請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87865完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 蔡欣穆 | zh_TW |
| dc.contributor.advisor | Hsin-Mu Tsai | en |
| dc.contributor.author | 王柏文 | zh_TW |
| dc.contributor.author | Bo-Wen Wang | en |
| dc.date.accessioned | 2023-07-24T16:10:32Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-07-24 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-06-20 | - |
| dc.identifier.citation | [1] Yunkai Zhai, Xing Xu, Baozhan Chen, Huimin Lu, Yichuan Wang, Shuyang Li, Xiaobing Shi, Wenchao Wang, Lanlan Shang, and Jie Zhao. 5G-network-enabled smart ambulance: Architecture, application, and evaluation. IEEE Network, 35(1):190– 196, 2021.
2] Jinsung Lee, Sungyong Lee, Jongyun Lee, Sandesh Dhawaskar Sathyanarayana, Hyoyoung Lim, Jihoon Lee, Xiaoqing Zhu, Sangeeta Ramakrishnan, Dirk Grunwald, Kyunghan Lee, and Sangtae Ha. Perceive: Deep learning-based cellular uplink prediction using real-time scheduling patterns. In Proc. ACM International Conference on Mobile Systems, Applications, and Services (MobiSys), page 377–390, 2020. [3] Gaetano Carlucci, Luca De Cicco, Stefan Holmer, and Saverio Mascolo. Analysis and design of the Google congestion control for web real-time communication (WebRTC). In Proc. International Conference on Multimedia Systems, 2016. [4] WebRTC home. https://webrtc.org/, 2023. [5] Pion WebRTC: A pure Go implementation of the WebRTC API. https://github.com/pion/webrtc, 2022. [6] Stefan Holmer, Magnus Flodman, and Erik Sprang. RTP Extensions for Transport-wide Congestion Control. Technical Report draft-holmer-rmcat-transport-wide-ccextensions-01, 2015. [7] Bo-Wen Wang, Wen-Hsuan Shen, Ming-Ju Hsieh, and Hsin-Mu Tsai. Ems-rtc: Lstm-based adaptive video streaming for smart ambulance. In 2023 IEEE Vehicular Networking Conference (VNC), pages 9–16, 2023. [8] Eymen Kurdoglu, Yong Liu, Yao Wang, Yongfang Shi, ChenChen Gu, and Jing Lyu. Real-time bandwidth prediction and rate adaptation for video calls over cellular networks. In Proc. International Conference on Multimedia Systems (MMSys), 2016. [9] Balázs Kreith, Varun Singh, and Jörg Ott. Fractal: Fec-based rate control for rtp. In Proceedings of the 25th ACM International Conference on Multimedia, MM ’17, page 1363–1371, New York, NY, USA, 2017. Association for Computing Machinery. [10] Hongzi Mao, Ravi Netravali, and Mohammad Alizadeh. Neural adaptive video streaming with pensieve. In Proceedings of the conference of the ACM special interest group on data communication, pages 197–210, 2017. [11] Anfu Zhou, Huanhuan Zhang, Guangyuan Su, Leilei Wu, Ruoxuan Ma, Zhen Meng, Xinyu Zhang, Xiufeng Xie, Huadong Ma, and Xiaojiang Chen. Learning to coordinate video codec with transport protocol for mobile video telephony. In Proc. ACM Annual International Conference on Mobile Computing and Networking (MobiCom), 2019. [12] Huanhuan Zhang, Anfu Zhou, Jiamin Lu, Ruoxuan Ma, Yuhan Hu, Cong Li, Xinyu Zhang, Huadong Ma, and Xiaojiang Chen. OnRL: Improving mobile video telephony via online reinforcement learning. In Proc. ACM Annual International Conference on Mobile Computing and Networking (MobiCom), 2020. [13] Francis Y Yan, Hudson Ayers, Chenzhi Zhu, Sadjad Fouladi, James Hong, Keyi Zhang, Philip Alexander Levis, and Keith Winstein. Learning in situ: a randomized experiment in video streaming. In NSDI, volume 20, pages 495–511, 2020. [14] C. Yue, R. Jin, K. Suh, Y. Qin, B. Wang, and W. Wei. Linkforecast: Cellular link bandwidth prediction in lte networks. IEEE Transactions on Mobile Computing, 17(07):1582–1594, jul 2018. [15] Qualcomm extensible diagnostic monitor. http://www.qualcomm.com/media/ documents/tags/qxdm, 2008. [16] Yuanjie Li, Chunyi Peng, Zengwen Yuan, Jiayao Li, Haotian Deng, and Tao Wang. Mobileinsight: Extracting and analyzing cellular network information on smartphones. In Proceedings of the 22nd Annual International Conference on Mobile Computing and Networking, pages 202–215, 2016. [17] MobileInsight. running your customized plugin on the phone. http://www. mobileinsight.net/tutorial-plugin.html, 2018. [18] ITU Telecom et al. Advanced video coding for generic audiovisual services. ITU-T Recommendation H. 264, 2003. [19] Dan Grois, Detlev Marpe, Amit Mulayoff, Benaya Itzhaky, and Ofer Hadar. Performance comparison of h.265/mpeg-hevc, vp9, and h.264/mpeg-avc encoders. In 2013 Picture Coding Symposium (PCS), pages 394–397, 2013. [20] Bartjan Jansen, Timothy Goodwin, Varun Gupta, Fernando A. Kuipers, and Gil Zussman. Performance evaluation of webrtc-based video conferencing. SIGMETRICS Perform. Evaluation Rev., 45:56–68, 2018. [21] Telecommunication Standardization Sector of ITU. ITU-T Recommendation G.114: Transmission Systems and Media : General Recommendations on the Transmission Quality for an Entire International Telephone Connection : One-Way Transmission Time. International Telecommunication Union, 2003. [22] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural Comput., 9(8):1735–1780, nov 1997. [23] Zhou Wang, A.C. Bovik, H.R. Sheikh, and E.P. Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4):600–612, 2004. [24] Leo Breiman. Random forests. Machine learning, 45:5–32, 2001. [25] Yihua Guo, Feng Qian, Qi Alfred Chen, Zhuoqing Morley Mao, and Subhabrata Sen. Understanding on-device bufferbloat for cellular upload. In Proc. Internet Measurement Conference (IMC), page 303–317, 2016. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87865 | - |
| dc.description.abstract | 一台智慧型救護車會不斷地分享病人的生命徵象數據和救護車內的影像流， 讓駐院醫生可以與救護人員合作，對病人進行早期評估甚至提供治療指南。不過 要讓醫生和救護人員之間合作順暢的前提是要有高品質的影像串流。影像品質差 或延遲高的串流會大幅增加對病人的準確診斷的困難度。
由於需要從移動的救護車傳送直播視訊，因此串流的效能受到行動網路的頻 寬快速變化的影響。在這種情況下，影片串流的比特率能夠快速適應行動網路服 務品質的變化並相應地進行調整是至關重要的。若影片串流的比特率超出行動網 路的可用頻寬，就有可能會發生卡頓以及破圖。我們必須讓醫生可以透過直播來 判斷病人的病況，要做到這件事，直播的時候必須儘量避免卡頓和破圖的發生。 為了達到這件事，我們必須使所用頻寬不超過頻道的可用頻寛。 為此，我們提出了EMS-RTC，一個針對救護車服務需求專門設計的即時視頻 串流平台。EMS-RTC 訓練了一個分類器，根據在現實駕駛情況下收集的一系列信 號和網絡相關指標的特徵，推斷出最佳的比特率。我們將EMS-RTC 與目前最具 代表性的自適應串流演算法（即Google 擁塞控制，GCC）進行比較。從真實世界 的行駛情況中收集的評估結果顯示，EMS-RTC 可以在可忽略降低一點影像品質的 成本下，將卡頓事件的總時間長度減少3.85 倍。 | zh_TW |
| dc.description.abstract | A smart ambulance continuously shares the patient’s vital signs data and video feeds from the ambulance so that the doctors stationed in the hospital can work with the paramedics in the ambulance, performing an early assessment of the patient or even providing treatment guidelines. One prerequisite to the seamless cooperation between the doctor and the paramedics is high-quality video streaming. Video streaming with bad image quality or high latency would introduce significant difficulty in providing accurate diagnoses of the patient. As the video needs to be delivered from a moving ambulance, the streaming performance is influenced by the fast variation of the service quality of the mobile network. Compared to static scenarios, additional channel impairments, such as the shadowing effect, is introduced in the mobile scenarios. In this case, it is crucial that the bitrate of the video streaming can quickly react to the changes in the service quality and is adjusted accordingly, such that the video quality leverages full available bandwidth, but does not exceed what the channel can support. To this end, we propose EMS-RTC, a real-time video streaming platform specialized for the need for ambulance services. EMS-RTC trains a classifier to infer the optimal bitrate based on features from a range of signal- and networkrelated metrics, collected in real-world driving scenarios. We compare EMS-RTC to a state-of-the-art ABR algorithm (i.e., Google congestion control, GCC). Evaluation results collected from real-world driving scenarios show that EMS-RTC reduces the total time duration of stall events by a factor of 3.85, at the cost of a neglectable reduction of image quality. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-07-24T16:10:32Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-07-24T16:10:32Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 iii
摘要 iv Abstract vi Contents viii List of Figures x List of Tables xii Chapter 1 Introduction 1 1.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 Chapter 2 Related Work 7 2.1 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 Chapter 3 Background 10 3.1 H.264 frame . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.2 Web Real-Time Communication(WebRTC) . . . . . . . . . . . . . . 11 3.3 Google congestion control (GCC) . . . . . . . . . . . . . . . . . . . 12 Chapter 4 System Design 14 4.1 System Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.2 Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.2.1 Model Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.3 Post processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 4.3.1 Maintaining a consistent sampling rate. . . . . . . . . . . . . . . . . 21 4.3.2 Mitigating data fluctuation caused by the size of the sent frame. . . . 21 4.4 Quality of service metric and data labeling . . . . . . . . . . . . . . 23 4.5 Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 4.5.1 Training data collection . . . . . . . . . . . . . . . . . . . . . . . . 26 4.5.2 Model architecture and training . . . . . . . . . . . . . . . . . . . . 27 4.5.3 Features importance . . . . . . . . . . . . . . . . . . . . . . . . . . 29 Chapter 5 Implementation 30 5.1 Sender . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 5.2 Receiver and Signaling server . . . . . . . . . . . . . . . . . . . . . 31 Chapter 6 Evaluation 33 6.1 Methodology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 6.2 Comparison of GCC and EMS-RTC . . . . . . . . . . . . . . . . . . 35 Chapter 7 Conclusion 40 Chapter 8 Future work 41 References 43 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 使用者體驗品質 | zh_TW |
| dc.subject | 長短期記憶模型 | zh_TW |
| dc.subject | 自適性比特率 | zh_TW |
| dc.subject | Google 擁塞控制 | zh_TW |
| dc.subject | Adaptive Bitrate | en |
| dc.subject | Quality of Experience | en |
| dc.subject | Long Short-Term Memory | en |
| dc.subject | Google Congestion Control | en |
| dc.title | 基於長短期記憶模型之智慧救護車自適應比特率影像直播系統 | zh_TW |
| dc.title | EMS-RTC LSTM-based Adaptive Video Streaming for Smart Ambulance | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 逄愛君;周承復;謝明儒 | zh_TW |
| dc.contributor.oralexamcommittee | Ai-Chun Pang;Cheng-Fu Chou;Ming-Ju Hsieh | en |
| dc.subject.keyword | 長短期記憶模型,自適性比特率,使用者體驗品質,Google 擁塞控制, | zh_TW |
| dc.subject.keyword | Long Short-Term Memory,Adaptive Bitrate,Quality of Experience,Google Congestion Control, | en |
| dc.relation.page | 46 | - |
| dc.identifier.doi | 10.6342/NTU202301100 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2023-06-21 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf | 15.9 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。