NN stock的問題，透過圖書和論文來找解法和答案更準確安心。 我們找到下列包括價格和評價等資訊懶人包

NN stock進入發燒排行的影片

單一與整合特徵選取與案例選取方法於醫學資料集之應用

為了解決NN stock的問題，作者王翔 這樣論述：

摘要............................................................................................................. iAbstract..................................................................................................... ii目錄........................................................................

................................... iii圖目錄....................................................................................................... vi表目錄..................................................................................................... viii第一章 緒論.....................................

..........................................................11.1 研究背景 ......................................................................................11.2 研究動機與目的 ..........................................................................21.3 研究問題與假設 ..............................................

............................31.4 論文架構 .....................................................................................4第二章 文獻探討 ......................................................................................52.1 特徵選取 (Feature Selection)....................................................

..52.1.1 GA (Genetic Algorithm) ....................................................62.1.2 C4.5 (Decision Tree C4.5，DT)........................................72.1.3 PCA (Principal components analysis) ...............................82.2 案例選取 (Instance Selection) ....................................

...............82.2.1 Drop3 (Decremental Reduction Optimization Procedure 3).........................................................................................92.2.2 IB3 (Instance-Based Learning 3).....................................112.2.3 AP (Affinity Propagation)...........................

.....................142.3 監督式學習分類器 (Supervised Learning Classifier).............162.3.1 SVM (Support Vector Machines，支援向量機)............162.3.2 K-Nearest Neighbor (K-NN，K-最近鄰居法)...............18第三章 實驗設計 ....................................................................................203.1 資料集....

.....................................................................................203.1.1 資料架構 .........................................................................203.1.2 資料介紹 .........................................................................213.2 實驗架構 ................................

...................................................223.2.1 實驗一：特徵選取 .........................................................233.2.2 實驗二：案例選取 ........................................................243.2.3 實驗三：特徵選取與案例選取之整合........................25第四章 實驗結果 ...........................................

.........................................274.1 實驗一：特徵選取 ....................................................................274.2 實驗二：案例選取 ...................................................................374.3 實驗三：特徵選取與案例選取之整合 ...................................494.4 小結............................

................................................................59第五章 結論.............................................................................................635.1 研究問題回覆 ...........................................................................635.2 實驗限制和未來展望 ...............................

................................635.3 個人總結 ...................................................................................64參考文獻...................................................................................................65圖 1、特徵選取示意圖 .......................................................

......................5圖 2、基因演算法 .....................................................................................6圖 3、決策樹[7].........................................................................................7圖 4、案例選取示意圖 .....................................................................

........9圖 5、Drop 演算法[12]............................................................................11圖 6、IB3 演算法[15]..............................................................................13圖 7、AP 的迭代過程[16].......................................................................15圖 8、Responsib

ilites 及 Availabilities[16].............................................16圖 9、SVM 示意圖[22]...........................................................................18圖 10、KNN 基本概念圖........................................................................19圖 11、實驗流程圖....................................

..............................................23圖 12、為單一特徵選取 .........................................................................24圖 13、單一案例選取 .............................................................................25圖 14、特徵選取與案例選取之整合 .....................................................26

圖 15、特徵選取與 KNN 分類器：UCI 資料集...................................30圖 16、特徵選取與 KNN 分類器：UCI 資料集...................................31圖 17、特徵選取與 SVM 分類器：UCI 資料集...................................35圖 18、特徵選取與 SVM 分類器：長庚醫院臨床資料集 ..................36- x -圖 19、案例選取與 KNN 分類器：UCI 資料集...............................

....41圖 20、案例選取與 KNN 分類器：長庚醫院臨床資料集 ..................42圖 21、案例選取與 SVM 分類器：UCI 資料集...................................47圖 22、案例選取與 SVM 分類器：長庚醫院臨床資料集 ..................48圖 23、特徵選取和案例選取與 KNN 分類器：UCI 資料集...............52圖 24、特徵選取和案例選取與 KNN 分類器：長庚醫院臨床資料集....................................................

...............................................................53圖 25、特徵選取和案例選取與 SVM 分類器：UCI 資料集...............57圖 26、特徵選取和案例選取與 SVM 分類器：長庚醫院臨床資料集...................................................................................................................58圖 27、UCI 資料集平均準確率 ...................

..........................................60圖 28、長庚醫院臨床資料集平均準確率 .............................................62表 1、UCI 公開資料集............................................................................20表 2、長庚醫院臨床資料集 ...................................................................21