Javier Serrano

Dr. Javier Serrano

Departamento de Sistemas Informáticos, UNIVERSIDAD POLITENICA MADRID, Madrid, Spain
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 March 2019 in IEEE Transactions on Broadcasting
Verified
Journal Article
Closed access
FAFederico Alvarez
Federico Alvarez
DBDavid Breitgand
David Breitgand
DGDavid Griffin
David Griffin
PAPasquale Andriani
Pasquale Andriani
SRStamatia Rizou
Stamatia Rizou
DJDavid Jiménez
David Jiménez

2 October 2024 in IEEE Access
Verified
Journal Article
Open access
ARAlberto Del Rio
Alberto Del Rio
DJDavid Jiménez
David Jiménez
JSJavier Serrano
Javier Serrano
This research article presents a comparison between two mainstream Deep Reinforcement Learning (DRL) algorithms, Asynchronous Advantage Actor-Critic (A3C) and Proximal Policy Optimization (PPO), in the context of two diverse environments: CartPole and Lunar Lander. DRL algorithms are widely known for their effectiveness in training agents to navigate complex environments and achieve optimal policies. Nevertheless, a methodical assessment of their effectiveness in various settings is crucial for comprehending their advantages and disadvantages. In this study, we conduct experiments on the CartPole and Lunar Lander environments using both A3C and PPO algorithms. We compare their performance in terms of convergence speed and stability. Our results indicate that A3C typically achieves quicker training times, but exhibits greater instability in reward values. Conversely, PPO demonstrates a more stable training process at the expense of longer execution times. An evaluation of the environment is needed in terms of algorithm selection, based on specific application needs, balancing between training time and stability. A3C is ideal for applications requiring rapid training, while PPO is better suited for those prioritizing training stability.

17 December 2024 in AI
Verified
Journal Article
Open access
PDF file
PBPilar Schümmer Bengoa
Pilar Schümmer Bengoa
ARAlberto Del Rio
Alberto Del Rio
JSJavier Serrano
Javier Serrano
DJDavid Jiménez
David Jiménez
GIGuillermo Sánchez Illán
Guillermo Sánchez Illán
ÁGÁlvaro Llorente Gómez
Álvaro Llorente Gómez
Background: In the last decade, numerous methods have been proposed to define and detect outliers, particularly in complex environments like networks, where anomalies significantly deviate from normal patterns. Although defining a clear standard is challenging, anomaly detection systems have become essential for network administrators to efficiently identify and resolve irregularities. Methods: This study develops and evaluates a machine learning-based system for network anomaly detection, focusing on point anomalies within network traffic. It employs both unsupervised and supervised learning techniques, including change point detection, clustering, and classification models, to identify anomalies. SHAP values are utilized to enhance model interpretability. Results: Unsupervised models effectively captured temporal patterns, while supervised models, particularly Random Forest (94.3%), demonstrated high accuracy in classifying anomalies, closely approximating the actual anomaly rate. Conclusions: Experimental results indicate that the system can accurately predict network anomalies in advance. Congestion and packet loss were identified as key factors in anomaly detection. This study demonstrates the potential for real-world deployment of the anomaly detection system to validate its scalability.

10 February 2018 in Energies
Verified
Journal Article
Open access
PDF file
DJDavid Jiménez
David Jiménez
SHSara H.
Sara H.
Jesus Fraile-ArdanuyJesus Fraile-Ardanuy
Jesus Fraile-Ardanuy
JSJavier Serrano
Javier Serrano
RRubén Fernández
Rubén Fernández
FAFederico Alvarez
Federico Alvarez
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.

5 June 2018 in IEEE Transactions on Broadcasting
Verified
Journal Article
Open access
ADAlexandros Doumanoglou
Alexandros Doumanoglou
DGDavid Griffin
David Griffin
JSJavier Serrano
Javier Serrano
NZNikolaos Zioulis
Nikolaos Zioulis
TPTruong Khoa Phan
Truong Khoa Phan
PDPetros Daras
Petros Daras
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, real-time 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.

14 October 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ARAlberto Del Rio
Alberto Del Rio
JSJavier Serrano
Javier Serrano
DJDavid Jiménez
David Jiménez
LCLuis Miguel Contreras-Murillo
Luis Miguel Contreras-Murillo
FAFederico Alvarez
Federico Alvarez
Media applications are amongst the most demanding services. They require high amounts of network capacity as well as computational resources for synchronous high-quality audio–visual streaming. Recent technological advances in the domain of new generation networks, specifically network virtualization and Multiaccess Edge Computing (MEC) have unlocked the potential of the media industry. They enable high-quality media services through dynamic and efficient resource allocation taking advantage of the flexibility of the layered architecture offered by 5G. The presented work demonstrates the potential application of Artificial Intelligence (AI) capabilities for multimedia services deployment. The goal was targeted to optimize the Quality of Experience (QoE) of real-time video using dynamic predictions by means of Deep Reinforcement Learning (DRL) algorithms. Specifically, it contains the initial design and test of a self-optimized cloud streaming proof-of-concept. The environment is implemented through a virtualized end-to-end architecture for multimedia transmission, capable of adapting streaming bitrate based on a set of actions. A prediction algorithm is trained through different state conditions (QoE, bitrate, encoding quality, and RAM usage) that serves the optimizer as the encoding values of the environment for action prediction. Optimization is applied by selecting the most suitable option from a set of actions. These consist of a collection of predefined network profiles with associated bitrates, which are validated by a list of reward functions. The optimizer is built employing the most prominent algorithms in the DRL family, with the use of two Neural Networks (NN), named Advantage Actor–Critic (A2C). As a result of its application, the ratio of good quality video segments increased from 65% to 90%. Furthermore, the number of image artifacts is reduced compared to standard sessions without applying intelligent optimization. From these achievements, the global QoE obtained is clearly better. These results, based on a simulated scenario, increase the interest in further research on the potential of applying intelligence to enhance the provisioning of media services under real conditions.