2010 Fiscal Year Final Research Report
Development of statistical traffic models and their application to information security
| Project/Area Number |
21700060
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Computer system/Network
|
|---|
| Research Institution | Hiroshima University |
|---|
Principal Investigator |
OKAMURA Hiroyuki Hiroshima University, 大学院・工学研究院, 准教授 (10311812)
|
|---|
| Project Period (FY) |
2009 – 2010
|
| Keywords | 隠れマルコフモデル / マルコフ型到着過程 / トラッフィクモデル / EMアルゴリズム / 一般化EMアルゴリズム / 変分近似 / 並列計算 / マルチコアCPU |
|---|
| Research Abstract |
The project developed statistical models for network traffic analysis with bot hidden Markov models (HMMs) and Markovian arrival processes (MAPs) by revealing the mathematical relationship between HMMs and MAPs. We also considered parallelization of the parameter estimation algorithm for the proposed HMM-MAP-based models to handle a long-term observation for network packet arrivals. Moreover, we proposed the applicable example of the developed parameter estimation algorithm towards the information security.
|
