Encoding Temporal Markov Dynamics in Graph for Time Series Visualization
نویسندگان
چکیده
Time series is attracting more attention across statistics, machine learning and pattern recognition as it appears widely in both industry and academia, but few advances has been achieved in effective time series visualization due to its temporal dimensionality and complex dynamics. Inspired by recent effort on using network metrics to characterize time series for classification, we present an approach to visualize time series as complex networks based on first order Markov process and temporal ordering. In contrast to classical bar charts, line plots and other statistics based graph, our approach delivers more intuitive visualization that better preserves both the temporal dependency and frequency structures. It provides a natural inverse operation to map the graph back to time series, making it possible to use graph statistics to characterize time series for better visual exploration and statistical analysis. Our experimental results suggest the effectiveness on various tasks such as system identification, classification and anomaly detection on both synthetic and the real time series data.
منابع مشابه
A method for analyzing the problem of determining the maximum common fragments of temporal directed tree, that do not change with time
In this study two actual types of problems are considered and solved: 1) determining the maximum common connected fragment of the T-tree (T-directed tree) which does not change with time; 2) determining all maximum common connected fragments of the T-tree (T-directed tree) which do not change with time. The choice of the primary study of temporal directed trees and trees is justified by the wid...
متن کاملStreamStory: Exploring Multivariate Time Series on Multiple Scales
In visualizing multivariate time series, it is difficult to simultaneously present both the dynamics and the structure of the data in an informative way. This paper presents an approach for the interactive visualization, exploration, and interpretation of multivariate time series. Our approach builds an abstract representation of the data based on a hierarchical, multiscale structure, where eac...
متن کاملDiffMatrix: Matrix-based Interactive Visualization for Comparing Temporal Trends
Line graphs have been commonly used for visualizing temporal trends in time series data. Since comparing trends is one of the main tasks for analyzing multiple temporal trends, many efforts have been made to enhance visual representations of line graphs to help people efficiently compare multiple temporal trends. However, as the number of line graphs increases, the overlap makes it difficult to...
متن کاملTemporal Registration in In-Utero Volumetric MRI Time Series
We present a robust method to correct for motion and deformations in in-utero volumetric MRI time series. Spatio-temporal analysis of dynamic MRI requires robust alignment across time in the presence of substantial and unpredictable motion. We make a Markov assumption on the nature of deformations to take advantage of the temporal structure in the image data. Forward message passing in the corr...
متن کاملSteady Visualization of the Dynamics in Fluids Using -Machines
The visualization of unsteady scientific data is still a challenging problem. Most techniques rely on the animation of individual time-steps. In this paper we propose a steady visualization of the dynamics in fluids using -machines. -machines are a concept from computational mechanics and can be thought of as finite state machines that can be visualized as directed graphs. The nodes are the cau...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1610.07273 شماره
صفحات -
تاریخ انتشار 2016