Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Outlier detection method for time-series data

A technology for outlier detection and time series data, which is applied in electrical digital data processing, special data processing applications, instruments, etc., can solve problems such as time series data processing that cannot be real-valued attributes, and achieve the effect of improving accuracy.

Inactive Publication Date: 2012-02-22
NANJING UNIV
View PDF0 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the research methods for periodic time-series data, most of the processing is sequence data of nominal attributes, and time-series data of real-valued attributes cannot be processed

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Outlier detection method for time-series data
  • Outlier detection method for time-series data
  • Outlier detection method for time-series data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0032] The data set used in this example represents the number of people in the school building at different times, and its construction method is shown in Table 1.1. This is designed based on the actual situation. The teaching building does not open before six o’clock, so the number of people is 0. The number of people on normal working days is obviously more than that on weekends, and there are usually peak hours in the morning and afternoon. N(μ, σ) in the table means that the data satisfies a normal distribution with μ as the expectation and σ as the standard deviation.

[0033] Table 1.1 The construction method of the data set of the number of people in the teaching building. The distribution of the number of people in each day corresponds to a time series data.

[0034] time (hours)

[0035] Simultaneously, the present embodiment assumes that January and August of each year are respectively winter vacation and summer vacation, and the teaching building is not o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an outlier detection method for time-series data. The method comprises the following steps of: dividing the time-series data in a training data set by the day from the Monday to the Sunday, and then clustering; establishing a data distribution model, under week granularity, of the time-series data by using the maximum cluster in each clustering result; according to the data distribution model, searching all abnormal values in the training data set, and respectively acquiring the data distribution model at each time interval; by searching, judging whether a periodic event which occurs with time granularity, greater than the week granularity, as a period exists in the abnormal values which accord with the data distribution model at each time interval; if the periodic event exists, recording the periodic event as a class of special period mode; judging whether the time-series data in a test data set accords with a week mode, if so, determining that the time-series data is a non-outlier, otherwise, judging whether the time-series data accords with the special period mode; and if the time-series data accords with the special period mode, determining that the time-series data is the non-outlier, otherwise, determining that the time-series data is an outlier.

Description

technical field [0001] The invention relates to a data feature retrieval method, in particular to a time series data outlier detection method based on a multi-granularity periodic pattern. Background technique [0002] Outlier detection is one of the four types of knowledge discovery tasks in data mining. Its purpose is to find data objects that are inconsistent with the general behavior or model of other data, that is, outliers. In real life, there are various time series data containing periodic events, and outlier detection for time series data has practical significance in many fields. [0003] Time-series outlier detection based on periodic pattern analysis can guide people to study the causes of outliers, which is conducive to timely resolution and response to sudden or abnormal events. At present, most of the time series outlier detection methods do not take into account the periodicity of the time series data itself. In the research methods for periodic time-series...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/30
Inventor 商琳高阳杨育彬罗玉盘
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com