Saideep Tiku
Ph.D. PreliminaryDec 16, 2019, 9:30 am - 11:30 am
ECE B4
SARTHI: A Secure, Accurate, Real-Time, and Heterogeneity-Resilient Indoor Localization Framework with Smartphones
Abstract: Indoor localization is an emerging internet-of-things (IoT) application domain that is poised to
reinvent the way we navigate in various indoor environments. Ubiquitously available Wi-Fi signals
have enabled low-cost fingerprinting-based localization solutions that can work with commodity
smartphones. However, fingerprinting based indoor localization frameworks face several challenges
such as mobile device resource limitations, device heterogeneity, indoor environment uncertainties,
wireless signal variations, and security vulnerabilities. These factors reduce the accuracy, reliability,
predictability, and energy-efficiency of indoor localization frameworks and represent a major barrier in
solving the localization problem in real-world settings. To counter these challenges, this thesis
proposes a novel framework for energy-efficient, real-time, and robust indoor localization that utilizes
deep learning and statistical techniques, which are prototyped and validated on a variety of handheld
mobile devices.
reinvent the way we navigate in various indoor environments. Ubiquitously available Wi-Fi signals
have enabled low-cost fingerprinting-based localization solutions that can work with commodity
smartphones. However, fingerprinting based indoor localization frameworks face several challenges
such as mobile device resource limitations, device heterogeneity, indoor environment uncertainties,
wireless signal variations, and security vulnerabilities. These factors reduce the accuracy, reliability,
predictability, and energy-efficiency of indoor localization frameworks and represent a major barrier in
solving the localization problem in real-world settings. To counter these challenges, this thesis
proposes a novel framework for energy-efficient, real-time, and robust indoor localization that utilizes
deep learning and statistical techniques, which are prototyped and validated on a variety of handheld
mobile devices.
Adviser: Sudeep Pasricha
Co-Adviser: NA
Non-ECE Member: Shrideep Pallickara
Member 3: Anthony Maciejewski
Addional Members: H. J. Siegel
Co-Adviser: NA
Non-ECE Member: Shrideep Pallickara
Member 3: Anthony Maciejewski
Addional Members: H. J. Siegel
Publications:
[1] S. Tiku, S. Pasricha, “PortLoc: A Portable Data-driven Indoor Localization Framework for Smartphones,” IEEE Design and Test (D&T), 2019.
[2] S. Tiku, S. Pasricha, “SHERPA: A Lightweight Smartphone Heterogeneity Resilient Portable Indoor Localization Framework,” IEEE International Conference on Embedded Software and Systems (ICESS), 2019.
[3] A. Mittal, S. Tiku, S. Pasricha, “Adapting Convolutional Neural Networks for Indoor Localization with Smart Mobile Devices,” ACM Great Lakes Symposium on VLSI (GLSVLSI), 2018 (Best Paper Award)
[4] S. Tiku, S. Pasricha, “Overcoming Security Vulnerabilities in Deep Learning Based Indoor Localization Frameworks on Mobile Devices,” to appear, Transactions on Embedded Computing Systems (TECS), 2020.
[5] C. Langlois, S. Tiku, S. Pasricha, “Indoor localization with smartphones,” IEEE Consumer Electronics (CE), 2017.
[6] S. Tiku, S. Pasricha, “Energy-Efficient and Robust Middleware Prototyping for Smart Mobile Computing,” IEEE Rapid System Prototyping (RSP), 2017.
[7] S. Pasricha, J. Doppa, K. Chakrabarty, S. Tiku, D. Dauwe, S. Jin, P. Pande, “Data Analytics Enables Energy-Efficiency and Robustness: From Mobile to Manycores, Datacenters, and Networks,” ACM/IEEE Conference on Hardware/Software Co-design and System Synthesis (CODES+ISSS), Oct 2017
[1] S. Tiku, S. Pasricha, “PortLoc: A Portable Data-driven Indoor Localization Framework for Smartphones,” IEEE Design and Test (D&T), 2019.
[2] S. Tiku, S. Pasricha, “SHERPA: A Lightweight Smartphone Heterogeneity Resilient Portable Indoor Localization Framework,” IEEE International Conference on Embedded Software and Systems (ICESS), 2019.
[3] A. Mittal, S. Tiku, S. Pasricha, “Adapting Convolutional Neural Networks for Indoor Localization with Smart Mobile Devices,” ACM Great Lakes Symposium on VLSI (GLSVLSI), 2018 (Best Paper Award)
[4] S. Tiku, S. Pasricha, “Overcoming Security Vulnerabilities in Deep Learning Based Indoor Localization Frameworks on Mobile Devices,” to appear, Transactions on Embedded Computing Systems (TECS), 2020.
[5] C. Langlois, S. Tiku, S. Pasricha, “Indoor localization with smartphones,” IEEE Consumer Electronics (CE), 2017.
[6] S. Tiku, S. Pasricha, “Energy-Efficient and Robust Middleware Prototyping for Smart Mobile Computing,” IEEE Rapid System Prototyping (RSP), 2017.
[7] S. Pasricha, J. Doppa, K. Chakrabarty, S. Tiku, D. Dauwe, S. Jin, P. Pande, “Data Analytics Enables Energy-Efficiency and Robustness: From Mobile to Manycores, Datacenters, and Networks,” ACM/IEEE Conference on Hardware/Software Co-design and System Synthesis (CODES+ISSS), Oct 2017
Program of Study:
CS 545
ECE 554
ECE 561
ECE 567
ECE 569
ECE 661
ECE 666
ENGR 510
CS 545
ECE 554
ECE 561
ECE 567
ECE 569
ECE 661
ECE 666
ENGR 510