A Framework for Periodic Outlier Pattern Detection in Time-Series Sequences
Download as PPTX, PDF1 like656 views
The document discusses a framework for detecting periodic outlier patterns in time-series data, highlighting their significance in various applications such as fraud detection and anomaly identification. It emphasizes that outlier patterns, which differ from regular patterns, hold valuable insights that may signal critical changes in the data. Additionally, the paper addresses privacy concerns related to data visualization and outlines system requirements for implementing the proposed detection method.
A Framework for Periodic Outlier Pattern Detection in Time-Series Sequences
- 1. IEEE TRANSACTIONS ON CYBERNETICS, VOL. 44, NO. 5, MAY 2014 A Framework for Periodic Outlier Pattern Detection in Time- Series Sequences
- 2. Abstract Periodic pattern detection in time-ordered sequences is an important data mining task, which discovers in the time series all patterns that exhibit temporal regularities. Periodic pattern mining has a large number of applications in real life; it helps understanding the regular trend of the data along time, and enables the forecast and prediction of future events. An interesting related and vital problem that has not received enough attention is to discover outlier periodic patterns in a time series. Outlier patterns are defined as those which are different from the rest of the patterns; outliers are not noise. While noise does not belong to the data and it Is mostly eliminated by preprocessing, outliers are actual instances in the data but have exceptional characteristics compared with the majority of the other instances. Outliers are unusual patterns that rarely occur, and, thus, have lesser support (frequency of appearance) in the data. Outlier patterns may hint toward discrepancy in the data such as fraudulent transactions, network intrusion, and change in customer behavior, recession in the economy, epidemic and disease Biomarkers, severe weather conditions like tornados, etc. We argue that detecting the periodicity of outlier patterns might be more important in many sequences than the periodicity of regular, more frequent patterns. In this paper, we present a robust and time Index Terms-Outlier periodic patterns, performance, periodicity detection, suffix tree, surprising patterns, surprising periodicity, time series, and unusual periods.
- 3. Proposed System In general, privacy risks square measure essential quandary related to confidential information of each structure therefore care needs to be taken so as to preserve confidential information. Visualization of knowledge by graphical, applied statistical and hierarchal illustration square measure evolved to represent the info as within the existing system. The usage of vary values, interpretation of disturbance known as noise are added erected with range values of the time series data to be visualized. The algorithmic rule known as information fly is to be accustomed add rip-roaring information with vary values of your time series, this successively doesn't pertain the end-user to predict the particular statistic from the visualization. Hence this method overcomes the disadvantage raised within the existing system.
- 4. Existing System In the existing system, the Concept of privacy protective has been developed in order to preserve information with none clue even once Multiple generalized techniques has been introduced to filter the info and cluster that square measure supported the statistic grouping formula it's unconcealed in varied fields. Hence the strategy of approximation was developed before reveling the info. Visualization of Data by suggests that of Graphical, Statistical and Hierarchal representation are evolved within the system so as to preserve the Data. Accurate vary for the information’s to be preserved has been erected to envision the statistic data. The prediction is that visualization of the time series data according to the range values does not make out the end user to frame a clear idea about the data. But it makes out the end user to predict using the range values.
- 5. System Requirements Hardware Requirements Processor : Core 2 duo Speed : 2.2GHZ RAM : 2GB Hard Disk : 160GB Software Requirements: Platform : DOTNET (VS2010)Dot net framework 4.0 Database : SQL Server 2008 R2