(3.227.0.150) 您好!臺灣時間:2021/05/06 12:46
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:::

我願授權國圖
: 
twitterline
研究生:田榮雯
研究生(外文):Rong-Wen Tien
論文名稱:以FPGA實現倒傳遞類神經網路並應用於肌電圖分類
論文名稱(外文):EMG Classification using Artificial Neural Network Implement on FPGA
指導教授:徐良育徐良育引用關係
指導教授(外文):Liang-Yu Shyu
學位類別:碩士
校院名稱:中原大學
系所名稱:醫學工程研究所
學門:工程學門
學類:綜合工程學類
論文種類:學術論文
論文出版年:2001
畢業學年度:89
語文別:中文
論文頁數:97
中文關鍵詞:FPGA心縮式陣列類神經網路肌電圖倒傳遞神經網路
外文關鍵詞:Systolic ArrayBack-Propagation Neural NetworkArtificial Neural NetworkFPGAElectromyogram
相關次數:
  • 被引用被引用:12
  • 點閱點閱:338
  • 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:0
  • 收藏至我的研究室書目清單書目收藏:1
語言為人類溝通、表達思想最重要的能力。通常失去語言能力的人,簡稱聽障人士,皆因聽覺系統或發音系統發生障礙造成。在日常生活上,聽障人士僅能運用手語、唇語,或是利用紙筆作為溝通的工具。當聽障人士與正常人溝通時,便無法細膩的表現語意。至今,針對聽障人士仍無一個有效的輔具來改善溝通上的不便。另一方面,在臨床病理研究中,肌電訊號已廣泛應用在診斷肌肉性、神經性病變及設計控制義肢手部動作等;義肢控制的設計上,主要以類神經網路作為肌電訊號辨識處理的主要核心。因此,建構一可攜式的肌電訊號/語音轉換系統,消除聽障人士溝通上的困難,為本研究主要的動機。而研究的架構上,將以硬體電路實現辨識手語的類神經網路。
本研究的目的,是以倒傳遞神經網路作為肌電訊號(EMG)辨識系統的主軸,並實現在FPGA晶片上。研究中,先以Matlab軟體作為軟體程式驗證的環境,依據基本倒傳遞網路演算法並自行發展之General Back-propagation Neural Network(GBPN)網路,利用負梯度學習法則來完成學習效果。搭配本實驗室研發之七通道肌電訊號擷取系統,擷取手前臂肌電訊號,透過六種基本特徵植萃取處理,經正規化後送入神經網路作實際應用的模擬與測試。對照組的設計,為本研究室同步之實驗數據,針對十一種手部動作,可達90%以上辨識率。軟體實驗中,應用相同之網路架構測試GBPN,平均辨識率可達80%以上。
以軟體印證GBPN網路可行後,對於硬體線路的設計,首重執行的效率與所需的晶片面積。利用具有管線和單一指令多資料流特性的一維心縮式陣列,做為電路設計的基本概念。電路上將分為三部分,包含前向網路單元、權植修正單元與記憶體。
目前,GBPN受限於晶片面積不足的因素,完成FFN-BLOCK、RAM模組,功能上僅能應用於案例模式。經由功能上及時序上軟體模擬與印證下,GBPN可正確運作。此外,GBPN應用在肌電圖分類中,經有效選擇輸入資訊,其網路結構可大幅減少,使所需運算時間縮短為原先之50%。
Langue is the most important ability for human to communicate and express thoughts. Most of the time, hearing system or vocal organ obstacles cause the person to lose his ability to speak. These persons can make use of sign language, lip reading or paper and pen as tools to communicate with other person. However, person without special training cannot understand the sign language. Until now, there is still no effect auxiliary tool to assist hearing impaired person to communicate.
On the other hand, the electromyogram (EMG) is used extensively on diagnosing muscular or nerve pathological disorder. Additionally, EMG is also used in the control of prosthesis. Within these applications, the artificial neural network (ANN) is commonly used as the core of EMG identification.
In this study, a back-propagation neural network is realized on the FPGA chip that will be used in a multi-channel EMG system for hand gesture identification. First, a Matlab program is developed to test the general back-propagation neural network (GBPN). It is then realized on the FPGA chip. To put the emphasis on the throughput, the systolic architectures that have pipeline and parallel processing capability is used in the design of digital circuit. The digital circuit is divided into three parts, including feed-forward network unit (FFN-BLOCK), weight update unit (WUD-BLOCK) and memory (RAM). Due to the restriction of FPGA chip, only the FFN-BLOCK and memory parts are completed in this study.
The GBPN software is tested with an average identification rate over 80%. On the other hand, the function and timing simulation of the FPGA circuit demonstrate that the GBPN hardware can function correctly. Additionally, the characteristic and redundancy of GBPN input are examined. It is found that with proper selection of inputs, the GBPN can perform comparable with only one-third of input.
摘要1
AbstractIII
謝誌V
目錄VI
圖索引VIII
表索引IX
第一章 緒論1
1.1 前言1
1.2 目的2
1.3 論文架構3
第二章 背景與原理4
2.1 肌電訊號特性與應用簡介4
2.2 文獻回顧6
2.2.1 類神經網路應用於肌電圖判讀6
2.2.2 神經網路硬體發展現況7
2.3 類神經網路9
2.3.1類神經網路簡介9
2.3.2倒傳遞神經網路10
2.4 數位電路設計14
2.4.1 心縮式陣列原理14
2.4.2 VHDL16
2.4.3 FPGA/CPLD16
第三章 研究方法20
3.1 肌電圖資料20
3.2 實驗設計22
3.3 軟體部分23
3.3.1 GBPN軟體設計23
3.3.2 軟體GBPN測試方法28
3.4 硬體部分29
3.4.1 VHDL設計環境與程式架構29
3.4.2 硬體設備30
3.4.3 測試系統架構32
3.5 GBPN電路設計37
3.5.1 電路設計37
第四章 實驗結果與討論46
4.1 實驗結果46
4.1.1 GBPN程式模擬46
4.1.2 GBPN電路模擬測試49
4.1.3 GBPN實際測試58
4.2 問題討論59
4.2.1 GBPN軟體59
4.2.2 GBPN硬體電路67
第五章 結論70
參考文獻72
附錄A FPGA、C50腳位對應表74
附錄B 實驗樣本特徵值原始資料75
附錄C 實驗樣本之肌電特徵值與類神經網路期望輸出之互相關係數原始資料86
[1]焦李成著,神經網路系統理論,儒林圖書有限公司,1991。[2]陳占霈著,類神經網路晶片上學習能力之VLSI實作和其即時應用,逢甲大學碩士論文,Jun 1996。[3]陳建宇著,多電極手部動作辨識系統,中原大學碩士論文,Jun 2001。[4]賴亮全等合譯,蓋統生理學-生理及疾病機轉,華杏出版股份有限公司,1998。[5]林嘉興譯著,完整的VHDL使用者指引,美商麥格羅∙希爾國際股份有限公司(臺灣),2000。[6]張育蒼等編著,Xilinx(PC) Training Manual,CIC,Feb 2001。[7]鐘文政等編著,DSP TMS320C50原理與實習應用,長高電腦圖書,1998。[8]蘇木春等編著,機器學習:類神經網路、模糊系統以及基因演算法則,全華科技圖書股份有限公司,1999。[9]J.G. Webster, Medical Instrumentation: application and design, John Wiley & Cons, INC., 1998.[10]Memec Design Services, Design & Application Documentation, 1998.[11]Xilinx, The Programmable Logic Data Book 2000, Xilinx, 2000.[12]Xilinx, Xilinx Design Reuse Methodology for ASIC and FPGA Designers: System-On-A-Chip designs reuse solutions.[13]H.P. Huang, et al, “Development of a Myoelectric Discrimination System for a Multi-Degree Prosthetic Hand”, Proceedings of IEEE International Conference on Robotics and Automation, 1999.[14]H.P. Huang, et al, “DSP-Based Controller for a Muti-Degree Prosthetic Hand”, Proceedings of IEEE International Conference on Robotics and Automation, pp.1378-1383, 2000.[15]L.R. Lin and H.P. Huang, “Mechanism Design of A New Mutifingered Robot Hand”, Proceedings of IEEE International Conference on Robotics and Automation, 1996.[16]C.I. Cristodoulou, et al, “A NEW Technique for the Classification and Decomposition of EMG Signals”, Neural Networks, Proceedings. , IEEE International Conference on, pp.2303—2308, 1995.[17]T.F. Lo, et al, “Signals Analysis of Electromyogram by Artificial Neural Network”, pp.535-538, 1994, IEEE.[18]D. NISHIKWA, et al, “EMG Prosthetic Hand Controller Discriminating Ten Motions using Real-time Learning Method”, Proceedings of IEEE International Conference on intelligent Robotics and Systems, 1999.[19]Texas Instruments, TMS320C5X User’s Guide, 1993.[20]Texas Instruments, TMS320C5x DSP Starter Kit User’s Guide, 1994.[21]K.C. Chang, Digital Systems Design with VHDL and Synthesis-An Integrated Approach, IEEE, 1999.[22]P.J. Ashenden, The Designer’s Guide to VHDL, Morgan Kaufmann Publishers, Inc., 1996.[23]C.A. Tucker, “Self-Organizing Maps for Time Series Analysis of Electromyography Data, pp.3577-3580, 1999, IEEE.[24]S.R. Jones, et al, “Learning in Linear Systolic Neural Network Engines: Analysis and Implementation”, IEEE Transactions on Neural Networks, pp.584-593, 1994.[25]M.M. Nicolás, et al, “General Purpose Neuroemulator Architecture: Design and VHDL Simulation”, Electronics, Circuits and Systems, 1998 IEEE International Conference on, pp.293 —296 Volume 3, 1998.[26]R.G. Girones, et al, “Systolic Implementation of a Pipelined On-Line Backpropagation”, Microelectronics for Neural, Fuzzy and Bio-Inspired Systems, 1999. MicroNeuro ‘99. Proceedings of the Seventh International Conference on, pp.387 —394, 1999.[27]J.G. Taylor, et al, Neural Networks and Their Applications, John Wiley & Sons Ltd., pp.245-253, 1996.[28]M. Perko, et al, “Low-cost, high-performance CNN simulator implemented in FPGA”, Cellular Neural Networks and Their Applications, 2000. (CNNA 2000). Proceedings of the 2000 6th IEEE International Workshop on , pp.277-283, 2000.[29]L. Tarassenko, A Guide to Neural Computing Applications, John Wiley & Sons Inc., 1998.[30]R. Gadea, et al, “Artificial Neural Network Implementation on a single FPGA of a Pipelined On-Line Backpropagation”, System Synthesis, 2000. Proceedings. The 13th International Symposium on , pp. 225 —230.[31]H. Hikawa, “Pulse mode multilayer neural network with floating point operation and on-chip learning”, Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on, pp.71-76 Volume 2, 2000.
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