查詢結果分析
來源資料
頁籤選單縮合
| 題 名 | 不同裝置間收訊強度差異之自動調適=Adopting Unsupervised Learning for Solving RSS Hardware Variance Problem |
|---|---|
| 作 者 | 崔文; 莊育祥; | 書刊名 | 電腦與通訊 |
| 卷 期 | 127 2009.03[民98.03] |
| 頁 次 | 頁91-98 |
| 專 輯 | 新型態網際網路服務技術專題 |
| 分類號 | 448.8 |
| 關鍵詞 | 無線定位系統; 無線網路; 自動學習; Wireless localization systems; WiFi network; Unsupervised learning; |
| 語 文 | 中文(Chinese) |
| 中文摘要 | 在使用收訊強度(RSS)的定位技術中,不同裝置的收訊強度差異可能會造成很大的定位誤差。雖然手動調整定位模型可以獲得大幅改善,但過於費工。本文提出自動學習的方法,實驗顯示在100秒的學習時間內就可以達成定位準度的改善。 |
| 英文摘要 | Hardware variance can significantly degrade the positional accuracy of a RSS-based localization system. Although manual adjustment can reduce positional error, it is not scalable for increasing number of devices. We propose in this paper a fully automatic method based on unsupervised learning for solving the hardware variance solution. We have designed and implemented our methods in a working WiFi positioning system, and evaluated them using different hardware systems with varying degrees of RSS patterns. Our experimental results have demonstrated the effectiveness of our methods in both positional accuracy improvements and convergent time. |
本系統中英文摘要資訊取自各篇刊載內容。