As a result of increased miniaturization and sophistication of technology in the field of consumer electronics, the overall demand for these devices has increased. Furthermore, as the world becomes digital, a growing number of individuals save, manage, and share their lives online. Enormous volumes of data from Consumer Electronics constitutes Big Data. To gain insights and valuable information, Clustering of such Big data becomes important in the present scenario. Using innovative ways in clustering and extracting valuable information from this rapidly increasing data in order to provide more personalisation features to users is a crucial step ahead. This paper explores the traditional as well as newer and innovative techniques that have been employed for clustering of big data as well as analytics and their applications to consumer electronics. Fuzzy clustering techniques based on fuzzy membership in which data elements can belong to more than one cluster at a time due to which this technique has an upper hand over conventional clustering algorithms are thus examined in this work. Additionally, this paper presents the drawbacks of fuzzy clustering algorithms and their solutions using Fuzzy-Neuro and Ensemble Clustering based techniques. All of this is being done to advance consumer data analytics via innovation to provide users a better experience.
Fuzzy Based Clustering of Consumers' Big Data in Industrial Applications
Santaniello D.
2023-01-01
Abstract
As a result of increased miniaturization and sophistication of technology in the field of consumer electronics, the overall demand for these devices has increased. Furthermore, as the world becomes digital, a growing number of individuals save, manage, and share their lives online. Enormous volumes of data from Consumer Electronics constitutes Big Data. To gain insights and valuable information, Clustering of such Big data becomes important in the present scenario. Using innovative ways in clustering and extracting valuable information from this rapidly increasing data in order to provide more personalisation features to users is a crucial step ahead. This paper explores the traditional as well as newer and innovative techniques that have been employed for clustering of big data as well as analytics and their applications to consumer electronics. Fuzzy clustering techniques based on fuzzy membership in which data elements can belong to more than one cluster at a time due to which this technique has an upper hand over conventional clustering algorithms are thus examined in this work. Additionally, this paper presents the drawbacks of fuzzy clustering algorithms and their solutions using Fuzzy-Neuro and Ensemble Clustering based techniques. All of this is being done to advance consumer data analytics via innovation to provide users a better experience.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.