(3.235.191.87) 您好!臺灣時間:2021/05/13 14:17
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

: 
twitterline
研究生:張釜菘
研究生(外文):Fu-Sung Chang
論文名稱:使用SVM分類器於醫療保健之應用-利用智慧型手機內建之三軸加速度計於動作辨識
論文名稱(外文):The application of using the SVM classifier in medical care- use the smartphone with triaxial accelerometer for the posture recognitionFu-Sung ChangInstitute of Information ManagementThe application of using the SVM classifier in medical care- use the smartphone with triaxial accelerometer for the posture recognitionFu-Sung ChangInstitute of Information ManagementThe application of using the SVM classifier in medical care- use the smartphone with triaxial accelerometer for the posture recognitionFu-Sung ChangInstitute of Information ManagementThe application of using the SVM classifier in medical care- use the smartphone with triaxial accelerometer for the posture recognition
指導教授:郝沛毅郝沛毅引用關係
指導教授(外文):郝沛毅
學位類別:碩士
校院名稱:國立高雄應用科技大學
系所名稱:資訊管理系
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:中文
論文頁數:68
中文關鍵詞:SVM分類器加速度感測器動作識別醫療照顧情境感知
外文關鍵詞:SVM
相關次數:
  • 被引用被引用:1
  • 點閱點閱:1075
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:67
  • 收藏至我的研究室書目清單書目收藏:2
近年來,慢性疾病已經佔據了全球致死率成因的60%,估計在2020年,會有高達73%的民眾因為慢性疾病而死。 近二十年來的文獻顯示,亞洲人像印度人、華人、菲律賓人等因肥胖而罹患代謝症候群的危險性似乎較白人更為嚴重。目前已經有許多文獻指出,肥胖與慢性疾病的發生具有正相關的關係。定期且規律的運動習慣,有助於降低慢性疾病所造成的風險。
本研究的目的在於以智慧型手機內建的三軸加速度感測器建立動能感知系統,精確辨識並記錄人體日常生活的八個動作類別與動作進行時間,並回饋給使用者作為每日運動量的紀錄以及減重的依據。除了日常生活中自組運動管理平台,進一步可與醫療機構合作,醫生給予使用者適當的運動量建議,有助於建立使用者平日養成運動健身的習慣,並降低慢性疾病發生的機率。
最後,本論文在實驗部分評估所使用的SVM分類器之效能,分別探討下列兩點:(1)選取出的特徵向量之有效性,(2)分類模型的辨識能力在人體動作辨識有不錯的效果。
disease. The purpose of this research is aimed to use single 3 axis accelerometer which embedded in smart phone to develop an activity recognition system. It can detected and take down the 8 types of human daily activity and their duration. Besides, the user will be rewarded the record as a diet basis. It can be a self-exercise manager platform, moreover, can be used by medical organization. Through this system, doctor can provide user appropriate exercise suggestion which will help user to form exercise habit, and lower the morbidity of chronic disease. Finally, this research evaluated the performance of the classifier in practical experiment. Our result have successfully validated: 1) the effectiveness of feature selection 2) recognition capability of the classifier and achieve satisfactory performance for human activity recognition.
第一章 導論 ....................................................................................................... 1
1.1 研究背景與動機 ........................................................................................................................... 1
1.2 研究目的與特定目標 ................................................................................................................... 4
1.2.1 從智慧手機中收取三軸加速度感測訊號.............................................................................................. 5
1.2.2 從加速度訊號中擷取出具有代表性的特徵集合............................................................................... 6
1.2.3 建立適合用於系統的分類模型.................................................................................................................. 6
1.3 章節摘要 ........................................................................................................................................ 8
第二章 相關文獻回顧 ........................................................................................ 9
2.1 情境感知 ( Context Awareness ) .............................................................................................. 9
2.2 特徵擷取與特徵選取 ................................................................................................................. 11
2.2.1 時域特徵............................................................................................................................................................ 13
2.2.2 頻域特徵............................................................................................................................................................ 13
2.2.3 資訊增益(information gain) ....................................................................................................................... 13
2.3 動作辨識演算法 ......................................................................................................................... 16
2.4 支持向量機(Support Vector Machine,SVM).................................................................... 20
2.4.1 SVM運作原理 ................................................................................................................................................. 20
2.4.2 非線性支持向量機........................................................................................................................................ 23
2.4.3 多類別支持向量機(multi-class SVM) .................................................................................................. 26 2.5 系統應用 ......................................................................................................................................... 32
第三章 應用SVM分類器於人體動作辨識 ....................................................... 34
3.1 研究概述 ...................................................................................................................................... 34
3.2 系統架構流程 ............................................................................................................................. 34
3.3 訓練資料收集 ............................................................................................................................. 35
3.4 定義動作類別 ............................................................................................................................. 37
3.5 分類模型訓練 ............................................................................................................................. 38
3.6 擷取具代表性特徵及篩選 ........................................................................................................ 39
3.7 測試 .............................................................................................................................................. 48
第四章 實驗設計與結果分析 ........................................................................... 49
4.1 實驗環境設置 ................................................................................................................................ 49
4.1.1 實驗資料收集格式 .......................................................................................................................................... 49
4.2 實驗設計與結果分析 ................................................................................................................ 52
4.2.1 分類模型特徵最佳化 ..................................................................................................................................... 53
4.2.2 不同分類方法間之分析比較 ...................................................................................................................... 58
4.3 實驗總結 ........................................................................................................................................... 59
第五章 結論與未來展望................................................................................... 61
5.1 結論 ................................................................................................................................................... 61
5.2 未來展望 ........................................................................................................................................... 62
參考文獻 ............................................................................................................. 63
[1] Quinlan, J. R., “Induction of decision trees,” Machine Learning, No. 1, pp. 81-106, 1986
[2] 中華民國行政院衛生署:http://www.doh.gov.tw/
[3] Reaven GM, Lithell H, and Landsberg L, “Hypertension and associated metabolicabnormalities-the role of insulin resistance and the sympathoadrenal system,” N Engl J Med, pp. 334–374, 1996
[4] Schou T, Gardner HJ, “A Wii remote, a game engine, five sensor bars and a virtual reality theatre,” Proceedings of the 19th Australasian conference on Computer-Human Interaction: Entertaining User Interfaces, Adelaide, Australia: ACM, pp. 231–234, 2007.
[5] Doscher J, Evangelist M, “Accelerometer Design and Applications,” Accelerometer Application Seminar by Analog Devices, 2000.
[6] Tong Zhang, Jue Wan, Liang Xu, Ping Liu, “Fall detection by wearable sensor and one-class SVM algorithm,” Lecture Notes in Control and Information Sciences, pp. 858–863, 2006.
[7] Lee S, Mase K, “Activity and Location Recognition Using Wearable Sensors,” . IEEE Pervasive Computing, Vol. 1, no. 3, pp. 24–32, 2002.
[8] Figo D, Diniz P, Ferreira D, Cardoso J, “Preprocessing techniques for context recognition from accelerometer data,” Personal and Ubiquitous Computing, 2010.
[9] Pärkkä J, Ermes M, Korpipää P, Mäntyjärvi J, Peltola J, Korhonen I, “Activity classification using realistic data from wearable sensors,” IEEE Transactions on Information Technology in Biomedicine. Vol. 10, no. 1, pp. 119–128, 2006.
[10] Veltink PP, Bussmann J, Vries de IW, Martens W, Lummel van R, “Detection of static and dynamic activities using uniaxial accelerometers,” IEEE Transactions on Rehabilitation Engineering, Vol. 4(4), pp. 375–385, 1996.
[11] Golding A, Lesh N, “Indoor navigation using a diverse set of cheap, wearable sensors,” Digest of Papers. Third International Symposium on Wearable Computers. San Francisco, CA, USA, p. 29–36, 1999.
[12] Ravi N, D N, Mysore P, Littman ML, “Activity recognition from accelerometer data,” proceedings of the seventeenth conference on innovative applications of artificial intelligence(IAAI), Vol. 3, PP. 1541–1546, 2005.
[13] Rodgers JL, Nicewander WA, “Thirteen Ways to Look at the Correlation Coefficient,” The American Statistician, Vol. 42, no. 1, pp. 59–66, 1988.
[14] Siewiorek D, Smailagic A, Furukawa J, Krause A, Moraveji N, Reiger K, Shaffer J, Fei Lung Wong, “SenSay: a context-aware mobile phone,” Proceedings of the 7th IEEE International Symposium on Wearable Computers, White Plains, NY, USA, pp. 248–249, 2003.
[15] Lester J, Choudhury T, Borriello G,“A Practical Approach to Recognizing Physical Activities,” Pervasive Computing, pp. 1–16, 2006.
[16] Jeong D, Kim S, Chung W, “Classification of Posture and Movement Using a 3-axis Accelerometer”, Proceedings of the 2007 International Conference on Convergence Information Technology, IEEE Computer Society, pp. 837–844, 2007.
[17] Karantonis D, Narayanan M, Mathie M, Lovell N, Celler B, “Implementation of a Real-Time Human Movement Classifier Using a Triaxial Accelerometer for Ambulatory Monitoring,” IEEE Transactions on Information Technology in Biomedicine, Vol. 10, no. 1, pp. 156–167, 2006.
[18] Laerhoven KV, Aidoo KA, Lowette S. “Real-time Analysis of Data from Many Sensors with Neural Networks,” Proceedings of the 5th IEEE International Symposium on Wearable Computers, Los Alamitos, CA, USA, pp. 115–122, 2001.
[19] Lester J, Choudhury T, Borriello G,“A Practical Approach to Recognizing Physical Activities,” Pervasive Computing, pp. 1–16, 2006.
[20] Schmidt A, Gellersen HW, Beigl M, “A Wearable Context-Awareness Component,” Proceedings of the 3rd IEEE International Symposium on Wearable Computers, IEEE Computer Society, pp. 176, 1999.
[21] Bao L, Intille SS, “Activity Recognition from User-Annotated Acceleration Data ,” Proceedings of the 2nd International Conference on Pervasive Computing and Communications, Lecture Notes in Computer Science, Vol. 3001, pp. 1–17, 2004.
[22] Huynh T, Schiele B, “Analyzing features for activity recognition,” Proceedings of the 2005 joint conference on Smart objects and ambient intelligence: innovative context-aware services: usages and technologies. Grenoble, France: ACM, pp. 159-163, 2005.
[23] Friedman N, Geiger D, Goldszmidt M, “Bayesian Network Classifiers,” Machine Learning, Vol. 29(2-3), pp. 131–163, 1997.
[24] Aminian, K, Robert, Ph, Jequier, E, Schutz, Y, “ Estimation of speed and incline of walking using neural network,” Instrumentation and Measurement Technology Conference(IMTC 1994), Conference Proceedings. 10th Anniversary. Advanced Technologies in I & M., 1994 IEEE, Vol. 1, pp. 160–162, 1994.
[25] Iso T, Yamazaki K, “Gait analyzer based on a cell phone with a single three-axis accelerometer,” Proceedings of the 8th conference on Human-computer interaction with mobile devices and services. Helsinki, Finland: ACM, pp. 141–144, 2006.
[26] Vail D, Veloso M, “Learning from Accelerometer Data on a Legged Robot,” In Proceedings of the 5th IFAC/EURON Symposium on Intelligent Autonomous Vehicles, 2004.
[27] Lombriser C, Bharatula NB, Roggen D, Tröster G, “On-body activity recognition in a dynamic sensor network,” Proceedings of the ICST 2nd international conference on Body area networks, Florence, Italy: ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering), pp. 1–6, 2007.
[28] Kern N, Schiele B, Schmidt A, “Recognizing context for annotating a live life recording,” Personal and Ubiquitous Computing, Vol. 11(4), pp. 251–-263, 2007.
[29] Cooley JW, Lewis PAW, Welch PD, “The fast Fourier transform algorithm: Programming considerations in the calculation of sine, cosine and Laplace transforms,” Journal of Sound and Vibration, Vol. 12(3), pp.315–337, 1970.
[30] Yang J, Wang J, Chen Y, “Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers” Pattern Recognition Letters , Vol. 29(16), pp. 2213–2220, 2008.
[31] Healey J, Logan B, “Wearable Wellness Monitoring Using ECG and Accelerometer Data,” Proceedings of the 9th IEEE International Symposium on Wearable Computers, pp. 220–221, 2005.
[32] Williamson DF, Pamuk E, Thun M, Flanders D, Byers T, Heath C, “Prospective study of intentional weight loss and mortality in never-smoking overweight US white women aged 40–64 years” Vol. 141(12) pp. 1128–1141, 1995.
[33] Eric Guenterberg, Allen Yang, Roozbeh Jafari, Ruzena Bajcsy, and Shankar Sasatry, “A Method for Extracting Temporal Parameters Based on Hidden Markov Models in Body Sensor Networks With Inertial Sensors”. IEEE Transactions on Information Technology in BioMedicine, Vol. 13, no. 6, pp. 1019–1030, 2009.
[34] S.-W. Lee and K. Mase, “Recognition of walking behaviors for pedestrian navigation,” Proceedings of 2001 IEEE Conference on Control Applications (CCA01), pp. 1152–1155, 2001.
[35] Chow, C. K., Liu, C. N. , "Approximating discrete probability distributions with dependence trees", IEEE Transactions on Information Theory, Vol. 14(3), pp. 462–467, 1968.
[36] F. Foerster, M. Smeja, and J. Fahrenberg. “Detection of posture and motion byaccelerometry: a validation in ambulatory monitoring,” Computers in Human Behavior, Vol. 15(5), pp. 571–583, 1999.
[37] Abe, S., “Analysis of Support Vector Machines”, Neural Networks for SignalProcessing, Proceeding of the 12th IEEE Workshop on, Sept, 2002, pp89-98.
[38] Niranjan Bidargaddi, Antti Sarel, Lasse Klingbeil and Mohanraj Karunanithi. “Detecting walking activity in cardiac rehabilitation by using accelerometer”
[39] B. Schilit, N. Adams, and R. Want, 「Context-aware computing
applications,」 in Proceedings of IEEE Workshop on Mobile Computing
Systems and Applications, December 1994, pp. 85-90.
[40] 利德江,“應用兩階段分類法提昇SVM 法之分類準確率”,國立成功大學資訊管理研究所碩士論文,2004年6月.
[41] 王駿發,林博川,王家慶,宋豪靜,“以支援向量機為基礎之新穎語者切換偵測演算法”, ROCLING 2005.
[42] 黃冠達,林伯慎,“應用支撐向量機於中文關鍵詞驗證之研究”2007.
[43] 胡毓志,“不完整資料學習演算法使用支援向量機器”, 國立交通大學資訊科學研究所碩士論文, 2002 年6 月.
[44] 江其峰,“支持向量機的特性篩選方法”, 東海大學數學研究所碩士論文, 2002 年6月.
[45] 劉仁嘉,“應用於文件分類的自建構式模糊特徵擷取法” 國立中山大學電機工程研究所碩士論文,2009 年6月.
[46] 王婷婷,黃小燕,劉明, “基於SVM分類區域的傳感器網路節點自訂為算法”計算機應用,2009第29卷,第四期,1064-1068.
[47] 黃國豪,陳碧茵,賴世偉,林春合,“博物館學習導覽系統之建置、應用與成效分析”,數位學習科技期刊,民國 98 年,第一卷第四期,307-325.
[48] 吳毓傑、陳振南,“以叢聚式作法進行中文新聞分類”,第八屆
國際資訊管理研究暨實務研討會,第1 卷,民國91 年11 月23日,頁619-627.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔