Harnessing Crowdsourcing and Machine Learning for Mobile Services Performance Analysis | Chapter 8 | Advances and Challenges in Science and Technology Vol. 2

 Data accumulation from user terminals or specialized group devices is necessary for crowdsourcing the evaluation of quality of knowledge (QoE) on mobile networks. With this method, mobile operators and professors may more affordably address large-scale issues, embellish resource distribution, and supply networks. Based on this strategy, we present here a vocabulary of dataset generation though movable signals measurements, and also a inclusive study utilizing crowdsourced data from consumer terminals to analyze the QoE of common Internet services, such as on-demand program streaming, netting browsing, and file downloading. The dataset, comprising over 220,000 calculations collected from two different dealer terminals and various maneuverability test modes, was obtained from a bigger French mobile driver in the Ile-de-France region over a six-month ending in 2021. Various models from the literature are then achieved to estimate the QoE in terms of consumer Mean Opinion Score (MOS), utilizing features at two together the radio and use levels. Furthermore, a detailed analysis of the calm dataset is conducted to identify the root causes of weak performance, disclosing that radio provisioning issues are not the singular factor donating to anomalies. Lastly, the chapter survey the prediction accuracy of HD broadcast streaming duties, considering factors to a degree launch occasion, bitrate, and MOS, based solely on material indicators. The analysis surrounds both ordinary readable form and encrypted traffic within different maneuverability modes, providing valuable acumens into QoE optimization in mobile networks.

Author(s) Details:

Lamine Amour,
ESME Engineering School / ESME Research Lab, France.

Abdulhalim Dandoush,
ESME Engineering School / ESME Research Lab, France and University of Doha for Science and Technology (UDST), Qatar and Laboratoire de Traitement et Transport de l’Information (L2TI) institution of Sorbonne University, France.

Please see the link here: https://stm.bookpi.org/ACST-V2/article/view/11931