查詢結果分析
來源資料
頁籤選單縮合
題 名 | 結合多尺度主成分分析法與支持向量機在想像彩色圖像與中文文字之腦波差異分析=Analysis the Difference EEG of Imaging Color Pictures and Chinese Words via Multi-scale Principal Component Analysis and Support Vector Machine |
---|---|
作 者 | 張菀珍; 葉榮木; 蔡俊明; 林詠翔; | 書刊名 | 資訊科學應用期刊 |
卷 期 | 7:1 2011.06[民100.06] |
頁 次 | 頁1-28 |
分類號 | 448.94 |
關鍵詞 | 多尺度主成分分析法; 多貝西小波; 支持向量機; Multi-scale principal component analysis; Daubechies wavelet; Support vectormachines; |
語 文 | 中文(Chinese) |
中文摘要 | 大腦人機介面以及大腦運作機制是醫學界以及科學界研討的相關課題。由於大腦 的訊號是非常複雜性的訊號,所以在大腦訊號的「特徵擷取」以及「分類」這兩方面 上,一直是世界各個團隊所共同努力的方向。本研究是採用離散小波轉換中的多貝西 小波結合多尺度主成分分析法搭配支持向量機來做圖像提示以及文字提示的特徵擷取 以及分類。本實驗的受測者共有13 位,實驗結果對於S4 受測者來說正確分類率高達 88.89%,而其他的受測者大部分也都有70%以上,整體的平均正確率可達到72.65%。 本研究對於圖像提示以及文字提示來說具有良好的分類效果。 |
英文摘要 | The brain computer interface and brain action are researched by medical science and science. The brain signals are very complication, so according to these reasons, “feature extraction” and “classification” of EEG are the main issues in BCI regions.In “feature extraction”, this study adopted multi-scale principle component analysis (multi-scale PCA) to analyze EEG signals.In “classification”, support vector machine (SVM) which usually has high accuracy is used to classify EEG of imaging color pictures and Chinese words in this study. We present results of this study based on 13 different healthy subjects in total who participated in our experiments. The performance in the experiment, one of subjects, S4 has highest accuracy of classification which can be reach to 88.89%, and averaged accuracy of all subjects is 72.65%. |
本系統中英文摘要資訊取自各篇刊載內容。