現在位置首頁 > 博碩士論文 > 詳目
論文中文名稱:應用機器學習演算法實現行動裝置感測器動態分析室內定位 [以論文名稱查詢館藏系統]
論文英文名稱:Application of Machine Learning Algorithms to Achieve a Mobile Device Dynamic Analysis of Indoor Positioning Sensor [以論文名稱查詢館藏系統]
院校名稱:臺北科技大學
學院名稱:管理學院
系所名稱:資訊與財金管理系碩士班
畢業學年度:103
畢業學期:第二學期
中文姓名:陳柏志
英文姓名:PO CHIH CHEN
研究生學號:102938008
學位類別:碩士
語文別:中文
指導教授中文名:吳建文
指導教授英文名:CHIEN WEN WU
口試委員中文名:陳育威;李炯三
中文關鍵詞:行動裝置網路資料庫室內定位機器學習感測器
英文關鍵詞:Mobile devicesnetwork databasesindoor positioningmachine learningsensors
論文中文摘要:近年來行動裝置科技的日新月異,行動感測裝置為生活帶來的便利也隨之受到重視。其中,室內定位的相關研究為主要的應用類別,然而行動裝置感測器最有價值的不在於感測資料的蒐集,而是藉由感測資料進行使用者周遭狀態的分析判讀,根據過往的感測資料建構室內定位的感測模型,並且能利用該模型針對訊息做即時分析。因此,如何結合行動裝置感測技術包含加速度感應器、方位感應器、旋轉向量感應器、磁場感應器,並且連接雲端資料庫的基礎設施,加上機器學習演算法,從雲端資料庫接收不同來源感應器的訊號資料,為實現行動裝置感測器動態分析室內定位技術發展的關鍵。
本研究進行真實的室內環境實驗,設計了MDP定位演算法對實驗環境進行分析,發現利用了馬可夫特性找出了定位結果在精度三公尺以內含有高比例的方法,且在精度一公尺以下在特定的室內環境情況有高過三角定位的表現。
論文英文摘要:In recent years, mobile device technology advances, actions sensing device for the convenience of life also will be taken seriously. Among them, the relevant research on indoor positioning for major application categories, but the most valuable mobile device sensor is not sensing data collection, but data were analyzed by sensing interpretation users around the state, according to the past Construction of indoor location sensing data sensing model, and can use this model for the message to do instant analysis. So, how to combine mobile devices sensing techniques include acceleration sensors, position sensors, rotation vector sensors, magnetic sensors, and cloud database connectivity infrastructure, coupled with machine learning algorithms, received from different sources cloud repositories sensor signal data for the realization of a mobile device sensor key indoor positioning technology development dynamic analysis. The study was conducted indoor environment experiment designed MDP positioning algorithm to analyze the experimental environment, found that the use of the Markov method of locating feature to find the results contain a high proportion of less than three meters accuracy, and precision of one meter or less in at indoor environmental conditions specific high performance through triangulation.
論文目次:目錄

摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
第二章 文獻探討 3
2.1 空間定位技術應用 3
2.1.1以全球定位系統為基礎的定位應用 4
2.1.2基於智慧手機的室內PDR 定位系統 4
2.1.3以無線通道模型為基礎的應用 5
2.2以Android 為基礎的感測器應用 3
2.3機器學習演算法 6
2.3.1強化學習演算法 7
2.3.2馬可夫決策程序 8
第三章 系統架構與設計 9
3.1 建置基本監測環境 10
3.1.1 建立環境參數 11
3.2 三角定位法 12
3.3 參數分析 14
第四章 實驗結果與分析 16
4.1 實驗配置 16
4.2 實驗結果 17
4.2.1 三角定位實驗結果 18
4.2.2強化學習演算法定位實驗結果 20
4.3 綜合比較 28
第五章 結論 30
參考文獻 31
論文參考文獻:參考文獻
[1] W. Kang, S. Nam, Y. Han, and S. Lee, ”Improved Heading Estimation for Smartphone-Based Indoor Positioning Systems,” in Proc. IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, 2012.
[2] M. Popa, J. Ansari, J. Riihijarvi, P.Mahonen, ”Combining Cricket System and Inertial Navigation for Indoor Human Tracking,” in Proc. WCNC, 2008.
[3] W. C .Hu, N. Kaabouch, L. Chen and H. J. Yang, “Incremental location searching for route anomaly detection,” IEEE International Conference on Electro/Information Technology (EIT), 15-17 May 2011, pp.1-6.
[4] Jimenez A R, Seco F, Zampella F, et al. PDR with a Footmounted IMU and Ramp Detection[J]. Sensors, 2011, 11(10):9393-9410.
[5] M. Fowler, Domain Specific Languages, AW, 2010. [10] R.Jirawimut, P. Ptasinski, V. Garaj, F. Cecelja, W.Balachandran, ”A Method for Dead Reckoning ParameterCorrection in Pedestrian Navigation System,” in Proc. IEEE Instrumentation an Measurement Technology Conference, 2001.
[6] J. Werb and C. Lanzl, “Designing a Positioning System for Finding Things and People Indoors,” IEEE Spec., vol. 35, no. 9,Sep. 98, pp. 71–78.
[7] A. H. Sayed, A. Tarighat, “Network-basedwireless location: challenges faced in developing techniques for accurate wireless location information,” IEEE Signal Processing Magazine, vol. 22, pp. 24-40, July 2005.
[8] A. Coates, B. Huval, T. Wang, D. J. Wu, A. Y. Ng, and B. Catanzaro. Deep learning with COTS HPC. In International Conference on Machine Learning, 2013.
[9] R. S. Sutton, “Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding,” Advances in Neural Information Processing Systems, no. 8, MIT Press, 1996, pp.1038-1044.
[10] M.Alnaanah and A. Aljaafreh, “A simplified method for off-line track matching for fleet managements,” 2011 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT), 6-8 Dec. 2011, pp.
[11] Sørensen and T. Berglund, “Location tracking on smartphone using IEEE802.11b/g based WLAN infrastructure at ITU of Copenhagen,” Pervasive Computing Course 2010, fall 2010..
[12] P. Barsocchi, S. Lenzi, S. Chessa and G. Giunta, “A novel approach to indoor RSSI localization by automatic calibration of the wireless propagation model,” Vehicular Technology Conference, 2009, pp. 1-5
[13] J. Y. Wang, C. P. Chen, T. S. Lin, C. L. Chuang, T. Y. Lai and J. A. Jiang, “High-precision RSSI-based indoor localization using a transmission power adjustment strategy for wireless sensor networks,” The 14th IEEE International Conference on High Performance Computing And Communications /The 9th IEEE International Conference on Embedded Software And Systems (HPCC-2012/ICESS-2012), 25-27 June 2012, pp. 1634-1638.
[14] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. 2014.
[15] A. Coates, B. Huval, T. Wang, D. J. Wu, A. Y. Ng, and B. Catanzaro. Deep learning with COTS HPC. In International Conference on Machine Learning, 2013.
[16] A. Mohamed, G. Dahl, and G. Hinton. Acoustic modeling using deep belief networks. IEEE Transactions on Audio, Speech, and Language Processing, (99), 2011.
[17] 蘇木春、張孝德/著,機器學習:類神經網路、模糊系統以及基因演算法則(修訂二版)全華圖書
論文全文使用權限:同意授權於2020-07-14起公開