The focus of research into 5G networks to date has been largely on the required advances in network architectures, technologies, and infrastructures. Less effort has been put on the applications and services that will make use of and exploit the flexibility of 5G networks built upon the concept of software-defined networking (SDN) and network function virtualization (NFV). Media-based applications are amongst the most demanding services, requiring large bandwidths for high Manuscript
Air pollution and climate change are some of the main problems that humankind is currently facing. The electrification of the transport sector will help to reduce these problems, but one of the major barriers for the massive adoption of electric vehicles is their limited range. The energy consumption in these vehicles is affected, among other variables, by the driving behavior, making range a value that must be personalized to each driver and each type of electric vehicle. In this paper we offer a way to estimate a personalized energy consumption model by the use of the vehicle dynamics and the driving events detected by the use of the smartphone inertial sensors, allowing an easy and non-intrusive manner to predict the correct range for each user. This paper proposes, for the classification of events, a deep neural network (Long-Short Time Memory) which has been trained with more than 22,000 car trips, and the application to improve the consumption model taking into account the driver behavior captured across different trips, allowing a personalized prediction. Results and validation in real cases show that errors in the predicted consumption values are halved when abrupt events are considered in the model.
In voice controlled multi-room smart homes ASR and speaker identification systems face distance speech conditions which have a significant impact on performance. Regarding voice command recognition, this paper presents an approach which selects dynamically the best channel and adapts models to the environmental conditions. The method has been tested on data recorded with 11 elderly and visually impaired participants in a real smart home. The voice command recognition error rate was 3.2% in off-line condition and of 13.2% in online condition. For speaker identification, the performances were below very speaker dependant. However, we show a high correlation between performance and training size. The main difficulty was the too short utterance duration in comparison to state of the art studies. Moreover, speaker identification performance depends on the size of the adapting corpus and then users must record enough data before using the system.
Recent advances in media capture and processing technologies have enabled new forms of true 3-D media content that increase the degree of user immersion. The demand for more engaging forms of entertainment means that content distributors and broadcasters need to fine-tune their delivery mechanisms over the Internet as well as develop new models for quantifying and predicting user experience of these new forms of content. In the work described in this paper, we undertake one of the first studies into the quality of experience (QoE) of real-time 3-D media content streamed to virtual reality (VR) headsets for entertainment purposes, in the context of game spectating. Our focus is on tele-immersive media that embed real users within virtual environments of interactive games. A key feature of engaging and realistic experiences in full 3-D media environments, is allowing users unrestricted viewpoints. However, this comes at the cost of increased network bandwidth and the need of limiting network effects in order to transmit a realistic, realtime representation of the participants. The visual quality of 3-D media is affected by geometry and texture parameters while the temporal aspects of smooth movement and synchronization are affected by lag introduced by network transmission effects. In this paper, we investigate varying network conditions for a set of tele-immersive media sessions produced in a range of visual quality levels. Further, we investigate user navigation issues that inhibit free viewpoint VR spectating of live 3-D media. After reporting on a study with multiple users we analyze the results and assess the overall QoE with respect to a range of visual quality and latency parameters. We propose a neural network QoE prediction model for 3-D media, constructed from a combination of visual and network parameters.
Media applications are amongst the most demanding services requiring high amounts of network capacity as well as extremely low latency for synchronous audiovisual streaming in production quality. Recent technological advances in the 5G domain hold the promise to unlock the potential of the media industry by offering high quality media services through dynamic efficient resource allocation. Actual implementations are now required to validate whether advanced media applications can be realised benefiting from ultra-low latency, very-high bandwidth and flexible dynamic configuration offered by these new 5G networks. A truly integrated approach is needed that focuses on the media applications not only on the management of generic network functions and the orchestration of resources at the various radio, fronthaul/backhaul, edge and core network segments. The H2020 5G PPP Phase 2 project 5G-MEDIA [1] leverages new options for more flexible, ad-hoc and cost-effective production workflows by replacing dedicated lines and hardware equipment with software functions (VNFs) facilitating (semi-) automated smart production in remote locations. Highly scalable virtualized media services deployed on or close to the edge reduce complexity for the user, ensure operational reliability and increase the Quality of Experience (QoE). Virtual compression engines have the potential to replace dedicated encoder/decoder hardware while the network optimisation (Cognitive Network Optimizer) in combination with the Quality of Service (QoS) monitoring helps to overcome the current internet best-effort principle and ensures that the required performance needs are met at all times.
To ensure high Quality of Experience (QoE) for end users, many media applications require significant quantities of computing and network resources, making their realization challenging in resource constrained environments. In this paper, we present the approach of the 5G-MEDIA project, providing an integrated programmable service platform for the development, design and operations of media applications in 5G networks, facilitating media service management across the service life cycle. The platform offers tools to service developers for efficient development, testing and continuous correction of services. One step further, it provides a service virtualization platform offering horizontal services, such as a Media Service Catalogue and accounting services, as well as optimization mechanisms to flexibly adapt service operations to dynamic conditions with efficient use of infrastructure resources. The paper outlines three use cases where the platform was tested and validated.
Nowadays, the most commonly used configuration to supply high-speed trains is 2 × 25 kV power supply system. The location of ground faults in 2 × 25 kV power supply systems is a difficult task, since the use of distance protection relays to localize ground faults positions doesn't work properly as the relation between the distance and the impedance seen by the distance protection relays is not linear and therefore the location is not accurate enough. A new simple and economical method to identify the subsection between autotransformers (ATS) and the conductor (positive or negative) where the ground fault is happening, based on the comparison of the angle between the current and the voltage of the positive terminal in each autotransformer, was developed recently. Consequently, after the identification of the subsection and the conductor with the ground fault, only this subsection where the ground fault is present, will be quickly removed from service, with the minimum effect on rail traffic. The high-speed trains demand a power about 12-16 MW, hence a significant current flow through the conductors of the 2 × 25 kV power system. This paper presents a study about the influence of the current consumed by the high-speed trains on this novel ground fault identification method. The operation of the method is correct even with the high-speed train currents in the section with a ground fault. This fact has been validated through numerous computer simulations, obtaining excellent results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.