Scalable Wi-Fi Fingerprinting Localization by Deep Similarity Network

Wi-Fi received signal strength (RSS) fingerprinting is a leading method for indoor positioning due to its widespread infrastructure. Traditional fingerprinting classifies location by signal distance from a reference point (RP), assuming similarity between path and radio signal distances. Recently, model-based deep learning has been used to classify location estimates by identifying patterns in the radio environment. However, this method often loses consistency between space and signals as it learns without considering the correlation between RPs, necessitating retraining on unmeasured points. To address these limitations, we propose a scalable deep similarity model that can incorporate new RPs without the need for retraining. This model maintains consistency between distance and RSS by preserving the feature distribution using a center estimator to effectively learn RSS features through an embedding network. Subsequently, a deep similarity network (DSN) employing scaled dot product similarity (SDPS), a novel distance-based deep architecture, estimates location by comparing RSS features with the RP. We designed the model end-to-end and optimized it using cross-entropy loss. The proposed model approximates the location coordinates as the center of mass based on the estimated probabilities of RPs. Our results demonstrate that the model not only achieves improved performance over state-of-the-art techniques but also maintains its scalability and performance consistency with the addition and deletion of RPs.