In my Master’s thesis I worked with data of the Marconi100 supercomputer from CINECA. I propose the use of several autoencoder models for anomaly detection on supercomputers, allowing this problem to be approached with semi-supervised learning techniques. For the development of the project, a sequence of real data from CINECA’s Marconi 100 supercomputer, obtained over several months, has been used. Two different model training approaches are compared. The first is a model trained with data from all the nodes of the supercomputer. In the second approach, observing significant differences between nodes, one model is trained for each node. The results were analysed by evaluating the positive and negative aspects of each approach.Anomaly detection autoencoder architecture used in the project

On the other hand, a replica of the Marconi 100 supercomputer was developed in a virtual reality environment that allows the data from each node to be visualised at different points in time. The real-time visualisation of information such as the power consumed, the temperatures of the cores (GPU and CPU) or the prediction of anomalies of the autoencoder model can be of great help in the early detection of errors and preventive maintenance tasks of this type of high-performance systems. The Python language and the VTK library have been used for the development. This had made it possible to create a full-scale replica in a virtual environment, accessible through virtual reality devices.

In this proyect we have developed an object grasping system in Unreal Engine 4. For the creation of this system, we have started from a base project named UnrealGrasp that has been modified to use the hand detection framework offered by Oculus and to be able to interact with the objects in the virtual environment only with our own hands.The work consisted in the implementation of an algorithm that decides when to move and lock the fingers of our virtual hand, as well as when we are grasping an object and when ithas been released. Once this was done, it can be used to interact in an environment with many objects. Different people have been asked to grasp different objects as they spawn in the environment. These objects appear sequentially and in different orientations to encourage differenttypes of grasping. This information has been collected in the format of a heat map, creat-ing a dataset of 12 objects that can be used in different fields, such as training an artificial intelligence system or making a more exhaustive study on grasping. Finally, an environment has been created in which the user can move and interact with objects of all kinds: toys, technical tools, laboratory utensils or foodstuffs, among others. This is intended to demonstrate the wide range of applications of this new technology.

This project has been carried out as a multimedia engineering degree final project. It has been developed with Unreal Engine and the Oculus hand tracking framework.

Pandemic! is a videogame for all audiences that serves to raise public awareness of the current situation while having fun. This videogame combines the genre of resource management with that of action, as your main objective is to prevent the population from becoming infected while you have to carry out your day-to-day tasks.
Has been created entirely from scratch, including its own engines. Among these engines we have a graphics engine, developed using OpenGL, the network engine, where the RakNet library has been used and finally, the game engine. We have also used FMOD to integrate the sound, Nuklear to create the interface and Bullet for the game physics. Once the project has been completed, it has been published on the indie distribution platform Itch.io, where it is available for download

In addition, to make the multiplayer I have created a network engine using the RakNet library. The client-server architecture has been used and functionalities have been developed, such as a NAT server that acts as an intermediary and allows ports to be opened between users. Or a system of rooms that can be accessed with a generated numerical code.

I have created a blog for a gastronomic business. This blog has some sections such as the landing page, the events page, the training page or the contact page. It has been created from scratch following the designer's templates. For this I used the NextJS framework and Bootstrap.

I created a basic neural network and trained it with real data on the clothes I would wear at any given time. To do this I created a metric describing how warm the clothes are, with 0 being no clothes and 5 being a heavy winter jacket. In this way the AI began to understand the metric and give accurate results. I am now studying which of the inputs are most important in making this prediction. The current inputs are temperature, relative temperature, humidity and wind.I am also generating a data set with information from other people.

In this Node-RED project I used the Telegram-bot library to create a bot to communicate with. The system was running on a RaspberryPi, which performed its task perfectly.

Using this I implemented different logics to develop functionalities that I personally needed. The bot gave me information about the weather, nearby petrol station prices and even allowed me to play sounds on my Raspberry wherever I was.

My working group and I developed a game using the SFML library and a JSON loading library. We created all the artwork for the game, including the sprites, HUD design and backgrounds. In addition, we had to do the level design and optimise it to get proper feedback.

To develop the game we used design patterns like facade, singlenton and composite. Furthermore we implemented our own decision trees.

I created this app for the followers of a Spanish television program called Operación Triunfo.

Connecting it with the database managed with phpMyAdmin I added different functionalities, every week I published a new questionnaire with new questions about the program and also gave the possibility of saving the score in a ranking if the user managed to get there and wanted. With all this I got a significant amount of active users. The app has almost 5k downloads.

I created this app in a proyect of a subject of the degree. With this app you can see the weather in your selected locations in Spain. You could see information about the prediction, temperature, humidity and UV rate. Moreover, it mostrate information about the next 4 days.

This project was born out of a personal need. I had too many plants in my garden and I needed them to water themselves. So I decided to use an Arduino Mega connected to the internet.

I created an API with access to the database and a web page with which to develop all the functionalities easily. I programmed this logic allowing me to communicate with the Arduino through the Restful API and allowing to directly switch on and off any existing pump or light, even open a motorized door. You can also program the switching off or switching on of any of these things from the web interface, telling it the days of the week and time when the action should be done.

I made a personal web in order to see the information about the flight that is crossing over my house. In the page we can see data like the altitude, speed, distance to the point of view, flight number, company or the plane model and photo. I just created this because I like aircrafts and I wanted to learn how to create an web page and make api requests using fetch in javascript.

As an undergraduate project I had to model, texture and render a modern Apple-style coffee shop. For the modelling I used Blender and 3DSMax and finally I rendered the scene using Arnold from 3DSMax. Although it is not a completely finished project due to the short time we had it was very useful to learn a bit of each phase of the pipeline from modelling to rendering.

I created this app in a proyect of a subject of the degree. With this app you can pass numbers from decimal to binary. As well as performing the basic operations (add, subtract, multiply and divide) in both binary and decimal. In addition, you can see the result in two's complement and in sign and magnitude.