With the rapid growth of mobile communication technologies and smart devices, demand for location-based services has surged. Fingerprint-Based positioning using wireless signals is now a leading method for indoor localization. However, wireless signals from access points (APs) fluctuate due to time-varying noise, causing fingerprint signals sampled at the same location to differ over time, sometimes significantly. This variability not only hinders accurate fingerprint map construction but also disrupts precise matching between the target point’s fingerprint and the map, leading to inconsistent positioning results. To address this, we propose RSLoc, an indoor localization system based on a KAN convolutional network. First, APs with weak or erratic signals are excluded, and a refined fingerprint map is generated. We then develop a deep network model, FFEM, based on KAN convolution. The model is trained using a sample library derived from fingerprint data, optimized through entropy regularization and pruning. The FFEM model generates a mapping of the target point, calculates its similarity to the fingerprint map, and selects appropriate neighboring points for effective localization. Experiments using different mobile devices show that RSLoc improves average positioning accuracy by 33%-44% compared to methods like LORI and FML. Moreover, removing invalid APs and constructing the sample library reduce errors, enhancing accuracy by over 48% and 29%, respectively.

The protection of people's safety is often achieved by relying on high-precision localization, and the demand for accurate indoor localization services has continued to grow. Especially, RFID localization has become a research hotspot for scholars. For the method of using the ranging model to realize RFID localization, when in an ideal radio frequency propagation environment, the observed RFID signal strength is directly related to the distance between the reader and the tag. Therefore, by using range information related to multiple reference tags, the reader can be clearly located in space. However, simply using the distance between the localization point and the reader obtained by the path propagation model to calculate the localization will produce a large localization error. In fact, the path propagation model reflects the general trend of signal propagation, and the corresponding model parameters need to be calculated based on the distance between the localization and the reader. For this reason, this paper proposes the localization using ranging in segment area based on fuzzy logic (RFL). The RFL method uses fuzzy logic to obtain the weights of localization belonging to different segments, and then constructs the propagation model of different segments and obtains the coordinates under this model. Finally, the segment weights calculate the final coordinates. The experiments show that RFL is superior to the maximum likelihood estimation and simple signal propagation model.