Now 13095 visitors
Today:0 Yesterday:0
Total: 178324 216S 51P 5R
2026-10-21, Week 43
Member Login
TACT Journal Homepage
Call for Paper
Committee
Find My Paper
Author Homepage
Statistics & History
Welcome Message
Paper Procedure
FAQ
Paper Archives
Outstanding Papers
Program & Proceedings
Presentation Platform
Hotel & Travel Info
Photo Gallery
Scheduler Login
Seminar
Archives Login
Sponsors


















Online Q&A Session
Paper Number Author:
Paper Title
Keyword
Q&A Number **Select your question number !!
Questioner eMail:
Question
Answer
by
Author
Save Q&A

* Edit or answer any Q&A by selecting Q&A number Hyper Link below + Write button (Save)
ICACT20210237 Question.1
Questioner: smw2lee@gmail.com    2021-02-09 오전 11:06:37 		ICACT20210237 Answer.1
Answer by Auhor shubhamkj2405@gmail.com   2021-02-09 오전 11:06:37
Chrome Click!!
On slide 8, Presenter labeled each line with noise and data labels to evaluate the accuracy of our unsupervised approach. Our evaluation method consists of manually labeling each input and determining the accuracy of the processed file by comparing it with the manual labels. Is there any reason to specify the labeling manually rather than automatically? Dear Member, Thanks for your question. Yes, as this is an unsupervised approach,we wanted to somehow make sure that we are generating the right output in terms on line types. So to validate pur algorithm we decided to use accuracy as a metric, by doing so we were able to identify the algorithm efficiency in identifying noise and data lines.
ICACT20210237 Question.2
Questioner: satyabrataaich@gmail.com    2021-02-09 오후 10:23:40 		ICACT20210237 Answer.2
Answer by Auhor shubhamkj2405@gmail.com   2021-02-09 오후 10:23:40
Chrome Click!!
Thank you for your slides. It's a good work. I would like to know what kind of validation techniques are available for this kind of problem? And also what are other performance parameters other than accuracy has to look for for validating this kind of problem Dear Member, thanks for your question. The most ideal validation metric would be plotting a ROC curve, however, that would provide a random estimate and for this use case, we wanted to be completely sure of the performance in terms of efficiency. In this paper, we have only worked on accuracy as a parameter but we are working on optimization of the algorithm to be used on large scale logs without batch processing. I hope this answers your question.