Big Data Analytics and Deep Learning: Technologies for Scalable Information Processing and Extracting Awareness

Guardado en:

Bibliografiske detaljer
Udgivet i:	The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings (2025), p. 1-6
Hovedforfatter:	Prakalya, S B
Andre forfattere:	Shanmugam Muthu, Pandi, V Samuthira, Khaled Tawfiq Al-Assaf, Jain, Alok, Dinesh, M
Udgivet:	The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Fag:	Parallel processing Quantum computing Data processing Datasets Deep learning Big Data Banking Artificial neural networks Predictive analytics Health care Edge computing Generative adversarial networks Data analysis Manufacturing Machine learning Decision making Innovations Distributed processing Data storage Massive data points Neural networks Recurrent neural networks Electronic commerce Unstructured data Anomalies Real time Federated learning Barriers Predictive maintenance Economic
Online adgang:	Citation/Abstract
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!

Beskrivelse
Resumen:	Conference Title: 2025 International Conference on Information, Implementation, and Innovation in Technology (I2ITCON)Conference Start Date: 2025 July 4Conference End Date: 2025 July 5Conference Location: Pune, IndiaBig Data has emerged as an essential tool for decision-making and innovation due to the exponential growth of data in various industries, such as healthcare, banking, manufacturing, and social media. However, there are substantial obstacles to obtaining useful insights and practical information from the massive amount, speed, and diversity of data. An effective strategy for dealing with these issues is to use Big Data analytics in conjunction with Deep Learning methods. Scalable solutions for processing massive datasets and deriving meaningful insights from complicated data are the focus of this research, which investigates the potential integration of Big Data analytics with Deep Learning technology. Data storage, administration, and processing approaches like distributed computing and parallel processing-that allow the handling of large-scale datasets-are reviewed in the first part of the research as important Big Data topics. The article continues by discussing various Deep Learning designs that can better handle and learn from large, unstructured datasets. These architectures include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Generative Adversarial Networks (GANs). Predictive analytics, automated decision systems, and real-time decision-making are just a few areas that can benefit from the combined use of these technologies, which the study investigates. Anomaly detection in healthcare, predictive maintenance in manufacturing, and consumer behavior research in e-commerce are just a few of the many industries highlighted by the paper's integration of these technologies. Data quality, model interpretability, computational resources, and scalability are some of the limitations and obstacles that the article explores when integrating Big Data analytics with Deep Learning. It also talks on how important it is to protect people's personal information, especially when dealing with sensitive data in industries like healthcare and banking. In the last section of the research, we go over some of the upcoming developments in these technologies that could make Big Data analytics and Deep Learning even more efficient and scalable. These include things like federated learning, quantum computing, and edge computing. In the end, this study hopes to give a complete framework for companies that want to use Big Data and Deep Learning to analyze information rapidly and get meaningful insights to drive innovation and informed decisions.
DOI:	10.1109/I2ITCON65200.2025.11210740
Fuente:	Science Database