由於現今行動網路和智慧型行動裝置的技術進步與普及化，線上影音串流服務的網路使用者數量也隨之增加。Youtube、Netflix等知名影音服務提供者為了要能夠應付日漸增加的頻寬需求，開始發展以HTTP為基礎之自適應串流機制(HTTP Adaptive Streaming, HAS)，將過去由伺服器端負責調變畫質的自適應機制設置在客戶端，以減少伺服器端的負擔，進而提升使用者體驗。為了協助推廣HAS，動態視訊專家小組(Moving Picture Experts Group, MPEG)制定了一套標準，稱為Dynamic Adaptive Streaming over HTTP(DASH)。我們發現過去的參考文獻鮮少考慮到DASH遇到網路環境不穩定時的狀況，因DASH是建立在傳輸控制協定(TCP)之上，TCP掉落封包必須重傳的特性，會使DASH運作在網路環境不穩定時的吞吐量明顯下降。為了使DASH在此狀況中能提供較好的串流服務品質，其針對網路資源變化的自適應機制則變得極為重要。本篇論文中，我們提出了基於核心移動平均(Kernel Moving Average, KMA)的自適應機制，讓DASH的客戶端能夠準確估測網路資源，並能夠對伺服器端要求當下網路環境所能承載之最適化的影像片段。在實驗驗證階段，我們實際建立了完整的DASH系統用以檢測我們的構想，相較其他自適應機制，實驗結果裡顯示出我們提出的KMA自適應機制可以讓客戶端在網路環境不穩時維持較高的頻寬使用率，進而維持較高的影片平均碼率，以提供使用者更好的多媒體串流品質。

Due to the revolution of networks and the popularity of smart devices, the multimedia streaming service over wireless networks has become more popular. The multimedia streaming service provider like Youtube and Netflix have developed HTTP adaptive streaming (HAS) to handle the ever-increasing network bandwidth requirement. A HAS based system would adopt video quality adaption at the client side instead at the server side, decreasing the overhead of the server, and thus improving the user experience. To help popularizing HAS, Moving Picture Experts Group (MPEG) develops the Dynamic Adaptive Streaming over HTTP (DASH) standard. Few past works in the literature considered to improve the DASH based video quality in an unstable network environment. Since DASH is based on the transmission control protocol (TCP), which would retransmit lost packets, the throughput of a DASH-based system may therefore significantly decrease in an unstable network environment. For increasing the video streaming quality of DASH, the network resource estimation method in an adaptive mechanism would play an important role. In this thesis, we propose to set up a KMA-based self-adaptation scheme in the DASH client to estimate the network resource and choose an appropriate video segment quality. To validate our proposed concept, we build a real environment based on the DASH standard to conduct some experiments. The results show that the proposed KMA-based self-adaptation scheme can keep a higher bandwidth usage rate, and retain a higher average bit rate of video compared to the default mechanism and the others. The service quality of a DASH-based streaming can thus be improved.

[1] Cisco Systems, Inc., “Networking index: Forecast and methodology,2014–2019,” Cisco Visual, February 2015.
[2] A. C. Begen, T. Akgul, and M. Baugher, “Watching video over the web: Part 1: Streaming protocols,” IEEE Internet Comput., vol. 15, no. 2, pp. 54–63, Mar.–Apr. 2011.
[3] A. Vakali and G. Pallis, “Content delivery networks: Status and trends,” IEEE Internet Computing. vol. 7. no. 6. pp. 68-74, Nov. 2003.
[4] I. Sodagar, “The MPEG-DASH standard for multimedia streaming over the internet,” IEEE Multimedia, vol. 18, no. 4, pp. 62–67, 2011.
[5] ISO/IEC IS 23009-1: “Information technology - dynamic adaptive streaming over HTTP (DASH) - part 1: Media presentation description and segment formats,” 2012.
[6] J.-W. Park, R. P. Karrer, and J. Kim, “TCP-ROME: A transport-layer parallel streaming protocol for real-time online multimedia environments,” J. Commun. Netw., vol. 13, no. 3, pp. 277–285, 2011.
[7] T. C. Thang, H. T. Le, H. X. Nguyen, A. T. Pham, and J. W. Kang, Y. M. Ro “Adaptive video streaming over HTTP with dynamic resource estimation, IEEE/KICS J. Communications and Networks, vol. 15, no. 6, pp. 635–644, Dec. 2013.
[8] H. T. Le, D. V. Nguyen, N. P. Ngoc, A. T. Pham, and T. C. Thang, ”Buffer-based bitrate adaptation for adaptive http streaming,” in Proc. IEEE ATC2013, HoChiMinh City, Vietnam, Oct. 2013.
[9] M.-C. Yu, and J.-S. Leu, “Kernel weighted scheme for improving mobile sensor-node Connectivity,” IEEE Sensors Journal, vol. 13, no. 4, pp. 1200¬¬–1206, Apr. 2013
[10] J.-S. Leu, N. H. Tung, and C.-Y. Liu, “Non-parametric RSS prediction based energy saving scheme for moving smartphones,” IEEE Trans. Computers, pp. 1793–1801, Jul. 2014.
[11] M. Zhao, X. Gong, J. Liang, W. Wang, X. Que, S. Cheng, “QoE-driven cross-layer optimization for wireless dynamic adaptive streaming of scalable videos over HTTP,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 3, pp. 451465, Mar. 2015.
[12] N. Bouten, S. Latre, J. Famaey, W. Van Leekwijck, F. De Turck, “In-network quality optimization for adaptive video streaming services,” IEEE Transactions on Multimedia, vol. 16, no. 8, pp. 2281–2293, Dec. 2014.
[13] D. Jarnikov and T. Ozcelebi, “Client intelligence for adaptive streaming solutions,” in Proc. of the IEEE International Conference on Multimedia and Expo (ICME), Jul. 2010.
[14] C. Liu, I. Bouazizi, and M. Gabbouj, “Rate adaptation for adaptive HTTP streaming,” in Proc. ACM Multimedia Syst. Conf. (MMsys), 2011, pp. 169–174.
[15] C. Chatfield, "Time Series Forecasting," Chapman & Hall, London, 2001.
[16] G. A. F. Seber, and A. J. Lee, "Linear Regression Analysis," John Wiley & Sons Inc, 2003.