Now 5922 visitors
Today:0 Yesterday:0
Total: 151493 286S 69P 26R
2026-11-12, Week 46
Member Login
TACT Journal Homepage
Author Homepage
Call for Paper
Paper Procedure
Paper Submission/Update
Invoice/Registration
CRF Submission/Update
Find My Paper
Statistics & History
Welcome Message
Committee
FAQ
Paper Archives
Outstanding Papers
Program & Proceedings
Presentation Platform
Hotel & Travel Info
Photo Gallery
Scheduler Login
Seminar
Archives Login
Sponsors




















IEEE/ICACT20210239 Question.3
Questioner: ra-maneekut@kddi-research.jp    2021-02-10 ¿ÀÈÄ 11:29:04
IEEE/ICACT20210239 Answer.3
Answer by Auhor yfhou@okayama-u.ac.jp   2021-02-10 ¿ÀÈÄ 11:29:04
Is this prediction accuracy adequate for finding spectrum hole in real-time scenario ? What are the next steps to improve the accuracy of this model ? Thanks a lot for your question. Yes, the method can be used for a real-time scenario. But the prediction accuracy is perhaps not good because many traffic patterns will be included in the busy and idle duration data for a real-time case. Data categorization just gives a simple way to improve the accuracy of prediction for partial time-series data. Maybe we can use other efficient ML method such as LSTM(Long short-term memory) method to further improve the accuracy of partial data.

Select Voice