Editor/Reviewer login
Frequency : 12 issues per year
Subject : Computer Applications and Technology
ISSN : 2319–8656 (Online)
Home Archives Volume 13 Issue 11 ijcatr13111008

IJCATR Volume 13 Issue 11

Efficient Data Recognition and Classification in IoT Ecosystem using Optimized K-Means Algorithm and Hybrid Deep Learning Model

Ihediuche Evangeline Ndidi, Ike Mgbeafulike
10.7753/IJCATR1311.1008
keywords : Internet of Things (IoT), Cloud Computing, K-Means Clustering, Machine Learning, Data Recognition, Data Classification.

PDF
With the exponential increase in IoT devices, there is a growing demand for efficient threat recognition and classification to handle massive data generated in Cloud-IoT environments. This research introduces a hybrid machine learning framework that combines an optimized K-Means clustering algorithm with a machine learning model to enhance data processing in IoT systems. The optimized K-Means algorithm facilitates initial data grouping, significantly reducing computational complexity and improving clustering accuracy. Subsequently, a hybrid model integrates Convolutional Neural Network (CNN) for feature extraction and Support Vector Machine (SVM) for precise classification, effectively handling the diverse and high-dimensional data in Cloud-IoT systems. Experimental results show that the proposed method achieves superior accuracy and processing efficiency compared to conventional approaches, making it a robust solution for scalable IoT data management.
@artical{i13112024ijcatr13111008,
Title = "Efficient Data Recognition and Classification in IoT Ecosystem using Optimized K-Means Algorithm and Hybrid Deep Learning Model",
Journal ="International Journal of Computer Applications Technology and Research(IJCATR)",
Volume = "13",
Issue ="11",
Pages ="49 - 53",
Year = "2024",
Authors ="Ihediuche Evangeline Ndidi, Ike Mgbeafulike"}
  • .The paper proposes a hybrid framework integrating optimised K-Means clustering with a CNN-SVM model for IoT data recognition and classification.
  • The optimised K-Means algorithm enhances clustering accuracy and reduces computational complexity for IoT environments.
  • The hybrid CNN-SVM model combines feature extraction and precise classification, achieving superior performance in handling high-dimensional IoT data.
  • Experimental results demonstrate improved accuracy and efficiency compared to traditional methods, making the framework scalable for real-time IoT applications.
Copyright © 2012-2024 International Journal of Computer Applications Technology and Research All Rights Reserved.