Research output
Publications
Selected peer-reviewed, accepted, and submitted manuscripts spanning wireless neural fields, physics-informed learning, beamforming, sensing, and geolocation. For the complete citation list, visit my Google Scholar profile.
Neural wireless fields and environment-aware intelligence
-
WiNeRF: Hardware-Constrained Radiance Fields for Actionable Wireless Channel Modeling
Learns spatially continuous, complex-valued wireless channel representations from sparse commodity WiFi CSI, outperforming neural baselines by 3–6.7 dB SNR and supporting beamforming, AoA, and RSSI mapping workflows.
-
PU-HNO: Physics-Unrolled Hybrid Neural Operator for High-Fidelity Radio-Map Prediction
Predicts high-fidelity indoor radio maps from low-fidelity ray-tracing outputs and scene priors through a three-stage cascade that captures reflection, diffraction, and scattering effects, learning stable propagation structure from noisy finite-ray labels.
-
I-NAV: Inverse Navigation for Questionnaire-Based Geolocation in GPS-Denied Environments
Enables offline geolocation through inverse navigation, matching commercial routing engines within 2–3 minutes of travel-time accuracy and achieving strong spatial overlap with ORS regions.
-
MetaFAP: Meta-Learning for Frequency Agnostic Prediction of Metasurface Properties
Predicts metasurface properties across frequencies with a meta-learning formulation, achieving MSE below 0.01 and strong correlation across datasets of varying difficulty.
Peer-reviewed journal articles
-
Beyond Traditional Beamforming: Singular Vector Projection Techniques for MU-MIMO
-
Real-time Seismic Intensity Prediction using Self-supervised Contrastive GNN for Earthquake Early Warning
-
A CNN-based Multifaceted Signal Processing Framework for Heart Rate Proctoring Using Millimeter Wave Radar Ballistocardiography
-
A CNN-LSTM-based Fusion Separation Deep Neural Network for 6G Ultra-Massive MIMO Hybrid Beamforming
Conference proceedings
-
Reconfigurable Intelligent Surface Assisted Interference Suppression With Impedance Regulated Deep Neural Network (IR-DNN)
-
Self-supervised Contrastive Learning for 6G UM-MIMO THz Communications: Improving Robustness Under Imperfect CSI
-
A Fast Effective Greedy Approach for MU-MIMO Beam Selection in mm-Wave and THz Communications
-
Analysis of Frequency Content and Statistical Relationship among Earthquake Parameters of Seismic Data in Bangladesh
-
Automated Level Crossing System: A Computer Vision-Based Approach with Raspberry Pi Microcontroller
-
Deep Learning Based Power Allocation in 6G URLLC for Jointly Optimizing Latency and Reliability