15th New England Workshop on Software-Defined Radio
Worcester Polytechnic Institute, 100 Institute Road, Worcester, MA, USA
Main Event: Friday 30 May 2025, 9:00 AM (US Eastern) – 5:00 PM (US Eastern)
Tutorials: Thursday 29 May 2025, 5:00 PM (US Eastern) – 9:00 PM (US Eastern)
The 2025 New England Workshop on Software-Defined Radio (NEWSDR 2025) is the fifteenth installment of an annual workshop series organized by the Boston SDR User Group (SDR-Boston). We are very excited about this year’s NEWSDR event being hosted in-person on the beautiful campus of Worcester Polytechnic Institute (WPI) in Worcester, MA, USA. The primary goal of this workshop is to provide a forum that enables SDR enthusiasts to get together, collaborate, and introduce SDR concepts to those interested in furthering their knowledge of SDR capabilities and available resources. NEWSDR 2025 welcomes both experienced SDR enthusiasts as well as individuals who are interested in getting started with SDR.
This website will continue to be updated as the event evolves, so please visit frequently for the latest information about NEWSDR 2025!
Workshop Registration
Attendance at NEWSDR 2025 is free, but advance registration is required to ensure access to on-campus parking, guest Wi-Fi, and meals. Click here to register. The deadline to register is 22 May 2025.
Community Spotlight Talks & Posters: Abstract Submission
Interested in giving a 2-3 minute spotlight talk and a poster presentation about your SDR-related activities at NEWSDR 2025? If so, click here to submit your talk/poster abstract information. Deadline for abstract submission is 21 May 2025. Acceptance notifications will be sent out by COB 23 May 2025.
Latest Agenda
NEWSDR 2025 activities are distributed over Thursday 29th (evening tutorials) and Friday 30th (main event) on the first and second floors of the WPI Innovation Studio (see map below).
Thursday 29 May 2025 — Evening Session
(Rooms IS105, IS203, IS205, IS207)
| 05:00pm – 06:00pm EDT | Networking Session (with Pizza) Innovation Studio, 2nd Floor Diamond Lounge Area |
| 06:00pm – 09:00pm EDT | Tutorial (Sponsor): NI “FPGA Programming on the USRP with the RFNoC Framework“ Room IS203 |
| 06:00pm – 09:00pm EDT | Tutorial: OAI/EUROCOM/Northeastern University “Innovation and Prototyping in O-RAN using Open-Source Testbeds“ Room IS205 |
| 06:00pm – 09:00pm EDT | Tutorial (Sponsor): PI-Radio “Pi-Radio: Experimentation in the FR3 bands“ Room IS207 |
Friday 30 May 2025 — Morning Session
(Room IS203/IS205)
| 09:00am – 09:15am EDT | Welcome Address and Event Overview NEWSDR Organizing Committee |
| 09:15am – 10:00am EDT | Opening Talk: Florian Kaltenberger (EUROCOM) “Driving Innovation in 6G Wireless Technologies: The OpenAirInterface Approach“ |
| 10:00am – 10:30am EDT | Sponsor Talks: AMD NI (Neel Pandeya) Pi-Radio (Aditya Dhananjay) |
| 10:30am – 11:15am EDT | Spotlight Talks/Poster Preview Session Posters P1-P10 |
| 11:10am – 11:45am EDT | Networking Session (with coffee) |
| 11:45am – 12:15pm EDT | Invited Talk: Ryan Volz (MIT Haystack Observatory) “Distributing the “S” in SDR: radioconda and software management tools“ |
Lunch will be served during 12:15pm – 1:15pm EDT in Innovation Studio, 2nd Floor Diamond Lounge Area (priority access given to online registrants)
Friday 30 May 2025 — Afternoon Session
(Room IS203/IS205)
| 01:15pm – 02:15pm EDT | Keynote Talk: J. Nicholas Laneman (SpectrumX, Notre Dame) “Towards a New Kind of Radio Spectrum Understanding and Management“ |
| 02:15pm – 02:45pm EDT | Networking Session (with coffee) |
| 02:45pm – 03:30pm EDT | Fireside Chat: “Software Radio and Wireless Communication Education“ Panelists: KC Patel (UMass Boston) Galahad Wernsing (WPI) Daniel Sheen (MIT) Moderator: Alexander Wyglinski (WPI) |
| 03:30pm – 05:00pm EDT | Short Talks (25 minutes each): Raj Bhattacharjea (DeepSig) “RFML Beyond Signal Classification: ML Signal Processing, Generative AI for Channel Modeling, and Learned Comms for 6G“ Ruolin Zhou (UMass Dartmouth) “Adaptive and Explainable Machine Learning for Spectrum Sensing in Dynamic RF Environments“ Kazunori Akiyama (MIT Haystack Observatory) “AI Applications in Black Hole Imaging with the Event Horizon Telescope“ |
| 05:00pm – 05:10pm EDT | Closing Ceremony NEWSDR Organizing Committee |
Presenter & Panelist Information
Keynote Talk: “Towards a New Kind of Radio Spectrum Understanding and Management“
Abstract: Imagine if we could develop a cost-effective, distributed system that provides a fine-grain understanding of how the radio spectrum is actively being utilized across frequency, time, and space within a given building, throughout a city, or even over a larger geographic area. How might we design next-generation radio systems and applications to be more flexible and take advantage of unused spectrum based upon such information? How might we allocate and manage radio spectrum differently with these capabilities?
This talk will outline recent progress in developing spectrum awareness at scale through integration of novel software-defined radio prototypes, cloud-based data storage and management platforms, and advanced visualization and analysis tools that leverage the latest AI/ML advancements. Such efforts are being pursued by a growing community of researchers supported through SpectrumX, the National Science Foundation (NSF) Spectrum Innovation Center.
Presenter: Dr. Nick Laneman is Director of SpectrumX, Founding Director and currently Co-Director of the Wireless Institute in the College of Engineering, and Professor in the Department of Electrical Engineering at the University of Notre Dame. He joined the faculty in August 2002 shortly after earning a Ph.D. in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology (MIT). His research and teaching interests are in wireless system design, radio spectrum access, technology standards, and regulatory policy. Laneman is an IEEE Fellow, has received the IEEE Kiyo Tomiyasu Award, the Presidential Early-Career Award for Scientists and Engineers (PECASE), and the NSF CAREER Award, and has been recognized twice by Thomson Reuters as an ISI Highly Cited Researcher. He is author or co-author on over 145 publications and is co-inventor on 8 U.S. patents.
Opening Talk: “Driving Innovation in 6G Wireless Technologies: The OpenAirInterface Approach“
Abstract: The development of 6G wireless technologies is rapidly advancing, with the 3rd Generation Partnership Project (3GPP) entering the pre-standardization phase and aiming to deliver the first specifications by 2028. This talk explores the OpenAirInterface (OAI) project, an open-source initiative that plays a crucial role in the evolution of 5G and future 6G networks. OAI provides a comprehensive implementation of 3GPP and O-RAN compliant networks, including Radio Access Network (RAN), Core Network (CN), and software-defined User Equipment (UE) components. This paper details the history and evolution of OAI, its licensing model, and the various projects under its umbrella, such as RAN, the CN, and the Operations, Administration and Maintenance (OAM) projects. It also highlights the development methodology, Continuous Integration/Continuous Delivery (CI/CD) processes, and end-to-end systems powered by OAI. Furthermore, the paper discusses the potential of OAI for 6G research, focusing on spectrum, reflective intelligent surfaces, and Artificial Intelligence (AI)/Machine Learning (ML) integration. The open-source approach of OAI is emphasized as essential for tackling the challenges of 6G, fostering community collaboration, and driving innovation in next-generation wireless technologies.
Presenter: Florian Kaltenberger is an Associate Professor in the Communication Systems department at EURECOM (Biot, France), a visiting professor at Northeastern University (Boston, MA, USA). He is also a special advisor to the board of the OpenAirInterface Software Alliance. Mr. Kaltenberger received his Diploma degree (Dipl.-Ing.) and his PhD both in Technical Mathematics from the Vienna University of Technology 2002 and 2007 respectively. He joined EURECOM in 2007 and has been working on the open-source project OpenAirInterface ever since then. Today he is coordinating the developments of the OAI radio access network project group, which delivered support for 5G non-standalone access in 2020 and for 5G standalone access in 2021. He also manages several research projects (industrial and academic) around the platform with special focus on massive and distributed multi-antenna systems, positioning and localization as well as non-terrestrial networks.
Invited Talk: “Distributing the “S” in SDR: radioconda and software management tools“
Abstract: One of the biggest hurdles to getting started in using software-defined radios is getting the software installed and working. In this talk, I will introduce the Radioconda distribution and installer, which builds on the cross-platform conda-forge software ecosystem to make it easier to install a growing set of SDR tools. I’ll describe why I think this is a powerful approach, and how you can start using it yourself and maybe contribute to the maintenance effort. I’ll also look to the future and explore how I see the landscape evolving with the next-generation of conda-based tools, namely Pixi. Finally, I’ll also touch a bit on software that I’ve been working on: the Digital RF data format used by MIT Haystack Observatory and beyond, and NVIDIA’s Holoscan which we’re using for the SpectrumX Mobile Experiment Platform (MEP).
Presenter: Dr. Ryan Volz is a Research Scientist at MIT Haystack Observatory with interests in signal processing, statistical estimation, and novel instrumentation applied particularly to radio science. His current projects include: implementation, analysis, and management for the Zephyr meteor radar network, a novel MIMO system designed to estimate the 3-D wind field in the upper atmosphere by way of meteor trail scattering; software and processing for the SpectrumX Mobile Experiment Platform (MEP), an RFSoC 4×2 and NVIDIA Jetson-based SDR-in-a-box designed for measuring RFI; and maintainance of Radioconda, a conda-based software radio distribution and installer.
Short Talk: “RFML Beyond Signal Classification: ML Signal Processing, Generative AI for Channel Modeling, and Learned Comms for 6G“
Abstract: Machine-learning based algorithms are slowly being adopted into RF signal processing chains. The main driver is that conventional signal processing algorithms of the past were derived under simplifying assumptions about things like linearity, noise, and interference, but these algorithms are only approximately optimal in the presence of more realistic effects (e.g., amplifier non-linearities, non-Gaussian interference statistics, etc.). Therefore, most conventional signal processing algorithms fall short of theoretical performance bounds while being practically very useful. In RF machine learning, algorithms in a signal processing chain are re-imagined as nonlinear input-output mappings with free parameters that are fit to the data. Individual learnable operations can be jointly optimized using end-to-end metrics, leading to a co-design of the entire signal processing chain for optimality without restrictions or assumptions on the kinds of channel models and impairments that can be used. The first examples of RF machine learning appeared in the literature about 8 years ago and were for modulation recognition and signal detection and classification; however, the field has advanced to other things such as end-to-end communications waveform design via machine learning, and generative AI applications for the RF domain are beginning to be explored. This tutorial presents an overview of a selection of topics in these areas, namely machine learning and generative AI for: signal classification, signal processing, and fully learned wireless communications waveforms.
Presenter: Dr. Bhattacharjea is the Director of Machine Learning at DeepSig and is leading his team in applying the latest advances in machine learning to the RF spectral domain. He is also an Adjunct Principal Research Engineer with the School of Electrical and Computer Engineering at Georgia Tech, where he conducts and publishes research in the areas of machine learning for communication systems. He has a passion for the pure and applied mathematics that underlie signal processing, electromagnetism, and machine learning. He has served as research faculty and taught at his alma mater, Georgia Tech, where he received his Ph.D. in Electrical Engineering in 2014.
Short Talk: “Adaptive and Explainable Machine Learning for Spectrum Sensing in Dynamic RF Environments“
Abstract: As software-defined radio (SDR) platforms advance to address increasingly congested and contested spectrum environments, there is a critical need for intelligent, adaptive, and explainable signal characterization techniques capable of operating in open-world and dynamic RF environments. This talk introduces a machine learning (ML) framework designed to enhance the adaptability, efficiency, and trustworthiness of spectrum sensing in dynamic wireless environments. Our approach integrates four key pillars: deep learning-based signal classification, incremental learning for continual adaptation, prototype learning for interpretable representations, and explainable ML (XML) to provide transparency into model decisions. Each component is designed to address core challenges faced in real-world SDR deployments, such as concept drift, emerging signal types, and the need for interpretable AI decisions in critical applications. This talk is especially relevant to researchers focused on intelligent radios, dynamic spectrum access, and trustworthy wireless AI systems. By unifying incremental learning and explainable AI in the SDR context, we highlight a path toward next-generation, mission-adaptive spectrum intelligence systems where learning is continual, models are interpretable, and decisions are resilient and actionable in real time.
Presenter: Dr. Ruolin Zhou is an Associate Professor in the Department of Electrical and Computer Engineering at the University of Massachusetts – Dartmouth. Her research focuses on software defined radio (SDR), AI/ML for wireless communications with a particular emphasis on spectrum sensing, sharing and management, cyber & electromagnetic spectrum (EMS) security, and hardware security. Her work has been funded by National Science Foundation (NSF), the Office of Naval Research (ONR), Air Force Research Laboratory (AFRL), Army Research Laboratory (ARL), and industry partners such as Lockheed Martin. She has received several notable awards including the 2024 IEEE Region 1 Outstanding Teaching in an IEEE Area Award, senior-level faculty research fellow of the ONR Summer Faculty Research Program in 2022 and 2023, the Best Team Award of the 2020-2021 AFRL SDR Beyond 5G University Challenge, and the Best Demo Award of the IEEE Global Communications Conference (GLOBECOM) in 2010. Dr. Zhou is currently serving as the 2025 Vice President for Technical Activities within the IEEE Reliability Society (RS), the RS liaison on IEEE Women in Engineering, a steering committee member of the IEEE Future Networks Technical Community (FNTC) and the IEEE Internet of Things Technical Community (IoT TC), and a co-chair of the IEEE Future Networks Entrepreneurs Mentorship program (FNEM).
Short Talk: “AI Applications in Black Hole Imaging with the Event Horizon Telescope“
Abstract: Black holes, a fundamental prediction of Einstein’s general relativity, are now recognized as ubiquitous in the universe and central to questions about the nature of space-time under strong gravity, the accretion (i.e., infall) of matter, the formation of powerful, collimated outflows known as “jets,” and their cosmic role in driving the evolution of stars and galaxies. The Event Horizon Telescope (EHT), an Earth-sized network of radio telescopes operating at 230 GHz (1.3 mm wavelength), has revolutionized studies of black hole physics at event-horizon scales. The EHT is renowned for capturing the first-ever images of black holes, which reached an estimated four billion people worldwide within just a month, transforming public perceptions of black holes and the universe and significantly shaping the scientific priorities of the community. The EHT computationally forms a planet-sized aperture using an intercontinental array of radio telescopes, enabling it to resolve these extremely compact objects. As a computational telescope, its performance critically depends on the quality of data processing algorithms, including computational imaging techniques. Algorithm development remains a key active area of research, driven by the rapidly growing need for larger-scale and more complex modeling of black holes, enabled by planned extensions. Rapid advancements in AI, particularly in accelerating Bayesian parameter inference and providing more expressive regularization for high-dimensional images than traditional hand-crafted regularizers, have driven the development of AI-powered algorithms for EHT data processing and physical interpretation. This talk will outline the ongoing development and applications of AI-based approaches in the EHT community, highlighting AI-enabled discoveries in astronomy.
Presenter: Kazunori Akiyama is a research scientist at the Massachusetts Institute of Technology (MIT) Haystack Observatory. He received his undergraduate degree in physics from Hokkaido University in 2010, followed by master’s and doctoral degrees in astronomy from the University of Tokyo in 2012 and 2015, respectively. After his Ph.D., he held a JSPS Overseas Postdoctoral Fellowship at Haystack in 2015 and a Jansky Fellowship at the National Radio Astronomy Observatory in 2017. He has been a research scientist at MIT since 2020. His research focuses on high-angular-resolution studies of supermassive black holes and active galactic nuclei using very long baseline interferometry (VLBI) and developing novel data processing and computational imaging algorithms for radio astronomy. Akiyama joined the Event Horizon Telescope (EHT) project in 2010, where he co-founded and co-led the computational imaging team responsible for the first-ever images of black holes. He now co-leads the next-generation EHT Algorithm & Inference Working Group and heads the Haystack team and the Japan Consortium for the Black Hole Explorer mission, a U.S.-led space VLBI concept extending the EHT to space. The awards he received include the Young Astronomer Award from the Astronomical Society of Japan (2020), the Young Scientists’ Prize from the Japan Ministry of Education, Culture, Sports, Science and Technology (2020), and the Breakthrough Prize in Fundamental Physics as a co-recipient (2019).
Fireside Chat Panel: “Software Radio and Wireless Communication Education“
Abstract: The past decade has witnessed significant advances in how wireless communications in taught in class. Software-defined radio technology, open-source software, the DIY/maker community, and numerous other factors have profoundly influenced the educational experience of undergraduate students in how they learn about wireless transmissions, communication systems engineering, and electromagnetic propagation. In this panel, we discuss with three experts in wireless education how this landscape has evolved over the past decade, its impact on the current generation of wireless innovators, problem solvers, and leaders, and their predictions on the next decade of wireless education.
Panelists: K. C. Kerby-Patel received the B.S., M.S., and Ph.D. degrees in electrical engineering from the University of Illinois at Urbana-Champaign, Champaign, IL, USA, in 2003, 2005, and 2009, respectively. From 2009 to 2014 she was a Lead Communications Engineer with the MITRE Corporation. She joined the Engineering faculty at the University of Massachusetts Boston in 2014 and is currently an Associate Professor there. She received a DARPA Young Faculty Award in 2015. Her research in applied electromagnetics addresses the intersection of antenna theory and microwave circuit techniques with new electromagnetic problems and applications.
Dr. Galahad M. B. Wernsing earned B.S. (2019), M.S. (2020), and Ph.D. (2024) degrees in Electrical and Computer Engineering from Worcester Polytechnic Institute. During the Covid lockdowns, Dr. Wernsing started Holy Grail Labs, a company focused on upgrading vintage automotive electronics, and has since grown the company to be a global leader in fuse box modernization. Dr. Wernsing’s research interests include wireless communications, novel radar systems, low-level computer security, and analog circuits.
Daniel Sheen, KC1EPN, received his B.S in Electrical Science and Engineering in 2019, and his M.Eng in Electrical Engineering and Computer Science in 2021, both from the Massachusetts Institute of Technology (MIT). He is currently pursuing a PhD at MIT, working with MIT Haystack Observatory and the Terahertz Integrated Electronics Group. Much of his free time during undergrad was spent upgrading and operating MIT’s amateur radio stations (W1MX and W1XM). Among his many projects was the initial hardware and software to enable use of the Green Building Radome for Earth Moon Earth (EME) communications and 1420 MHz radio astronomy, which was subsequently used to support remote teaching of radio astronomy experimental techniques by MIT Junior Lab (JLab) during the pandemic. During his master’s degree he continued working on antenna and radio system development at Haystack Observatory, where he designed the UHF phased array feed currently used at the Westford Radio Telescope. Following his master’s degree, he worked at Diversified Technologies inc. developing solid state microwave amplifier systems, before returning to MIT in the Fall of 2022. Since then, in addition to his thesis work, he helped coordinate the renovation of the radome and a complete replacement of the associated radio systems. He continues to support the use of the radome by JLab, including maintaining a dedicated fork of Haystack’s srt-py software and advising students directly working with the radios for more advanced projects.
Moderator: Alexander M. Wyglinski is the Associate Dean of Graduate Studies and Professor of Electrical and Computer Engineering at Worcester Polytechnic Institute (WPI), Worcester, Mass, USA, as well as the Director of the Wireless Innovation Laboratory at WPI. Dr. Wyglinski served as the President of the IEEE Vehicular Technology Society during 2018-2019. He received his B.Eng. and Ph.D. degrees in Electrical Engineering from McGill University, Montreal, Canada in 1999 and 2005, and his M.Sc.(Eng.) degree in Electrical Engineering from Queen’s University, Kingston, Canada in 2000. Dr. Wyglinski’s current research interests are in wireless communications, cognitive radio, machine learning for wireless systems, software defined radio prototyping, connected and autonomous vehicles, and dynamic spectrum sensing. Dr. Wyglinski has published over 50 peer-reviewed journal papers, over 135 peer-reviewed conference papers, and 3 textbooks throughout his academic career. He has been sponsored by both government agencies and industry such as the National Science Foundation, Office of Naval Research, Air Force Research Laboratory, MIT Lincoln Laboratory, Toyota InfoTechnology Center USA, Verizon, MITRE, Analog Devices, and Raytheon.
Tutorial Information
Tutorial: “FPGA Programming on the USRP with the RFNoC Framework“
Abstract: This workshop provides a tutorial on the RFNoC framework, including a discussion on its design and capabilities, demonstrations of several practical examples, and a walk-through of implementing a user-defined RFNoC Block and integrating it into both UHD and GNU Radio. The RFNoC (RF Network-on-Chip) framework is the FPGA architecture used in USRP devices, specifically the E310, E312, E320, X300, X310, N300, N310, N320, N321, X410. The RFNoC framework enables users to program the USRP FPGA, and facilitates the integration of custom FPGA-based algorithms into the signal processing chain of the USRP radio. Users can create modular, FPGA-accelerated SDR applications by chaining multiple RFNoC Blocks together and integrating them into both C++ and Python programs using the UHD API, and into GNU Radio flowgraphs. Attendees should gain a practical understanding of how to use the RFNoC framework to implement custom FPGA processing on the USRP radio platform.
Presenter: Neel Pandeya is a Principal SDR Engineer and Group Manager at National Instruments in Austin, Texas, USA. His background and interests are in open-source software development, kernel and embedded software development, wireless communications, 4G/LTE and 5G/NR networks, DSP and signal processing, FPGA programming, and software-defined radio (SDR). He has previous technical management experience and university teaching experience, and formerly held a TS/SCI government security clearance. He is a co-founder and co-organizer of the New England Workshop for SDR (NEWSDR), and is a co-organizer of the GNU Radio Conference (GRCon) as well as the 5G Workshop at IEEE MILCOM. He holds a Bachelor’s Degree in Electrical Engineering (BSEE) from Worcester Polytechnic Institute (WPI), and a Master’s Degree in Electrical Engineering (MSEE) from Northeastern University (NEU), and is a member of IEEE and Eta Kappa Nu (HKN). He has an Amateur Radio License, and is aspiring to obtain a private pilot license.
Tutorial: “Innovation and Prototyping in O-RAN using Open-Source Testbeds“
Abstract: This tutorial starts with a brief introduction to the Open Radio Access Network (O-RAN) paradigm and its role in the Next Generation (NextG) cellular networks that are expected to be programmable, resilient, cloud-native, agile, and intelligent. The OpenAirInterface (OAI) software is widely known for providing an end-to-end 3GPP standard-compliant open-source 5G NR protocol stack. The ability to run on general-purpose computing hardware along with off-the-shelf software-defined radios (SDR) and commercial radio units (RUs) made OAI a key enabler for experimentation in O-RAN. We then present the role of OAI in standards-driven research, prototyping, and interoperability testing of multi-vendor networks in O-RAN. Research use cases in spectrum sharing, sensing and localization, and autonomous flying 5G networks are presented. The tutorial then runs into a hands-on session where the participants will be guided in setting up an end-to-end 5G network in their laptops in RF simulator mode (a mode that does not involve over-the-air transmission). Through several exercises, the audience will gain skills in understanding the logs, debugging, and changing network configuration parameters. For the audience attending the hands-on session, it is strongly encouraged to set up a virtual machine (VM) and install OAI prior to the tutorial by following the instructions provided in the following link: https://github.com/RajeevGa/ieee_ants2024_oai_tutorial)
Presenter: Rajeev Gangula is a Research Assistant Professor at the Institute for the Wireless Internet of Things, Northeastern University, Boston. He obtained his M.Tech degree from Indian Institute of Technology, Guwahati, and Ph.D. degrees from Télécom ParisTech (Eurecom), France. After his Ph.D., he held research engineer positions at Sequans Communications, Paris, and Eurecom, Biot, France. While working as a research engineer at Eurecom, he was leading the prototyping activity in developing autonomous aerial cellular relay drones capable of providing flexible and enhanced (LTE, 5G) connectivity to mobile users. His current research interests include positioning and sensing in 5G and beyond networks, connected robotics, spectrum sharing, and prototyping with software-defined radios.
Tutorial: “Pi-Radio: Experimentation in the FR3 bands“
Abstract: Building an SDR is a boatload of fun. It requires you to get your hands dirty with many tasks, spread across different areas. For example, you will need to build simple circuits using bread-boards, play with evaluation kits, design PCBs, perform HFSS simulations of antennas, program FPGAs, write device drivers, and so on. In this tutorial, we will explore these aspects in greater detail. You will learn the basics of how to design, manufacture, and test your own SDR.
Presenter: Aditya Dhananjay received the Ph.D. degree from the Courant Institute of Mathematical Sciences, New York University (NYU), New York, NY, USA.,He was involved in mesh radio routing and resource allocation protocols, data communication over cellular voice channels, low-cost wireless rural connectivity, OFDM equalization, and phase noise mitigation in mm-wave networks. He currently holds a post-doctoral position with NYU Wireless and is the co-founder of Pi-Radio. He has developed and supervised much of the mm-wave experimental work at the center. He has authored several refereed articles (including at SIGCOMM and MobiCom). He holds one patent and two provisional patents in the millimeter-wave space.
Posters
P1: “Sniffing CANBUS Signals using Inductive Sensing and Software-Defined Radios”
Authors: Srivatsan Mukunthraj, Xiaoyan Sun, Alexander M. Wyglinski
Affiliation: Worcester Polytechnic Institute
Abstract: This project aims to bring to light the possibility of using inductive sensing to sniff messages from a vehicle’s Controller Area Network (CAN) without ever having a physical connection to the system. This is achieved by firstly creating a custom vehicle test-bench to simulate the CAN system and then using an inductive probe to measure the electromagnetic fields emitted by the communication wires. With the use of a Software-Defined Radio (SDR) technology and Python signal processing libraries, this report evaluates the effectiveness of this new wireless inductive sensor attack and demonstrates that signals traveling through the CAN network can be eavesdropped on by unauthorized third parties.
P2: “On Generative AI for Software-Defined Radio Education“
Authors: Samuel Forero Miranda, Alexander M. Wyglinski
Affiliation: Worcester Polytechnic Institute
Abstract: ECE 331X: Software Radio Design was created to make Software-Defined Radio (SDR) education more accessible to students with limited experience in signal processing or programming. The course was structured around five hands-on milestones designed to progressively build theoretical and practical skills. To further lower barriers to entry and support diverse learning styles, generative AI tools like ChatGPT were introduced as optional aids. This section highlights each module, how students used AI, and the observed impact on learning outcomes.
P3: “Emergent Semantic Communication: Principles and ORAN Integration Challenges“
Authors: Christo K Thomas and Walid Saad
Affiliation: Virginia Tech
Abstract: Next-generation communication systems (e.g., 6G) aim to enable transformative applications like the metaverse, digital twins, and smart environments, requiring seamless integration of physical, digital, and virtual worlds. However, traditional wireless techniques using spatial, temporal, and frequency resources fall short in meeting the demands for near-zero latency, trust, and ultra-synchronization. While AI-native networks show promise, current data-driven wireless systems face challenges such as limited interpretability, centralized training, poor generalization, and high computational cost. To overcome these challenges, we introduce Emergent Semantic Communications (ESC)—a paradigm shift in AI-native wireless systems wherein the objective is to communicate the meaning present in the data rather than raw information that consumes huge bandwidth. In particular, ESC leverages generalizable AI and signaling games to develop semantic languages that convey semantics defined as causal structures (defined as cause and effect relations) present in the data. We provide novel analytical results including semantic information, bounds on average bit length for semantic transmission demonstrating reduction in bandwidth usage and semantic error probability measures. Furthermore, we will discuss the key challenges and benefits of integrating ESC into the ORAN framework. This includes examining its implications across various layers, such as semantics-aware scheduling and resource allocation, semantics-aware QoS management, and generalizable physical layer design.
P4: “Multi-Modality Sensing in Millimeter Wave Beamforming for Connected Vehicles Using Deep Learning“
Authors: Muhammad Baqer Mollah
Affiliation: University of Massachusetts Dartmouth
Abstract: This poster presents a deep learning-based solution for utilizing the multi-modality sensing data for predicting the optimal beams having sufficient mmWave received powers so that the best V2I and V2V line-of-sight links can be ensured proactively. The proposed solution has been tested on real-world measured mmWave sensing and communication data, and the results show that it can achieve up to 98.19% accuracies while predicting top-13 beams. Correspondingly, when compared to existing been sweeping approach, the beam sweeping searching space and time overheads are greatly shortened roughly by 79.67% and 91.89%, respectively which confirm a promising solution for beamforming in mmWave enabled communications.
P5: “Adaptive Continuous-Time Neural Networks for SDR Channel Estimation“
Authors: Dasheng Zhang and Ruolin Zhou
Affiliation: University of Massachusetts Dartmouth
Abstract: Wireless communication signals are fundamentally continuous-time, yet most neural network models rely on discrete-time approximations, which struggle to capture the true temporal dynamics of rapidly varying channels. This poster presents a continuous-time modeling approach using Liquid Time-Constant (LTC) neural networks, which are designed to operate directly on continuous-time signals with dynamic, input-dependent state updates. Motivated by the limitations of traditional architectures in handling nonlinear, multipath, and time-varying conditions, our method enables real-time channel estimation with fewer parameters and improved stability. Experiments on digitally modulated signals over AWGN channels show that the LTC model achieves competitive bit error rate (BER) performance and faster convergence in moderate-to-high SNR regimes. The continuous formulation also mitigates gradient vanishing, making it more suitable for learning long-term dependencies in dynamic channels. This work highlights the potential of continuous-time neural networks as a new tool for adaptive, signal-aware SDR systems in future wireless networks.
P6: “AI/ML-enabled Dynamic Spectrum Surveillance – OTA Anomaly Detection and Localization“
Authors: Jin Feng Lin, Charles Montes, Eric Savage, Garret Magalhaes, Cam Popillo, Ruolin Zhou, and John Wu
Affiliation: University of Massachusetts Dartmouth
Abstract: With the increasing reliance on wireless signals for navigation and communication, threats like GPS spoofing and fake aircraft transmissions pose serious risks to safety and situational awareness. To address this, we aim to develop a dynamic spectrum surveillance system using USRP radios with up to eight antennas. Our system will detect and localize anomalous signals in real time. We compare traditional signal processing and machine learning approaches through over-the-air testing, to determine the most effective strategy for deployment in contested and civilian spectrum environments.
P7: “EDGES – Searching for the Signal from the First Stars“
Authors: Rigel Cappallo
Affiliation: MIT/Haystack
Abstract: There is a signature plastered across the entire sky that holds the key to understanding the formation of the very first stars in our universe. This signature is hidden within a cacophony of other signals; finding it is akin to detecting the flap of a hummingbird’s wings miles away in the middle of a hurricane. But it is not impossible. The EDGES experiment reported a detection of this signal for the first time with a paper in Nature in 2018 and is currently deploying instruments in remote locations across the globe in order to solidify and enhance the initial detection. In 2022, I was part of two separate three-man teams that deployed the EDGES system in the outback of Western Australia and on Devon Island, the largest uninhabited island in the world, located far north in the Canadian Arctic. More recently, we deployed a fully autonomous system for the 2024-2025 winter season in Adak, Alaska, an island in the middle of the Aleutian island chain.
P8: “Radio Astronomy Observations and Satellites Interference with an SDR Backend“
Authors: Samuel Thé, Frank Lind, Daniel Sheen, Aleks Pop Stefanja, and Ryan Volz
Affiliation: MIT Haystack Observatory
Abstract: Software Defined Radios (SDR) are widely used in radio astronomy, where progress in their design has enabled recording increasingly broader spectral bandwidths. With the surge of Radio Frequency Interference (RFI) sources in historically quiet parts of the spectrum, using such bandwidths requires however an increase of the instrument dynamic range. Observatories have traditionally been built in remote locations to provide isolation from man made noise. The growing number of mega-constellations of satellites poses a new challenge for such observatories. The increasing number of satellites in low-Earth orbit exposes previously secluded radio telescopes to communications signals many orders of magnitude stronger than the faint celestial signals of interest for radio astronomy. Such signals can distort the analog components of receivers, corrupting measurements over the entire receiver bandwidth. Even avoiding such extreme cases, the aggregate out-of-band emissions from mega-constellations have the potential to contaminate measurements. In this work, we present recent observations and simulations of the aggregated impact of satellites on our measurements with the 18.3m Westford telescope of the MIT Haystack Observatory. Additionally, we present the Mobile Experiment Platform (MEP) as a tool to help measure and characterize RFI.
P9: “Open-Source Software-Defined Harmonic Radar System to Track Honey Bee Foraging Behavior“
Authors: Diego Penaloza and Julio V. Urbina
Affiliation: Pennsylvania State University
Abstract: Honey bee foraging is a complex behavior involving thousands of individuals making decisions about where to collect pollen and nectar based on resource quality and distance to flowers. Direct observation is limited by the large colony size and long activity periods, highlighting the need for automated tracking tools that do not disrupt natural behavior. To address this, we developed an open-source harmonic radar system to track individual bees using lightweight non-linear transponders. The system is based on a USRP X310 software-defined radio, upgraded to transmit/receive in the X-band/Ku-band by implementing RF front ends for up/down conversion using commercial components. A 300 W solid-state amplifier was integrated to enable high-power pulse transmission, while phase coherence and time synchronization were achieved using an external FPGA and a 10 MHz reference clock with PPS. We present the system architecture and validation of sensitivity and range resolution enhancement through pseudorandom noise phase modulation with codes of length 1023, achieving up to 30 dB of compression gain using GNU Radio and Python. This system demonstrates the feasibility of using advanced SDR-based harmonic radar for non-invasive tracking of honey bee foraging, providing a scalable and open-source accessible tool for behavioral and ecological studies in natural environments.
P10: “LibIQ: Toward Real-Time Spectrum Classification in O-RAN dApps“
Authors: Noemi Giustini, Filippo Olimpieri, Andrea Lacava, Salvatore D’Oro, Tommaso Melodia, and Francesca Cuomo
Affiliation: Northeastern University
Abstract: The O-RAN architecture is transforming cellular networks by adopting Radio Access Network (RAN) softwarization and disaggregation concepts to enable data-driven monitoring and control of the network. Such management is enabled by RAN Intelligent Controllers, which facilitate near-real-time and non-real-time network control through xApps and rApps. However, they face limitations, including latency overhead in data exchange between the RAN and RIC, restricting real-time monitoring, and the inability to access user plain data due to privacy and security constraints. In this paper, we leverage dApps deployed within the RAN to enable real-time RF spectrum classification using LibIQ, a novel library that processes I/Q time-series data for efficient spectrum monitoring, visualization, and RF signals classification via a Convolutional Neural Network (CNN). To achieve accurate spectrum analysis, we created an extensive dataset of time-series-based I/Q samples, representing distinct signal types captured using a custom dApp running on a 5G deployment over the Colosseum network emulator and an Over-The-Air SDR-based testbed. We evaluate our model by deploying LibIQ in heterogeneous scenarios with varying center frequencies, time windows, and external RF signals. The model classifies the I/Q samples, achieving an average accuracy of approximately 97.8% in identifying signal types across all scenarios
On-Campus Parking
Online registrants were sent earlier this week a visitor parking pass that must be clearly displayed on the dashboard of the vehicle (any other vehicle without a visitor parking pass or the pass is not clearly presented will be ticketed). All attendees should park in the main parking area (not the visitor parking spots) of the Park Avenue garage located at 151 Salisbury St, Worcester, MA (see map below).
Sponsors/Exhibitors
 |  |
 |
If your company is interested in participating in NEWSDR 2025, please contact us at gr-newsdr-info@wpi.edu for additional information.
Questions or comments? Please feel free to contact us at gr-newsdr-info@wpi.edu.