Comparative Study on Different Data Fusion Techniques

Abstract

Technological advances in sensors and many other communication areas have created a large amount of data that is continuously created every day at an unprecedented scale. The diversity of data sets from different sources and domains is being faced in the big data era. Since the data is in different formats and different structures, how to unlock the quality information/knowledge from the multiple data sets is the most challenging task in big data. And this can be solved by the data fusion method. Data fusion is one of the most efficient methods to extract quality information from the data sets by combining the different data sets more than any other individual data source. The success of big data is based on the ability to extract meaningful information from such a massive amount of information through data analytics to attain efficient decision-making. A timely fusion and analysis of big data provides highly reliable, efficient, and accurate decision-making on the data sets. Data Fusion has achieved numerous successes in many areas such as image recognition, biometrics, natural language processing, healthcare, etc. The key objective of the paper is to provide an overview of various literature on data fusion, such as different methodologies of data fusion, and the challenges and opportunities are discussed under each method.