Kusuma, Lusia Rakhmawati

Design and Implementation of an Android-Based Indoor Signal Strength Positioning System Using Multivariate Gaussian Mixture Model with Wi-Fi RSSI Fingerprinting

Introduction

Design and implementation of an android-based indoor signal strength positioning system using multivariate gaussian mixture model with wi-fi rssi fingerprinting. Design an Android-based indoor positioning system using Wi-Fi RSSI fingerprinting and a Multivariate Gaussian Mixture Model (MGMM). Achieves high accuracy (0.433m MAE) and real-time performance.

Abstract

Indoor positioning systems (IPS) are crucial where GPS accuracy is limited, but Wi-Fi RSSI-based methods face challenges from signal fluctuations and computational complexity. This research designed and implemented an Android application for indoor signal-strength positioning using a Multivariate Gaussian Mixture Model (MGMM) algorithm based on Wi-Fi RSSI fingerprinting. The system utilized three 2.4 GHz access points to collect Received Signal Strength Indicator (RSSI) data, building a fingerprint database. MGMM was integrated with Maximum Likelihood Estimation (MLE) for parameter estimation and Bayes' Theorem for probabilistic position determination. Testing was conducted in furnished and unfurnished rooms (30 trials per condition). Results showed 90% accuracy (within a 1-meter tolerance radius), a Mean Absolute Error (MAE) of 0.433 meters, and a Root Mean Square Error (RMSE) of 0.796 meters in furnished environments. In unfurnished rooms, the system achieved 100% accuracy (MAE and RMSE = 0 meters). The average system latency was 62 ms, confirming real-time responsiveness. This study demonstrates MGMM’s effectiveness in modeling RSSI distributions and enhancing IPS accuracy. Keywords: Indoor Positioning System, Wi-Fi RSSI-Fingerprint, Multivariate Gaussian Mixture Model, Android Application, Accuracy.

Review

This paper presents a compelling solution for indoor positioning, a domain where traditional GPS falters. The authors address the inherent challenges of Wi-Fi RSSI-based systems, specifically signal variability and computational load, by proposing an Android-based application leveraging a Multivariate Gaussian Mixture Model (MGMM) with Wi-Fi RSSI fingerprinting. The core innovation lies in the robust probabilistic framework of MGMM, integrated with Maximum Likelihood Estimation and Bayes' Theorem, to accurately model the fluctuating RSSI signals and provide precise position estimates. This approach offers a promising direction for real-time, user-friendly indoor navigation, particularly in complex indoor environments. The methodology is clearly outlined, detailing the use of three 2.4 GHz access points for data collection and the construction of a comprehensive fingerprint database. The choice of MGMM is theoretically sound for handling the multimodal and stochastic nature of RSSI distributions. The experimental design, involving tests in both furnished and unfurnished environments with 30 trials per condition, provides a good basis for evaluating system performance under varying real-world conditions. The reported results are impressive, particularly the 100% accuracy and zero error metrics (MAE and RMSE) in unfurnished rooms, and the strong performance (90% accuracy within 1m, MAE 0.433m, RMSE 0.796m) in furnished settings. The low average system latency of 62 ms further confirms the practical viability for real-time applications, effectively mitigating concerns about computational complexity often associated with model-based approaches. Overall, this study makes a significant contribution to the field of indoor positioning systems. The effective integration of MGMM within an Android platform showcases a practical and accurate solution that can overcome common limitations of Wi-Fi RSSI-based methods. The achieved accuracy and real-time responsiveness make this system highly suitable for various applications, from asset tracking to navigation in complex indoor spaces. Future work could potentially explore the system's scalability with more access points or larger areas, its robustness against changes in environmental dynamics over time, or the energy efficiency implications for prolonged use on mobile devices. Nevertheless, the research clearly demonstrates the power of MGMM in enhancing IPS accuracy and provides a strong foundation for future advancements in this critical area.

Full Text

Comments

You need to be logged in to post a comment.