查詢結果分析
相關文獻
- 使用小波係數所萃取的特徵自動化分析肺音
- 合歡山臺灣冷杉土壤之發育與分類
- 鑰匙辨識之評估與比較
- 全民健康保險下疾病分類編碼品質與相關影響因素研究
- Fractal Image Coding Using Projection-Based Classification and Variable Shape Matching
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- The Family Sapotaceae in Taiwan
- Genus Tisis Walker from Malaysia and Indonesia (Lepidoptera: Lecithoceridae), with Description of Three New Species
- Synopsis of the Genus Hygroplasta Meyrick in the World with Description of a New Species (Lepidoptera: Lecithoceridae)
- 談稅則分類的理論與實務
頁籤選單縮合
題 名 | 使用小波係數所萃取的特徵自動化分析肺音=Automatic Lung Sound Analysis Using Features Extracted from Wavelet Coefficients |
---|---|
作 者 | 呂敏祥; 張光瓊; 陳彥融; | 書刊名 | 龍華科技大學學報 |
卷 期 | 32 2012.06 [民101.06] |
頁 次 | 頁101-114 |
分類號 | 410.1644 |
關鍵詞 | 肺音; 小波轉換; 小波係數; 分類; SOCMAC; Lung sound; Wavelet transform; Wavelet coefficient; Clustering; |
語 文 | 中文(Chinese) |
中文摘要 | 本文使用 SOCMAC類神經網路設計肺音分類器,以尋找最適合於萃取肺音特徵的小波基底。本研究使用 12種小波基底,其中包含了 Coiflet-2、Coiflet-3、Coiflet-4、 Coiflet-5、Daubechies-5、Daubechies-6、Daubechies-7、Daubechies-8、Symlet-5、Symlet-6、 Symlet-7、Symlet-8。對於各種基底所萃取的肺音特徵,經由調整分類器的參數,各自達到最佳的分類效果。實驗結果顯示, Symlet-8基底所萃取的肺音特徵具有最佳的分類正確率。在最佳的狀況下,分類器的學習正確率可達 88.91%,而測試正確率可達到86.70%。 |
英文摘要 | In this paper, we use a SOCMAC neural network to design a lung sound classifier. To find the best representation for lung sounds, we use 12 different wavelet bases to decomposition the lung sounds, which include Coiflet-2, Coiflet-3, Coiflet-4, Coiflet-5, Daubechies-5, Daubechies-6, Daubechies-7, Daubechies-8, Symlet-5, Symlet-6, Symlet-7, and Symlet-8. For every basis, the parameters of the lung sound classifier are selected so that the classifier has the best classification accuracy. Experiment results show that the lung sound features extracted by using Symlet-8 basis have the best classification accuracy, out of the 12 different wavelet bases. With the optimal parameters of the classifier, the classification accuracy of the learning and testing phases are 88.91% and 86.70%, respectively, for the Symlet-8 extracted features. |
本系統中英文摘要資訊取自各篇刊載內容。