AI-Based Wireless Sensor IoT Networks for Energy-Efficient Consumer Electronics Using Stochastic Optimization

Masood, Fahad and Khan, Muhammad Abbas and Alshehri, Mohammed S. and Ghaban, Wad and Saeed, Faisal and Albarakati, Hussain Mobarak and Alkhayyat, Ahmed (2024) AI-Based Wireless Sensor IoT Networks for Energy-Efficient Consumer Electronics Using Stochastic Optimization. IEEE Transactions on Consumer Electronics. ISSN 0098-3063

[thumbnail of WSIN_for_Consumer_Elect_IEEE_Tran.pdf]
Preview
Text
WSIN_for_Consumer_Elect_IEEE_Tran.pdf - Accepted Version

Download (554kB)

Abstract

Wireless Sensor Networks (WSNs) integration with the Internet of Things (IoT) expands its potential by providing ideal communication and data sharing across devices, allowing more considerable monitoring and management in Consumer Electronics (CE). WSNs have an essential limitation in terms of energy resources since sensor nodes frequently run on limited power from batteries. This limitation necessitates the consideration of energy-efficient techniques to extend the network’s lifetime. In this article, an integrated approach has been presented to improve the energy efficiency of Wireless Sensor IoT Networks (WSINs) by leveraging modern machine learning algorithms with stochastic optimization. Recursive Feature Elimination (RFE) is utilized for the feature selection thus optimizing the input features for various machine learning models. These models are rigorously evaluated for their aptness to predict and mitigate energy consumption concerns inside WSINs. Subsequently, the stochastic optimization technique utilizes the uniform and normal distributions to model energy consumption situations. The results show that RFE-driven feature selection has significant effects on model performance and that Random Forest is effective at reaching higher accuracy. This research provides valuable perspectives for the design and implementation of WSINs in CE, supporting sustainable smart devices, by addressing energy consumption concerns using an optimized approach.

Item Type: Article
Identification Number: 10.1109/TCE.2024.3416035
Dates:
Date
Event
1 June 2024
Accepted
19 June 2024
Published Online
Uncontrolled Keywords: Wireless sensor networks, Energy efficiency, Internet of Things, Machine learning, Consumer electronics, Feature extraction, Routing
Subjects: CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions: Faculty of Computing, Engineering and the Built Environment > College of Computing
Depositing User: Gemma Tonks
Date Deposited: 16 Aug 2024 10:40
Last Modified: 16 Aug 2024 10:41
URI: https://www.open-access.bcu.ac.uk/id/eprint/15730

Actions (login required)

View Item View Item

Research

In this section...