跳到主要內容

臺灣博碩士論文加值系統

(100.28.2.72) 您好!臺灣時間:2024/06/13 13:37
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:劉柏陽
研究生(外文):Liu,Bo-Yang
論文名稱:應用類分子神經系統於序列降噪:以手部復健動作為例
論文名稱(外文):Application Of Artificial Neuro Molecular Systems To Sequence Noise Reduction: An Example Of Hand Rehabilitation Movements
指導教授:陳重臣陳重臣引用關係
指導教授(外文):Chen,Jong-Chen
口試委員:陳重臣連俊瑋蔡家安
口試委員(外文):Chen, Jong-ChenLain, Jiunn-WoeiTsai, Chia-An
口試日期:2023-06-20
學位類別:碩士
校院名稱:國立雲林科技大學
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:2023
畢業學年度:111
語文別:中文
論文頁數:42
中文關鍵詞:類分子神經系統手部復健降噪手部機器人
外文關鍵詞:Artificial Neuro MolecularHand RehabilitationNoise ReductionHand Robots
相關次數:
  • 被引用被引用:0
  • 點閱點閱:92
  • 評分評分:
  • 下載下載:20
  • 收藏至我的研究室書目清單書目收藏:0
手部作為人體中最為泛用的肢體部位,人們以此完成日常生活乃至職場中絕大多 數的任務,而因職業災害或腦中風疾病後遺症等,導致手部失能,需透過長期的復 健療程,而手部機器人常被用以輔助病患完成復健動作。在機械輔助醫療當中,雜 訊的干擾將變得敏感,降低或消除雜訊干擾的技術扮演了重要的角色,本研究以類 分子神經系統、小波轉換、自回歸移動平均、降噪自編碼器的降噪方法進行比較, 並在 VREP 模擬軟體中建立手部模型,最終以動態時間規劃方式計算運動軌跡誤 差,探討不同方法在不同信噪比對復健動作的影響並驗證類分子神經系統的降噪 能力。實驗結果中,最佳的方法為長短期記憶的降噪自編碼器降噪方法,在高干擾 的環境下動作軌跡誤差平均下降了 52.4%;中干擾環境下平均下降了 43.5%;低干 擾環境下平均下降了 18.2%,而類分子神經系統在高干擾環境下效果較佳,動作軌 跡誤差在高干擾環境下平均下降了 36.4%,驗證了類分子神經系統的降噪效果以及 對序列資料的學習能力。
As the most common limb in the human body, people use it to perform most of the tasks in daily life and even in the workplace. However, due to the sequelae of occupational disasters or stroke diseases, the hand is disabled and needs to undergo a long-term rehabilitation process, and hand robots are often used to assist patients to complete rehabilitation movements. In the field of mechanically assisted medicine, the interference of noise will become sensitive, and the technology to reduce or eliminate noise interference plays an important role. In this study, noise reduction methods such as Artificial Neuro Molecular(ANM), Wavelet transform, Autoregressive Integrated Moving Average model(ARIMA), and Denoising Autoencoder(DAE) are used to compare the noise reduction methods, and the hand model is built in Virtual Robot Experimentation Platform(VREP) simulation software, and the motion trajectory gap is finally calculated by Dynamic Time Warping(DTW). To investigate the effect of different methods on the rehabilitation actions at different signal-to-noise ratios(SNR) and to verify the noise reduction ability of ANM. In the experimental results, the best method is the DAE method with Long short-term memory(LSTM), and the average reduction of motion track gap is 52.4% in the high interference environment, 43.5% in the medium interference environment, and 18.2% in the low interference environment, while the ANM is more effective in the high interference environment, and the average reduction of motion track gap is 36.4% in the high interference environment. The noise suppression effect and the learning ability of sequence data of the ANM were verified.
摘要 i
Abstract ii
目錄 iii
表目錄 iv
圖目錄 v
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
第二章 文獻探討 3
2.1 雜訊 3
2.2 降噪技術 3
2.3 類分子神經系統 4
第三章 研究方法 7
3.1 研究架構 7
3.2 研究設備與裝置 9
3.2.1 機器人模擬器 9
3.3 信號雜訊比 10
3.4 實驗模型設計 10
3.4.1 類分子神經系統 10
3.4.2 小波轉換 12
3.4.3 自回歸整合移動平均 12
3.4.4 降噪自編碼器 13
3.5 動態時間規劃 15
3.6 研究範圍與限制 16
第四章 實驗結果 17
4.1 類分子神經系統 18
4.2 小波轉換 20
4.3 自回歸整合移動平均 22
4.4 降噪自編碼器 24
4.4.1 人工神經網路 24
4.4.2 遞迴神經網路 26
4.4.3 長短期記憶網路 29
第五章 結論 32
參考文獻 33


Beylkin, G., Coifman, R., & Rokhlin, V. (1991). Fast wavelet transforms and numerical algorithms I. Communications on pure and applied mathematics, 44(2), 141-183.
Black, F. (1986). Noise. The journal of finance, 41(3), 528-543.
Box, G. E., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: forecasting and control. John Wiley & Sons.
Chakroun, R., & Frikha, M. (2020). Robust features for text-independent speaker recognition with short utterances. Neural Computing and Applications, 32(17), 13863-13883.
Chatterjee, S., Thakur, R. S., Yadav, R. N., Gupta, L., & Raghuvanshi, D. K. (2020). Review of noise removal techniques in ECG signals. IET Signal Processing, 14(9), 569-590.
Chen, J.-C. (1993). Computer experiments on evolutionary learning in a multilevel neuromolecular architecture. Wayne State University.
Chen, J.-C. (1998). Problem solving with a perpetual evolutionary learning architecture. Applied Intelligence, 8(1), 53-71.
Chen, J.-C. (2020). Continual learning for addressing optimization problems with a snake-like robot controlled by a self-Organizing model. Applied Sciences, 10(14), 4848.
Chen, J.-C., & Conrad, M. (1994a). Learning synergy in a multilevel neuronal architecture. BioSystems, 32(2), 111-142.
Chen, J.-C., & Conrad, M. (1994b). A multilevel neuromolecular architecture that uses the extradimensional bypass principle to facilitate evolutionary learning. Physica D: Nonlinear Phenomena, 75(1-3), 417-437.
Chen, J.-C., & Conrad, M. (1997). Evolutionary learning with a neuromolecular architecture: a biologically motivated approach to computational adaptability. Soft Computing, 1(1), 19-34.
Deng, Y., Wang, L., Jia, H., Tong, X., & Li, F. (2019). A sequence-to-sequence deep learning architecture based on bidirectional GRU for type recognition and time location of combined power quality disturbance. IEEE Transactions on Industrial Informatics, 15(8), 4481-4493.
Dimri, T., Ahmad, S., & Sharif, M. (2020). Time series analysis of climate variables using seasonal ARIMA approach. Journal of Earth System Science, 129, 1-16.
Fu, B., Zhao, X., Song, C., Li, X., & Wang, X. (2019). A salt and pepper noise image denoising method based on the generative classification. Multimedia Tools and Applications, 78(9), 12043-12053.
Johnson, D. H. (2006). Signal-to-noise ratio. Scholarpedia, 1(12), 2088.
Kahneman, D., Sibony, O., & Sunstein, C. (2022). Noise. HarperCollins UK.
Khan, S., & Alghulaiakh, H. (2020). ARIMA model for accurate time series stocks forecasting. International Journal of Advanced Computer Science and Applications, 11(7).
Lee, J., & Kunii, T. L. (1995). Model-based analysis of hand posture. IEEE Computer Graphics and applications, 15(5), 77-86.
Mirjalili, S. (2019). Genetic algorithm. In Evolutionary algorithms and neural networks (pp. 43-55). Springer.
Munir, M., Chattha, M. A., Dengel, A., & Ahmed, S. (2019). A comparative analysis of traditional and deep learning-based anomaly detection methods for streaming data. 2019 18th IEEE international conference on machine learning and applications (ICMLA),
Sagun, A. G. S., & Tanguilig III, B. T. (2020). ACTIVE NOISE REDUCTION USING WAVELET TRANSFORM. Innovatus, 3(1), 1-1.
Salvador, S., & Chan, P. (2007). Toward accurate dynamic time warping in linear time and space. Intelligent Data Analysis, 11(5), 561-580.
Starosolski, R. (2020). Hybrid adaptive lossless image compression based on discrete wavelet transform. Entropy, 22(7), 751.
Tandra, R., & Sahai, A. (2005). Fundamental limits on detection in low SNR under noise uncertainty. 2005 international conference on wireless networks, communications and mobile computing,
Vlok, J. D., & Olivier, J. C. (2014). Blind sequence‐length estimation of low‐SNR cyclostationary sequences. Iet Communications, 8(9), 1578-1588.
Wen, M., Li, P., Zhang, L., & Chen, Y. (2019). Stock market trend prediction using high-order information of time series. IEEE Access, 7, 28299-28308.
Xie, Y., Wang, Z., & Ji, S. (2020). Noise2Same: Optimizing a self-supervised bound for image denoising. Advances in neural information processing systems, 33, 20320-20330.
Yang, T., & Yang, W.-B. (2008). Performance analysis of direct-sequence spread-spectrum underwater acoustic communications with low signal-to-noise-ratio input signals. The Journal of the Acoustical Society of America, 123(2), 842-855.
Zhong, G., Gao, W., Liu, Y., Yang, Y., Wang, D.-H., & Huang, K. (2020). Generative adversarial networks with decoder–encoder output noises. Neural Networks, 127, 19-28.
方國定、陳重臣. (民88). 以產品面探討跨組織資訊系統之採用: 自主性學習之類分子神經系統應用. 資管學報, 6(1), 63-83.
陳重臣、方國定. (民88). 以類分子神經系統對B型肝炎臨床資料作診斷預測、分析、交叉驗證. 管理與系統, 6(4), 433-458.
勞動部職業安全衛生署. (2022). 職業災害統計網路填報系統手部傷害損失日數換算圖表 | 政府資料開放平臺. https://data.gov.tw/dataset/41485
廖國勛, 蔣志雄, & 陳重臣. (2008). 類分子神經系統在新生兒之全靜脈營養的應用. 管理與系統, 15(1), 161-176.
臺北市勞動檢查處. (2017). 臺北市勞動檢查處-常見問答-「暫時全失能」之傷害損失日數要如何填寫? https://lio.gov.taipei/News_Content.aspx?n=DB345115745B8F8F&sms=87415A8B9CE81B16&s=1BC0151C5ABE55CF
許慧億(2020)。從利用自製壓力彎度手套於各種日常手部動作資料擷取與分析到機器手臂實際製作與應用。﹝碩士論文。國立雲林科技大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/hfppfw。

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top