An online algorithm for segmenting time series

Keogh, Eamonn; Chu, Selina; Hart, David M.; Pazzani, Michael J.

doi:10.1109/icdm.2001.989531

Cited by 778 publications

(675 citation statements)

References 15 publications

Supporting

Mentioning

664

Contrasting

Unclassified

Order By: Relevance

“…Here, our primary objective was to demonstrate how model-based techniques are used for improving various aspects of query processing over sensor data. Lastly, we discussed data compression techniques, like, linear approximation [34,39,48], multi-model approximations [39,40,50] and orthogonal transformations [1,22,53,7].…”

Section: Discussionmentioning

confidence: 99%

“…The other two approaches perform better than the sliding window approach, but they need to scan all data, hence they cannot be used for approximating streaming data. Based on this observation, Keogh et al [34] propose a new algorithm that combines the online processing property of the sliding window approach and the performance of the bottomup approach. This approach needs a predefined buffer length.…”

Section: Methods For Data Segmentationmentioning

confidence: 99%

“…In [34], the piecewise linear approximation algorithms are categorized in three groups: sliding window, top-down and bottom-up. The sliding window approach expands the data segment as long as the data tuples fit.…”

Section: Methods For Data Segmentationmentioning

confidence: 99%

“…Among several different data stream approximation techniques, piecewise linear approximation has been the most widely used [34,39]. Piecewise linear approximation models the data stream with a separate linear function per data segment.…”

Section: Piecewise Approximationmentioning

confidence: 99%

“…Moreover, the linear filter [34] is a simple piecewise linear approximation technique in which the sensor values are approximated by a line connecting the first and second point of the segment. When a new data tuple cannot be approximated by this line with the specified error bound, a new segment is started.…”

Section: Piecewise Approximationmentioning

confidence: 99%

See 4 more Smart Citations

A Survey of Model-based Sensor Data Acquisition and Management

Sathe

Papaioannou

Jeung³

et al. 2012

Managing and Mining Sensor Data

View full text Add to dashboard Cite

In recent years, due to the proliferation of sensor networks, there has been a genuine need of researching techniques for sensor data acquisition and management. To this end, a large number of techniques have emerged that advocate model-based sensor data acquisition and management. These techniques use mathematical models for performing various, day-to-day tasks involved in managing sensor data. In this chapter, we survey the state-of-the-art techniques for model-based sensor data acquisition and management. We start by discussing the techniques for acquiring sensor data. We, then, discuss the application of models in sensor data cleaning; followed by a discussion on model-based meth-

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methods For Data Segmentationmentioning

confidence: 99%

Section: Methods For Data Segmentationmentioning

confidence: 99%

Section: Piecewise Approximationmentioning

confidence: 99%

Section: Piecewise Approximationmentioning

confidence: 99%

See 3 more Smart Citations

A Survey of Model-based Sensor Data Acquisition and Management

Sathe

Papaioannou

Jeung³

et al. 2012

Managing and Mining Sensor Data

View full text Add to dashboard Cite

show abstract

On‐line adaptive trend extraction of multiple physiological signals for alarm filtering in intensive care units

Charbonnier

Gentil

2009

Adaptive Control & Signal

View full text Add to dashboard Cite

This paper presents an alarm validation system dedicated to patient monitoring in intensive care units (ICU). Several physiological signals are continuously acquired and an on-line trend extraction method is implemented for each one. A trend is a succession of contiguous semi-quantitative episodes, expressing the time evolution of a signal with several symbols. The difference between the trend and the signal is considered as a residual. In this paper, trend extraction is based on several thresholds that are adapted on-line, following the signal variations. Multivariate change indices are further deduced from the trends and the residuals. They provide an indication of changes to patient hemodynamic and respiratory state. An alarm validation system based on these indices is then proposed, which uses fuzzy decision making. Whenever a monitoring system sets off an alarm, the system proposed carries out a backward analysis of the physiological variables monitored. The system enables various policies to be implemented: filtering of false alarms due to artifacts, confirmation of true alarms due to a patient state change. The system was tested on more than 50 h of data recorded on adult patients in an ICU unit, when 105 SpO 2 alarms were set off by a fixed threshold alarm system. The comparison between the decision made on-line by the validation system and the decision made by a medical expert for each of these alarms showed that the system is able to recognize 100% of true alarms and filter 50-80% of false alarms.

show abstract