Godfrey Oise, Onyemaechi Clement Nwabuokei, chukwuma Emmanuel Ozobialu, Otega Prosper Jenarhome, Onoriode Michael Atake, Unuigbokhai Nkem Belinda, Akilo Babalola Eyitemi

Enhancing Indoor Positioning Accuracy with Ant Colony Optimization and Dual Clustering

Introduction

Enhancing indoor positioning accuracy with ant colony optimization and dual clustering. Enhance indoor positioning accuracy with an ACO-based dual clustering method for Wi-Fi fingerprinting. Achieve high classification accuracy and 93.51% computational efficiency.

Abstract

Indoor positioning systems are crucial for public safety, healthcare, and IoT, but Wi-Fi fingerprinting faces challenges such as signal interference, multipath effects, and high computational costs. These issues reduce positioning accuracy and make real-time localization difficult.This paper introduces an Ant Colony Optimization (ACO)-based dual clustering method to enhance Wi-Fi fingerprinting accuracy and efficiency. ACO performs coarse clustering by optimizing initial data groupings, while K-means refines clusters for improved precision. The Weighted K-Nearest Neighbor (WKNN) algorithm is then applied for real-time positioning by selecting the most similar signal sub-bases.Experiments show that the proposed method achieves 100% accuracy in building classification and 91% accuracy in floor classification. For latitude and longitude prediction, Random Forest and SVC outperform XGBoost, achieving MSE values of 0.0048 (latitude) and 0.0055 (longitude). The approach also reduces computational overhead by 93.51%, improving efficiency.The study presents a robust, scalable solution for indoor positioning and introduces the Dual Clustering Wi-Fi Localization Dataset (DCWiLD) for future research. Future work will focus on dataset balancing, BLE/UWB integration, and energy optimization for IoT applications.

Review

This paper addresses a critical challenge in indoor positioning systems: enhancing the accuracy and efficiency of Wi-Fi fingerprinting, which is hampered by issues such as signal interference, multipath effects, and high computational costs. The abstract clearly articulates the significance of accurate indoor localization for public safety, healthcare, and IoT applications, thereby establishing a strong motivation for the research. By highlighting the practical limitations of existing methods, the authors set the stage for their proposed solution, which aims to provide a robust and scalable alternative to improve real-time localization capabilities. The core of the proposed solution is an innovative Ant Colony Optimization (ACO)-based dual clustering method. This approach cleverly combines ACO for initial coarse data grouping, leveraging its optimization capabilities, with K-means for subsequent cluster refinement, aiming for enhanced precision. Following the clustering, the Weighted K-Nearest Neighbor (WKNN) algorithm is employed for real-time positioning, focusing on selecting the most similar signal sub-bases. A notable contribution is the introduction of the Dual Clustering Wi-Fi Localization Dataset (DCWiLD), which is a valuable resource for reproducibility and future research in the field, demonstrating a commitment to advancing the collective knowledge base. The experimental results presented are compelling, showcasing significant improvements across various metrics. The method achieves impressive accuracy in building classification (100%) and floor classification (91%), which are fundamental for effective indoor navigation. For more granular latitude and longitude predictions, the performance of Random Forest and SVC, with remarkably low MSE values of 0.0048 and 0.0055 respectively, indicates a high degree of precision. Furthermore, the substantial reduction in computational overhead by 93.51% is a crucial practical advantage, making the system viable for real-time and resource-constrained environments. The paper concludes by outlining clear and relevant future work, including dataset balancing, integration with other technologies like BLE and UWB, and energy optimization, suggesting a well-thought-out research roadmap for continuous improvement.

Full Text

Comments

You need to be logged in to post a comment.