Home // MODERN SYSTEMS 2025, International Conference of Modern Systems Engineering Solutions // View article
Authors:
Carlos Moreno
Ezequiel Frias
Vinod Kumar Verma
Eric Gamess
Keywords: Quality of Service; WebRTC; Video-Calling; Neural Networks; Prediction
Abstract:
The development of video-calling applications using Web Real-Time Communication (WebRTC) represents an efficient and modern solution for real-time communications, enabling the direct transmission of audio, video, and data between browsers with no need for additional plugins. This research aimed to design and develop a WebRTC-based videocalling application capable of predicting Quality of Service (QoS) patterns through the implementation of an Artificial Neural Network (ANN). The proposal focused on analyzing key indicators (e.g., latency, jitter, and packet loss) that play a critical role in shaping user-perceived quality. The development of the predictive model was performed by using a Recurrent Neural Network (RNN) of the Long Short-Term Memory (LSTM) type. To validate the solution, four representative scenarios were established: acceptable quality, moderate degradation, critical quality, and extreme conditions. The results demonstrated that the LSTM model successfully captured the temporal behavior of QoS metrics and generated predictions within acceptable ranges according to standards defined by specialized organizations and industry leaders. It is concluded that the integration of LSTM neural networks into WebRTC applications constitutes a viable and effective strategy to enhance proactive QoS management and optimize the end-user experience.
Pages: 29 to 37
Copyright: Copyright (c) IARIA, 2025
Publication date: October 26, 2025
Published in: conference
ISBN: 978-1-68558-316-3
Location: Barcelona, Spain
Dates: from October 26, 2025 to October 30, 2025