簡易檢索 / 詳目顯示

回結果列表
研究生： 黃閔珊
Huang, Min-Shan
論文名稱： 於行動裝置上具持續性和個人化之日常行為辨識系統設計
A Framework for Continuous and Personalized Daily Activity Recognition on Mobile Devices
指導教授： 曾新穆
Tseng, Shin-Mu
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2014
畢業學年度： 102
語文別： 英文
論文頁數： 95
中文關鍵詞： 行為辨識 、個人化模型 、低電能消耗 、日常行為記錄 、行動裝置
外文關鍵詞： activity recognition, personalized model, energy efficiency, daily activity report, mobile devices
相關次數： 點閱：123  下載：4 
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

    • 基於行動裝置之行為辨識是普適計算中的一個重要研究主題，且已應用於許多領域，例如健康照護、情境感知與安全促進等。目前已有行為辨識系統相繼被開發，但是仍有以下不足之處：1) 在現有系統中，都是使用一般通用的模型來辨識使用者行為，而缺乏個人化特色； 2) 因受限於行動裝置上的有限的電池容量及記憶體，目前現有系統較無法長時間紀錄行為辨識後的結果，並產生全天性之日常行為記錄。有鑒於此，本研究提出一個新的架構，來建立植基於行動裝置之個人化行為辨識系統，且能持續性和長時間的紀錄行為辨識後的結果，作為日常行為的紀錄報告。此系統利用在行動裝置內嵌的三維加速器，即時辨識使用者的行為，不僅能有高準確率，也能耗費較少的電池使用量。此外，我們亦分析與比較兩種加速器資料分段法 ─ 固定滑動視窗法和行為改變點偵測法，以及兩種具代表性的分類演算法 ─ K-Nearest Neighbors 和 Support Vector Machine 在系統中的優缺點。最後，經由廣泛的實驗評估，本論文提出的持續性和個人化之日常行為辨識系統能夠在多種公開的資料集中具有一定的準確率。

    Activity Recognition (AR) has attracted an immeasurable amount of attention in pervasive computing. Although a number of AR systems have been developed to meet the demands of emerging fields, the following problems still remain to be addressed: (1) the existing systems do not adopt personalized models to recognize users’ activities; 2) due to limitation of battery and memory on mobile devices, the existing systems are not able to record the recognized activities over a long time. This thesis thus proposes a framework for Continuous and Personalized Daily Activity Recognition System which utilizes a single accelerometer embedded in mobile devices to recognize users’ activities in a timely manner, and that enables the implemented system to be promised of accuracy and energy efficiency for generating a full-day Daily Activity Report. Moreover, this thesis analyzes the advantages and drawbacks of two segmentation methods (i.e., Fixed Window Size and Change Point Detection) and two classification algorithms (i.e., K-Nearest Neighbors and Support Vector Machine) in terms of theory and experiments with public datasets.

    摘要 I ABSTRACT II 誌謝 III Content IV List of Tables VI List of Figures VIII 1. Introduction 1 1.1 Background 1 1.2 Motivation 5 1.3 Challenges 7 1.4 Research Aims 9 1.5 Thesis Organization 10 2. Related Works 11 2.1 Activity Recognition on Mobile Devices 11 2.2 Online Activity Recognition 14 2.3 Energy Efficiency for Activity Recognition 15 2.4 Personalization for Activity Recognition 17 2.5 Algorithms for Activity Recognition 19 2.5.1 Online Activity Recognition using K-Nearest Neighbors 21 2.5.2 Online Activity Recognition using Support Vector Machine 23 2.6 Summary of Related Works 24 3. Proposed Framework 26 3.1 Overview of Our Proposed Framework 26 3.2 Preliminary 28 3.3 Model Building Phase 29 3.3.1 Data Separation 30 3.3.2 Segmentation with Fixed Window Size 30 3.3.3 Preprocessing 31 3.3.4 Feature Extraction 33 3.3.5 Classifier Building 35 3.3.5.1 K-Nearest Neighbors 36 3.3.5.2 Support Vector Machine 41 3.4 Activity Recognition Phase 41 3.4.1 Segmentation with Change Point Detection 41 3.4.2 Online Classification 44 3.4.2.1 Online Classification using K-Nearest Neighbors 45 3.4.2.2 Online Classification using Support Vector Machine 46 3.4.3 Classifier Updating 46 3.4.3.1 The K-Nearest Neighbors Model Updating 46 3.4.3.2 The Support Vector Machine Model Updating 47 4. Empirical Evaluation 49 4.1 Dataset Description 49 4.2 Experimental Metrics and Parameters 53 4.2.1 The Definition of the Experimental Metrics 53 4.2.2 The Definition of the Experimental Parameters 56 4.3 Experimental Results 57 4.3.1 The Impact of Fragments on Accuracy 57 4.3.1.1 Experimental Flow for Fragments 57 4.3.1.2 The Experimental Results of Fragments 58 4.3.2 The Impact of Segments on Accuracy 60 4.3.2.1 Experimental Flow for Segments 61 4.3.2.2 The Experimental Results of Segments 61 4.3.3 The Effectiveness of Segmentation with Change Point Detection 63 4.3.4 The Impact of Window Size on Accuracy 67 4.3.5 The Impact of Continuous Activity on Accuracy 68 4.3.6 The Impact of Personalized Models on Accuracy 71 4.3.7 The Execution Time of Training Models 74 4.3.8 The Usage of Memory Resources 75 4.3.9 Energy Efficiency of the Proposed System 77 4.4 Discussions on Experimental Results 77 5. Conclusions and Future Work 83 5.1 Conclusions 83 5.2 Future Work 85 References 86 VITA 95

    [1] K. Z. Ali and S. Won, “A Model for Abnormal Activity Recognition and Alert Generation System for Elderly Care by Hidden Conditional Random Fields Using R-Transform and Generalized Discriminant Analysis Features,” Telemedicine & e-Health, vol. 18, Issue 8, page 641, 2012.
    [2] D. Anguita, A. Ghio, L. Oneto, X. Parra and J. L. Reyes-Ortiz, “Energy efficient smartphone-based activity recognition using fixed-point arithmetic,” Journal of Universal Computer Science. Special Issue in Ambient Assisted Living: Home Care. vol. 19, 2013.
    [3] D. Anguita, A. Ghio, L. Oneto, X. Parra and J. L. Reyes-Ortiz, “Human Activity Recognition on Smartphones using a Multiclass Hardware-Friendly Support Vector Machine,” International Workshop of Ambient Assited Living, 2012.
    [4] L. Atallah, B. Lo, R. King, “Sensor positioning for activity recognition using wearable accelerometers,” IEEE Transactions on Biomedical Circuits and System, 5(4):320–329, 2011.
    [5] A. Avci, S. Bosch, M. Marin-Perianu, R. Marin-Perianu and P. Havinga , “Activity Recognition Using Inertial Sensing for Healthcare, Wellbeing and Sports Applications: A Survey,” 23rd International Conference on Architecture of Computing Systems (ARCS), 2010.
    [6] L. Bao and S. S. Intille, “Activity Recognition from User-Annotated Acceleration Data,” Pervasive Computing Lecture Notes in Computer Science, vol. 3001, pages 1-17, 2004.
    [7] T. Brezmes, J.-L. Gorricho and J. Cotrina, “Activity Recognition from Accelerometer Data on a Mobile Phone,” Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living Lecture Notes in Computer Science, vol. 5518, pages 796-799, 2009.
    [8] R. Chavarriaga, H. Sagha, A. Calatroni, S. T. Digumarti, G. Tröster, J. R. Millán, and D. Roggen, “The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition,” Pattern Recognition Letters, vol. 34, Issue 15, pages 2033–2042, 2013.
    [9] D. Choujaa and N. Dulay, “Activity recognition using mobile phones: achievements, challenges, and recommendations,” How To Do Good Research in Activity Recognition: experimental methodology, performance evaluation and reproducibility, Workshop in conjunction with Pervasive, 2010.
    [10] W. Dargie, “Analysis of Time and Frequency Domain Features of Accelerometer Measurements,” in Proceeding of the 3rd IEEE Workshop on Performance Modeling and Evaluation of Computer and Telecommunication Networks, 2009.
    [11] S. Das, L. Green, B. Perez, and M. Murphy, “Detecting user activities using the accelerometer on android smartphones,” The Team for Research in Ubiquitous Secure Technology, TRUSTREU Carnefie Mellon University, 2010.
    [12] M. O. Derawi, C. Nickely, P. Bours, and C. Busch, “Unobtrusive user-authentication on mobile phones using biometric gait recognition,” in Proceedings of the 6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pages 306–311, 2010.
    [13] S. Dernbach, B. Das, N. C. Krishnan, B. L. Thomas and D. J. Cook, “Simple and Complex Activity Recognition through Smart Phones,” in Proceedings of Intelligent Environments, 2012.
    [14] A. Duque, F. J. Ordóñez, P. Toledo and A. Sanchis, “Offline and Online Activity Recognition on Mobile Devices Using Accelerometer Data,” Ambient Assisted Living and Home Care Lecture Notes in Computer Science, Vol. 7657, pages 208-215, 2012.
    [15] J. B. Gomes, S. Krishnaswamy, M. M. Gaber, P. A. C. Sousa and E. Menasalvas, “MARS: A Personalised Mobile Activity Recognition System,” 13th International Conference on Mobile Data Management, pages 316-319, 2012.
    [16] J. B. Gomes, S. Krishnaswamy, M. M. Gaber, P. A. C. Sousa and E. Menasalvas, “Mobile activity recognition using ubiquitous data stream mining,” Data Warehousing and Knowledge Discovery Lecture Notes in Computer Science, vol. 7448, pages 130-141, 2012.
    [17] D. Gordon, J. Czerny, T. Miyaki and M. Beigl, “Energy-Efficient Activity Recognition Using Prediction,” 16th International Symposium on Wearable Computers, pages 29-36 ,2012.
    [18] G. Guo, H. Wang, D. Bell, Y. Bi and K. Greer, “KNN Model-Based Approach in Classification,” On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE Lecture Notes in Computer Science, vol. 2888, pages 986-996, 2003.
    [19] T. Guo, Z. Yan, K. Aberer, “An Adaptive Approach for Online Segmentation of Multi-Dimensional Mobile Data,” in Proceedings of the 11th International ACM Workshop on Data Engineering for Wireless and Mobile Access, pages 7-14, 2012.
    [20] Z. He, L. Jin, “Activity Recognition from acceleration data Based on Discrete Consine Transform and SVM,” in Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics, pages 5041-5044, 2009.
    [21] S. Kaghyan and H. Sarukhanyan, “Activity recognition using K-nearest neighbor algorithm onsmartphone with Tri-axial accelerometer,” International Journal of Informatics Models and Analysis, pages 146-156, 2012.
    [22] N. Kawaguchi, N. Ogawa, Y. Iwasaki, K. Kaji, T. Terada, K. Murao, S. Inoue, Y. Kawahara, Y. Sumi,and N. Nishio, “HASC Challenge: Gathering Large Scale Human Activity Corpus for the Real-World Activity Understandings,” in Proceedings of the 2nd Augmented Human International Conference, pages 27:1-27:5, 2011.
    [23] M. Keally, G. Zhou, G. Xing, J. Wu and A. J. Pyles, “PBN: towards practical activity recognition using smartphone-based body sensor networks,” in Proceedings of the 9th International Conference on Embedded Networked Sensor Systems, 2011.
    [24] S. M. Khan, M. R. Ahamed, and R. O. Smith, “A feature extraction method for realtime human activity recognition on cell phones,” in Proceedings of International Symposium on Quality of Life Technology, 2011.
    [25] A. M. Khan, A. Tufail, A. M. Khattak, and T. H. Laine, “Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs,” International Journal of Distributed Sensor Networks, vol. 2014, Article ID 503291, 14 pages, 2014.
    [26] M. Kose, O. Incel, and C. Ersoy, “Online Human Activity Recognition on Smart Phones,” 2nd International Workshop on Mobile Sensing, pages 0-4, 2012.
    [27] J. R. Kwapisz, G. M. Weiss, and S. A. Moore, “Activity recognition using cell phone accelerometers,” SIGKDD Explor. Newsl., 12:74–82, 2011.
    [28] Y. Liang, X. Zhou, Z. Yu, B. Guo and Y. Yang, “Energy Efficient Activity Recognition Based on Low Resolution Accelerometer in Smart Phones,” Advances in Grid and Pervasive Computing Lecture Notes in Computer Science, vol. 7296, pages 122-136, 2012.
    [29] B. Liu, T. J. Huang, J. Cheng and W. Gao, “A New Statistical-based Method in Automatic Text Classification,” Journal of Chinese Information Processing, 16(6):18-24, 2002.
    [30] J. W. Lockhart and G. M. Weiss, “The Benefits of Personalized Smartphone-Based Activity Recognition Models,” in Proceedings of the 2014 SIAM International Conference on Data Mining, 2014.
    [31] C. McCall, K. Reddy and M. Shah, “Macro-Class Selection for Hierarchical K-NN Classification of Inertial Sensor Data,” Second International Conference on Pervasive and Embedded Computing and Communication Systems (PECCS), 2012.
    [32] Y. Nam, JW. Park, “Physical Activity Recognition using a Single Triaxial Accelerometer and a Barometric Sensor for Baby and Child Care in a Home Environment,” Journal Of Ambient Intelligence and Smart Environments, 5(4):381–402, 2013.
    [33] J. Parkka, L. Cluitmans and M. Ermes, “Personalization Algorithm for Real-Time Activity Recognition Using PDA, Wireless Motion Bands, and Binary Decision Tree,” in IEEE Transactions on Information Technology in Biomedicine, vol. 14, no. 5, pages 1211-1215, 2010.
    [34] L. Qiang, J. A. Stankovic, M. A. Hanson, A. T. Barth, J. Lach, and Z. Gang, "Accurate, Fast Fall Detection Using Gyroscopes and Accelerometer-Derived Posture Information," in Wearable and Implantable Body Sensor Networks, pages 138-143, 2009.
    [35] A. Rai, Z. Yan, D. Chakraborty, T. K. Wijaya, and K. Aberer, “Mining complex activities in the wild via a single smartphone accelerometer,” in Proceedings of the Sixth International Workshop on Knowledge Discovery from Sensor Data, ser. SensorKDD ’12, pages 43–51, 2012.
    [36] N. Ravi, N. Dandekar, P. Mysore, M.L. Littman, “Activity recognition from accelerometer data,” in Proceedings of the 17th Conference on Innovative Applications of Artificial Intelligence, pages 1541–1546, 2005.
    [37] A. Reiss and D. Stricker, “Personalized mobile physical activity recognition,” in Proceedings of IEEE 17th International Symposium on Wearable Computers, 2013.
    [38] A. Reiss, D. Stricker, “Introducing a New Benchmarked Dataset for Activity Monitoring,” 16th International Symposium on Wearable Computers (ISWC), pages 108-109, 2012.
    [39] D. Roggen, K. Forster, A. Calatroni, T. Holleczek, Y. Fang, G. Troster, P. Lukowicz, G. Pirkl, D. Bannach, K. Kunze, A. Ferscha, C. Holzmann, A. Riener, R. Chavarriaga, and J. del R. Millan, "Opportunity: Towards opportunistic activity and context recognition systems," IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks & Workshops (WoWMoM), pages 1-6, 2009.
    [40] M. Sharifzadeh, F. Azmoodeh, and C. Shahabi, “Change Detection in Time Series Data Using Wavelet Footprints,” in Proceedings of the 9th international conference on Advances in Spatial and Temporal Databases, pages 127-144, 2005.
    [41] D. Sharma and S. Khurana, “Secure personal recognition system based on hashes keys,” International Journal of Advanced Science and Technology, vol. 47, 2012.
    [42] P. Siirtola, and J. Röning "Recognizing Human Activities User-independently on Smartphones Based on Accelerometer Data," International Journal of Interactive Multimedia & Artificial Intelligence, vol. 1, no. 5, 2012.
    [43] S. N. Srirama, H. Flores abd C. Paniagua, “Zompopo: Mobile Calendar Prediction Based on Human Activities Recognition Using the Accelerometer and Cloud Services,” 5th International Conference on Next Generation Mobile Applications, Services and Technologies (NGMAST), pages 63-69, 2011.
    [44] L. Sun, D. Zhang, B. Li, B. Guo, S. Li, M. Mokhtari, “Activity recognition on an accelerometer-embedded mobile phone with varying positions and orientations,” in 7th International Conference on Ubiquitous Intelligence and Computing, 2010.
    [45] S. Thiemjarus, “A Device-Orientation Independent Method for Activity Recognition,” in Proceedings of the 2010 International Conference on Body Sensor Networks, pages 19-23, 2010.
    [46] W. Ugulino, D. Cardador, K. Vega, E. Velloso, R. Milidiu and H. Fuks, “Wearable Computing: Accelerometers' Data Classification of Body Postures and Movements,” in Proceedings of 21st Brazilian Symposium on Artificial Intelligence, pages 52-61, 2012.
    [47] V. Q. Viet, A. F. P. Negera, H. M. Thang and D. Choi, “Energy saving in forward fall detection using mobile accelerometer,” International Journal of Distributed Systems and Technologies, vol. 4, no. 1, pages 78–94, 2013.
    [48] Q. V. Vo, M. T. Hoang, and D. Choi, “Personalization in Mobile Activity Recognition System Using -Medoids Clustering Algorithm,” International Journal of Distributed Sensor Networks, vol. 2013, Article ID 315841, 12 pages, 2013.
    [49] A. K. Wagner, A. K. Wagner, F. Zhang and D. Ross-Degnan, “Segmented regression analysis of interrupted time series studies in medication use research,” Journal of Clinical Pharmacy and Therapeutics, vol. 27, Issue 4, pages 299–309, 2002.
    [50] G. M. Weiss and J. W. Lockhart, “The impact of personalization on smartphone-based activity recognition,” in Proceedings of 26th Conference on Artificial Intelligence (AAAI), Workshop on Activity Context Representation, 2012.
    [51] G. M. Weiss and J. W. Lockhart, “Identifying user traits by mining smart phone accelerometer data”, in International Workshop on Knowledge Discovery from Sensor Data (SensorKDD), 2011.
    [52] Z. Xing, J. Pei, P. S. Yu, and K. Wang, “Extracting interpretable features for early classification on time series,” in Proceedings of the 11th SIAM International Conference on Data Mining, pages 439-451, 2011.
    [53] Y. Xue, L. Jin, “A Naturalistic 3D Acceleration-based Activity Dataset & Benchmark Evaluations,” in Proceedings of the 2010 IEEE International Conference on Systems, Man, and Cybernetics, pages 4081-4085, 2010.
    [54] Z. Yan, D. Chakraborty, A. Misra, H. Jeung and K. Aberer, “SAMMPLE: Detecting Semantic Indoor Activities in Practical Settings using Locomotive Signatures,” 16th International Symposium on Wearable Computers, 2012.
    [55] Z. Yan, V. Subbaraju, D. Chakraborty, A. Misra, and K. Aberer, “Energy-efficient continuous activity recognition on mobile phones: An activity-adaptive approach,” in Proceedings of the 16th Annual International Symposium on Wearable Computers, 2012.
    [56] J. Yang, ”Toward physical activity diary: Motion recognition using simple acceleration features with mobile phones,” in Proceedings of the 1st International Workshop on Interactive Multimedia for Consumer Electronics, pages 1-10, 2009.
    [57] L. Ye and E. Keogh, “Time Series shapelets: a new primitive for data mining,” in Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data mining, pages 947-956, 2009.
    [58] Z. Yong, “An Improved kNN Text Classification Algorithm based on Clustering”, Journal of Computers, vol. 4, No. 3, 2009.
    [59] M. Yoshizawa, W. Takasaki, R. Ohmura, “Parameter exploration for response time reduction in accelerometer-based activity recognition,” in Proceedings of the 2013 ACM Conference on Pervasive and Ubiquitous Computing, pages 653–664, 2013.
    [60] Y. Zheng, W.-K. Wong, X. Guan and S. Trost, “Physical Activity Recognition from Accelerometer Data Using a Multi-Scale Ensemble Method,” Twenty-Fifth Annual Conference on Innovative Applications of Artificial Intelligence, 2013.
    [61] HASC Hub. Available online: http://hub.hasc.jp/ (accessed on 21 July 2014).
    [62] Activity and Context Recognition with Opportunistic Sensor Configurations. Available online: http://www.opportunity-project.eu/challengeDataset (accessed on 21 July 2014).
    [63] Physical Activity Monitoring for Aging People. Available online: http://www.pamap.org/index.html (accessed on 21 July 2014).
    [64] Human-Computer Intelligent Interaction Label. Available online: http://www.hcii-lab.net/data/scutnaa/EN/naa.html (accessed on 21 July 2014).
    [65] Center for Research in Computer Vision (CRCV). Available online: http://crcv.ucf.edu/main (accessed on 21 July 2014).
    [66] Group of Research and Development of Groupware Technologies. Available online:
    http://groupware.les.inf.puc-rio.br/har (accessed on 21 July 2014).

    下載圖示 校內：2019-09-04公開
    校外：2019-09-04公開
    QR CODE