On the detection and representation of trends

Jarvis Tat Yin Cheung, George Stephanopoulos

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

A novel time-domain pattern-based approach for trending is presented. The approach is based on an interval-based qualitative and semi-quantitative representation capable of transforming the time-records of data into meaningful and explicit descriptions of trends at different time scales. The representation of trends is based on the triangular representation , whereas the detection of trends from data records is based on qualitative scaling. Together, they provide a unified formal framework for the consistent detection and representation of trends from arbitrary noisy data in a compact and natural manner. Because the representation is generic to trends and intuitive to humans, it can provide useful multi-scale dynamic data models for different process applications such as data compression, data reconciliation and rectification, fault diagnosis, trend interpretation, adaptive control, quality control, learning patterns from historical data, economic evaluation, process modelling, monitoring, planning and optimization.

Original languageEnglish (US)
Pages (from-to)755-774
Number of pages20
JournalAdvances in Instrumentation, Proceedings
Volume45
Issue numberpt 2
StatePublished - Dec 1 1990
Externally publishedYes
EventProceedings of the ISA '90 International Conference and Exhibition Part 4 (of 4) - New Orleans, LA, USA
Duration: Oct 14 1990Oct 18 1990

Fingerprint

Data compression
Failure analysis
Quality control
Data structures
Planning
Economics
Monitoring

ASJC Scopus subject areas

  • Engineering(all)

Cite this

On the detection and representation of trends. / Cheung, Jarvis Tat Yin; Stephanopoulos, George.

In: Advances in Instrumentation, Proceedings, Vol. 45, No. pt 2, 01.12.1990, p. 755-774.

Research output: Contribution to journalConference article

@article{5a66348dda2347eda4d5a6e98848e313,
title = "On the detection and representation of trends",
abstract = "A novel time-domain pattern-based approach for trending is presented. The approach is based on an interval-based qualitative and semi-quantitative representation capable of transforming the time-records of data into meaningful and explicit descriptions of trends at different time scales. The representation of trends is based on the triangular representation , whereas the detection of trends from data records is based on qualitative scaling. Together, they provide a unified formal framework for the consistent detection and representation of trends from arbitrary noisy data in a compact and natural manner. Because the representation is generic to trends and intuitive to humans, it can provide useful multi-scale dynamic data models for different process applications such as data compression, data reconciliation and rectification, fault diagnosis, trend interpretation, adaptive control, quality control, learning patterns from historical data, economic evaluation, process modelling, monitoring, planning and optimization.",
author = "Cheung, {Jarvis Tat Yin} and George Stephanopoulos",
year = "1990",
month = "12",
day = "1",
language = "English (US)",
volume = "45",
pages = "755--774",
journal = "Advances in Instrumentation, Proceedings",
issn = "0065-2814",
number = "pt 2",

}

TY - JOUR

T1 - On the detection and representation of trends

AU - Cheung, Jarvis Tat Yin

AU - Stephanopoulos, George

PY - 1990/12/1

Y1 - 1990/12/1

N2 - A novel time-domain pattern-based approach for trending is presented. The approach is based on an interval-based qualitative and semi-quantitative representation capable of transforming the time-records of data into meaningful and explicit descriptions of trends at different time scales. The representation of trends is based on the triangular representation , whereas the detection of trends from data records is based on qualitative scaling. Together, they provide a unified formal framework for the consistent detection and representation of trends from arbitrary noisy data in a compact and natural manner. Because the representation is generic to trends and intuitive to humans, it can provide useful multi-scale dynamic data models for different process applications such as data compression, data reconciliation and rectification, fault diagnosis, trend interpretation, adaptive control, quality control, learning patterns from historical data, economic evaluation, process modelling, monitoring, planning and optimization.

AB - A novel time-domain pattern-based approach for trending is presented. The approach is based on an interval-based qualitative and semi-quantitative representation capable of transforming the time-records of data into meaningful and explicit descriptions of trends at different time scales. The representation of trends is based on the triangular representation , whereas the detection of trends from data records is based on qualitative scaling. Together, they provide a unified formal framework for the consistent detection and representation of trends from arbitrary noisy data in a compact and natural manner. Because the representation is generic to trends and intuitive to humans, it can provide useful multi-scale dynamic data models for different process applications such as data compression, data reconciliation and rectification, fault diagnosis, trend interpretation, adaptive control, quality control, learning patterns from historical data, economic evaluation, process modelling, monitoring, planning and optimization.

UR - http://www.scopus.com/inward/record.url?scp=0025541004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025541004&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0025541004

VL - 45

SP - 755

EP - 774

JO - Advances in Instrumentation, Proceedings

JF - Advances in Instrumentation, Proceedings

SN - 0065-2814

IS - pt 2

ER -