Results - Details
Search command : Author="Τζίτζικας"
And Author="Ιωάννης"
Current Record: 8 of 47
|
Identifier |
000440098 |
Title |
GPU-accelerated streaming analytics |
Alternative Title |
Ανάλυση δεδομένων σε ροή μέσω κάρτας γραφικών |
Author
|
Λεβέντης, Χριστόφορος Σ.
|
Thesis advisor
|
Πρατικάκης, Πολύβιος
|
Reviewer
|
Ιωαννίδης, Σωτήριος
Τζίτζικας, Ιωάννης
|
Abstract |
Streaming analytics is the analysis of huge pools of “in-motion” data, known as
streams. These streams are triggered by a specific event that happens as a direct result
of an action or set of actions, like a financial transaction, a social post or a website
click. Streamed data can originate from various sources such as Internet of Things (IoT)
devices, bank transactions, mobile devices and sensors. By performing streaming
analytics, enables the ability to work faster and stay ahead in competition. The above
analysis helps organizations to process their data and extract valuable informations in
order to stay agile and identify new opportunities. Therefore, this analysis leads to
smarter business moves, more efficient operations, higher profits, happier customers
and responsiveness. In this work, we present a GPU-based solution which can perform
analysis on data in stream or at rest. This solution uses a sentiment-based lexicon and
performs pattern matching operation over the data to extract valuable information
such as sentiment score and frequent used words. This tool can also can track trends
for both short and long term events by manually adjusting the desired time window
intervals. Lastly, our evaluation applies the GPU-based component in a Quality of
Service scenario where we examine the incoming call transcripts of different call
centers and report various insights.
|
Language |
English |
Subject |
Data analytics |
|
Κατανεμημένη αναγνώριση προτύπων |
Issue date |
2021-07-30 |
Collection
|
School/Department--School of Sciences and Engineering--Department of Computer Science--Post-graduate theses
|
|
Type of Work--Post-graduate theses
|
Permanent Link |
https://elocus.lib.uoc.gr//dlib/2/8/f/metadata-dlib-1622016432-204710-26547.tkl
|
Views |
558 |