A Novel Method for Big Data Analytics and Summarization based on Fuzzy Similarity Measure

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Researchers

Research units

Abstract

The use of Internet of Things (IoT) sensors and devices is on a sharp rise with the help of infrastructures like 5G cellular networks. However, with this swift expansion come major challenges such as management of the vast data collected by these IoT devices. In the paper, we propose a method which takes advantage of fuzzy similarity to significantly simplify the big data analysis and management for human operators and machines. A use case in the area of smart buildings was utilized to illustrate its potential application. A comparison is made between the ideal situation and the data collected from an office room. The considered environmental factors in this research are temperature, humidity, and workplace lighting and then the collected data was utilized to make triangular fuzzy numbers and after that, we compare them with an efficient fuzzy similarity measure. In addition to data summarization and abstraction, this method also protects the main information from inaccuracy. The advantage of the fuzzy controlling system is its aptitude to deal with nonlinearities and uncertainties.

Details

Original languageEnglish
Title of host publicationProceedings - IEEE 11th International Conference on Service-Oriented Computing and Applications, SOCA 2018
Publication statusPublished - 2018
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Service-Oriented Computing and Applications - Paris, France
Duration: 6 Nov 20189 Nov 2018
Conference number: 11

Conference

ConferenceIEEE International Conference on Service-Oriented Computing and Applications
Abbreviated titleSOCA
CountryFrance
CityParis
Period06/11/201809/11/2018

    Research areas

  • Big data summarization, Environmental factors, Fuzzy similarity measure, Internet of things

Download statistics

No data available

ID: 31196896