Deep Gaussian process based radio map construction and localization
Abstract: With the increasing demand for location-based service, WiFi-based localization has become one of the most popular methods due to the wide deployment of WiFi and its relatively low cost. In this talk, we present a deep Gaussian process based indoor radio map construction and location estimation system. Received signal strength (RSS) samples, as well earth magnetic field readings, are used to generate accurate and fine-grained radio maps with confidence intervals using deep Gaussian process, while the model parameters are optimized with an offline Bayesian training method. Utilizing the maps, an LSTM based location prediction model is pre-trained with the artificial trajectory data and then fine-tuned with the signal measurements collected by the mobile device to be localized. Our extensive experiments demonstrate the excellent performance of the proposed system.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- Victoria, British Columbia
- Canada
- Building: ECS
- Room Number: 660
Speakers
Deep Gaussian process based radio map construction and localization
Abstract:
With the increasing demand for location-based service, WiFi-based localization has become one of the most popular methods due to the wide deployment of WiFi and its relatively low cost. In this talk, we present a deep Gaussian process based indoor radio map construction and location estimation system. Received signal strength (RSS) samples, as well earth magnetic field readings, are used to generate accurate and fine-grained radio maps with confidence intervals using deep Gaussian process, while the model parameters are optimized with an offline Bayesian training method. Utilizing the maps, an LSTM based location prediction model is pre-trained with the artificial trajectory data and then fine-tuned with the signal measurements collected by the mobile device to be localized. Our extensive experiments demonstrate the excellent performance of the proposed system.
Biography:
SHIWEN MAO is a professor and Earle C. Williams Eminent Scholar Chair, and Director of the Wireless Engineering Research and Education Center (WEREC) at Auburn University. His research interest includes wireless networks, multimedia communications, and smart grid. He is a Distinguished Lecturer of IEEE Communications Society and the IEEE Council of RFID. He is the editor-in-chief of IEEE Transactions on Cognitive Communications and Networking. He received the SEC 2023 Faculty Achievement Award for Auburn, the IEEE ComSoc TC-CSR Distinguished Technical Achievement Award in 2019, the Auburn University Creative Research & Scholarship Award in 2018, and NSF CAREER Award in 2010. He is a co-recipient of the 2021 Best Paper Award of Elsevier/KeAi Digital Communications and Networks Journal, the 2021 IEEE Communications Society Outstanding Paper Award, the 2021 IEEE Internet of Things Journal Best Paper Award, the IEEE Vehicular Technology Society 2020 Jack Neubauer Memorial Award, the 2004 IEEE Communications Society Leonard G. Abraham Prize in the Field of Communications Systems, and several conference best paper/demo awards. He is a Fellow of the IEEE and IET.
Address:Canada