Wi-Fi Fingerprint Based Indoor Localization Using Few Shot Regression

EasyChair Preprint no. 11930

Abstract

Deep learning techniques, particularly those based on Wi-Fi fingerprinting, have become increasingly prevalent in the field of indoor positioning. These methods typically require specialized training for specific environments and often lack adaptability to changes in indoor settings. In contrast, this study introduces an indoor positioning approach based on few-shot regression. The aim is to enable the model to rapidly adapt to new indoor environments using a limited number of labeled Wi-Fi Received Signal Strength Indicator (RSSI) samples. This research treats indoor location prediction as a regression problem, initially pre-training the model on a Wi-Fi dataset from a source domain and establishing a general mapping relationship between Wi-Fi signals and locations using the concept of basis functions. Subsequently, the model is fine-tuned with a small set of Wi-Fi samples from the target domain to learn specific weights. This process of transferring the model from the source to the target domain aids in achieving accurate positioning in new and constantly changing environments. Experimental results demonstrate the method’s superior performance in positioning accuracy, showing a 57.9% improvement over few-shot classification and a 13% improvement over KNN.

Keyphrases: adaptive localization, few shot regression, Wi-Fi

@Booklet{EasyChair:11930,
  author = {Xuechen Chen and Jiaxuan Yi and Aixiang Wang and Xiaoheng Deng},
  title = {Wi-Fi Fingerprint Based Indoor Localization Using Few Shot Regression},
  howpublished = {EasyChair Preprint no. 11930},

  year = {EasyChair, 2024}}