Titulo Estágio
Bio-Inspired Automatic Feature Engineering for Audiology
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
ECOS-CISUC
Enquadramento
Hearing loss is a health problem that can have serious consequences in the medium / long term, causing problems in terms of language, cognitive and social development. According to the World Health Organization, around 466 million people (5% of the world population) have hearing loss problems [1]. It is estimated that by 2050 this number will increase to around 900 million people, that is, 1 in 10 people will have limited hearing loss (greater than 40 dB). In the population over 65, which is on the rise, it is estimated that 30% of people have limited hearing loss.
The impact of hearing loss can be measured at several levels. On the one hand, there is an impact on the lives of people who, having difficulty communicating, see their quality of life negatively affected. On the other hand, there is an economic impact associated with the non-treatment of hearing loss, estimated at US $ 750 billion. These figures include costs for medical treatment, education, and lost productivity.
[1] - https://www.who.int/news-room/fact-sheets/detail/deafness-and-hearing-loss
Objetivo
The goal of this dissertation is to design and implement grammar based bio-inspired approaches for automatically feature selection and engineering to maximize the performance of Machine Learning Models.
Plano de Trabalhos - Semestre 1
- Review of literature and familiarisation with the thematic
- Analysis of the dataset
- Implementation of the first prototype
- Preliminary results analysis
- Writing of the intermediate report
Plano de Trabalhos - Semestre 2
- Prototype refinement
- Implementation of a second version of the prototype
- Model validation and refinement
- Scientific article with the main results
- Writing of the dissertation
Condições
The student will work in the context of the interdisciplinary project A4A - Audiology for All, involving several industrial and academic partners: Sensing Evolution (Evollu), University of Coimbra (UC), and Escola Superior de Tecnologia da Saúde de Coimbra (ESTeSC)
The work will be conducted in the Evolutionary and Complex Systems (ECOS) group from CISUC.
Observações
There is a possibility of the student being awarded a scholarship (Bolsa de Investigação para Licenciado) for at least 6 months, renewable for an equal period by agreement between the advisor and the intern. The scholarship will follow the Fundação para a Ciência e Tecnologia (FCT) monthly stipend guidelines.
Orientador
Nuno António Marques Lourenço
naml@dei.uc.pt 📩