Flow time series clustering for demand pattern recognition in drinking water distribution systems: New insights about the most adequate methods

This study presents a proposal of clustering methodologies for demand pattern recognition using network flow data collected from a large set of drinking water distribution networks in Portugal. Most of the existing studies about clustering in flow time series rely on hierarchical or k-Means clusteri...

ver descrição completa

Detalhes bibliográficos
Autor principal: Gomes, Pedro André Fonseca Garez (author)
Formato: masterThesis
Idioma:eng
Publicado em: 2019
Assuntos:
Unsupervised learning
Time series clustering
Flow time series
Demand pattern recognition
Water distribution systems
Aprendizagem não supervisionada
Clustering de series temporais
Séries temporais de caudal
Reconhecimento de padrões de consumo
Sistemas de distribuição de água
Algoritmo > Algorithm
Clusters > Clusters
Séries temporais
Utilização da água
Portugal
Texto completo:http://hdl.handle.net/10071/20195
País:Portugal
Oai:oai:repositorio.iscte-iul.pt:10071/20195

Texto Completo

http://hdl.handle.net/10071/20195

Registros relacionados