Abstract
The implementation of traffic differentiation measures by internet service providers (ISPs) has raised concerns regarding net neutrality, potentially leading to discriminatory practices that challenge existing regulatory frameworks. The complexity of this issue intensifies with the advent of 5G networks as they dynamically assemble elements of the physical infrastructure to create logically segregated domains customised to accommodate usage scenarios with specific requirements, resulting in the categorisation of users, applications, and services into distinct groups which possess the capacity to disrupt the non-discriminatory treatment of data flows. Within this context, a pivotal question arises: how can regulatory authorities effectively evaluate traffic differentiation in 5G networks? In response, this paper proposes an innovative application of the standardised network data analytics function (NWDAF) to facilitate the assessment of internet traffic differentiation. We introduce this novel concept and demonstrate its implementation through a proof -of -concept prototype. By leveraging the NWDAF, regulators may obtain direct and automatic access to performance metrics of 5G networks, enabling the analysis of the traffic management mechanisms employed by ISPs.

Abstract
Over the years, mobile networks were deployed using monolithic hardware based on proprietary solutions. Recently, the concept of open Radio Access Networks (RANs), including the standards and specifications from O-RAN Alliance, has emerged. It aims at enabling open, interoperable networks based on independent virtualized components connected through open interfaces. This paves the way to collect metrics and to control the RAN components by means of software applications such as the O-RAN-specified xApps. We propose a private standalone network leveraged by a mobile RAN employing the O-RAN architecture. The mobile RAN consists of a radio node (gNB) carried by a Mobile Robotic Platform autonomously positioned to provide on-demand wireless connectivity. The proposed solution employs a novel Mobility Management xApp to collect and process metrics from the RAN, while using an original algorithm to define the placement of the mobile RAN. This allows for the improvement of the connectivity offered to the User Equipments.

Abstract

Abstract
We introduce VEMOCLAP: Video EMOtion Classifier using Pretrained features, the first readily available and open-source web application that analyzes the emotional content of any user-provided video. We improve our previous work, which exploits open-source pretrained models that work on video frames and audio, and then efficiently fuse the resulting pretrained features using multi-head cross-attention. Our approach increases the state-of-the-art classification accuracy on the Ekman-6 video emotion dataset by 4.3% and offers an online application for users to run our model on their own videos or YouTube videos. We invite the readers to try our application at serkansulun.com/app.

Abstract
This paper addresses the critical challenge of optimising beacon placement to support indoor location services and proposes a methodology to optimise the Base Station (BS) coverage keeping or even improving the system precision. The algorithm builds on top of the building schematics and takes into account several aspects that affect the radio link range (materials attenuation, Line of Sight (LOS) conditions, transmitted power and radio sensibility). The outcome is available as a coverage heat map. It is then compared with a standard layout following existing expert guidelines to evaluate the efficacy of the proposed layout.

Abstract
We introduce a novel method for movie genre classification, capitalizing on a diverse set of readily accessible pretrained models. These models extract high-level features related to visual scenery, objects, characters, text, speech, music, and audio effects. To intelligently fuse these pretrained features, we train small classifier models with low time and memory requirements. Employing the transformer model, our approach utilizes all video and audio frames of movie trailers without performing any temporal pooling, efficiently exploiting the correspondence between all elements, as opposed to the fixed and low number of frames typically used by traditional methods. Our approach fuses features originating from different tasks and modalities, with different dimensionalities, different temporal lengths, and complex dependencies as opposed to current approaches. Our method outperforms state-of-the-art movie genre classification models in terms of precision, recall, and mean average precision (mAP). To foster future research, we make the pretrained features for the entire MovieNet dataset, along with our genre classification code and the trained models, publicly available.