SGP-RI: A Real-Time-Trainable and Decentralized IoT Indoor Localization Model Based on Sparse Gaussian Process with Reduced-Dimensional Inputs
Zhe Tang, Sihao Li, Zichen Huang, Guandong Yang, Kyeong Soo Kim, Jeremy S. Smith
TL;DR
The paper addresses the limitations of centralized indoor localization on dynamic, privacy-sensitive environments by proposing a real-time-trainable and decentralized framework (SGP-RI) that runs on IoT devices. It combines Sparse Gaussian Process regression with reduced-dimensional inputs obtained through WAP-based feature filtering and RP-based inducing-point selection, achieving $O(NM^2)$ complexity for scalable on-device learning. Across single-building and multi-building datasets, SGP-RI achieves localization performance comparable to full GP while using substantially fewer inducing inputs and enabling continuous online retraining to adapt to changing RSSI statistics. The approach enhances reliability, privacy, and adaptability in large-scale IoT deployments by obviating dependence on a central server and enabling on-device fingerprint collection and model updates.
Abstract
Internet of Things (IoT) devices are deployed in the filed, there is an enormous amount of untapped potential in local computing on those IoT devices. Harnessing this potential for indoor localization, therefore, becomes an exciting research area. Conventionally, the training and deployment of indoor localization models are based on centralized servers with substantial computational resources. This centralized approach faces several challenges, including the database's inability to accommodate the dynamic and unpredictable nature of the indoor electromagnetic environment, the model retraining costs, and the susceptibility of centralized servers to security breaches. To mitigate these challenges we aim to amalgamate the offline and online phases of traditional indoor localization methods using a real-time-trainable and decentralized IoT indoor localization model based on Sparse Gaussian Process with Reduced-dimensional Inputs (SGP-RI), where the number and dimension of the input data are reduced through reference point and wireless access point filtering, respectively. The experimental results based on a multi-building and multi-floor static database as well as a single-building and single-floor dynamic database, demonstrate that the proposed SGP-RI model with less than half the training samples as inducing inputs can produce comparable localization performance to the standard Gaussian Process model with the whole training samples. The SGP-RI model enables the decentralization of indoor localization, facilitating its deployment to resource-constrained IoT devices, and thereby could provide enhanced security and privacy, reduced costs, and network dependency. Also, the model's capability of real-time training makes it possible to quickly adapt to the time-varying indoor electromagnetic environment.