跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 郭士賢
Shih-Hsien Kuo
論文名稱： Indoor/Outdoor Detection of Smartphones
指導教授： 孫敏德
Min-Te Sun
口試委員:
學位類別： 碩士
Master
系所名稱： 資訊電機學院 - 資訊工程學系在職專班
Executive Master of Computer Science & Information Engineering
論文出版年： 2017
畢業學年度： 105
語文別： 英文
論文頁數： 51
中文關鍵詞： 室內外定位 、機器學習 、手機感測器
外文關鍵詞： Mobile phone sensor, Pattern classification
相關次數： 點閱：19  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 近十年來智慧型手機的發展迅速,隨著軟硬體的提升,應用也跟著多元化。本篇論文將應用智慧型手機上的感測器(加速度器, 陀螺儀, 和重力計等等)來收集資料,並且使用機器語言來分析資料以達到偵測使用者是否處於室內或戶外。使用的機器語言演算法包含kNN, Naive Bayes, ANN和SVM。方法上首先會使用收集到的一部分資料來學習並建構模型; 另一部分的資料會套用這些演算法的模型來顯示預測室內戶外的準確率。接下來會針對可以調整參數的演算法,像是kNN的k值, ANN的隱藏層數量做進一步的效能調校。另一方面也會使用k-fold cross validation 和AUC來驗證建構模型是否過適(overfitting)。最後的實驗結果我們得到SVM在4個演算法中能產生穩定的建構模型與高度準確度。

    The indoor/outdoor detection for smartphones has many potential applications. In this thesis, the practice of indoor/outdoor detection is treated as the supervised learning problem. The data are collected from different time and places, which contain features from IMU sensors (i.e., accelerometers, gyroscope, and gravity and so on). A number of machine learning algorithms, including kNN, Naive Bayes, ANN, and SVM, are adopted to build the prediction model using the training dataset, and the performance of different models are verified using the test dataset. The parameters in some models are tuned, such as k value in kNN and the number of hidden layers in ANN, in order to obtain the best prediction performance. On the other hand, 10-fold cross validation and AUC are used to verify if any model overfits the training dataset. At the end, we have identified that SVM with linear kernel has the best and most stable performance for smartphone indoor/outdoor detection among all different learning algorithms.

    1 Introduction 1 2 RelatedWork 4 3 Preliminary 6 3.1 kNN . . . . . . . . . . . . . . . . . . . . . . . . . 6 3.2 Naive Bayes . . . . . . . . . . . . . . . . . . . . . 8 3.3 ANN . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.4 SVM . . . . . . . . . . . . . . . . . . . . . . . . . 12 4 Design 15 4.1 Data preprocessing . . . . . . . . . . . . . . . . . 15 4.2 Data preparation for training models . . . . . . . . 19 4.2.1 kNN . . . . . . . . . . . . . . . . . . . . . . . . 19 4.2.2 ANN . . . . . . . . . . . . . . . . . . . . . . . . 20 4.2.3 SVM . . . . . . . . . . . . . . . . . . . . . . . . 21 5 Performance 22 5.1 Data collection . . . . . . . . . . . . . . . . . . . 22 5.2 The holdout method . . . . . . . . . . . . . . . .. . 22 5.2.1 k-fold cross validation . . . . . . . . . . . . . . 23 5.3 Overfitting on training data . . . . . . . . . . . . 24 5.4 Performance metrics . . . . . . . . . . . . . . . . . 24 5.5 ROC curves . . . . . . . . . . . . . . . . . . .. . . 27 5.5.1 AUC . . . . . . . . . . . . . . . . . . . . . . . . 28 5.6 Experiments . . . . . . . . . . . . . . . . . . . . . 29 6 Conclusions 40 Reference 41

    [1] Android. https://www.android.com.
    [2] Google play. https://play.google.com/store.
    [3] R. https://www.r-project.org/.
    [4] Androsensor, 2015. https://play.google.com/store/apps/details?id=com.fivasim.androsensor&hl=zh_TW.
    [5] P. Bahl and V. N. Padmanabhan. Radar: an in-building rf-based user location and tracking system. In Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat.No.00CH37064), volume 2, pages pp. 775{784, 2000.
    [6] S. K. Datta, C. Bonnet, and N. Nikaein. Android power management: Current and future trends. In 2012 The First IEEE Workshop on En-abling Technologies for Smartphone and Internet of Things (ETSIoT),pages 48{53, 2012.
    [7] A. El-Rabbany. Introduction to GPS : The Global Positioning System.ARTECH HOUSE, INC., 2002.
    8] H. Jia, S. Su, W. Kong, H. Luo, and G. Shang. MobiIO: Push the limit of indoor/outdoor detection through human's mobility traces. In 2014 International Conference on Indoor Positioning and Indoor Navigation (IPIN), pages 197{202, 2014.
    [9] N. Kroll, M. Jäger, and S. Süß. Context-aware indoor-outdoor detection for seamless smartphone positioning. In The Eighth International Conference on Advanced Geographic Information Systems, Applications, and Services, 2016.
    [10] M. Kuhn and K. Johnson. Applied Predictive Modeling. Springer Science, 2013.
    [11] B. Lantz. Machine Learning with R Second Edition. Packt Publishing Ltd., 2015.
    [12] X. Wang and G. Bertrand. Some sequential algorithms for a generalized distance transformation based on minkowski operations. IEEE Transac-tions on Pattern Analysis and Machine Intelligence, 14(11):1114-1121,1992.
    [13] P. Zhou, Y. Zheng, Z. Li, M. Li, and G. Shen. IOdetector: A generic service for indoor outdoor detection. In Proceedings of the 10th ACM Conference on Embedded Network Sensor Systems, SenSys '12, pages 113-126, 2012.

    QR CODE
    :::