Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Look Ahead: a DASH adaptation algorithm

  • Belda Ortega, Román|||0000-0003-2244-2371
  • Arce Vila, Pau|||0000-0001-5726-9228
  • Guerri Cebollada, Juan Carlos|||0000-0002-5807-1923
  • De Fez Lava, Ismael
This paper proposes a video quality adaptation algorithm based on the Dynamic Adaptive Streaming over HTTP (DASH) standard for on-demand video services. When a video is encoded with constant quality, the resulting bitstream has variable bitrate due to the inherent nature of the video encoding process. The proposed algorithm, called Look Ahead, takes into account this bitrate variability in order to calculate, on the fly, the appropriate quality level that minimizes the number of interruptions during the playback. Moreover, the Look Ahead algorithm has been implemented and integrated into ExoPlayer v2, the latest version of the library developed by Google to play DASH contents. The proposed algorithm is compared to the Müller and Segment Aware Rate Adaptation (SARA) algorithms as well as to the adaptive algorithm integrated into ExoPlayer. The comparison reflects that Look Ahead outperforms the Müller, SARA and the ExoPlayer adaptive algorithms in terms of number and duration of video playback stalls, with hardly decreasing the average video quality.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Performance evaluation and testbed for delivering SRT live content using DASH Low Latency streaming systems

  • Belda Ortega, Román|||0000-0003-2244-2371
  • Arce Vila, Pau|||0000-0001-5726-9228
  • Guerri Cebollada, Juan Carlos|||0000-0002-5807-1923
  • De Fez, Ismael
[EN] The work presented in this paper focuses on the implementation of a testbed for the evaluation of content distribution systems using LL-DASH (Low Latency DASH -Dynamic Adaptive Streaming over HTTP-) and devices that provide real-time sources or servers using real-time protocols, such as RTSP (Real Time Streaming Protocol) or SRT (Secure Reliable Transport). These protocols are widely used by IP (Internet Protocol) cameras or by production and transmission systems, such as OBS Studio or vMix. The objective is to show the necessary processes in detail (so they can be reproduced in future works related to low latency services) and to minimize the end-to-end delay, obtaining values in the order of 2 seconds or less. The implementation has been done using FFmpeg software, players like Dash.js or Shaka-Player and implementing a Python web server with LL-DASH support to optimize the transmission delay., This work is supported by the Centro para el Desarrollo Tecnológico Industrial (CDTI) from the Government of Spain under the project Nueva plataforma a bordo basada en redes 5G y Wi-Fi 6 para medios de transporte terrestre (CDTI IDI20210624).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Predicting requested flight levels with machine learning

  • Mateos Villar, Manuel
  • Martín, Ignacio
  • García, Pedro
  • Alcolea, Ruben
  • Herranz, Ricardo
  • García Cantú-Ros, Oliva
  • Prats Menéndez, Xavier
The objective of this paper is to present a machine learning approach for the prediction of the Requested Flight Level received during the pre-tactical phase of the Air Traffic Flow and Capacity Management process. A set of machine learning models are proposed in order to determine which Requested Flight Level is the most likely to be filed by an airspace user for a certain origin-destination pair. Results show that the proposed system outperforms the pre-tactical traffic forecasting approach currently used by the European Network Manager in 60% of the 14,465 origin-destination pairs considered in the study, reducing the error of the current solution by 4.8%., Manuel Mateos’ PhD is funded by SESAR’s Engage Knowledge Transfer Network, which has received funding from the SESAR Joint Undertaking under the European Union’s Horizon 2020 research and innovation programme under grant agreement No 783287. The opinions expressed herein reflect the authors’ view only. Under no circumstances shall the SESAR Joint Undertaking be responsible for any use that may be made of the information contained herein. The authors would also like to acknowledge the support of the Spanish Centre for Industrial Development (CDTI) through the PRETA project (Grant no. IDI-20190029)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Full-scale pre-tactical route prediction machine learning to increase pre-tactical demand forecast accuracy

  • Mateos Villar, Manuel
  • Martín, Ignacio
  • García, Pedro
  • Herranz, Ricardo
  • García Cantú-Ros, Oliva
  • Prats Menéndez, Xavier
The objective of this paper is to present an artificial intelligence-based methodology to predict the Flight plans that will be received during the pre-tactical phase of the Air Traffic Flow and Capacity Management (ATFCM) process. For this purpose, input features equivalent to those of EUROCONTROL’s PREDICT solution are fed to a Multinomial Logistic Regression algorithm over pre-clustered air routes in order to determine which route cluster is the most likely to be filed by an airspace user within each OD-pair. Results show that this procedure is capable of outperforming the current PREDICT solution in almost 40% of the 5,699 OD pairs considered and reducing current solution’s error by 11%, showing good and scalable prediction capabilities., Manuel Mateos´ PhD is funded by the 1st SESAR ENGAGE KTN Call for PhDs, developed in collaboration between Nommon and the Technical University of Catalonia. This PhD study has received funding from the SESAR Joint Undertaking under the European Union’s Horizon 2020 research and innovation programme under grant agreement No 783287. The opinions expressed herein reflect the authors’ view only. Under no circumstances shall the SESAR Joint Undertaking be responsible for any use that may be made of the information contained herein. Finally, the authors would like to acknowledge the support of the Spanish Centre for Industrial development (CDTI) through the PRETA project (Grant no. IDI-20190029), Peer Reviewed, Postprint (published version)