TY - CHAP
T1 - Collaborative Data Mining for Intelligent Home Appliances
AU - Matei, Oliviu
AU - Di Orio, Giovanni
AU - Jassbi, Javad
AU - Barata, José
AU - Cenedese, Claudio
N1 - Sem PDF.
ProSEco project of EU's 7th FP (MP-2013 609143)
PY - 2016
Y1 - 2016
N2 - The augmentation of physical devices and resources with electronics, software, sensing elements and network connectivity is a "hot topic" as confirmed also by the several research projects and activities on internet-of-things (IoT) and cyber-physical systems (CPS) research streams. It is obvious that intelligent products are taking more responsibility in future collaborative networks. Recent products are becoming more and more intelligent and connected by using the existing network infrastructure, meaning that products are becoming active agents in networks and valuable data sources that are capable to provide data continuously during their operation. This is leading to a massive amount of data that can be used by product manufacturers to be and remain competitive in market sharing. In this scenario, the application of collaborative data mining techniques, supported by machine learning algorithms, is aimed to enable the analysis of the data provided from multiple and above all distributed data sources in order to discover and extract useful knowledge about the behavior of the users along with the usage patterns of their devices and appliances.
AB - The augmentation of physical devices and resources with electronics, software, sensing elements and network connectivity is a "hot topic" as confirmed also by the several research projects and activities on internet-of-things (IoT) and cyber-physical systems (CPS) research streams. It is obvious that intelligent products are taking more responsibility in future collaborative networks. Recent products are becoming more and more intelligent and connected by using the existing network infrastructure, meaning that products are becoming active agents in networks and valuable data sources that are capable to provide data continuously during their operation. This is leading to a massive amount of data that can be used by product manufacturers to be and remain competitive in market sharing. In this scenario, the application of collaborative data mining techniques, supported by machine learning algorithms, is aimed to enable the analysis of the data provided from multiple and above all distributed data sources in order to discover and extract useful knowledge about the behavior of the users along with the usage patterns of their devices and appliances.
KW - Collaborative data mining
KW - Intelligent home appliance
KW - Collaborative network
U2 - 10.1007/978-3-319-45390-3_27
DO - 10.1007/978-3-319-45390-3_27
M3 - Chapter
SN - 978-3-319-45390-3
VL - 480
T3 - IFIP Advances in Information and Communication Technology
SP - 313
EP - 323
BT - Collaboration in a Hyperconnected World
A2 - Afsarmanesh, Hamideh
A2 - Camarinha-Matos, Luis M.
A2 - Lucas Soares, António
PB - Springer International Publishing AG
CY - Cham
T2 - 17th IFIP WG 5.5 Working Conference on Virtual Enterprises, PRO-VE 2016
Y2 - 3 October 2016 through 5 October 2016
ER -