Graduate Exam Abstract

Abstract: This dissertation introduces SPARK, a suite of novel machine learning (ML) frameworks for Wi-Fi fingerprinting-based indoor localization, engineered to achieve high accuracy indoor localization, energy efficiency on resource-limited devices, security for ML models, adaptability to evolving environments, and transparent ML decision-making. Indoor localization faces persistent challenges, including device heterogeneity, environmental changes, costly data collection, privacy concerns, vulnerability to adversarial attacks, and the opacity of ML models. SPARK tackles these issues through key ML innovations such as attention and transformer-based networks for device-invariant learning, Siamese networks with contrastive learning for long-term stability, privacy-preserving federated learning, efficient ML-based data augmentation, continual and adaptive learning paradigms for ML models in dynamic environments, adversarial defense strategies for ML models, and a logic-gate-inspired method for ML model explainability. Validated in real-world scenarios, SPARK advances the development of robust, scalable, secure, and transparent indoor localization systems.

Adviser: Prof. Sudeep Pasricha
Co-Adviser: N/A
Non-ECE Member: Prof. Nikhil Krishnaswamy
Member 3: Prof. Anthony Maciejewski
Addional Members: Prof. Anura Jayasumana

Publications:
LIST OF CONFERENCE PUBLICATIONS

• S. Tiku, D. Gufran, and S. Pasricha. "Multi-head attention neural network for smartphone invariant indoor localization." IEEE international conference on indoor positioning and indoor navigation (IPIN), 2022. (Best Paper Award)
• D. Gufran, S. Tiku, and S. Pasricha. "VITAL: Vision transformer neural networks for accurate smartphone heterogeneity resilient indoor localization." ACM/IEEE Design Automation Conference (DAC), 2023.
• D. Gufran, and S. Pasricha. "FedHIL: Heterogeneity resilient federated learning for robust indoor localization with mobile devices." International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS), 2023.
• D. Gufran, and S. Pasricha. "CALLOC: Curriculum adversarial learning for secure and robust indoor localization." ACM/IEEE Design, Automation & Test in Europe Conference & Exhibition (DATE), 2024.
• D. Gufran, P. Anandathirtha, and S. Pasricha. "SENTINEL: Securing Indoor Localization against Adversarial Attacks with Capsule Neural Networks." International Conference on Compilers, Architectures, and Synthesis for Embedded Systems (CASES), 2024.
• A. Singampalli, D. Gufran, and S. Pasricha. "SAFELOC: Overcoming Data Poisoning Attacks in Heterogeneous Federated Machine Learning for Indoor Localization." IEEE/ACM Design, Automation & Test in Europe Conference (DATE), 2024.
• A. Singampalli, D. Gufran, and S. Pasricha. "DAILOC: Domain-Incremental Learning for Indoor Localization using Smartphones." IEEE international conference on indoor positioning and indoor navigation (IPIN), 2025.
• D. Gufran, and S. Pasricha. "GATE: Graph Attention Neural Networks with Real-Time Edge Construction for Robust Indoor Localization using Mobile Embedded Devices. " International Conference on Compilers, Architectures, and Synthesis for Embedded Systems (CASES), 2025. (Best Paper Candidate)
• D. Gufran, and S. Pasricha. "Towards Explainable Indoor Localization: Interpreting Neural Network Learning on Wi-Fi Fingerprints Using Logic Gates." IEEE international conference on indoor positioning and indoor navigation (IPIN), 2025.

LIST OF JOURNAL PUBLICATIONS

• D. Gufran, S. Tiku, and Sudeep Pasricha. "SANGRIA: Stacked autoencoder neural networks with gradient boosting for indoor localization." IEEE Embedded Systems Letters (ESL), 2023.
• D. Gufran, S. Tiku, and Sudeep Pasricha. "STELLAR: Siamese multiheaded attention neural networks for overcoming temporal variations and device heterogeneity with indoor localization." IEEE Journal of Indoor and Seamless Positioning and Navigation (ISPIN-J), 2023.
• D. Gufran, and S. Pasricha. "FedHIL: Heterogeneity resilient federated learning for robust indoor localization with mobile devices." ACM Transactions on Embedded Computing Systems (TECS), 2023.
• D. Gufran, P. Anandathirtha, and S. Pasricha. "SENTINEL: Securing Indoor Localization against Adversarial Attacks with Capsule Neural Networks." IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2024.
• A. Singampalli, D. Gufran, and S. Pasricha. "CIELO: Class-Incremental Continual Learning for Overcoming Catastrophic Forgetting with Smartphone-based Indoor Localization." IEEE Access, 2025.
• D. Gufran, and S. Pasricha. "GATE: Graph Attention Neural Networks with Real-Time Edge Construction for Robust Indoor Localization using Mobile Embedded Devices. ACM Transactions on Embedded Computing Systems (TECS), 2025.

LIST OF BOOK CHAPTER PUBLICATIONS

Book Title - Machine Learning for Indoor Localization and Navigation.
• D. Gufran, S. Tiku, and S. Pasricha "Heterogeneous device resilient indoor localization using vision transformer neural networks." Machine Learning for Indoor Localization and Navigation, Springer Nature, 2023.
• S. Tiku, D. Gufran, and S. Pasricha " Smartphone invariant indoor localization using multi-head attention neural network." Machine Learning for Indoor Localization and Navigation, Springer Nature, 2023.
Book Title – Springer Handbook of Data Engineering
• D. Gufran, and S. Pasricha "Heterogeneity-Resilient Federated Learning for High Accuracy Indoor Localization using Edge Devices", Springer Handbook of Data Engineering, Springer Nature, 2025.

Program of Study:
ECE 581C
ECE 561
ECE 513
ECE 658
ECE 569
CS 542
CS 545
SYSE 541