IoT Network Anomaly Detection in Smart Homes Environment Using Hybrid Machine Learning Approach

Zapisane w:
Opis bibliograficzny
Wydane w:The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings (2025), p. 1882-1888
1. autor: Senthil, J
Kolejni autorzy: Karthikeyan, N K, Senthilkumar, R, Kamalakannan, R S
Wydane:
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Hasła przedmiotowe:
Dostęp online:Citation/Abstract
Etykiety: Dodaj etykietę
Nie ma etykietki, Dołącz pierwszą etykiete!

MARC

LEADER 00000nab a2200000uu 4500
001 3207023017
003 UK-CbPIL
024 7 |a 10.1109/ICICT64420.2025.11005081  |2 doi 
035 |a 3207023017 
045 2 |b d20250101  |b d20251231 
084 |a 228229  |2 nlm 
100 1 |a Senthil, J  |u Anna University, Sri Krishna College of Engineering and Technology College,Department of CSE,Coimbatore,Tamilnadu,India 
245 1 |a IoT Network Anomaly Detection in Smart Homes Environment Using Hybrid Machine Learning Approach 
260 |b The Institute of Electrical and Electronics Engineers, Inc. (IEEE)  |c 2025 
513 |a Conference Proceedings 
520 3 |a Conference Title: 2025 International Conference on Inventive Computation Technologies (ICICT)Conference Start Date: 2025 April 23Conference End Date: 2025 April 25Conference Location: Kirtipur, NepalThe rapid growth of Internet of Things (IoT) devices in smart home environments has led to increased security vulnerabilities and intrusion risks. These resourceconstrained devices require lightweight and effective anomaly detection systems. This research aims to develop a hybrid anomaly detection framework that combines a one-dimensional Convolutional Neural Network (CNN) for feature extraction with LightGBM for classification. The proposed model is evaluated using two benchmark datasets-TON-IoT and UNSW BoT-IoT-based on performance metrics including accuracy, precision, recall, and F1-score. Experimental results demonstrate that the hybrid model outperforms traditional classifiers in both detection accuracy and computational efficiency. This approach provides a lightweight and scalable solution for real-time anomaly detection in smart home IoT networks. This study thus introduces a novel hybrid approach combining CNN-based feature extraction with LightGBM classification, and is optimized for lightweight intrusion detection in IoT smart home environments. 
653 |a Feature extraction 
653 |a Accuracy 
653 |a Performance measurement 
653 |a Classification 
653 |a Internet of Things 
653 |a Artificial neural networks 
653 |a Smart buildings 
653 |a Smart houses 
653 |a Home environment 
653 |a Anomalies 
653 |a Machine learning 
653 |a Real time 
653 |a Intrusion detection systems 
653 |a Economic 
700 1 |a Karthikeyan, N K  |u Coimbatore Institute of Technology,Department of IT,Coimbatore,Tamilnadu,India 
700 1 |a Senthilkumar, R  |u Shree Venkateshwara Hi-Tech Engineerng College,Department of CSE,Gobi,Tamilnadu,India 
700 1 |a Kamalakannan, R S  |u Shree Venkateshwara Hi-Tech Engineerng College,Department of Electronics and Communication Engineering,Gobi,Tamilnadu,India 
773 0 |t The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings  |g (2025), p. 1882-1888 
786 0 |d ProQuest  |t Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3207023017/abstract/embedded/75I98GEZK8WCJMPQ?source=fedsrch