Research

My research focuses on wireless communication, RF sensing, antenna engineering, and sensing-oriented wireless systems for future ISAC and 6G applications. Over the years, my work has gradually evolved from conventional communication-system problems toward systems where communication hardware itself also functions as a sensing platform. I am particularly interested in antenna and microwave-based sensing systems that can be physically built, experimentally validated, and deployed under real operating conditions. Much of my work combines RF engineering, microwave sensing, SDR prototyping, embedded systems, signal processing, and lightweight machine-learning-based inference using experimentally measured data rather than simulation-only environments. A recurring theme in my research is using wireless infrastructure not only to transmit information, but also to perceive and interpret the surrounding environment. This idea has shaped much of my recent work in RF sensing, multimodal sensing, and integrated sensing and communication architectures.

Early Work in Wireless Communication Systems

My earlier research focused on communication-system design, particularly MIMO-OFDM systems. During this period, I worked on channel estimation, PAPR reduction, signal reliability, and physical-layer security. One part of the work involved data-aided channel estimation methods that combined pilot symbols with reliable data carriers to improve estimation accuracy while reducing pilot overhead. I also explored several PAPR reduction techniques using predictive filtering, companding, precoding, and orthogonal basis methods under nonlinear amplifier and fading-channel conditions. Alongside this, I worked on physical-layer security using chaotic encryption integrated into OFDM structures. Although these problems addressed different aspects of communication systems, they shared the same engineering objective: improving wireless-system performance while keeping the solutions computationally practical. This period gave me a strong foundation in communication theory, signal processing, and wireless-system design.

Transition Toward RF Sensing

My research direction changed significantly during my PhD at the Norwegian University of Science and Technology (NTNU), where I worked on the AQMA project funded by the Research Council of Norway. During this period, I became increasingly interested in whether communication hardware itself could operate as a sensing system. Instead of treating antennas only as radiating structures, I started exploring whether their electromagnetic behavior could also be used to detect and characterize the surrounding environment. That shift gradually moved my work toward microwave sensing, antenna-based sensing systems, and integrated sensing and communication. The research combined RF engineering, electromagnetics, microwave sensing, signal processing, and machine learning. I worked extensively with CST, HFSS, COMSOL, and ADS for antenna and RF-system design, while MATLAB and Python were used for signal processing and inference development. A large part of the work was experimental. During my PhD, I fabricated and tested more than 500 antenna prototypes using PCB milling systems and carried out extensive RF measurements and laboratory validation. I also contributed to the development of wireless sensing laboratories, PCB fabrication facilities, and AI-oriented sensing infrastructure. One conclusion became increasingly clear during this work: future wireless systems will likely integrate sensing directly into the physical layer instead of treating it as a separate subsystem.

Microwave Chemical Sensing and MIMO RF Sensing

A major part of my doctoral research focused on microwave sensing systems using antenna structures functionalized with advanced sensing materials, including MoS₂, MoS₂/MoOₓ heterostructures, molecularly imprinted polymers, and carbon-nanotube composites. Unlike conventional resistive sensors, these systems operate through changes in electromagnetic behavior, making them naturally compatible with wireless interrogation and RF-system integration. Using these approaches, I demonstrated selective detection of volatile organic compounds such as methanol, ethanol, and isopropanol under room-temperature operation. An important direction that emerged from this work was extending single sensing elements into MIMO sensing architectures. This introduced several practical challenges, including mutual coupling, cross-sensitivity, interference between sensing elements, and stable inference under noisy measurement conditions. To address these problems, I worked on compact antenna structures together with learning-based inference models trained directly on experimentally measured RF data. This work eventually led to the development of a microwave MIMO electronic nose system capable of simultaneous sensing and communication within the same framework. The research resulted in multiple journal publications, startup funding, ongoing patent evaluation, and nomination of my PhD thesis for a Best Doctoral Thesis Award in sensor research.

Machine Learning and Experimental Inference

Machine learning in my work is mainly used as a practical inference layer built on top of RF and electromagnetic behavior. I am more interested in physically meaningful and experimentally stable models than purely black-box architectures disconnected from the sensing hardware itself. Most of my work therefore combines physics-aware feature extraction with lightweight learning-based inference. The focus has included classification, concentration estimation, adaptive inference, multimodal fusion, and learning under practical noise and channel uncertainty. All models are trained and validated using experimentally measured data rather than synthetic-only datasets. I have also worked with SDR-based prototyping using USRP platforms, embedded systems, FPGA-assisted implementations, and real-time inference pipelines for deployable sensing systems.

Current Research Direction

My current research focuses on deployable integrated sensing and communication systems for future wireless infrastructure. One major direction involves replacing bulky VNA-based RF sensing systems with compact on-chip RF readout architectures that are more suitable for scalable deployment. Another direction involves combining RF sensing with computer vision and multimodal inference to improve robustness and semantic awareness in complex environments. I am also interested in UAV-assisted ISAC systems for applications such as traffic monitoring, environmental sensing, disaster response, and infrastructure-limited communication. More broadly, I am interested in how future wireless networks can evolve from passive communication infrastructure into intelligent distributed sensing systems capable of interacting with their physical environment in real time.

Research Projects and Funding

• Machine Learning Assisted Signal Processing for Antenna-Sensor Arrays (MLSP-ASA)
  Research Council of Norway, Project No. 353890 (2024–2025)

• Air Quality Monitoring using Massive MIMO Antennas (AQMA)
  Research Council of Norway, Project No. 324061 (2022–2025)

Long-Term Research Vision

My long-term research goal is to contribute to wireless systems where sensing, communication, and machine intelligence operate within the same architecture instead of existing as isolated subsystems. I believe future 6G systems will increasingly move toward environment-aware and context-aware wireless infrastructure, where communication networks continuously interact with the physical world rather than simply transporting data between devices. My work aims to contribute to that transition through experimentally validated, hardware-aware, and practically deployable sensing and communication systems.