請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/99197完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張智星 | zh_TW |
| dc.contributor.advisor | Jyh-Shing Roger Jang | en |
| dc.contributor.author | 葉揚昀 | zh_TW |
| dc.contributor.author | Yang-Yun Yeh | en |
| dc.date.accessioned | 2025-08-21T16:46:22Z | - |
| dc.date.available | 2025-08-22 | - |
| dc.date.copyright | 2025-08-21 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-08-03 | - |
| dc.identifier.citation | N. Ahmad, R. A. R. Ghazilla, N. M. Khairi, and V. Kasi. Reviews on various inertial measurement unit (imu) sensor applications. International Journal of Signal Processing Systems, 1(2):256–262, 2013.
A. Angelucci and A. Aliverti. An imu-based wearable system for respiratory rate estimation in static and dynamic conditions. Cardiovascular Engineering and Technology, 14(3):351–363, 2023. S. Beck, B. Laufer, S. Krueger-Ziolek, and K. Moeller. Measurement of respiratory rate with inertial measurement units. Current Directions in Biomedical Engineering, 6(3):237–240, 2020. A. Cesareo, Y. Previtali, E. Biffi, and A. Aliverti. Assessment of breathing parameters using an inertial measurement unit (imu)-based system. Sensors, 19(1):88, 2018. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020. D. A. Forsyth and J. Ponce. Ransac: Searching for good points. Computer vision: a modern approach, 17:302–305, 2012. 57 M. García. Angular velocity from quaternions. https://mariogc.com/post/angular-velocity-quaternions/, 2022. J.-S. R. Jang. Audio signal processing and recognition. http://mirlab.org/jang/books/audiosignalprocessing/, 2005. T. C. Lee. Background audio subtraction in mobile app recording using adaptive filtering methods. National Taiwan University Department of Information Engineering Dissertation, pages 1–50, 2019. B. Long, A. Koyfman, and M. A. Vivirito. Capnography in the emergency department: a review of uses, waveforms, and limitations. The Journal of emergency medicine, 53(6):829–842, 2017. K. Maharatna, E. Grass, and U. Jagdhold. A 64-point fourier transform chip for highspeed wireless lan application using ofdm. IEEE Journal of Solid-State Circuits, 39(3):484–493, 2004. K. O’shea and R. Nash. An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458, 2015. M. Portnoff. Time-frequency representation of digital signals and systems based on short-time fourier analysis. IEEE Transactions on Acoustics, Speech, and Signal Processing, 28(1):55–69, 2003. K. R. Rao, D. N. Kim, and J. J. Hwang. Fast Fourier transform-algorithms and applications. Springer Science & Business Media, 2011. R. G. Valenti, I. Dryanovski, and J. Xiao. Keeping a good attitude: A quaternionbased orientation filter for imus and margs. Sensors, 15(8):19302–19330, 2015. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/99197 | - |
| dc.description.abstract | 現今使用IMU感測器預測人體呼吸頻率的研究，主要聚焦在利用主成分分析(Principal Components Analysis)降維與多種濾波器過濾掉非呼吸的訊號，進而預測人體呼吸頻率。我們的實驗設置與方法利用主動降噪的概念，提出了使用可適性濾波器(Adaptive Filtering)以及頻譜圖(Spectrogram)結合機器學習預測人體呼吸頻率。結果顯示，頻譜圖結合機器學習的方法除了可以在人體處於靜態活動(例如坐、站)的條件下能準確預測人體呼吸頻率外，特別在人體處於動態活動(例如走路、跑步)的條件下會比只使用可適性濾波器和其他論文的方法更準確且一致。 | zh_TW |
| dc.description.abstract | Recent research on human respiratory rate estimation using IMUs (Inertial Measurement Units) has mainly focused on applying PCA (Principal Component Analysis) for dimension reduction and using various filters to remove non-respiratory signals, thereby predicting the respiratory rate. Our experimental setup and methodology introduce the concept of ANC (Active Noise Cancellation), proposing the use of adaptive filtering and spectrograms combined with machine learning to predict human respiratory rate. The results show that the method using spectrograms combined with machine learning can accurately predict respiration rate not only during static actions (such as sitting or standing) but also achieves greater accuracy and consistency compared to adaptive filtering methods and previous works, especially during dynamic actions (such as walking or running). | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-08-21T16:46:22Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-08-21T16:46:22Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Acknowledgements i
摘要 iii Abstract v Contents vii List of Figures xi List of Tables xiii Denotation xv Chapter 1 Introduction 1 1.1 Human RR Estimation 1 1.2 Motivation 2 1.3 Research Topic and Contribution 3 1.4 Chapter Overview 4 Chapter 2 Related Work 5 2.1 Component Separation and Filtering Methods 5 2.1.1 Foundation in Static Conditions 5 2.1.2 Extension to Dynamic Conditions 7 2.2 Relative Orientation Method 8 Chapter 3 Methods 11 3.1 IMU Alignment 11 3.1.1 IMU Data Type 12 3.1.2 Alignment Process 12 3.2 ANC 13 3.2.1 Adaptive Filtering Methods 14 3.2.1.1 LMS 15 3.2.1.2 LMS+LS 16 3.2.1.3 RLS 17 3.2.1.4 LRLS 18 3.2.2 Pitching Tracking 19 3.3 Machine Learning 22 3.3.1 Fourier Transform 22 3.3.2 Spectrograms 24 3.3.3 ML Models 38 3.3.3.1 MLP 28 3.3.3.2 CNN 29 3.3.3.3 ViT 30 Chapter 4 Experimental Setup 33 4.1 Dataset 33 4.2 Evaluation Metrics 34 4.3 Environment 35 4.4 Parameter Settings 36 4.4.1 ANC Parameters 36 4.4.2 ML Parameters 39 4.5 Roadmap of Experiments 41 Chapter 5 Results 43 5.1 Ablation Study 43 5.2 Overall MAR Comparison 44 5.3 Prediction vs. Ground Truth 46 5.4 Actions MAPE Comparison 48 5.5 ANC+ML vs. ANC 48 5.6 Inference Speed 50 Chapter 6 Conclusions and Future Work 53 6.1 Conclusions 53 6.2 Future Work 54 References 57 | - |
| dc.language.iso | en | - |
| dc.subject | IMU感測器 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 人體呼吸頻率預測 | zh_TW |
| dc.subject | 數位訊號處理 | zh_TW |
| dc.subject | 主動降噪 | zh_TW |
| dc.subject | 頻譜圖 | zh_TW |
| dc.subject | human respiratory rate estimation | en |
| dc.subject | DIP | en |
| dc.subject | ANC | en |
| dc.subject | machine learning | en |
| dc.subject | spectrogram | en |
| dc.subject | IMU sensor | en |
| dc.title | 基於IMU感測器使用機器學習預測呼吸頻率 | zh_TW |
| dc.title | Machine Learning for IMU-Based Respiratory Rate Estimation | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.coadvisor | 林仁俊 | zh_TW |
| dc.contributor.coadvisor | Jen-Chun Lin | en |
| dc.contributor.oralexamcommittee | 王新民;陳冠宇 | zh_TW |
| dc.contributor.oralexamcommittee | Hsin-Min Wang;Kuan-Yu Chen | en |
| dc.subject.keyword | 人體呼吸頻率預測,IMU感測器,主動降噪,數位訊號處理,頻譜圖,機器學習, | zh_TW |
| dc.subject.keyword | human respiratory rate estimation,IMU sensor,ANC,DIP,spectrogram,machine learning, | en |
| dc.relation.page | 58 | - |
| dc.identifier.doi | 10.6342/NTU202503494 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2025-08-06 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資料科學學位學程 | - |
| dc.date.embargo-lift | 2025-08-22 | - |
| 顯示於系所單位： | 資料科學學位學程 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf | 4.85 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。