Integration of mobile devices in home automation with use of machine learning for object recognition

• Autor(a) principal: Passinhas, Rui Jorge Silva
• Data de Publicação: 2019
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10071/20251
• topic: Internet of things; Smart homes; Computer vision; Machine learning; Mobile devices; Internet das coisas; Casas inteligentes; Computação visual; Aprendizagem máquina; Dispositivos móveis

The concept of smart homes is increasingly expanding and the number of objects we have at home that are connected grows exponentially. The so-called internet of things is increasingly englobing more home devices and the need to control them is also growing. However, there are numerous platforms that integrate numerous protocols and devices in many ways, many of them being unintuitive. Something that we always carry with us is our mobile devices and with the evolution of technology, they have become increasingly powerful and equipped with lots of sensors. One of the bridges to the real world in these devices is the camera and its many potentials. The amount of information gathered can be used in a variety of ways and one topic that has also gathered tremendous relevance is Artificial Intelligence and Machine Learning algorithms. Thus, with the correct processing, data collected by the sensors could be used intuitively to interact with such devices present at home. This dissertation presents the prototype of a system that integrates mobile devices in home automation platforms by detecting objects in the information collected by their cameras, consequently allowing the user to interact with them in an intuitive way. The main contribution of the work developed is the non-explored until then integration, in the home automation context, of cutting-edge algorithms capable of easily outperforming humans into analyzing and processing data acquired by our mobile devices. Throughout the dissertation the referred concepts are explored as well as the potentiality of this integration and the results obtained.