Presentation | 2013-07-12 Enhancing Traceability Against Variations of Time Series using Automated Parameter Re-estimation Detection Hiroki NAKAYAMA, Shingo ATA, Ikuo OKA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | It is necessary to update the prediction model's parameter with the progress of the time to reduce the deterioration of the accuracy of prediction, since the time series data of traffic changes every moment. However, the frequency of parameter re-estimation differs greatly due to the characteristic of time series data. In this paper, we propose a method to detect the phase for re-estimation automatically by using the residual of prediction as feedback information. Our method reduces the prediction error by handling the phase of re-estimation and also reduces unnecessary re-estimation. We realized a lightweight and general control structure by using moving average and moving standard deviation. We demonstrate that by applying it to the real monitored data in a major P2P file-sharing system the traceability against variations of time series increased about 20%. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Trend Prediction / Time Series Analysis / Moving Average / Characteristic Detection |
Paper # | ICM2013-19 |
Date of Issue |
Conference Information | |
Committee | ICM |
---|---|
Conference Date | 2013/7/4(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Information and Communication Management(ICM) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Enhancing Traceability Against Variations of Time Series using Automated Parameter Re-estimation Detection |
Sub Title (in English) | |
Keyword(1) | Trend Prediction |
Keyword(2) | Time Series Analysis |
Keyword(3) | Moving Average |
Keyword(4) | Characteristic Detection |
1st Author's Name | Hiroki NAKAYAMA |
1st Author's Affiliation | Graduate School of Engineering, Osaka City University() |
2nd Author's Name | Shingo ATA |
2nd Author's Affiliation | Graduate School of Engineering, Osaka City University |
3rd Author's Name | Ikuo OKA |
3rd Author's Affiliation | Graduate School of Engineering, Osaka City University |
Date | 2013-07-12 |
Paper # | ICM2013-19 |
Volume (vol) | vol.113 |
Number (no) | 124 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |