運用腦波分析於癲癇檢測之研究

癲癇為常見的神經系統疾病，是一種腦部功能產生突發性障礙之腦神經疾病，發生率僅次於腦血管病變。癲癇發作時會引發神智昏迷、全身抽搐、口吐白沫等症狀，嚴重可能會影響智力，甚至引發休克，因此若能在早期治療，可以降低對生活的影響。腦電圖(Electroencephalogram, EEG)為癲癇主要的評估工具，透過腦波特徵的量測，可以檢測受測者是否罹患癲癇，並作為客觀的判斷依據。癲癇診斷一般是由訓練有素的醫師或專家以肉眼觀察腦電圖的方式診斷，無法快速診斷及治療，因此若可發展出快速診斷癲癇的方法或模式，並做出準確的分類，將可節省許多時間與成本。本研究目的是透過離散小波轉換(Discrete Wavelet Transform)分析腦電圖(EEG)的生理參數產生多個子帶(Subband)並擷取出特徵，使用最小熵原理法(Minimize Entropy Principle Approach, MEPA)結合關聯派翠網路(Associative Petri Net, APN)分類，並與其他常見方法包含決策樹(Decision tree)、支持向量機(Support Vector Machine)、類神經網路(Neural Network)、貝式網路(Bayes Net)、簡單貝氏分類器(Naïve Bayes)以及樹狀貝氏分類器(Tree Augmented Naïve Bayes)，比較其分類癲癇腦波的準確率，發展癲癇的診斷模型，減少診斷所花費的時間與醫療成本。結果顯示使用關聯派翠網路，準確率達到93.8%。醫師在診斷時，可以使用此診斷模型，並作為臨床診斷上客觀的判斷依據。

關鍵字

癲癇；腦波；離散小波轉換；最小熵原理；關聯派翠網路

並列摘要

Epilepsy is a common neurological diseases, it’s a disease of the cranial nerves. To suffer epilepsy of rate is second only to cerebrovascular attacks. Epilepsy may cause seizures, loss consciousness, impacted on intelligence, even into shock. The electroencephalogram (EEG) has been used as a tool for diagnosing epilepsy. Record by brain waves, can detect whether the subjects were suffering from epilepsy, and as an objective basis to judge. Diagnosis of epilepsy is a way visual observation by Professional doctors, it wasted time and costs. This study developed a model for Diagnosis of epilepsy through utilizing the discrete wavelet transform, minimize entropy principle approach, and associative Petri nets. This study also used decision tree, support vector machine, neural network, Bayes net, naïve Bayes, and tree augmented naïve Bayes compared to accuracy rate of associative Petri nets. Result, accuracy rate of associative Petri nets is 93.8%.

並列關鍵字

Epilepsy ； Electroencephalogram ； Discrete Wavelet Transform ； Minimize Entropy Principle Approach ； Association Petri Net

參考文獻

Acharya, U. R., Sree, S. V., & Suri, J. S. (2011). Automatic detection of epileptic EEG signals using higher order cumulant features. International journal of neural systems, 21(05), 403-414.

Acharya, U. R., Sree, S. V., Alvin, A. P. C., & Suri, J. S. (2012a). Use of principal component analysis for automatic classification of epileptic EEG activities in wavelet framework. Expert Systems with Applications, 39(10), 9072-9078.

Acharya, U. R., Sree, S. V., Ang, P. C. A., Yanti, R., & Suri, J. S. (2012b). Application of non-linear and wavelet based features for the automated identification of epileptic EEG signals. International journal of neural systems, 22(02), 1250002.

Adeli, H., Ghosh-Dastidar, S., & Dadmehr, N. (2007). A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy. Biomedical Engineering, IEEE Transactions on, 54(2), 205-211.

Andrzejak, R. G., Lehnertz, K., Mormann, F., Rieke, C., David, P., & Elger, C. E. (2001). Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state. Physical Review E, 64(6), 061907.

國際替代計量

運用腦波分析於癲癇檢測之研究

未授權

主題瀏覽