(JBE Vol. 23, No. 1, January 2018) (Regular Paper) 23 1, (JBE Vol. 23, No. 1, January 2018) ISSN 2287

Transcription

1 (Regular Paper) 23 1, (JBE Vol. 23, No. 1, January 2018) ISSN (Online) ISSN (Print) DASH ANFIS a), a), a) A Video-Quality Control Scheme using ANFIS Architecture in a DASH Environment Ye-Seul Son a), Hyun-Jun Kim a), and Joon-Tae Kim a) HTTP HTTP (HTTP-based Adaptive Streaming : HAS) DASH(Dynamic Adaptive Streaming over HTTP). DASH QoE(Quality of Experience). ANFIS(Adaptive Network based Fuzzy Inference System). ANFIS, VBR(Variable Bit-Rate).. NS-3 QoE. Abstract Recently, as HTTP-based video streaming traffic continues to increase, Dynamic Adaptive Streaming over HTTP(DASH), which is one of the HTTP-based adaptive streaming(has) technologies, is receiving attention. Accordingly, many video quality control techniques have been proposed to provide a high quality of experience(qoe) to clients in a DASH environment. In this paper, we propose a new quality control method using ANFIS(Adaptive Network based Fuzzy Inference System) which is one of the neuro-fuzzy system structure. By using ANFIS, the proposed scheme can find fuzzy parameters that selects the appropriate segment bitrate for clients. Also, considering the characteristic of VBR video, the next segment download time can be more accurately predicted using the actual size of the segment. And, by using this, it adjusts video quality appropriately in the time-varying network. In the simulation using NS-3, we show that the proposed scheme shows higher average segment bitrate and lower number of bitrate-switching than the existing methods and provides improved QoE to the clients. Keyword : MPEG-DASH, Adaptive bitrate streaming, Video-Quality Control, Neuro-Fuzzy System, ANFIS a) (Department of Electronic Engineering, Konkuk University) Corresponding Author : (Joon-Tae Kim) jtkim@konkuk.ac.kr Tel: ORCID: Manuscript received October 16, 2017; Revised December 29, 2017; Accepted December 29, Copyright 2017 Korean Institute of Broadcast and Media Engineers. All rights reserved. This is an Open-Access article distributed under the terms of the Creative Commons BY-NC-ND ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited and not altered.

2 2: DASH ANFIS (Ye-Seul Son et al.: A Video-Quality Control Scheme using ANFIS Architecture in a DASH Environment). HTTP [1]. HTTP HAS. HAS. HTTP. HAS MPEG DASH [2][3] DASH [4]-[6]. DASH [7]-[9].,.. VBR. [8] MPD(Media Presentation Description),. SARA. SARA.., [9] FDASH. FDASH (Fuzzy Logic Controller : FLC), f. FDASH NS-3. QoE [10]. FDASH,. DASH. [11]. ANFIS [12]., VBR, SARA.. NS-3 QoE.. ANFIS, ANFIS... ANFIS FLC,

3 1. ANFIS Fig. 1. The ANFIS architecture,, [11]. [12] [13] ANFIS. 1 ANFIS 5. 1 ANFIS,.,.. (1), (2). exp (1) (2).. 1 (3). (4)... (5).,., (5), (5) 0. (6).

4 2: DASH ANFIS (Ye-Seul Son et al.: A Video-Quality Control Scheme using ANFIS Architecture in a DASH Environment) ANFIS., [12] Table 1. The hybrid learning process Type Premise Parameters Consequent Parameters Reference Signal Forward path Fixed Least Squares Estimate Node Outputs Backward path Gradient Descent Fixed Error, ANFIS., ANFIS.. 2 ANFIS DASH QoE. 1 FDASH FLC,.,., FDASH FLC ANFIS Fig. 2. The ANFIS structure of the proposed quality control scheme

5 1. ANFIS 2, 2.,. (7). [9][14][15]. (9). 2. ANFIS Table 2. The ANFIS properties of the proposed scheme Number of Inputs Number of Outputs Number of input membership functions per input Number of fuzzy rules Type of input membership function Type of output membership function Gaussian membership function constant. FDASH,. (10).,,. (8).. (8). SARA.,,,.,, 2.. ANFIS.. 2. ANFIS

6 2: DASH ANFIS (Ye-Seul Son et al.: A Video-Quality Control Scheme using ANFIS Architecture in a DASH Environment) 3. (a) (b) Fig. 3. The training data extraction environment (a) Long-term change point-to-point link network (b) Periodic Short-term change point-to-point link network. 3 ANFIS,,., ANFIS., ANFIS. 3.. QoE [10].. [8].. NS-3. FDASH SARA,., QoE,, QoE [10][16]. 4 DASH 45, 89, 129, 177, 218, 256, 323, 378, 509, 578, 783, 1000, 1200, 1500, , 2900, 3300, 3600, 3900Kbps FDASH 20 SARA 8, 20, 30. DASH, DASH 5 TCP Wi-Fi,

7 . 1. ANFIS 4, ANFIS., ANFIS., Fig. 4. The trained fuzzy membership functions 5. Fig. 5. The comparison of training data and trained data 5 Wi-Fi SARA, FDASH, (a), (b). 6 FDASH..,,, FDASH 50. FDASH SARA. SARA,.

8 2: DASH ANFIS (Ye-Seul Son et al.: A Video-Quality Control Scheme using ANFIS Architecture in a DASH Environment) 6. Wi-Fi (a) (b) Fig. 6. The simulation results in Wi-Fi environment (a) segment bitrate (b) client buffer level

9 ,. SARA 125, 145, 230, , 200. QoE [10].., SARA.. QoE., Mbps, 13.6, 0. FDASH Mbps, FDASH. FDASH SARA Mbps 46.8, 0.,, SARA. QoE [10]. SARA SARA 3. Table 3. The Quantitative Simulation Results Algorithm SARA FDASH Proposed Scheme Average Segment Bitrate (Mbps) Number of Segment Bitrate Switching Number of Interruption

10 2: DASH ANFIS (Ye-Seul Son et al.: A Video-Quality Control Scheme using ANFIS Architecture in a DASH Environment) QoE.. ANFIS DASH. FDASH, ANFIS. VBR,,.. QoE,, NS-3. QoE. (References) [1] SANDVINE, IU, 2016 Global Internet Phenomena Report. North America and Latin America, [2] ISO/IEC :2014 (Second edition), Information technology Dynamic adaptive streaming over HTTP (DASH) Part 1: Media presentation description and segment formats, [3] T. Stockhammer, "Dynamic adaptive streaming over HTTP--: standards and design principles," Proceedings of the second annual ACM conference on Multimedia systems, San Jose, CA, USA, pp , [4] M. Park and Y. Kim, "MMT-based Broadcasting Services Combined with MPEG-DASH," Journal of Broadcast Engineering, Vol.20, No.2, pp , March [5] K. Yun, W. Cheong, J. Lee, and K. Kim, "Design and Implementation of Hybrid Network Associated 3D Video Broadcasting System," Journal of Broadcast Engineering, Vol.19, No.5, pp , September [6] Y. Kim, and M. Park, "MPEG-DASH Services for 3D Contents Based on DMB AF," Journal of Broadcast Engineering, Vol.18, No.1, January [7] H. Kim, Y. Son, and J. Kim, "A Modification of The Fuzzy Logic Based DASH Adaptation Algorithm for Performance Improvement," Journal of Broadcast Engineering, Vol. 22, No. 5, September [8] P. Juluri, V. Tamarapalli, and D. Medhi, "SARA : Segment aware rate adaptation algorithm for dynamic adaptive streaming over HTTP," Proceedings of Communication Workshop (ICCW), 2015 IEEE International Conference on, London, UK, pp , [9] DJ. Vergados, A. Michalas, and A. Sgora, "FDASH: A Fuzzy-Based MPEG/DASH Adaptation Algorithm," IEEE System Journal, Vol.10, No.2, pp , [10] L. Yitong, S. Yun, M. Yinian, L. Jing, L. Qi, and Y. Dacheng, A study on quality of experience for adaptive streaming service, Proceedings of Communications Workshops (ICC), 2013 IEEE International Conference on, Budapest, Hungary, pp , [11] CT. Lin, and CSG. Lee, "Neural-network-based fuzzy logic control and decision system," IEEE Transactions on computers, Vol.40, No.12, pp , December [12] JSR. Jang, "ANFIS: adaptive-network-based fuzzy inference system," IEEE transactions on systems, man, and cybernetics, Vol.23, No.3, pp , May/June [13] T. Takagi, and M. Sugeno, "Fuzzy identification of systems and its applications to modeling and control," IEEE transactions on systems, man, and cybernetics, Vol.SMC-15, No.1, pp , January- February [14] Q. He, C. Dovrolis, and M. Ammar. "On the predictability of large transfer TCP throughput," ACM SIGCOMM Computer Communication Review. Vol. 35, No. 4, pp , August, [15] J. Jiang, V. Sekar, and H. Zhang, Improving fairness, efficiency, and stability in http-based adaptive video streaming with festive, Proceedings of the 8th international conference on Emerging networking experiments and technologies, Nice, France, pp , [16] M. Seufert, S. Egger, M. Slanina, T. Zinner, T. Hobfeld, and P. Tran-Gia, "A Survey on Quality of Experience of HTTP Adaptive Streaming," IEEE Communications Surveys & Tutorials, Vol.17, No.1, March 2015.

11 : ~ : - ORCID : - :, : ~ : - ORCID : - :,, : : : ~ 2003 : LG DTV ~ : - ORCID : - : & TV,