運用樹莓派於邊緣運算之語者驗證系統的實現

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：68

、訪客IP：3.138.102.163

姓名

鄭瑋漢(Wei-Han Cheng) 查詢紙本館藏

畢業系所

通訊工程學系

論文名稱

運用樹莓派於邊緣運算之語者驗證系統的實現
(Implementation of Speaker Verification Using Raspberry Pi in Edge Computing)

相關論文

★ UHF頻段RFID彈藥管理系統之設計、實作與評估	★ 移動物偵測與追蹤之IP Camera系統
★ SDN自適應性自動化網路安全之研究	★ Wi-Fi Direct Service 應用於IoT
★ 射頻前端電路應用於載波聚合長期演進技術	★ 3C無線充電裝置運用在車載系統所產生之EMI輻射
★ 基於LoRa技術的物聯網前端防盜警示感測裝置實作與評估	★ DOCSIS 3.1 效能研究與下行通道干擾阻隔之設計
★ 藍芽無線光學投影翻譯筆	★ 手持裝置應用於MIMO ( 8x8 ) Wi-Fi系統之設計
★ 基於無伺服器運算之智慧農業雲端系統設計與研究	★ 嵌入式系統實現電梯物聯網
★ 在802.11 Ad-Hoc網路中基於速率考量之路由協定設計	★ 合作博弈與灰色模糊方法改善無線網路之性能
★ 採用拍賣策略之動態分散式方法於減少叢集小型基地台間干擾之研究	★ 在LTE-A下聚合未授權頻譜及動態分配資源以優化系統效能

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2027-7-26以後開放)

摘要(中)

邊緣或手持裝置逐漸普及和海量成長，造成雲計算（Cloud
Computing）的負載過大，延遲增長、可靠性降低等等問題。但隨著
晶片技術、物聯網（Internet of Things）技術的進步和提倡邊緣運算
（Edge Computing）概念的提倡，越多的邊緣裝置已經可以處理、執
行簡單的機器學習任務或程式執行，將大多機器學習和其他工作從雲
端下放至邊緣裝置上執行。
本論文將用樹莓派（Raspberry Pi）結合邊緣運算理念實現一語者
驗證系統。集中一地錄音和結合 One-versus-Rest 分類策略訓練一卷積
類神經網路（Convolutional Neural Network）模型，將模型部署到邊
緣裝置：樹莓派上，樹莓派即可原地端完成語者驗證的工作，無須交
由雲端或伺服器端負責機器學習辨識預測的工作。再將預測結果紀錄
於 Microsoft Azure 雲端資料庫上，以利日後使用。

摘要(英)

Due to growing popularity and rising quantity of handheld and edge devices, traditional Cloud Computing are facing overloading issues, such as increasing reaction time, low reliability, etc. Now, more and more edge devices can handle simple Machine Learning tasks and able to execute programs locally instead of the Cloud with the benefit of semiconductor chips technology evolution, Internet of Things improvement and the advocations of Edge Computing Theorem.
This paper implements a Speaker Verification framework using Raspberry Pi in Edge Computing. Record audio and create a Convolutional Nerul Network model combining Ove-versus-Rest strategy at one site. Deploy the model to our edge device: Raspberry Pi. It can execute our classification task on site rather than letting the cloud or server do the work. We then log the predictions on our Microsoft Azure Cloud SQL database for further usages.

關鍵字(中)

★ 物聯網
★ 邊緣運算
★ 卷積類神經網路（CNN）
★ 語者驗證

關鍵字(英)

★ Internet of Things
★ Edge Computing
★ Convolutional Neural Network
★ Audio Speaker Recognition

論文目次

中文摘要 I
英文摘要 II
誌謝 III
目錄 IV
圖目錄 VI
表目錄 VIII
第一章序論 1
1-1 前言 1
1-2 研究動機 2
1-3 論文架構 3
第二章相關研究背景 4
2-1 錄音邊緣裝置 4
2-1-1 ReSpeaker 2-Mics Pi HAT 麥克風模組 4
2-1-2 邊緣裝置―樹莓派 5
2-2 邊緣運算 7
2-3 語音特徵 MFCC 9
2-4 機器學習 11
2-4-1 資料強化 12
2-4-2 卷積類神經網路 CNN 13
2-4-3 分類測略 OvR 15
2-5 Microsoft Azure SQL Database 17
第三章系統情境與架構 19
3-1 情境比較 20
3-2 機器學習資料製作、模型訓練與部署 23
3-2-1 錄音資料強化 24
3-2-2 資料集製作 24
3-2-3 機器學習類神經網路架構和部署 25
3-3 邊緣裝置辨識預測和雲端資料庫紀錄 27
3-3-1 邊緣裝置辨識預測 28
3-3-2 雲端資料庫建置與連線 30
3-3-3 樹莓派安裝資料庫驅動程式 32
第四章模擬與分析 35
4-1 音訊語者驗證機器學習訓練與分析 36
4-1-1 音訊語者驗證機器學習訓練 36
4-1-2 模型訓練數據分析 38
4-2 雲端資料庫和實測結果分析 42
第五章結論與未來研究之方向 44
參考文獻 46

參考文獻

[1] A. Tripathi and A. Mishra, "Cloud computing security considerations,"
2011 IEEE International Conference on Signal Processing,
Communications and Computing (ICSPCC), 2011, pp. 1-5.
[2] N. Kaushik and T. Bagga, "Smart Cities Using IoT," 2021 9th
International Conference on Reliability, Infocom Technologies and
Optimization (Trends and Future Directions) (ICRITO), 2021, pp. 1-6.
[3] V. D. Vaidya and P. Vishwakarma, "A Comparative Analysis on Smart
Home System to Control, Monitor and Secure Home, based on
technologies like GSM, IOT, Bluetooth and PIC Microcontroller with
ZigBee Modulation," 2018 International Conference on Smart City and
Emerging Technology (ICSCET), 2018, pp. 1-4.
[4] Q. F. Hassan, "Internet of Things Applications for Agriculture",
Internet of Things A to Z: Technologies and Applications IEEE, 2018
[5] Y. -Z. Hsieh, "Internet of Things Pillow Detecting Sleeping Quality,"
2018 1st International Cognitive Cities Conference (IC3), 2018, pp.
266-267.
[6] 網路資料 on line resource: Statista: Internet of Things (IoT) connected
devices installed base worldwide from 2015 to 2025。取自：
https://www.statista.com/statistics/471264/iot-number-of-connecteddevices-worldwide/
[7] 網路資料 on line resource: Seeed Studio: Overview。取自：
https://wiki.seeedstudio.com/ReSpeaker_2_Mics_Pi_HAT/
[8] N. S. Yamanoor and S. Yamanoor, "High quality, low cost education
with the Raspberry Pi," 2017 IEEE Global Humanitarian Technology
Conference (GHTC), 2017, pp. 1-5.
[9] Ar Kar Kyaw, Hong Phat Truong, Justin Joseph, "Low-Cost
Computing Using Raspberry Pi 2 Model B," Journal of Computers vol.
13, no. 3, 2018, pp. 287-299.
[10] 網路資料 on line resource: Raspberry Pi Documentation: Raspberry
Pi OS。取自：
https://www.raspberrypi.com/documentation/computers/os.html
[11] M. Caprolu, R. Di Pietro, F. Lombardi and S. Raponi, "Edge
Computing Perspectives: Architectures, Technologies, and Open
Security Issues," 2019 IEEE International Conference on Edge
Computing (EDGE), 2019, pp. 116-123.
[12] 網路資料 on line resource: opensource.com: What is edge
computing?。取自：https://opensource.com/article/17/9/what-edgecomputing.
[13] M. Satyanarayanan, P. Bahl, R. Caceres and N. Davies, "The Case for
VM-Based Cloudlets in Mobile Computing," in IEEE Pervasive
Computing, vol. 8, no. 4, Oct.-Dec. 2009, pp. 14-23.
[14] 網路資料 on line resource: Intel: 甚麼是邊緣運算。取自：
https://www.intel.com.tw/content/www/tw/zh/edge-computing/what-isedge-computing.html
[15] J. Zhu and Z. Liu, "Analysis of Hybrid Feature Research Based on
Extraction LPCC and MFCC," 2014 Tenth International Conference on
Computational Intelligence and Security, 2014, pp. 732-735.
[16] Paul R. Hill, "Chapter 6.4.2 Frequency Masking," Audio and Speech
Processing with MATLAB, 2018, pp. 158
[17]網路資料 on line resource: SAVIOM: 12 jobs that robots(AI) will
replace in the future, and 12 that won’t。取自：
https://www.saviom.com/blog/12-jobs-that-robots-ai-will-replace-inthe-future-and-12-that-wont/
[18] B. M. Rashed and N. Popescu, "Machine Learning Techniques for
Medical Image Processing," 2021 International Conference on e-
Health and Bioengineering (EHB), 2021, pp. 1-4.
[19] Z. Tariq, S. K. Shah and Y. Lee, "Speech Emotion Detection using
IoT based Deep Learning for Health Care," 2019 IEEE International
Conference on Big Data (Big Data), 2019, pp. 4191-4196.
[20] 網路資料 on line resource: Cinnamon AI Taiwan: 深度學習: CNN
原理。取自：
https://cinnamonaitaiwan.medium.com/%E6%B7%B1%E5%BA%A6
%E5%AD%B8%E7%BF%92-cnn%E5%8E%9F%E7%90%86-
keras%E5%AF%A6%E7%8F%BE-432fd9ea4935
[21] 網路資料 on line resource: Google Machine Learning: ML
Practicum: Image Classification。取自：
https://developers.google.com/machine-learning/practica/imageclassification/convolutional-neural-networks
[22] Zhi-Hua Zhou, "Chapter 3.5: Multiclass Classification". Machine
Learning, 2016, pp. 68-69.
[23] Q. Sun, L. Luo, H. Peng and C. An, "A Method of Speaker
Recognition for Small-scale Speakers Based on One-versus-rest and
Neural Network," 2019 14th International Conference on Computer
Science & Education (ICCSE), 2019, pp. 771-774.
[24] I. Astrova, A. Koschel, C. Eickemeyer, J. Kersten and N. Offel,
"DBaaS comparison: Amazon vs. Microsoft," 2017 International
Conference on Information Society (i-Society), 2017, pp. 15-21.
[25] Z. Su, Y. Lin and V. R. L. Shen, "Intelligent Environmental
Monitoring System based on LoRa Long Range Technology," 2019
IEEE Eurasia Conference on IOT, Communication and Engineering
(ECICE), 2019, pp. 354-357.
[26] 網路資料 on line resource: Microsoft Azure: Azure SQL Database。
取自：https://azure.microsoft.com/zh-tw/products/azuresql/database/#features
[27] E. F. Codd. "A relational model of data for large shared data banks."
Communications of the ACM Vol. 13, Issue. 6 (June 1970), 1970, pp.
377–387.
[28] M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin,
S. Ghemawat, G. Irving, M. Isard et al., "Tensorflow: A system for
large-scale machine learning, " 12th {USENIX} Symposium on
Operating Systems Design and Implementation ({OSDI} 16), 2016, pp.
265–283
[29] O. Sharma, "A New Activation Function for Deep Neural Network,"
2019 International Conference on Machine Learning, Big Data, Cloud
and Parallel Computing (COMITCon), 2019, pp. 84-86.
[30] S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep
network training by reducing internal covariate shift", Proc.
International Conference on Machine Learning, 2015, pp. 448-456.
[31] 網路資料 on lone resource: TensorFlow: TensorFlow Lite | ML for
Mobile and Edge Device。取自：https://www.tensorflow.org/lite
[32] 網路資料 on line resource: Microsoft Docs: Azure Portal
Overview。取自：https://docs.microsoft.com/en-us/azure/azureportal/azure-portal-overview
[33] 網路資料 on line resource: Microsoft Docs: DTU-based purchasing
model overview。取自：https://docs.microsoft.com/zhtw/azure/azure-sql/database/service-tiers-dtu?view=azuresql
[34] 網路資料 on line resource: FreeTDS: Chapter1. What is FreeTDS？
取自：https://www.freetds.org/userguide/what.html
[35] 網路資料 on line resource: Towards Data Science: Daniel Godoy.
"Understanding binary cross-entropy / log loss: a visual explanation"。
取自：https://towardsdatascience.com/understanding-binary-crossentropy-log-loss-a-visual-explanation-a3ac6025181a
[36] I. Bilbao and J. Bilbao, "Overfitting problem and the over-training in
the era of data: Particularly for Artificial Neural Networks," 2017
Eighth International Conference on Intelligent Computing and
Information Systems (ICICIS), 2017, pp. 173-177.

指導教授

吳中實

審核日期

2022-7-26

推文