A Review on Complex Event Processing Approaches: Research Background and Challenges

Authors

อ.ดร.วรพล พงษ์เพ็ชร, น.ส.ปาริชาติ คนึงกิต

Published

NCIT2019

Abstract

With rapldly Increasing adoption of lot
tochnalogies In many business domains, data Is flowing Into distrlibuted
storages both on premise and off premise st an incredible rate and
volume. To gain insight from these data in arder to make a timely
decision is not a trivial task, and a highly efficient and data complexity
management are nooded to gnable such task. Traditional batch data
procussing focusing on calculation and processing on collection of data
Is nol sultalble for Tihe task. A data processing Iechnique that can handie
large and rapid data flow to enable real-time decision makding must be
considered instead. In this paper, we conduct a literature review and
analyze the Complex Event Processing (CEP) approach which is the
framework for continuous and real-time data processing. To this end.
the continuous and streaming data processing approaches including (1)
Information Flow Processing (FPi. (2) CEP advancements and บe
cases, (3) CEP and Machine Learning. and (4) Online Machine Leaming
are presanted in the analytical way.
According Ie aur comparative analysis, we found that Machina
Learning (ML) has a potantial to Incrgase the afliclency in CEP.
Specifically. Online IML is the method for continuous data processing
with the capability to fiexibly adjust the process rules. in addition. we
found that unsupervised learning is a promising approach to support
uniabaled data processing whereas the supervsed leaming model
reaquires Iabelad data in ordar ito datine the aurtput. Finally we give the
conciuding remarks on the ravigwad approaches and point out the
fufure works that are worth for further investigation.

(2561). ความท้าทายของนักแปลในการแปลสำนวนภาษาอังกฤษเป็นภาษาไทยในบันทึกเชิงชีวประวัติของ ฮิลลารี รอดแฮม คลินตัน เรื่อง ชีวิตและทางเลือก. NIDA Journal of Language and Communication, 23(34), 1-12.