  
Economic Modeling ◽  
Hospital Utilization ◽  
Patient Treatment ◽  
Department Of Veterans Affairs ◽  
Univariate Time Series ◽  
Over Time

Time series analysis is one of the methods health services researchers, managers and planners have to examine and predict utilization over time. The focus of this study is univariate time series techniques, which model the change in a dependent variable over time, using time as the only independent variable. These techniques can be used with administrative healthcare databases, which typically contain reliable, time-specific utilization variables, but may lack adequate numbers of variables needed for behavioral or economic modeling. The inpatient discharge database of the Department of Veterans Affairs, the Patient Treatment File, was used to calculate monthly time series over a six-year period for the nation and across US Census Bureau regions for three hospital utilization indicators: Average length of stay, discharge rate, and multiple stay ratio, a measure of readmissions. The first purpose of this study was to determine the accuracy of forecasting these indicators 24 months into the future using five univariate time series techniques. In almost all cases, techniques were able to forecast the magnitude and direction of future utilization within a 10% mean monthly error. The second purpose of the study was to describe time series of the three hospital utilization indicators. This approach raised several questions concerning Department of Veterans Affairs hospital utilization.

Sign in / Sign up

Export Citation Format

Share Document