A multilayer deep learning framework for auto-content tagging

Abstract

With the rapid and recent development of Internet of things (IoT), Bigdata, the most fundamental challenge is to explore the large volume of data from heterogeneous data sources (logs, audio, video, reports, news, social media, etc.). The tools and techniques that are being used in successful transforming of structured data into business intelligence simply do not work when it comes to unstructured data. An estimated 80% of data held by firms today are unstructured. We have powerful computations tools such as graphics processor units (GPUs) for complex calculations and Hadoop, spark for Bigdata management still technology is lacking in complete utilization of available data. Deep learning is a powerful tool to resolve the issues related to data, such as automatic extraction of complex data and representation of large volume unsupervised and uncategorized raw data. But extracted data do not have any standard format. In the survey of Bigdata mining system and IoT systems, it has been found that a layer is needed in Bigdata mining framework that can work on structured, unstructured and semi-structured data and can integrate the complete raw data. The proposed framework is a multilayer deep learning model that performed the clustering of unstructured huge text data followed by classification layer, CNN, to extract features and classify the raw data clusters in parallel manner. Conversion of unstructured data in standard format by automates content tagging helps decision-making systems to easily identify the related data and increase the data utilization.