平鎮地區的統計和資料探勘之世代研究;A Statistic and Data Mining Study from Generation Cohort Study in PINGZHEN District

NCUIR > college of Health Sciences and Technology > Institute of Systems Biology and Bioinformatics > Electronic Thesis & Dissertation > Item 987654321/68349

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/68349

Title:	平鎮地區的統計和資料探勘之世代研究;A Statistic and Data Mining Study from Generation Cohort Study in PINGZHEN District
Authors:	洪敏華;Hung,Ming-hua
Contributors:	系統生物與生物資訊研究所
Keywords:	世代研究;資料探勘;平鎮地區;生物資訊學;統計學;Cohort Study;Data Mining;Pingzhen District;Bioinformatics;Statistics
Date:	2015-07-23
Issue Date:	2015-09-23 11:29:38 (UTC+8)
Publisher:	國立中央大學
Abstract:	我們將利用生物資訊以科學角度來討論獲得的壢新醫院病患問卷。主要著重在分析並預測重大疾病例如心臟病和高血壓，因為是台灣最常見的幾種疾病，或是一些生活習慣，像是抽菸、飲食和運動。生物資訊是項跨學科的科學技術，他能夠開發管理並分析生物資料的方法，其中一個主要的功能就是建立軟體工具自行產生有用的生物資訊。生物資訊就是提供一個輸入端給所有的科技以紀錄和處理生物資料做為研究的第一步，他運用了很多電腦技術、統計機率和數學公式來分析所輸入的內容，在探討資料的過程中將包含人工智慧、電腦軟體或是資料探勘的演算法。另外為了要讓我們提出正當的推理和做出信服的結論，統計方法也占了很重要的角色。在我們使用原始檔案得到最初的預測後，會套用一些統計公式來優化我們的答案。最後的解答我們希望能達到一個平衡的樹並且得以就有興趣的幾個身體數值說明合理的相關規則，也能找到以上提到的幾種疾病和生活習慣於預測時與其更有關聯的屬性。;Bioinformatics is going to be used as a scientific method to discuss the information we received from the hospital. The main focus would be on the prediction of some major diseases, like heart attack and high blood pressure, for they are the most common problems in patients in Taiwan, or some of the lifestyle habits like smoking, eating and exercise. Bioinformatics is an interdisciplinary scientific field that develops software tools to generate useful biological knowledge. Bioinformatics can provide input to all scientific fields, and analyzing biological data may involve algorithms in artificial intelligence, soft computing or data mining. Also, for we to draw legitimate inference and make convincing conclusion from findings, statistics plays an important role. After we extracted the initial estimation from the data given to us, some statistic analyses would be applied to in order to optimize the answers. As for results, we hope to find balanced trees indicating reasonable rules for those features we are most interested in, including the attributes that may play a key role when predicting diseases and habits.
Appears in Collections:	[Institute of Systems Biology and Bioinformatics] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	595	View/Open

社群 sharing

Loading...