The demand for IPSs designed specifically for mobile and wearable devices has been rapidly increasing due to the expansion of the global market for Location-based Services (LBS), the widespread adoption of mobile LBS applications, and the ubiquity of mobile and wearable devices in our daily lives.
However, the development of IPSs for these devices requires addressing additional design requirements, such as low power consumption, utilization of built-in technologies, and cost-effective implementation.
To meet these challenges, Pavel Pascacio focused on leveraging Wi-Fi and Bluetooth Low Energy (BLE) technologies, in combination with lateration and fingerprinting techniques, which have garnered significant attention from research communities.
While these technologies are straightforward to implement based on Received Signal Strength (RSS), they often face issues such as signal fluctuations in Line-of-sight and Non-line-of-sight scenarios, as well as hardware heterogeneity, resulting in decreased positioning accuracy.
The doctoral dissertation conducted by Pascacio aimed to address these limitations and explore the potential of collaborative and machine learning-based techniques in improving the accuracy of traditional IPSs based on RSS. The research focused on developing and evaluating mobile device-based collaborative indoor techniques using Artificial Neural Networks (ANNs).
Findings and Evaluation of the proposed Collaborative Indoor Positioning Systems
The research followed a four-phase methodology that included a systematic review of Collaborative Indoor Positioning Systems (CIPSs), extensive experimental data collections using mobile devices, evaluation of traditional methods, and the development and evaluation of two variants of collaborative indoor positioning systems.
The evaluation of the CIPSs demonstrated that the first proposed variant outperformed traditional IPSs based on Lateration in terms of positioning accuracy, showing superior performance across different distances. Additionally, the second variant of the collaborative approach surpassed traditional IPSs based on BLE-fingerprinting and Wi-Fi-fingerprinting for short distances between collaborating devices.
Overall, the research findings highlighted the potential of collaborative methodologies and ANNs in improving the accuracy of IPSs, particularly in short and medium distances. However, further improvements are needed to match the performance of traditional IPSs based on fingerprinting for larger distances.
M.Sc. Pavel Pascacio conducted his doctoral research during 2019–2022 in a joint/double doctoral degree programme at Universitat Jaume I, Spain and Tampere University, Finland. It was funded by the European Union’s Horizon 2020 Research and Innovation programme under the Marie Skłodowska-Curie grant agreement No. 813278, A-WEAR.
Public Defense on Friday 9 June
The doctoral dissertation of M.Sc. Pavel Pascacio in the field of communications and computer science titled Collaborative Techniques for Indoor Positioning Systems will be publicly examined at the Universitat Jaume, Spain at 11 (CET) on Friday 09.06.2023 at Doctoral School building, in the thesis room "Vicent Martínez Guzmán". The Opponent will be Dr. Marteen Weyn, University of Antwerp, Belgium. The Custos will be Associate Professor Sven Casteleyn from the Department of Languages and Computer Systems, Univeristat Jaume I.
Photo: Edgar Martínez