請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/90741
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 吳安宇 | zh_TW |
dc.contributor.advisor | An-Yeu Wu | en |
dc.contributor.author | 陳奕達 | zh_TW |
dc.contributor.author | Yi-Ta Chen | en |
dc.date.accessioned | 2023-10-03T17:25:02Z | - |
dc.date.available | 2023-11-09 | - |
dc.date.copyright | 2023-10-03 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-04-07 | - |
dc.identifier.citation | [1] A. F. Abate, L. Cimmino, I. Cuomo, M. D. Nardo and T. Murino, “On the Impact of Multimodal and Multisensor Biometrics in Smart Factories,” IEEE Transactions on Industrial Informatics, vol. 18, pp. 9092-9100, 2022.
[2] A. Barros, P. Resque, J. Almeida, R. Mota, H. Oliveira, D. Rosário and E. Cerqueira, “Data Improvement Model Based on ECG Biometric for User Authentication and Identification,” Sensors, vol. 20, 2020. [3] S. Yin, M. Kim, D. Kadetotad, Y. Liu, C. Bae, S. J. Kim, Y. Cao and J.-S. Seo, “A 1.06- μ W Smart ECG Processor in 65-nm CMOS for Real-Time Biometric Authentication and Personal Cardiac Monitoring,” IEEE Journal of Solid-State Circuits, vol. 54, pp. 2316-2326, 2019. [4] T.-W. Sun, D. Ali and A.-Y. Wu, “Compressed-Domain ECG-Based Biometric User Identification Using Task-Driven Dictionary Learning,” ACM Trans. Comput. Healthcare, vol. 3, April 2022. [5] J. Ribeiro Pinto, J. S. Cardoso and A. Lourenço, “Evolution, Current Challenges, and Future Possibilities in ECG Biometrics,” IEEE Access, vol. 6, pp. 34746-34776, 2018. [6] A. L. Goldberger, L. A. Amaral, L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C. K. Peng and H. E. Stanley, “PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals.,” Circulation, vol. 101, no. 23, pp. E215-20, June 2000. [7] J.-P. Couderc, X. Xiaojuan, W. Zareba and A. J. Moss, “Assessment of the Stability of the Individual-Based Correction of QT Interval for Heart Rate,” Annals of Noninvasive Electrocardiology, vol. 10, pp. 25-34, 2005. [8] F. Agrafioti, K. Martin, and S. Oung, “Preauthorized wearable biometric device, system and method for use thereof,” U.S. Patent 9 472 033 B2, Oct. 18, 2016. [9] D. R. Seshadri, B. Bittel, D. Browsky, P. Houghtaling, C. K. Drummond, M. Y. Desai and A. M. Gillinov, “Accuracy of Apple Watch for Detection of Atrial Fibrillation,” Circulation, vol. 141, pp. 702-703, 2020. [10] Y. Chu, H. Shen and K. Huang, “ECG Authentication Method Based on Parallel Multi-Scale One-Dimensional Residual Network With Center and Margin Loss,” IEEE Access, vol. 7, pp. 51598-51607, 2019. [11] R. Palaniappan and S. M. Krishnan, “Identifying individuals using ECG beats,” in 2004 International Conference on Signal Processing and Communications, 2004. SPCOM '04., 2004. [12] S. Saechia, J. Koseeyaporn and P. Wardkein, “Human Identification System Based ECG Signal,” in TENCON 2005 - 2005 IEEE Region 10 Conference, 2005. [13] B. Noureddine, A. Naït-ali, R. Fournier and F. bereksi reguig, “ECG Based Human Authentication using Wavelets and Random Forests,” International Journal on Cryptography and Information Security, vol. 2, June 2012. [14] R. D. Labati, E. Muñoz, V. Piuri, R. Sassi and F. Scotti, “Deep-ECG: Convolutional Neural Networks for ECG biometric recognition,” Pattern Recognition Letters, vol. 126, pp. 78-85, 2019. [15] M. Ingale, R. Cordeiro, S. Thentu, Y. Park and N. Karimian, “ECG Biometric Authentication: A Comparative Analysis,” IEEE Access, vol. 8, pp. 117853-117866, 2020. [16] S.-C. Wu, P.-L. Hung and A. L. Swindlehurst, “ECG Biometric Recognition: Unlinkability, Irreversibility, and Security,” IEEE Internet of Things Journal, vol. 8, pp. 487-500, 2021. [17] N. Karimian, D. Woodard and D. Forte, “ECG Biometric: Spoofing and Countermeasures,” IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 2, pp. 257-270, 2020. [18] R. Bousseljot, D. Kreiseler and A. Schnabel, “Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet,” Biomedizinische Technik / Biomedical Engineering, vol. 40, p. 317–318, 1995-01-01. [19] D. Shin, J. Lee, J. Lee and H.-J. Yoo, “14.2 DNPU: An 8.1TOPS/W reconfigurable CNN-RNN processor for general-purpose deep neural networks,” in 2017 IEEE International Solid-State Circuits Conference (ISSCC), 2017. [20] Y.-H. Chen, T.-J. Yang, J. Emer and V. Sze, “Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile Devices,” IEEE Journal on Emerging and Selected Topics in Circuits and Systems, vol. 9, pp. 292-308, 2019. [21] S. K. Venkataramanaiah, S. Yin, Y. Cao and J.-S. Seo, “Deep Neural Network Training Accelerator Designs in ASIC and FPGA,” in 2020 International SoC Design Conference (ISOCC), 2020. [22] Deci, “DeciNets: How Deci’s AutoNAC Automatically Extended the Efficient Frontier of Accuracy-Latency for NVIDIA Cloud and Edge GPUs,” Deci, 2022. [Online]. Available: https://deci.ai/blog/decinets-autonac-accuracy-latency-nvidia-cloud-edge-gpus/. [23] G. M. Ven and A. S. Tolias, “Three scenarios for continual learning,” arXiv preprint arXiv: 1904.07734, 2019. [24] Z. Mai, R. Li, J. Jeong, D. Quispe, H. Kim and S. Sanner, “Online continual learning in image classification: An empirical survey,” Neurocomputing, vol. 469, pp. 28-51, 2022. [25] J. Konečnỳ, B. McMahan and D. Ramage, “Federated optimization: Distributed optimization beyond the datacenter,” arXiv preprint arXiv:1511.03575, 2015. [26] G.-B. Huang, Q.-Y. Zhu and C.-K. Siew, “Extreme learning machine: theory and applications,” Neurocomputing, vol. 70, no. 1-3, pp. 489-501, 2006. [27] R. Venkatesan and M. J. Er, “A novel progressive learning technique for multi-class classification,” Neurocomputing, vol. 207, 2016. [28] Y.-C. Chuang, Y.-T. Chen, H.-T. Li and A.-Y. A. Wu, “An Arbitrarily Reconfigurable Extreme Learning Machine Inference Engine for Robust ECG Anomaly Detection,” IEEE Open Journal of Circuits and Systems, vol. 2, pp. 196-209, 2021. [29] A. Safaei, Q. M. J. Wu, T. Akilan and Y. Yang, “System-on-a-Chip (SoC)-Based Hardware Acceleration for an Online Sequential Extreme Learning Machine (OS-ELM),” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 38, pp. 2127-2138, 2019. [30] B. McMahan, E. Moore, D. Ramage, S. Hampson and B. A. y. Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” in Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017. [31] G.-B. Huang, N.-Y. Liang, H.-J. Rong, P. Saratchandran and N. Sundararajan, “On-line sequential extreme learning machine.,” Computational Intelligence, vol. 2005, p. 232–237, 2005. [32] J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A. A. Rusu, K. Milan, J. Quan, T. Ramalho, A. Grabska-Barwinska, D. Hassabis, C. Clopath, D. Kumaran and R. Hadsell, “Overcoming catastrophic forgetting in neural networks,” Proceedings of the National Academy of Sciences, vol. 114, pp. 3521-3526, 2017. [33] Z. Li and D. Hoiem, “Learning without Forgetting,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, pp. 2935-2947, 2018. [34] S.-A. Rebuffi, A. Kolesnikov, G. Sperl and C. H. Lampert, “iCaRL: Incremental Classifier and Representation Learning,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2001-2010, 2017. [35] H. B. McMahan, E. Moore, D. Ramage, S. Hampson and others, “Communication-efficient learning of deep networks from decentralized data,” arXiv preprint arXiv:1602.05629, 2016. [36] S. Decherchi, P. Gastaldo, A. Leoncini and R. Zunino, “Efficient Digital Implementation of Extreme Learning Machines for Classification,” IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 59, pp. 496-500, 2012. [37] T. C. Yeam, N. Ismail, K. Mashiko and T. Matsuzaki, “FPGA implementation of extreme learning machine system for classification,” in TENCON 2017 - 2017 IEEE Region 10 Conference, 2017. [38] R. D. Labati, R. Sassi and F. Scotti, “ECG biometric recognition: Permanence analysis of QRS signals for 24 hours continuous authentication,” in 2013 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 31-36, 2013. [39] Y. Duan, J. Lu, J. Feng and J. Zhou, “Deep Localized Metric Learning,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 28, pp. 2644-2656, 2018. [40] F. Schroff, D. Kalenichenko and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815-823, 2015. [41] A. Hermans, L. Beyer and B. Leibe, “In Defense of the Triplet Loss for Person Re-Identification,” arXiv preprint arXiv:1703.07737, 2017. [42] K. A. Y. A. Mahmut and H. Ş. BİLGE, “Deep Metric Learning: A Survey,” Symmetry, vol. 11, no. 9, 2019. [43] E. Simo-Serra, E. Trulls, L. Ferraz, I. Kokkinos, P. Fua and F. Moreno-Noguer, “Discriminative Learning of Deep Convolutional Feature Point Descriptors,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 118-126, 2015. [44] K. Sohn, “Improved Deep Metric Learning with Multi-class N-pair Loss Objective,” in Advances in Neural Information Processing Systems, 2016. [45] R. Hadsell, S. Chopra and Y. LeCun, “Dimensionality Reduction by Learning an Invariant Mapping,” in 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), pp. 1735-1742, 2006. [46] K. Q. Weinberger, J. Blitzer and L. Saul, “Distance Metric Learning for Large Margin Nearest Neighbor Classification,” Advances in Neural Information Processing Systems, vol. 10, no. 2, 2005. [47] J. Wang, F. Zhou, S. Wen, X. Liu and Y. Lin, “Deep Metric Learning With Angular Loss,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2593-2601, 2017. [48] C.-Y. Wu, R. Manmatha, A. J. Smola and P. Krahenbuhl, “Sampling Matters in Deep Embedding Learning,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2840-2848, 2017. [49] H. Oh Song, Y. Xiang, S. Jegelka and S. Savarese, “Deep Metric Learning via Lifted Structured Feature Embedding,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4004-4012, 2016. [50] X. Wang, X. Han, W. Huang, D. Dong and M. R. Scott, “Multi-similarity loss with general pair weighting for deep metric learning,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5022-5030. 2019. [51] B. Yu and D. Tao, “Deep Metric Learning With Tuplet Margin Loss,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 6490-6499, 2019. [52] F. Cakir, K. He, X. Xia, B. Kulis and S. Sclaroff, “Deep Metric Learning to Rank,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1861-1870 , 2019. [53] K. Musgrave, S. Belongie and S.-N. Lim, “A metric learning reality check,” in European Conference on Computer Vision, pp. 681-699, 2020. [54] Y. Chen, Y. Chuang and A. Wu, “Online Extreme Learning Machine Design for the Application of Federated Learning,” in 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), pp. 188-192, 2020. [55] B.-f. Zhang, J.-s. Su and X. Xu, “A Class-Incremental Learning Method for Multi-Class Support Vector Machines in Text Classification,” in 2006 International Conference on Machine Learning and Cybernetics, pp. 2581-2585, 2006. [56] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt and B. Scholkopf, “Support vector machines,” IEEE Intelligent Systems and their Applications, vol. 13, pp. 18-28, 1998. [57] M. Karkooti, J. R. Cavallaro and C. Dick, “FPGA implementation of matrix inversion using QRD-RLS algorithm,” in Asilomar Conference on Signals, Systems, and Computers, 2005. [58] J. A. Apolinário, J. A. Apolinário and R. Rautmann, “QRD-RLS adaptive filtering,” 2009. [59] P. K. Meher, J. Valls, T.-B. Juang, K. Sridharan and K. Maharatna, “50 Years of CORDIC: Algorithms, Architectures, and Applications,” IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 56, pp. 1893-1907, 2009. [60] N.-Y. Liang, G.-B. Huang, P. Saratchandran and N. Sundararajan, “A fast and accurate online sequential learning algorithm for feedforward networks,” IEEE Transactions on neural networks, vol. 17, pp. 1411-1423, 2006. [61] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner and others, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, pp. 2278-2324, 1998. [62] J. e. a. Konečnỳ, “Federated learning: Strategies for improving communication efficiency,” arXiv preprint arXiv:1610.05492, 2016. [63] H.-T. Li, C.-Y. Chou, Y.-T. Chen, S.-H. Wang and A.-Y. A. Wu, “Robust and Lightweight Ensemble Extreme Learning Machine (ELM) Engine Based on Eigenspace Domain for Compressed Learning,” IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 66, no. 12, pp. 4699-4712, Dec 2019. [64] A. P. Bradley, “The use of the area under the ROC curve in the evaluation of machine learning algorithms,” Pattern Recognition, vol. 30, pp. 1145-1159, 1997. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/90741 | - |
dc.description.abstract | 隨著第四次工業革命的到來,工業物聯網(IIoT)中的設備在製造過程中產生大量機密數據,因此需要嚴格保護。用戶身份識別成為確保這些數據安全的必要條件。在各種用戶識別方法中,心電圖已逐漸成為眾所皆知的生物識別(Biometrics)方式,因為它能夠提供受測者活著的證明並且難以被竊取。本論文著重於心電圖生物識別中的用戶識別(User Identification)與身份驗證(Identity Verification)。面對以邊緣為中心的用戶識別任務中,所需要面對新的員工隨時會加入的挑戰,加上邊緣端的電池限制,我們亟需一個支援線上類別增量學習(O-CIL)且高能源效率的系統。面對雲端為中心的身分驗證任務,我們亟需優化系統的準確度與通用性。
本論文提出了一種可擴展的極限學習機 (S-ELM) 演算法,以克服新用戶於以邊緣為中心的基於心電圖用戶識別任務中的挑戰。我們選擇極限學習機(ELM)模型作為分類器,是因為它具有更快的學習速度。此外,極限學習機當中的解析解相對於深度學習分類器中的迭代解更適合使用於O-CIL場景下。因此本論文提出“其他”類概念賦予ELM的O-CIL的能力。為了在邊緣裝置上實現S-ELM,我們提出了可擴展的 QR 分解 ELM (S-QRD-ELM)並且將其使用TSMC 40nm製程來實現。在S-QRD-ELM引擎中,我們採用折疊(folding)和硬體共享(hardware-sharing)技術來設計,以提高整體引擎的能效。此外,本論文借助聯邦學習的概念,將聯邦平均算法(Federated Averaging)與 ELM結合,提出聯邦極限學習機系統(Fed-ELMS),使得邊緣裝置上的ELM模型能夠藉由相互合作來獲得更好的全局模型。 另一方面,本論文提出了一種可擴展的N-pair loss深度心電圖(SNL-Deep-ECG)系統,用於雲端上的身份驗證任務,以獲得更好的用戶體驗、準確度和通用性。單心電圖波形預處理方式縮短了訊號採集時間,提升了用戶體驗。使用N-pair loss訓練Deep-ECG模型相對於原始的交叉熵損失可以獲得更高的準確度。最後,本論文提出了混合數據庫驗證方法來驗證SNL-Deep-ECG的通用性。 綜上所述,本論文針對基於心電圖的邊緣裝置用戶識別和雲端身份驗證系統提出了多項前瞻性的設計,並希望我們所提出的技術能成為未來基於心電圖的生物識別系統中的關鍵技術。 | zh_TW |
dc.description.abstract | As the fourth industrial revolution arrives, smart devices in the Industrial Internet of Things (IIoT) generate massive amounts of confidential data which require strict protection and user identification comes in handy. Among the user identification methods, ECG signals have emerged as an attractive biometric modality due to their ability to provide intrinsic liveness proof and their difficulty in spoofing. In this dissertation, we focus on the ECG-based user identification and identity verification task. For edge-centric user identification tasks, facing the fact that new users would enter the smart factory and the battery limitation on edge devices, the system requires online class incremental learning (O-CIL) capability with high energy efficiency. On the other hand, for cloud-based identity verification system, the accuracy and generalizability need to be improved.
This dissertation presents a scalable extreme learning machine (S-ELM) algorithm to conquer the challenges of the edge-centric ECG-based user identification task. We select the extreme learning machine (ELM) model because it is lightweight and has a faster learning speed. “The others” class concept is proposed to enable the O-CIL capability of ELM. To implement both the S-ELM on edge devices, we propose the scalable QR-decomposition ELM (S-QRD-ELM) and its implementation with the TSMC 40nm technology. The S-QRD-ELM engine is designed with folding and hardware-sharing techniques for better energy efficiency. Finally, to collaboratively learn a good global model with local ELM models on the edge device, a federated ELM system (Fed-ELMS) is proposed. On the other hand, this dissertation presents a scalable N-pair loss Deep-ECG (SNL-Deep-ECG) system for deep-learning-based identity verification tasks on the cloud for better user experience, performance, and generalizability. The single-pulse preprocessing method shortens the signal collection time, thus improving the user experience. The N-pair loss is used to train the Deep-ECG model instead of the original cross-entropy loss for better performance. Finally, the mixed database validation scheme is proposed to validate the generalizability of the SNL-Deep-ECG. In summary, this dissertation presents advanced designs for ECG-based edge-centric user identification and cloud-based identity verification tasks. We expect the proposed frameworks to be the essential techniques for future ECG-based biometric systems. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-10-03T17:25:02Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-10-03T17:25:02Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | 論文口試委員審定書 ii
誌謝 iii 摘要 iv Abstract v CONTENTS vi LIST OF FIGURES xi LIST OF TABLES xv Chapter 1 Introduction 1 1.1 ECG-based Biometrics 1 1.2 Design Challenges and Research Contribution for Edge-centric ECG-based User Identification System 7 1.2.1 Issues of Complex Model, New Employees, and Training Offloading 7 1.2.2 Research Contribution for Edge-centric ECG-based User Identification System 10 1.3 Design Challenges and Research Contribution for ECG-based Identity Verification System on Cloud 13 1.3.1 Lack of Generalizability and Inappropriate Loss Function in the Deep-ECG 13 1.3.2 Research Contribution for Deep-learning-based ECG-based Identity Verification System on Cloud 16 1.4 Dissertation Organization 18 Chapter 2 Review of Existing ECG-based Biometric Techniques 20 2.1 Existing Techniques for Enabling Edge-centric ECG-based User Identification 20 2.1.1 Extreme Learning Machine (ELM) and Online Sequential Extreme Learning Machine (OS-ELM) 20 2.1.2 Online Class Incremental Learning (O-CIL) and Progressive ELM 22 2.1.3 Federated Learning and FederatedAveraging Algorithm for Collaboration at Edge 28 2.1.4 Hardware Implementations for ELM 30 2.2 Existing Techniques for Deep-learning-based ECG-based Identity Verification on Cloud 32 2.2.1 Deep-ECG 32 2.2.2 Metric Learning 35 2.3 Summary 39 Chapter 3 Scalable Extreme Learning Machine Algorithm for O-CIL 41 3.1 Scalable Extreme Learning Machine (S-ELM) Algorithm for the O-CIL Settings 41 3.1.1 Proposed S-ELM Algorithm 42 3.1.2 The Mathematical Proof of S-ELM 43 3.2 Simulation Results on S-ELM 45 3.2.1 Simulation Setup for S-ELM 45 3.2.2 Comparison Between Progressive ELM and Scalable ELM 46 3.2.3 Comparison Between S-ELM and SVM with O-CIL capability 47 3.3 Summary 49 Chapter 4 Scalable QR-decomposition Extreme Learning Machine (S-QRD-ELM) Engine Design 50 4.1 Proposed Scalable QR-decomposition-based Extreme Learning Machine (S-QRD-ELM) Algorithm 51 4.1.1 S-QRD-ELM with OL Capability 51 4.1.2 S-QRD-ELM with O-CIL Capability 53 4.1.3 Simulation Setup for S-QRD-ELM 55 4.1.4 Comparison between S-ELM and S-QRD-ELM 57 4.1.5 Comparison between S-QRD-ELM and BP-NN 58 4.2 Proposed S-QRD-ELM Engine 59 4.2.1 System Architecture 60 4.2.2 Finite State Machine and Architecture Mapping of Training and Inferencing Process 61 4.3 Optimizations Inside the S-QRD-ELM Engine 65 4.3.1 From 2D Systolic Array to 1D-DMLA for QRD and BS 65 4.3.2 From Non-integrated PE design to Integrated PE design with unified-CORDIC Circuit Design 69 4.3.3 CIL Module with Low Area and Power Overhead 71 4.3.4 Fixed-point Analysis 73 4.4 Chip Implementation and Measurement Results 75 4.4.1 Chip Implementation 75 4.4.2 Measurement Results 76 4.4.3 Comparisons with Prior Designs in terms of Energy Efficiency 77 4.5 Summary 80 Chapter 5 Federated Extreme Learning Machine System for Edge Device Collaboration 81 5.1 Federated Extreme Learning Machine System (Fed-ELMS) for Collaboration of Edge Devices 81 5.1.1 Centralized ELM Server 83 5.1.2 Local ELMs on Edge Devices 84 5.2 Fed-ELMS with S-QRD-ELM Engine 85 5.2.1 Learning process of the FS-QRD-ELMS 86 5.2.2 Advantages of Using S-QRD-ELM Instead of the OS-ELM 87 5.3 Ablation Study on Fed-ELMS 89 5.3.1 Simulation Setup for Fed-ELMS on MNIST 89 5.3.2 Experiment of Fed-ELMS on MNIST 90 5.3.3 Experiment of Comparing Fed-ELMS to Fed-NN on MNIST 92 5.4 Simulation on MIT-BIH Dataset 94 5.4.1 Simulation Settings on MIT-BIH NSRDB 94 5.4.2 Accuracy of the Global Model on the Centralized Server 95 5.5 Summary 98 Chapter 6 Scalable N-pair Loss-based Deep-ECG for ECG-based Identity Verification on Cloud 99 6.1 Proposed Scalable N-pair Loss-based Deep-ECG (SNL-Deep-ECG) System 99 6.1.1 Signal Preprocessing of SNL-Deep-ECG System 100 6.1.2 Training Phase of SNL-Deep-ECG 101 6.1.3 Inferencing Phase of SNL-Deep-ECG 103 6.2 Simulation Results of the SNL-Deep-ECG 103 6.2.1 Dataset Design and Experimental Settings 104 6.2.2 Comparison of the preprocess methods between Deep-ECG and SNL-Deep-ECG 106 6.2.3 Comparison verification performance between Deep-ECG and SNL-Deep-ECG in terms of Number of Class 107 6.3 Summary 109 Chapter 7 Conclusions and Future Works 111 7.1 Contributions 111 7.2 Future Directions 113 Reference 116 | - |
dc.language.iso | en | - |
dc.title | 心電圖身分辨識演算法與電路設計 | zh_TW |
dc.title | Algorithm and Circuit Designs for ECG-based Biometrics | en |
dc.type | Thesis | - |
dc.date.schoolyear | 111-2 | - |
dc.description.degree | 博士 | - |
dc.contributor.oralexamcommittee | 楊佳玲;陳坤志;謝明得;賴以威;沈中安;阮聖彰;黃穎聰 | zh_TW |
dc.contributor.oralexamcommittee | Chia-Lin Yang;Kun-Chih Chen;Ming-Der Shieh;I-Wei Lai;Chung-An Shen;Shanq-Jang Ruan;Yin-Tsung Hwang | en |
dc.subject.keyword | 極限學習機,深度學習,心電圖,身分辨識, | zh_TW |
dc.subject.keyword | Extreme Learning Machine,Deep Learning,Electrocardiography,User Identification, | en |
dc.relation.page | 124 | - |
dc.identifier.doi | 10.6342/NTU202300690 | - |
dc.rights.note | 同意授權(限校園內公開) | - |
dc.date.accepted | 2023-04-11 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 電子工程學研究所 | - |
顯示於系所單位: | 電子工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-111-2.pdf 目前未授權公開取用 | 5.21 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。