English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 63246/95943 (66%)
造訪人次 : 4846142      線上人數 : 260
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/52370


    題名: 模糊RFID資訊處理於居家安全
    其他題名: Fuzzy RFID information processing in home safety
    作者: 陳柏愷;Chen, Po-kai
    貢獻者: 淡江大學資訊工程學系碩士班
    許輝煌;Hsu, Hui-huang
    關鍵詞: RFID;RSSI;居家安全;模糊推論;危險數;回饋;RFID;RSSI;Home safety;Fuzzy inference;Dangerous number;Feedback
    日期: 2010
    上傳時間: 2010-09-23 17:34:58 (UTC+8)
    摘要: RFID近幾年成為熱門話題,其原因為成本的降低、政府努力推動、企業研究與開發,RFID應用方面相當廣闊,包含悠遊卡與ETC、門禁卡、門票、電子病例、物流倉儲、防盜晶片及人或物的追蹤與辨識等應用。
    我們主要研究為居家安全,提供居家危險警報的服務。我們使用RFID的技術來偵測老人與小孩在家是否發生危險,將容易發生危險的位置或物件佈置主動式標籤,透過讀取器讀取標籤訊號的強度(RSSI:0-255),將收集到的RSSI值用無線網路傳回電腦做資料處理。
    模糊推論分為位置與物件,其隸屬函數包含RSSI、年齡及危險等級,前兩者屬於輸入因子,第三項屬於輸出因子,經由模糊推論所推論出的代表值,我們稱為危險數,如果危險數超過門檻值就會發出警報,門檻值的訂定是在使用者認為安全的情況下,將測到的最大RSSI值,經由模糊推論產生危險數,再將危險數加1,加1的原因為RSSI值並不固定,此舉為了避免沒有必要的警報。為了貼近使用者的狀況,我們提出一個回饋機制,針對不同位置與物件給予回饋,我們的回饋是將RSSI的隸屬函數往右移動,這樣使用者就必須再更接近位置或物件才會推論出與之前一樣的危險數,多次的回饋後,也會讓位置與物件的危險值都低於門檻值,即表示不再危險。
    我們模擬老人與小孩在不同的情況進行推論,一開始隸屬函數沒有經過回饋,全部都為預設狀態,因此,不管在什麼情況下老人與小孩的結果都一樣;加入回饋機制後,針對不同的使用者給予不同的回饋,多次回饋後,推論出的結果都會慢慢符合使用者。RFID與影像技術一樣可以監控家中是否安全,不過RFID的設備與影像設備比較起來相對便宜;RFID在隱私權部分也較無爭議。
    Radio Frequency Identification (RFID) becomes a popular research topic in recent years, because the cost has been reduced. The government actively promoted, and the industry started to do research and develop. RFID can be applied to many areas like Easy Card, ETC, access control cards, tickets, electronic health records, logistics and warehouse, chip of anti theft, tracking and identification.
    We aim at enhancing home safety in our research that provides a service to issue dangerous alarms at home. We use the RFID technology to detect possible dangerous objects and locations for the elderly and children at home. First, we deploy active tags in dangerous locations and attach them to objects. The reader detects the signal strength, namely RSSI values, from the tags. We use wireless network to deliver the RSSI values to the computer. Finally, the computer processes the data and performs fuzzy inference. The fuzzy inference includes both locations and objects. There are three membership functions based ages and RSSI values (location tags and object tags). The inference can result in a dangerous degree. If the dangerous degree is over the threshold, the computer will issue an alarm. We also propose a feedback mechanism to revise the membership functions for personalization, and it is applied to both location and object membership functions.
    We simulated a few situations for both children and the elderly. At first, we did not give any feedback. The system issued alarms as expected. Then we gave the system a few times of feedbacks to simulate no-danger situations. After a few feedbacks, the membership functions were adjusted to an extent that the alarm was not issued any more for the same situation. RFID is cheaper than cameras and the privacy issue can be avoided.
    顯示於類別:[資訊工程學系暨研究所] 學位論文

    文件中的檔案:

    檔案 大小格式瀏覽次數
    index.html0KbHTML208檢視/開啟

    在機構典藏中所有的資料項目都受到原著作權保護.

    TAIR相關文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回饋