Criar Animais Virtuais Através de Machine Learning

• Autor(a) principal: Rocha, Hugo Tiago Trindade
• Data de Publicação: 2022
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10400.22/21781
• topic: Artificial Intelligence; Intelligent Agents; Artificial Neural Network; ANN; Fuzzy Logic; FL; Adaptive Neuro Fuzzy Inference System; ANFIS; Unity; Habitat Simulation; ML-Agents

Approximately 42 percent of threatened or endangered species are at risk due to invasive species. Some invasive species find the new habitat by themselves during migrations, others are misplaced by humans, be it by mistake or necessity. This project aims to create a virtual habitat, populated by intelligent agents that represent the animals present in it. Programmers and scientists can add invasive species, and simulate what might happen. This will allow a more proactive response to this type of crisis. Different data-driven models are explored in order to find the best one for the problem at hands. Game engines are discussed, they have improved greatly over the last decade, and are accessible to everyone. Reliable tools to build simple or complex prototypes that give us graphic representations that can be photo realistic