A Clustream strategy for Functional Boxplots on multiple streaming time series Antonio Balzanella and Elvira Romano Abstract In this paper we propose a micro-clustering strategy for Functional Box- plot variables defined on multiple streaming time series splitted in non overlapping windows. It is a two step strategy. In the first step it performs an on-line summa- rization keeping updated the set of functional data structures, named Functional Boxplot micro-clusters; in the second step it reveals the final summarization by pro- cessing, off-line, the Functional Boxplot micro-clusters. Thus a new definition of micro-cluster based on using the Functional Boxplot as the centroid is proposed. Moreover a proximity measure which allows to allocate the data to the new defined micro-clusters is defined. This will allow to get a graphical summarization of the streaming time series by five functional basic statistics. The obtained synthesis will be able to keep track of the dynamic evolution of the streams. Key words: Streaming time series, CluStream, Functional Boxplot 1 Introduction Data stream mining has gained a lot of attention due to the development of ap- plications where sensor networks are used for monitoring physical quantities such as electricity consumptions, environmental variables, computer network traffic. In these applications it is necessary to analyze potentially infinite flows of temporally ordered observations which cannot be stored and which have to be processed us- ing reduced computational resources. The on-line nature of these data streams re- quire the development of incremental learning methods which update the knowledge Antonio Balzanella Department of European and Mediterrean Studies, Second University of Naples, Caserta, Italy e-mail: antonio.balzanella@unina2.itElvira Romano Department of European and Mediterrean Studies, Second University of Naples, Caserta, Italy,e- mail: elvira.romano@unina2.it 1