進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-0908201811543200
論文名稱(中文) 基於離散多重路徑訊號模型的類神經網路室內定位之研究
論文名稱(英文) Research of Indoor Positioning Based on Discrete Multipath Signal Model with Neural Network
校院名稱 成功大學
系所名稱(中) 工程科學系
系所名稱(英) Department of Engineering Science
學年度 106
學期 2
出版年 107
研究生(中文) 李宛
研究生(英文) Wan Lee
學號 N96054057
學位類別 碩士
語文別 中文
論文頁數 59頁
口試委員 指導教授-卿文龍
口試委員-陳曉華
口試委員-郭文光
口試委員-熊大為
口試委員-陳紹基
中文關鍵字 室內定位  離散多重路徑訊號模型  射線追蹤法  倒傳遞類神經網路(BPNN)  廣益迴歸類神經網路(GRNN) 
英文關鍵字 indoor positioning  discrete multipath signal model  ray tracing  back-propagation neural network (BPNN)  generalized regression neural network (GRNN) 
學科別分類
中文摘要 由於GPS衛星定位與基地台無線定位系統在室內受到種種因素影響而無法提供精確定位,如何精確定位室內環境位置遂成為研究和應用的熱門議題。為解決無線訊號多重路徑效應對室內定位的影響,本論文提出了離散多重路徑訊號(discrete multipath signal, DMS)模型。空間中每個點接收到的多重路徑訊號不盡相同,利用此特性,將DMS模型做為位置指紋法的特徵,以射線追蹤法(ray tracing, RT)計算自由空間中每個格點的電場強度,建立DMS指紋資料庫,使用倒傳遞類神經網路(back-propagation neural network, BPNN)與廣義回歸類神經網路(generalized regression neural network, GRNN)來估測定位位置,並比較各種影響室內定位結果的因素,例如房間大小、發射源(access point, AP)數量、離線階段資料庫網格大小、類神經網路中隱藏層神經元數目。從實驗結果可得知AP的數量多寡與排列會影響定位結果,模擬實際的小房間場景(10m×8m×4m),定位誤差約為0.5m,誤差百分比為5%,約有90%的定位誤差在1m以內;大房間場景(100 m×80 m×4 m)約有90%的定位誤差在2m以內。和其他定位方法相比,小房間場景中,RSSI位置指紋法接近DMS定位結果;在大房間場景中,DMS使用BPNN與GRNN的定位結果都較其他方法來得好。
英文摘要 Global positioning system (GPS) is affected by many factors in the indoor environment and cannot provide accurate positioning. How to accurately locate in indoor environments has become very popular in recent years. In order to solve the multipath effects of wireless signal on indoor positioning, this paper proposes a discrete multipath signal model (DMS). Particularly, the multipath signals received at each point in space are not the same. Using this feature, the DMS model is used as a fingerprint for location fingerprinting. The ray tracing is used to calculate the electric field intensity of each grid point in the free space to establish the DMS fingerprint database. Subsequently, the back-propagation neural network (BPNN) and the generalized regression neural network (GRNN) are used to estimate the position. Various factors affecting the indoor positioning are evaluated, such as the size of the room, the number of access points (APs), and the number of hidden neurons in BPNN. The experimental results show that the number and arrangement of APs will significantly affect the results. Simulating a small room scenario (10 m×8 m×4 m), the error percentage is about 5%. Moreover, the distance error for the 90% error probability is within 1 m. In a large room scenario (100 m×80 m×4 m), the distance error for the 90% error probability is 2 m. Compared with conventional positioning methods, the positioning results of the proposed DMS using BPNN and GRNN are better than other methods.
論文目次 中文摘要 I
英文摘要 II
致謝 IX
目錄 X
圖目錄 XII
表目錄 XIV
第 1 章、 導論 1
1.1 基礎知識 1
1.1.1 定位情況概述 1
1.1.2 無線通道模型概論 1
1.1.3 射線追蹤法 (ray tracing, RT) 2
1.2 文獻探討 5
1.3 研究動機 8
1.4 論文架構 9
第 2 章、 室內定位系統 10
2.1 基本定位法 10
2.1.1 接收訊號角度定位法 (angle of arrival, AOA) 10
2.1.2 到達時間定位法 (time of arrival, TOA) 11
2.1.3 到達時間差定位法 (time difference of arrival, TDOA) 13
2.1.4 接收訊號強度定位法 (received signal strength indicator, RSSI) 14
2.1.5 位置指紋定位法 (location fingerprint, LF) 16
2.2 RSSI衰弱模型 18
2.2.1 自由空間傳播模型 (free space propagation model) 18
2.2.2 反射波多徑傳播模型 19
2.2.3 遮蔽模型 (shadowing model) 19
2.3 離散多重路徑訊號模型 21
第 3 章、 類神經網路 23
3.1 人工神經元模型 23
3.2 類神經網路基本架構 26
3.2.1 前饋式類神經網路 (feedforward neural network, FNN) 26
3.2.2 回饋式類神經網路 (recurrent neural network, RNN) 26
3.2.3 監督式學習 (supervised learning) 27
3.2.4 非監督式學習 (unsupervised learning) 28
3.2.5 半監督式學習 (semi supervised learning) 28
3.2.6 強化式學習 (reinforcement learning) 28
3.3 倒傳遞類神經網路(back-propagation neural network, BPNN) 30
3.4 廣義回歸類神經網路(generalized regression neural network, GRNN) 34
3.4.1 GRNN理論基礎 34
3.4.2 GRNN網路架構 35
3.4.3 K折交叉驗證 36
第 4 章、 電腦模擬與分析 37
4.1 AP數量比較 40
4.2 離線階段資料庫網格大小 42
4.3 BPNN隱藏層神經元數目比較 43
4.4 GRNN光滑因子的影響 46
4.5 雜訊對定位的影響 47
4.6 模擬隨機路徑 49
4.7 不同定位方法比較 54
第 5 章、 結論與未來工作 57
參考文獻 58
參考文獻 [1] 李志鵬, 江弘志, 林垂彩. WCDMA基頻訊號處理與系統設計實務. 滄海. (2007).
[2] 李芬, 張旭翔. 鏡像法計算室內天線場強分佈. 空間電子技術, 1, 008. (2009).
[3] 王才茂. 適用於室內環境之射線追蹤法輔助無線定位. 臺北科技大學電腦與通訊研究所學位論文. (2014).
[4] H. Liu, H. Darabi, P. Banerjee, and J. Liu. Survey of wireless indoor positioning techniques and systems. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 37(6), 1067-1080. (2007).
[5] S. Venkatraman, J. Caffery, and H. R. You. A novel TOA location algorithm using LOS range estimation for NLOS environments. IEEE Transactions on Vehicular Technology, 53(5), 1515-1524. (2004).
[6] N. Patwari,J. N. Ash,S. Kyperountas, A. O. Hero, R. L. Moses, and N.S. Correal. Locating the nodes: cooperative localization in wireless sensor networks. IEEE Signal processing magazine, 22(4), 54-69. (2005).
[7] P. Corral, E. Peña, R. Garcia, V. Almenar, and A. D. C. Lima. Distance estimation system based on ZigBee. In Computational Science and Engineering Workshops, 2008. CSEWORKSHOPS'08. 11th IEEE International Conference on (pp. 405-411). IEEE. (2008, July).
[8] P. Bahl, and V. N. Padmanabhan. RADAR: An in-building RF-based user location and tracking system. In INFOCOM 2000. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies. Proceedings. IEEE (Vol. 2, pp. 775-784). IEEE. (2000).
[9] S. He, and S.-H. Gary Chan. Wi-Fi fingerprint-based indoor positioning: Recent advances and comparisons. IEEE Communications Surveys & Tutorials, 18(1), 466-490. (2016).
[10] S. Sen, R. R. Choudhury, and S. Nelakuditi. SpinLoc: Spin once to know your location. In Proceedings of the Twelfth Workshop on Mobile Computing Systems & Applications (p. 12). ACM. (2012, February).
[11] J. Xiao, K. Wu, Y. Yi,L. Wang, and L. M. Ni. Pilot: Passive device-free indoor localization using channel state information. In Distributed computing systems (ICDCS), 2013 IEEE 33rd international conference on (pp. 236-245). IEEE. (2013, July).
[12] K. Wu, J. Xiao, Y. Yi, M. Gao, and L. M. Ni. Fila: Fine-grained indoor localization. In INFOCOM, 2012 Proceedings IEEE (pp. 2210-2218). IEEE. (2012, March).
[13] Y. Jin, W. S. Soh, and W. C. Wong. Indoor localization with channel impulse response based fingerprint and nonparametric regression. IEEE Transactions on Wireless Communications, 9(3). (2010).
[14] N. Al Khanbashi, N. Alsindi, S. Al-Araji, N. Ali, and J. Aweya. Performance evaluation of CIR based location fingerprinting. In Personal Indoor and Mobile Radio Communications (PIMRC), 2012 IEEE 23rd International Symposium on (pp. 2466-2471). IEEE. (2012, September).
[15] S. Sen, B. Radunovic, R. R. Choudhury, and T. Minka. You are facing the Mona Lisa: spot localization using PHY layer information. In Proceedings of the 10th international conference on Mobile systems, applications, and services (pp. 183-196). ACM. (2012, June).
[16] Y. Chapre, A. Ignjatovic, A. Seneviratne, and S. Jha. Csi-mimo: Indoor wi-fi fingerprinting system. In Local Computer Networks (LCN), 2014 IEEE 39th Conference on (pp. 202-209). IEEE. (2014, September).
[17] 王建又. 應用支持向量機於感測網路定位之研究. 中山大學應用數學系研究所學位論文, 1-68. (2016).
[18] 馮雪元. 無線信號傳播衰弱淺析. 科技視界, 36, 066. (2014).
[19] X. Cai, and G. B. Giannakis. Bounding performance and suppressing intercarrier interference in wireless mobile OFDM. IEEE Transactions on communications, 51(12), 2047-2056. (2003).
[20] D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Learning representations by back-propagating errors. nature, 323(6088), 533. (1986).
[21] 沈銘浩. 以RSSI為基礎之無線感測網路定位系統研究. 銘傳大學電腦與通訊工程學系碩士班碩士論文. (2012).
[22] D. F. Specht. A general regression neural network. IEEE transactions on neural networks, 2(6), 568-576. (1991).
[23] 王小川, 史峰, 郁磊, and 李洋. MATLAB 神經網路 43 個案例分析. 北京:北京航空航天大學出版社. (2013).
[24] 吳奕蓉. 在非直視環境下基於半正定規劃之混合型TOA和AOA定位. 成功大學電腦與通信工程研究所碩士論文. (2017).
[25] 林坤政. 利用無線感測網路模組進行室內定位之研究. 成功大學電機工程學系學位元論文, 1-88. (2007).
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2021-08-01起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2021-08-01起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw