Idioma:

Multi-Task Learning Improves Disease Models from Web Search

Zou, Bin ; Lampos, Vasileios ; Cox, Ingemar

Proceedings of the 2018 World Wide Web Conference, 2018, p.87-96

Republic and Canton of Geneva, Switzerland: International World Wide Web Conferences Steering Committee

Texto completo disponível

Citações Citado por

Enviar para

Título:
Multi-Task Learning Improves Disease Models from Web Search
Autor: Zou, Bin ; Lampos, Vasileios ; Cox, Ingemar
Assuntos: Applied computing -- Life and medical sciences -- Health informatics ; Computing methodologies -- Machine learning -- Learning paradigms -- Multi-task learning ; Computing methodologies -- Machine learning -- Learning paradigms -- Supervised learning -- Supervised learning by regression ; Information systems -- World Wide Web -- Web mining ; Theory of computation -- Theory and algorithms for application domains -- Machine learning theory -- Kernel methods -- Gaussian processes
É parte de: Proceedings of the 2018 World Wide Web Conference, 2018, p.87-96
Descrição: We investigate the utility of multi-task learning to disease surveillance using Web search data. Our motivation is two-fold. Firstly, we assess whether concurrently training models for various geographies - inside a country or across different countries - can improve accuracy. We also test the ability of such models to assist health systems that are producing sporadic disease surveillance reports that reduce the quantity of available training data. We explore both linear and nonlinear models, specifically a multi-task expansion of elastic net and a multi-task Gaussian Process, and compare them to their respective single task formulations. We use influenza-like illness as a case study and conduct experiments on the United States (US) as well as England, where both health and Google search data were obtained. Our empirical results indicate that multi-task learning improves regional as well as national models for the US. The percentage of improvement on mean absolute error increases up to 14.8% as the historical training data is reduced from 5 to 1 year(s), illustrating that accurate models can be obtained, even by training on relatively short time intervals. Furthermore, in simulated scenarios, where only a few health reports (training data) are available, we show that multi-task learning helps to maintain a stable performance across all the affected locations. Finally, we present results from a cross-country experiment, where data from the US improves the estimates for England. As the historical training data for England is reduced, the benefits of multi-task learning increase, reducing mean absolute error by up to 40%.
Editor: Republic and Canton of Geneva, Switzerland: International World Wide Web Conferences Steering Committee
Idioma: Inglês

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Multi-Task Learning Improves Disease Models from Web Search

Zou, Bin ; Lampos, Vasileios ; Cox, Ingemar

Republic and Canton of Geneva, Switzerland: International World Wide Web Conferences Steering Committee

Buscando em bases de dados remotas. Favor aguardar.