| dc.contributor.advisor | 曾正男 | zh_TW |
| dc.contributor.advisor | Tzeng, Jeng-Nan | en_US |
| dc.contributor.author (Authors) | 孫照恩 | zh_TW |
| dc.contributor.author (Authors) | Sun, Chao-En | en_US |
| dc.creator (作者) | 孫照恩 | zh_TW |
| dc.creator (作者) | Sun, Chao-En | en_US |
| dc.date (日期) | 2022 | en_US |
| dc.date.accessioned | 1-Aug-2022 18:12:15 (UTC+8) | - |
| dc.date.available | 1-Aug-2022 18:12:15 (UTC+8) | - |
| dc.date.issued (上傳時間) | 1-Aug-2022 18:12:15 (UTC+8) | - |
| dc.identifier (Other Identifiers) | G0108751005 | en_US |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/141178 | - |
| dc.description (描述) | 碩士 | zh_TW |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 應用數學系 | zh_TW |
| dc.description (描述) | 108751005 | zh_TW |
| dc.description.abstract (摘要) | 日前的疫情日趨嚴峻，鑒於目前關於COVID-19之檢測方式大致分為核酸檢測、抗體、抗原之快篩試劑檢測，其分別有耗時高成本高、潛伏期及感染前期無法檢測、以及準確度較低容易發生偽陰偽陽之缺點，且以上採檢方式皆須要透過侵入式的採檢方式才能達到效果，不免會降低社會大眾對於採檢的意願。因此本文希望透過以肺部的電腦斷層攝影圖觀察確診者之病灶位置、形狀、規模並利用奇異值分解對原始資料的主要特徵進行提取，利用圖與圖之間的特徵值差異先進行篩選以及預處理，再利用機器學習中監督式學習的支持向量機及相關的參數設定來對確診者與健康者之間產生區別分類進而對新輸入的病人資料進行預測。透過這種方式期望達到增加檢測量能、降低成本、提高檢測意願及準確度。 | zh_TW |
| dc.description.abstract (摘要) | The current epidemic is becoming more and more serious, and the current testing methods for COVID-19 are broadly divided into PCR, antibodies, and antigenic rapid test, which are time-consuming and costly, undetectable during the incubation period and pre-infection period, and less accurate which are prone to false negatives and false positives.Also, all of the above methods require invasive testing to achieve results, which will inevitably reduce the public`s desire for testing. Therefore, in this paper, we hope to extract the main features of the original data by observing the location, shape, and size of the lesions of the diagnosed patients with lung computed tomography and using the singular value decomposition, and then filter and pre-process the differences of the feature values between the images. Then we use support vector machine and adjustment the parameters of the model to classify and predict whether the people is diagnosed. In this way, we expect to increase detection performance, reduce costs, and improve willingness and accuracy of detection. | en_US |
| dc.description.tableofcontents | 致謝 ii中文摘要 iiiAbstract iv目錄 v圖目錄 vii第一章 緒論 1第一節 研究動機 1第二節 文獻探討 2第三節 理論、演算法及機器學習簡介 13第二章 初期方向探討與嘗試 24第一節 工具與資料選取 24第二節 影像分割及預處理 28第三節 像素變化觀測 31第四節 Canny邊緣檢測 35第五節 高斯混合模型 37第六節 支援向量機 41第三章 研究方法 44第一節 圖像揀選 44第二節 閾值設定與高斯模糊 47第三節 病灶區域判讀 48第四節 資料分類 49第四章 研究結果 51第五章 結論 59附錄 60參考文獻 73 | zh_TW |
| dc.format.extent | 7605555 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0108751005 | en_US |
| dc.subject (關鍵詞) | 機器學習 | zh_TW |
| dc.subject (關鍵詞) | 監督式學習 | zh_TW |
| dc.subject (關鍵詞) | 支持向量機 | zh_TW |
| dc.subject (關鍵詞) | 新型冠狀肺炎 | zh_TW |
| dc.subject (關鍵詞) | 影像辨識 | zh_TW |
| dc.subject (關鍵詞) | machine learning | en_US |
| dc.subject (關鍵詞) | Supervised learning | en_US |
| dc.subject (關鍵詞) | Support vector machine | en_US |
| dc.subject (關鍵詞) | Covid-19 | en_US |
| dc.subject (關鍵詞) | Image recognition | en_US |
| dc.title (題名) | 新冠肺炎斷層掃描的小樣本機器學習研究 | zh_TW |
| dc.title (題名) | Research of machine learning for small samples of covid-19 CT | en_US |
| dc.type (資料類型) | thesis | en_US |
| dc.relation.reference (參考文獻) | [1] S. V. Kogilavani , J. Prabhu, R. Sandhiya, M. Sandeep Kumar, UmaShankar Subramaniam, Alagar Karthick , M. Muhibbullah , and Sharmila Banu Sheik Imam(01,Feb,2022)COVID-19 Detection Based on Lung Ct Scan Using Deep Learning Techniques[2] Ines Chouat, Amira Echtioui, Rafik Khemakhem, Wassim Zouch, Mohamed Ghorbel & Ahmed Ben Hamida(22,January,2022)COVID-19 detection in CT and CXR images using deep learning models[3] COVID-CTset : A Large COVID-19 CT Scans dataset containing 63849 images from 377 patients[4] Implementing the "GrabCut" Segmentation Technique as a Plugin for the GIMP[5] 黃志勝 Chih-Sheng Huang 相關文章[6] (13,Feb,2019)Math behind Support Vector Machine[7] John C.Platt(26,Mar,1999)Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods[8] (19,Jan,2021)奇異值分解（SVD）演算法[9] 數值分析－曾正男 6-8 差值法 B spline[10] 李立宗(19,Oct,2019)科班出身的AI人必修課:OpenCv影像處理使用Python | zh_TW |
| dc.identifier.doi (DOI) | 10.6814/NCCU202200858 | en_US |
