Model-free offline change-point detection in multidimensional time series of arbitrary nature via ϵ -complexity: Simulations and applications

2018 ◽  
Vol 34 (5) ◽  
pp. 633-644 ◽  
Author(s):  
Boris Darkhovsky ◽  
Alexandra Piryatinska
Keyword(s):  
Time Series ◽  
Change Point ◽  
Change Point Detection ◽  
Model Free ◽  
Multidimensional Time Series ◽  
Point Detection

scholarly journals Retrospective Change-Points Detection for Multidimensional Time Series of Arbitrary Nature: Model-Free Technology Based on the ϵ-Complexity Theory

Entropy ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. 1626
Author(s):  
Alexandra Piryatinska ◽  
Boris Darkhovsky
Keyword(s):  
Time Series ◽  
Change Point ◽  
Change Point Detection ◽  
Change Points ◽  
Detection Problem ◽  
Model Free ◽  
Multidimensional Time Series ◽  
Simulation Results ◽  
Point Detection ◽  
Present Simulation

We consider a retrospective change-point detection problem for multidimensional time series of arbitrary nature (in particular, panel data). Change-points are the moments at which the changes in generating mechanism occur. Our method is based on the new theory of ϵ-complexity of individual continuous vector functions and is model-free. We present simulation results confirming the effectiveness of the method.

scholarly journals Change point detection with multiple alternatives reveals parallel evaluation of the same stream of evidence along distinct timescales

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Alexa Booras ◽  
Tanner Stevenson ◽  
Connor N. McCormack ◽  
Marie E. Rhoads ◽  
Timothy D. Hanks
Keyword(s):  
Change Point ◽  
Neural Mechanism ◽  
Detection Task ◽  
Change Point Detection ◽  
Model Free ◽  
Evidence Evaluation ◽  
Parallel Evaluation ◽  
Point Detection ◽  
Improved Accuracy

AbstractIn order to behave appropriately in a rapidly changing world, individuals must be able to detect when changes occur in that environment. However, at any given moment, there are a multitude of potential changes of behavioral significance that could occur. Here we investigate how knowledge about the space of possible changes affects human change point detection. We used a stochastic auditory change point detection task that allowed model-free and model-based characterization of the decision process people employ. We found that subjects can simultaneously apply distinct timescales of evidence evaluation to the same stream of evidence when there are multiple types of changes possible. Informative cues that specified the nature of the change led to improved accuracy for change point detection through mechanisms involving both the timescales of evidence evaluation and adjustments of decision bounds. These results establish three important capacities of information processing for decision making that any proposed neural mechanism of evidence evaluation must be able to support: the ability to simultaneously employ multiple timescales of evidence evaluation, the ability to rapidly adjust those timescales, and the ability to modify the amount of information required to make a decision in the context of flexible timescales.

scholarly journals Change Point Enhanced Anomaly Detection for IoT Time Series Data

Water ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 1633
Author(s):  
Elena-Simona Apostol ◽  
Ciprian-Octavian Truică ◽  
Florin Pop ◽  
Christian Esposito
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Change Point ◽  
Time Series Data ◽  
Multivariate Time Series ◽  
Change Point Detection ◽  
Change Points ◽  
Series Data ◽  
Prediction And Forecasting ◽  
Point Detection

Due to the exponential growth of the Internet of Things networks and the massive amount of time series data collected from these networks, it is essential to apply efficient methods for Big Data analysis in order to extract meaningful information and statistics. Anomaly detection is an important part of time series analysis, improving the quality of further analysis, such as prediction and forecasting. Thus, detecting sudden change points with normal behavior and using them to discriminate between abnormal behavior, i.e., outliers, is a crucial step used to minimize the false positive rate and to build accurate machine learning models for prediction and forecasting. In this paper, we propose a rule-based decision system that enhances anomaly detection in multivariate time series using change point detection. Our architecture uses a pipeline that automatically manages to detect real anomalies and remove the false positives introduced by change points. We employ both traditional and deep learning unsupervised algorithms, in total, five anomaly detection and five change point detection algorithms. Additionally, we propose a new confidence metric based on the support for a time series point to be an anomaly and the support for the same point to be a change point. In our experiments, we use a large real-world dataset containing multivariate time series about water consumption collected from smart meters. As an evaluation metric, we use Mean Absolute Error (MAE). The low MAE values show that the algorithms accurately determine anomalies and change points. The experimental results strengthen our assumption that anomaly detection can be improved by determining and removing change points as well as validates the correctness of our proposed rules in real-world scenarios. Furthermore, the proposed rule-based decision support systems enable users to make informed decisions regarding the status of the water distribution network and perform effectively predictive and proactive maintenance.

scholarly journals WATCH: Wasserstein Change Point Detection for High-Dimensional Time Series Data

2021 ◽  
Author(s):  
Kamil Faber ◽  
Roberto Corizzo ◽  
Bartlomiej Sniezynski ◽  
Michael Baron ◽  
Nathalie Japkowicz
Keyword(s):  
Time Series ◽  
Change Point ◽  
Time Series Data ◽  
Change Point Detection ◽  
Series Data ◽  
High Dimensional ◽  
Point Detection
Sign in / Sign up

Export Citation Format

Share Document