AI on Miquel's Portfolio

Ecoforecast

Tue, 21 Nov 2023 06:00:23 +0600

The challenge

With increasing digitalisation and the growing on data servers, the significance of sustainable computing is on the rise. That’s why the task is to predict which will be the European country that will have the highest surplus of green energy in the following hour. Knowing this information can be critical to make important decisions in order to reduce CO2 emissions. This challenge was the problem of a Nuwe competition.

JBarcelona 2023

Sun, 23 Apr 2023 06:00:23 +0600

The challenge

This challenge was the problem of a Nuwe competition. The goal of the challenge was to build a classification model which had to predict which costumers decide to end their contracts with the company we get the data from, so the percentage of people who stop being clients decreses by analyzing the reasons.

The approach

Since this was my first time building a model, I decided to start by looking at some guides and understand what had to exactly do the model. I manage to get something and predict some results, and it was really nice when I checked and turn out I had a f1-score of 0.9. Then I also tried some optimitzations which didn’t work, but that was enough to pass to the final.

HackUPC 2023

Tue, 07 Feb 2023 06:00:23 +0600

Our project

HackUPC is the main yearly hackathon organized in my university. In 2023 was my first time attending on site.

Me, AlexRG03, Martaw-code and Koldp took part at the competition. We were very indecisive in terms of which challenge to go for, but in the end we decided to work in the HP challenge, in which we had to build a prediction model to forecast the supply chain inventory units of HP. Because we wanted to get even more work we were also thinking about how to solve other challenges and even coding a bot that battled in a survival game between all other hackers.

PDDL on Mars

Sat, 14 Jan 2023 06:00:23 +0600

The statement

In 2075, the first colonizers of Mars have established a network of bases throughout the geography of the planet. Moving between these bases is done by rovers that can move supplies and specialized personnel.

We are in charge of planning the movements of the rovers from the base where they are parked, to pick up the supplies and personnel, to bring them in the requested place. We’ve been told that there are always more requests for supplies and personnel of those that can be used (life on Mars is very hard).

Knowledge Based Systems

Mon, 19 Dec 2022 06:00:23 +0600

The statement

In order to keep the older population in shape we had to build a program that recommends exercises and activities that are appropiate taking into account all factors of the individual and how may effect on the performance and goals.

I.e.: given certain information about a person, we had to output an exercise plan suitable for him/her.

The full statement is in the document below. Note that the statement is in Spanish.

Local Search

Mon, 24 Oct 2022 06:00:23 +0600

The statement

Given a set of power plants and clients, we had to optimize the profit. Power gets drained depending on the distance it needs to travel, clients don’t pay the same (not all of them are requiered to be served) and power plants costs depend on their size.

To solve the problem, we were asked to use Hill Climbing and Simulated Annealing.

The full statement below (in Spanish).

Our solution

Together with @JCasahuga and @XBLOYT, we used AIMA library and we determined the initial state, the operands as well as the heuristic function.

Royal Hackaway v6

Mon, 07 Feb 2022 06:00:23 +0600

Our project

When @BernatBC, @alexland7219, @Loparc, and I discovered that a shark plushies were one of the prizes of an clearly underated challenge, we realized that the UK’s hackathons needed a way to optimally distribute the shark flushies across the country.

Therefore, we develop a simulator that allows them to place the distribution centers and hackathons (and link them), as well as how many plushie vans you want and its capacity, and it will find a optimal route at the same time it satisfies the demand.