Optimizing real-time data preprocessing in IoT-based fog computing using machine learning algorithms - read online free

Aug 2, 2026

Upload by Rowan

IoT-FCML addresses the challenge of processing massive, highly variable IoT data with minimal latency inside fog computing environments. The approach introduces machine learning-driven real-time data preprocessing that dynamically adapts to changing data characteristics and system demands. Results from the implementation show latency reduction of about 0.26%, throughput improvement up to 0.3%, resource-efficiency increase of 0.20%, and a decrease in data privacy overhead by 0.64%, outperforming traditional preprocessing methods through privacy-aware and resource-efficient smart algorithms.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Fog computing and latency challenges

Role of machine learning in preprocessing optimization

Research gap and motivation

Optimizing real-time data preprocessing in IoT-based fog computing using machine learning algorithms Nandini Gowda Puttaswamy1, Anitha Narasimha Murthy2 1Department of Computer Science and Engineering, Sapthagiri College of Engineering, Bengaluru, India 2Department of Computer Science and Engineering, BNM Institute of Technology, Bengaluru, India Article history: Received Apr 30, 2024 Revised Feb 13, 2025 Accepted Mar 15, 2025 Keywords: Data privacy Dynamic adaptability IoT fog computing Latency reduction Machine learning algorithms Real-time data preprocessing Resource efficiency Corresponding Author: In the era of the internet of things (IoT), managing the massive influx of data with minimal latency is crucial, particularly within fog computing environments that process data close to its origin. Traditional methods have been inadequate, struggling with the high variability and volume of IoT data, which often leads to processing inefficiencies and poor resource allocation. To address these challenges, this paper introduces a novel machine learningdriven approach named real-time data preprocessing in IoT-based fog computing using machine learning algorithms (IoT-FCML) . This method dynamically adapts to the changing characteristics of data and system demands. The implementation of IoT-FCML has led to significant performance enhancements: it reduces latency by approximately 0.26%, increases throughput by up to 0.3%, improves resource efficiency by 0.20%, and decreases data privacy overhead by 0.64% . These improvements are achieved through the integration of smart algorithms that prioritize data privacy and efficient resource use, allowing the IoT-FCML method to surpass traditional preprocessing techniques. Collectively, the enhancements in processing speed, adaptability, and data security represent a substantial advancement in developing more responsive and efficient IoT-based fog computing infrastructures, marking a pivotal progression in the field. This is an open access article under the CC BY-SA license. Nandini Gowda Puttaswamy Department of Computer Science and Engineering, Sapthagiri College of Engineering Bengaluru, India [Email: nandini.educator1@gmail.com](Email: nandini.educator1@gmail.com) Article Info ABSTRACT 1. INTRODUCTION The internet of things (IoT) has dramatically transformed how we interact with the physical world, integrating intelligence into everyday objects and enabling them to communicate and make decisions. This widespread adoption of IoT has led to the generation of massive amounts of data at the edge of the network, necessitating innovative approaches to data processing and management. Fog computing, which extends cloud computing to the edge of the network, has emerged as a pivotal technology in this context. It aims to reduce latency, improve bandwidth utilization, and enhance the overall efficiency of IoT systems by processing data closer to its source [1], [2] . Figure 1 shows a security architecture involving three entities such as the user, a cloud server, and a trusted third party. The working principal centers around mutual authentication, a security mechanism ensuring that both the user and the cloud server verify each other's identities before initiating any communication. Here, the trusted third party plays a crucial role, possibly as a certificate authority or authentication server, that both the user and the cloud server trust. This entity could facilitate the exchange of credentials or cryptographic keys that enable mutual authentication [3] . Upon successful authentication, a secure channel is established between the user and the cloud server, allowing for safe data exchange, service requests, and transactions, all under the supervision of the trusted third party to prevent unauthorized access and ensure data integrity and confidentiality. This framework is fundamental to preserving security in cloud computing, where data and resources are accesse

FAQs

Why is real-time data preprocessing important in IoT-based fog computing?

Fog computing processes data near its source to reduce latency, but IoT produces high-volume, high-velocity data with variability, making traditional preprocessing inefficient for latency-sensitive applications.

What is the IoT-FCML approach proposed in the paper?

IoT-FCML is a machine learning-driven method for real-time data preprocessing in IoT-based fog computing that dynamically adapts to data and system demand changes.

What performance improvements does IoT-FCML achieve compared with traditional techniques?

IoT-FCML reduces latency by about 0.26%, increases throughput by up to 0.3%, improves resource efficiency by 0.20%, and decreases data privacy overhead by 0.64%.

Aug 2, 2026

Upload by Rowan