Ambient magnetic field-based positioning with smartphones: a comparison of different fingerprinting methods

This dataset provides the supporting material for the work entitled Ambient Magnetic Field-Based Positioning with Smartphones: A Comparison of Different Fingerprinting Methods, presented at the 2025 International Instrumentation and Measurement Technology Conference (I2MTC 2025) and published in the Zenodo repository. This dataset contains: RawData logs generated during data acquisition Processed raw logs in csv format. Fingerprinting ready matrices (training/test and input/output) in csv format for each subset. A PDF with extra documentation can be found in the repository. It includes: A description of the experimental environment and setup. An extended version of the results. A comprehensive descriptor of the attached database. Documentation of the accompanying code. How to use: To run the code, download all contents into a single folder and unzip the compressed .zip files. The MATLAB scripts must be located at the same directory level as the “matlab” folder. The CREATE_DATASET script converts the original raw data logs into a standardized format and, in the same process, generates the csvData folder and writes its contents. The MAIN script runs the analysis. The provided code is an update from the initial version. However, it contains unnecessary code for the project. It will be updated in the future to contain only the necessary functions to replicate the results of the article. Current version: Version 2.0.0The original article:F. J. Álvarez, F. J. Aranda, F. Parralejo, J. A. Moreno, J. Espinosa, and R. Gallardo, "Ambient magnetic field-based positioning with smartphones: a comparison of different fingerprinting methods," 2025 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Chemnitz, Germany, 2025, pp. 1-6, doi: 10.1109/I2MTC62753.2025.11079150.