簡易檢索 / 詳目顯示

研究生: 陳建翰
Chen, Chien-Han
論文名稱: 腳底壓力辨識系統結合機器學習之分析與研究
Study of Plantar-Pressure Recognition Systems with Machine-Learning Methods
指導教授: 林均翰
Lin, Chun-Han
學位類別: 碩士
Master
系所名稱: 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年: 2019
畢業學年度: 107
語文別: 中文
論文頁數: 28
中文關鍵詞: 腳底壓力辨識系統機器學習特徵提取低成本
英文關鍵詞: Biometrics, Machine Learning, Feature extraction, Low Cost
DOI URL: http://doi.org/10.6345/NTNU201900250
論文種類: 學術論文
相關次數: 點閱:196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
  • 由於近年來生物辨識技術的興起,讓認證方式不再同於以往的帳號密碼,不僅使生活更為便利且其安全程度也更為可靠,不過在廣大的生物辨識市場之中,系統成本與辨識度考量下要如何達成平衡一直都是辨識系統難以普及化的重點議題之一,在過去研究發現,系統在特徵提取的結果與系統著重於機器學習效果的比例較少,在訓練時所耗費的成本也較無研究。本論文主要在於研究探討分析腳底壓力資訊取出特徵,並與機器學習搭配組合,創造出快速取得腳底壓力資訊且快速訓練且擁有高準確率的系統模組,接著並進一步根據系統辨識率與感測器感測狀況來調整數量達到節省成本的目的。實驗結果顯示我們所開發的系統不僅在辨識結果上有不錯的成績,在訓練處理時時間與辨識時間上也能達到良好的效果,成本上也比先前的便宜,並獲得對此系統普及化與實作上有助的資訊。

    In recent years, the biometric technology has become more and more popular, and this makes authentication method is no longer limited to the way which only using account and password. It makes our life become not only convenient but secure. However, in the mass biometric market, the balance of system cost and identification accuracy are always been one of the key issues that the identification system is difficult to popularize. Previous study shows, the rate of using feature extraction and machine learning is not taking the high proportion than now. And there are few studies in research of the cost of data training. Because of this, our study is mainly for research and analyze the characteristics of foot pressure information, combining with machine learning to create a system module that can quickly train data and perform a high accuracy. And then based on the system identification accuracy and the sensor sensing condition, we can adjust the number of sensors to achieves the goal of cost saving. The result shows that the system not only performs good results in the identification accuracy but also saves the training and identification time. The cost is also more cheaper than before, and it will make the biometric technology become more popularization.

    目錄 iii 附圖目錄 v 表格目錄 vi 第一章 緒論 1 第二章 相關文獻探討 3 第一節 壓力感測設備的現況研究 3 第二節 壓力辨識方法的現況研究 5 第三節 研究議題 6 第三章 方法設計 7 第一節 腳底壓力辨識系統流程圖 7 第二節 資料接收與處理 8 第三節 提取特徵 9 3.3.1 原始壓力數值與圖像 9 3.3.2 平均值與平均值圖像 9 3.3.3 長寬 10 3.3.4 重心位置 11 第四節 資料儲存 12 第五節 更新模型 12 第六節 學習訓練並建立模型 12 3.6.1 SVM(Support Vector Machine) 13 3.6.2 CNN(Convolutional Neural Network) 13 3.6.3 RNN(Recurrent Neural Network) 13 3.6.4 RF(Random Forest) 13 3.6.5 GB(Gradient Boosting) 13 第四章 效能評估 14 第一節 實驗設定 14 4.1.1 硬體與設備 14 4.1.2 變數設定 15 4.1.3 數據紀錄與設定 15 第二節 腳底特徵對系統辨識率的關係 16 4.2.1 數據資料 16 4.2.2 特徵與系統辨識率 16 4.2.3 機器學習與系統辨識率的關係 18 第三節 感測器數量對系統辨識率的關係 18 4.3.1 感測器數量設定 18 4.3.2 使用40個與使用一半 19 4.3.3 TOP N(2≦N≦20) 20 第四節 訓練資料與辨識率的關係 22 第五節 機器學習與辨識時間的關係 23 第五章 結論和未來展望 24 參考文獻 26

    [1] Huijing Wang , Sanfeng Chen and Junyao Liu, "Measuring System of A 3D Force Platform for Plantar Pressure Distribution," IEEE International Conference on Automation and Logistics ,Shenyang, China, 5-7 Aug. 2009, pp. 906-910.
    [2] Jie Wang1, Hongshi Huang, Xiaoli Li and Yingfang Ao, "Application of the fuzzy C-means clustering algorithm in plantar pressure analysis," IEEE International Conference on Control and Decision, Yinchuan, China, 28-30 May 2016, pp. 2089-2094.
    [3] Bortolino Saggin, Diego Scaccabarozzi, and Marco Tarabini, "Metrological Performances of a Plantar Pressure Measurement System," IEEE Transactions on Instrumentation and Measurement, VOL. 62, NO. 4, Apr. 2013.
    [4] Sharvindsing Karia, Parasuraman, I. Elamvazuthi, Niranjan Debnath, Syed Saad Azhar Ali and MKA Ahamed Khan, "Plantar pressure distribution and gait stability: Normal VS high heel," IEEE International Symposium on Robotics and Manufacturing Automation (ROMA), Ipoh, Malaysia, 25-27 Sep. 2016.
    [5] Linah Wafai, Aladin Zayegh, Rezaul Begg and John Woulfe, "Asymmetry Detection during Pathological Gait Using a Plantar Pressure Sensing System," IEEE GCC Conference and exhibition, Doha, Qatar, 17-20 Nov. 2013, pp.182-187.
    [6] Monit Shah Singh1, Vinaychandran Pondenkandath, Bo Zhou, Paul Lukowicz and Marcus Liwicki, "Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection," IEEE International Conference on Neural Networks, Anchorage, AK, USA, 14-19 May 2017, pp. 2665-2672.
    [7] Bo Zhou, Monit Shah Singh, Sugandha Doda, Muhammet Yildirim, Jingyuan Cheng and Paul Lukowicz, "The Carpet Knows: Identifying People in a Smart Environment from a Single Step," IEEE International Conference on Pervasive Computing and Communications Workshops, Kona, HI, USA, 13-17 Mar. 2017.
    [8] Tarun Kumar Agrawal, Sebastien Thomassey, Cedric Cochrane, Guillaume Lemort, and Vladan Koncar, "Low-Cost Intelligent Carpet System for Footstep Detection," IEEE Sensors Journal, Vol. 17, No. 13, Jul. 2017, pp. 4239-4247.
    [9] Yong Feng, Yunjian Ge and Quanjun Song, "A Human Identification Method Based on Dynamic Plantar Pressure Distribution," IEEE International Conference on Information and Automation, Shenzhen, China, 6-8 Jun. 2011, pp. 329-332.
    [10] Nagaraj Hegde, Edward Melanson and Edward Sazonov, "Development of A Real Time Activity Monitoring Android Application Utilizing SmartStep," IEEE Annual International Conference on Engineering in Medicine and Biology Society (EMBC), 16-20 Aug. 2016, pp. 1886-1889.
    [11] Kuo-Hui Yeh, Chunhua Su, Wayne Chiu, and Lu Zhou, "I Walk, Therefore I Am: Continuous User Authentication with Plantar Biometrics," IEEE Communications Magazine, Vol. 56, No. 2, Feb. 2018, pp. 150-157.
    [12] Gu-Min Jeong, Phuc Huu Truong, and Sang-Il Choi, "Classification of Three Types of Walking Activities Regarding Stairs Using Plantar Pressure Sensors," IEEE Sensors Journal, Vol. 17, NO. 9, May 2017, pp. 2638-2639.
    [13] Ren Lvping, Li Deyu,Liu Chengrui, Yang Yang, Qian Yajun, Yang Songyan, Pu Fang and Niu Haijun, "Design of in-shoe plantar pressure monitoring system for daily activity exercise stress assessment," IEEE International Conference on Biomedical Engineering and Informatics (BMEI), Shanghai, China, 15-17 Oct. 2011, pp. 1367-1370.
    [14] Kanitthika K. and Soo Chan K, "Pressure Sensor Positions on Insole used for Walking Analysis," IEEE International Symposium on Consumer Electronics, JeJu Island, South Korea, 22-25 Jun. 2014.
    [15] Andrea M. Cristiani, Gian Mario Bertolotti, Elisa Marenzi and Stefano Ramat, "An Instrumented Insole for Long Term Monitoring Movement, Comfort, and Ergonomics," IEEE Sensors Journal, Vol.14, No. 5, May 2014, pp. 1564-1572.
    [16] Hyung Kun Park, HyeonBeom Yi and Woohun Lee, "Recording and Sharing Non-Visible Information on Body Movement while Skateboarding," ACM CHI Conference on Human Factors in Computing Systems, Denver, Colorado, USA, 6-11 May 2017, pp. 2488-2492.
    [17] Mehrdad Heydarzadeh, Javad Birjandtalab, Maziyar Baran Pouyan, Mehrdad Nourani, Sarah Ostadabbas, "Gaits Analysis Using Pressure Image for Subject Identification," IEEE International Conference on Biomedical & Health Informatics, Orlando, FL, USA, 16-19 Feb. 2017, pp. 333-336.
    [18] Linah Wafai, Aladin Zayegh, Rezaul Begg and John Woulfe, "Asymmetry Detection during Pathological Gait Using a Plantar Pressure Sensing System," IEEE GCC Conference and exhibition, Doha, Qatar, 17-20 Nov. 2013, pp.182-187.
    [19] Faris Mattar, Hala AL Qudaimat, Bashar Al Qaroot and Musa Al Yaman, "Low Cost Foot Plantar-Pressure Scanning Pad," IEEE Middle East Conference on Biomedical Engineering (MECBME), Beirut, Lebanon, 6-7 Oct. 2016.

    無法下載圖示 電子全文延後公開
    2024/12/31
    QR CODE