植基於雲端運算之生醫訊號辨識系統

Biomedical Signal Analytic System Based On Cloud Computing

周緯志(Weizhi Zhou)

指導教授 ： 賴飛羆

國立臺灣大學/電機資訊學院/生醫電子與資訊學研究所/碩士(2012年)

https://doi.org/10.6342/NTU.2012.10814

摘要

生醫訊號的分析與分類在醫學領域上是一項重要的課題。在機器學習中，建立模型與分析生理訊號用來找出病人的生理訊號模式。這步驟包括使用權重來指示生理訊號與病人狀態的不同關係。我們建立一個包含了抽取特徵和分類器的分析系統。使用者可用這個系統以分析生醫訊號。並給使用者檢查分類器的判斷結果正確與否給予系統回饋的功能，使得系統在使用者使用後可以越來越進步。我們使用雲端平台加速癲癇患者腦波圖分析的流程。在抽取特徵部分使得本來需要1920分鐘的時間才能跑完的資料降低到只需要85分鐘就可以跑完。在分類器部分使得本來需要2058分鐘的時間的資料降低到只需要119分鐘就可以跑完。本研究改善了抽取特徵和分類器所需的時間並能透過使用者的回饋改善準確率。

關鍵字

雲端運算 ； 生醫訊號 ； 支援向量機 ； 腦波分析

並列摘要

The analysis and classification of biomedical signals is an important issue in medical field. In machine learning, building models and analyzing physiological signals are used to find the physiological signal pattern of patient status. The process uses weighting, which indicates different relationships between physiological signals and patient status. We build up a distributed system which contains feature extraction and classification. Users can utilize this system to analyze biomedical signals and give feedbacks to the system. After users give feedback, the accuracy of classification can be improved. We utilized this cloud platform to accelerate the process of electroencephalography signal analyzing in seizure patients. In the feature extraction part, it reduces the computing time from 1920 minutes to 85 minutes. In the classifier part, it reduces the computing time from 2058 minutes to 119 minutes.

並列關鍵字

Cloud computing ； Biosignal ； Support Vector Machine ； EEG analysis

參考文獻

1. Fisher, R.S., et al., Epileptic seizures and epilepsy: definitions proposed by the International League Against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE). Epilepsia, 2005. 46(4): p. 470-2.

2. D. Hirtz, D.J.T., K. Gwinn-Hardy, M. Mohamed, A. R. Chaudhuri and R. Zalutsky, How common are the "common" neurologic disorders? Neurology, 2007. 68: p. 326.

3. Engel, J., Jr., A proposed diagnostic scheme for people with epileptic seizures and with epilepsy: report of the ILAE Task Force on Classification and Terminology. Epilepsia, 2001. 42(6): p. 796-803.

4. Pelvig, D.P., et al., Neocortical glial cell numbers in human brains. Neurobiol Aging, 2008. 29(11): p. 1754-62.

5. Pakkenberg, B. and H.J. Gundersen, Total number of neurons and glial cells in human brain nuclei estimated by the disector and the fractionator. J Microsc, 1988. 150(Pt 1): p. 1-20.