查詢結果分析
來源資料
相關文獻
- The Partition in Linear Space for Predicting the Secondary Structure of Proteins
- 以多面法預測蛋白質二級結構
- 以灰色線性規劃為基礎之重新調度法作動態發電分配
- 豬血蛋白質之酵素水解
- Excitatory and Inhibitory Amino Acid Levels in the Cerebrospinal Fluids of Children with Neurological Disorders
- 七股潟湖表層海水的顆粒性和溶解性游離胺基酸的組成和分布
- 飲食蛋白質量對血漿游離胺基酸的影響
- Influence of Vacuum Frying Time on the Chemical Constituents of Fried Carrot Chips
- Minimum-Torque Trajectory Planning of Redundant Manipulators between Two Joint Configurations
- 保久乳之蛋白質營養價值之分析
頁籤選單縮合
題名 | The Partition in Linear Space for Predicting the Secondary Structure of Proteins=分割線性空間以預測蛋白質二級結構 |
---|---|
作者 | 謝維華; |
期刊 | 東海學報 |
出版日期 | 19950700 |
卷期 | 36:2(理學院) 民84.07 |
頁次 | 頁147-176 |
分類號 | 319.711 |
語文 | eng |
關鍵詞 | 訊息理論法; 神經網路模型; 線性規劃; 蛋白質二級結構; 胺基酸; Information theory method; Neural network models; Linear programming; Protein secondary structure; Amino acid; |
中文摘要 | 透過局部密碼化手續,訊息理論法及神經網路法都在建立三個平面以分割空間, 作為預測蛋白質二級結構的模型。 我們首先比較上述二法,然後建立一個線性規劃模型,希望用更客觀的方式,尋找三 個分割空間的平面,以預測蛋白質二級結構。我們發現分佈在空間裡的點雖有其規律性, 但是以三個平面是無法達到理想的分割結果。這是預測精確度無法提高的原因。 |
英文摘要 | In the language of local encoding schemes, both the information theory method and the two-layer neural network model, which are 3-stale predictors, partition 20k-dimensional space with three planes to distinguish the predicted secondary structures. The structure assigned to the middle amino acid in a new segment is determined by the location of the segment in space. We constructed a linear programming model and attempted to find an acceptable separating plane. According to our experiments, the distribution of points in space is ambiguous, and it is difficult to find planes performing well for a training set. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。