Topics within our research lines for B. Sc. thesis (TFG) and M. Sc. thesis (TFM):
TFM: A Comparative Analysis of A3C and SAC Algorithms in Deep Reinforcement Learning
OBJETIVE:
This thesis aims to conduct a comprehensive comparison between two prominent deep reinforcement learning algorithms, Asynchronous Advantage Actor-Critic (A3C) and Soft Actor-Critic (SAC). Both A3C and SAC have demonstrated remarkable success in tackling complex tasks in continuous and discrete action spaces, respectively. However, a thorough investigation into their strengths, weaknesses, and performance across various benchmarks and environments remains unexplored.
This study will compare both algorithms in Python using TensorFlow and OpenAI Gym (A3C provided), providing an in-depth analysis of their sample efficiency, convergence rate, stability, and scalability.
REQUIREMENTS:
Python (TensorFlow), Reinforcement Learning theory
CONTACT PERSON:
Alberto del Río – arp@gatv.ssr.upm.es
TFG: Media Production Control for Enhanced Content Creation
OBJETIVE:
The proposed Master thesis aims to develop a media production control module for optimizing content creation processes. The Studio Production module will integrate information from diverse sources and employ innovative techniques to produce media content that seamlessly combines these inputs into a cohesive and engaging stream.
REQUIREMENTS:
Python, Multimedia tools (OBS).
CONTACT PERSON:
Álvaro Llorente – alg@gatv.ssr.upm.es
TFM: Comparative Analysis of Network Characteristic Measurement Tools: A Study of Features and Performance
OBJECTIVE:
The objective of this Bachelor/Master thesis is to conduct a comprehensive comparison between different network measurement tools to evaluate their capabilities in assessing various network characteristics, such as jitter, bandwidth, latency, and packet loss. The study will focus on open-source tools, including Scapy for Python, Socket programming, ping, nmap, and pyping, to understand their included features and the time taken to perform these measurements accurately.
REQUIREMENTS:
Network fundamentals (TCP/UDP); Programming languages (Bash, Python)
CONTACT PERSON:
Alberto del Río – arp@gatv.ssr.upm.es
TFM: Network Anomaly Detection using Machine Learning Techniques
OBJECTIVE:
The objective of this Master’s thesis is to design and implement algorithms for network anomaly detection. The study aims to develop a system that can identify unusual behavior, security threats, and potential network outages by analyzing network traffic patterns. By utilizing machine learning techniques, the research will focus on creating an efficient and accurate anomaly detection system for network administrators and security personnel.
REQUIREMENTS:
Network fundamentals (TCP/UDP); Programming languages (Bash, Python)
CONTACT PERSON:
Alberto del Río – arp@gatv.ssr.upm.es
TFM: Predictive Bandwidth Usage Modeling for Efficient Network Resource Management
OBJECTIVE:
The goal of this Master’s thesis is to develop a predictive model for bandwidth usage based on historical data. The study will analyze and process historical bandwidth usage patterns to forecast future bandwidth demands accurately. By employing time series analysis, machine learning, or statistical methods, the research aims to provide network administrators with valuable insights to proactively manage network resources, prevent congestion, and optimize overall network performance.
REQUIREMENTS:
Network fundamentals (TCP/UDP); Programming languages (Bash, Python)
CONTACT PERSON:
Javier Serrano – jsr@gatv.ssr.upm.es
TFM: Dynamic Routing Optimization for Enhanced Packet Delivery
OBJECTIVE:
The objective of this Master’s thesis is to optimize dynamic routing algorithms for faster and more efficient packet delivery in computer networks. The research will focus on analyzing routing paths, network topology, and link conditions to propose enhancements to existing dynamic routing protocols. The study aims to improve the routing decision-making process, reduce latency, and optimize the network’s ability to adapt to changing conditions.
REQUIREMENTS:
Network fundamentals (TCP/UDP); Programming languages (Bash, Python)
CONTACT PERSON:
Javier Serrano – jsr@gatv.ssr.upm.es
TFM: A Comprehensive Assessment of Network Performance by means of a Network Health Index
OBJECTIVE:
The goal of this Master’s thesis is to develop a comprehensive network health scoring system that evaluates multiple performance metrics to provide an overall network health assessment. The research will identify key network performance indicators, such as bandwidth utilization, latency, packet loss, and error rates, and develop a scoring system to quantify the network’s overall health. By leveraging data analysis and visualization techniques, the study aims to empower network administrators with a holistic view of the network’s performance, aiding in proactive maintenance and troubleshooting efforts.
REQUIREMENTS:
Network fundamentals (TCP/UDP); Programming languages (Bash, Python)
CONTACT PERSON:
Alberto del Río– arp@gatv.ssr.upm.es
TFG: Development of a Python-based Network Performance Probe for Multi-Tool Measurement
OBJECTIVE:
Network performance is critical for ensuring efficient and reliable data transmission in modern communication infrastructures. This proposal outlines the development of a versatile and comprehensive network performance probe using Python. The proposed probe will leverage various online measurement tools to assess critical network characteristics, including latency, jitter, bandwidth, and packet loss.
REQUIREMENTS:
Network fundamentals (TCP/UDP); Programming languages (Bash, Python)
CONTACT PERSON:
Alberto del Río– arp@gatv.ssr.upm.es
TFM: Sistema de up-scaling basado en deep-learing para transformar señales de TV de HD a UHD con muy alta calidad, HDR y WCG
Objetivo: El TFM implementará un sistema para realizar up-scaling de señal de vídeo digital HD a UHD, incluyendo cambios en el rango dinámico y en la colorimetría de la imagen, haciendo uso de deep learning. El objetivo final es que dicho sistema de up-scaling ofrezca muy alta calidad, y que funcione en tiempo real. Para ello se cuenta con la colaboración de RTVE y de su infraestructura de computación, dado que RTVE aspira a utilizar dicho sistema de up-scaling para su canal de TV UHD. Este TFM se oferta en el marco de la Cátedra RTVE en la UPM, que será quien proporcione contenidos para los procesos de entrenamiento y aprendizaje de la red, y contará con una ayuda económica en forma de beca, a través del programa Impulsa RTVE.
Requisitos: Conocimientos y experiencia de programación en python y del desarrollo de sistemas de deep learning con imágenes y/o vídeo digital.
Persona de contacto: José Manuel Menéndez – jm.menendez@upm.es