News

The publication by Dr. Jithin Jagannath, Nickolas Polosky, and Anu Jagannath of ANDRO’s Marconi-Rosenblatt AI/ML Innovation Lab written in cooperation with Dr. Francesco Restuccia and Dr. Tommaso Melodia of Institute for the Wireless Internet of Things, Northeastern University among the top-cited article of the Ad Hoc Networks (Elsevier) Journal over the past three years. The paper, ‘Machine learning for wireless communications in the Internet of Things: A comprehensive survey’, was published in October 2019.

Congratulations to the Marconi-Rosenblatt AI/ML Innovation Lab team on this incredible accomplishment!

If interested, please find the article here https://www.androcs.com/wp/wp-content/uploads/2019/10/Jagannath19ADH_ML.pdf

Dr. Andy Drozd, CEO of ANDRO Computational Solutions, LLC, successfully completed Round 2: Signals of the Pulse Accelerator that kicked off September 9, 2021. Pulse is designed to help emerging technology companies accelerate growth and development that supports the public safety and first responder sectors. Working together in a collaborative program, selected participants engaged directly with specialists and experts from business, technology, and public safety to develop a plan for the commercialization of their solution.

This 12-week virtual program, also completed by Tim Woods and Fred Frantz of ANDRO, has been honed by implementers with over 10 years of experience accelerating technology-based businesses.

Participants receive over 50 hours of ongoing strategic consulting and market research to help validate existing target markets, expanding understanding, and uncovering new opportunities. The businesses worked with hand-picked, highly experienced specialists and subject matter experts who are active in their field.

Learn more here Welcome to PULSE Accelerator | Round 2: Signal (thepulseaccelerator.com)

On 1/8/22, Mr. Nicholas Polosky presented his work titled, “Machine Learning Subsystem for Autonomous Collision Avoidance on a small UAS with Embedded GPU” at IEEE International Workshop on Communication and Networking for Swarms Robotics (Robocom) 2022.

In this work, ANDRO’s Marconi-Rosenblatt AI/ML Innovation Lab introduced and demonstrated MR-iFLY, a framework that combines the strengths of traditional approaches and machine learning for autonomous collision avoidance for sUAS with minimal sensors. This is part of Navy SBIR Phase II work that is being done at ANDRO’s MR Lab.

Read the full paper here

ANDRO Computational Solutions, LLC is proud to announce that Anu Jagannath, Senior Scientist and Co-Director of the Marconi-Rosenblatt AI/ML Innovation Lab, has been elevated to an IEEE Senior Member level. This is a very significant accomplishment.  Senior Member is the highest grade for which IEEE members can apply or be nominated.  Senior Membership grade is held by only 8% of IEEE’s approximately 428,000 members.  Elevation to this grade requires extensive experience and reflects professional maturity and documented achievements of significance.

Anu Jagannath and Dr. Jithin Jagannath, leaders of the Marconi-Rosenblatt AI/ML Laboratory at ANDRO, had their article Dataset for Modulation Classification and Signal Type Classification for Multi-Task and Single Task Learning accepted to Elsevier Journal on Computer Networks.

Abstract

Wireless signal characterization is a growing area of research and an essential tool to enable spectrum monitoring, tactical signal recognition, spectrum management, signal authentication for secure communication, and so on. Recent years have witnessed several deep neural network models to perform single task signal characterization such as radio fingerprinting for emitter identification, automatic modulation classification, spectrum sharing, etc. However, with the emergence of 5G and the prospects of beyond 5G communication, there has been an increased deployment of edge devices that requires lightweight neural network models to perform signal characterization. To this end, a multi-task learning model that can perform multiple signal characterization tasks with a single neural network model has been proposed. However, due to the novel nature of multi-task learning as applied to signal characterization, there is a lack of a corresponding dataset with multiple labels for each waveform. In this paper, we openly share a synthetic wireless waveforms dataset suited for modulation recognition and wireless signal (protocol) classification tasks separately as well as jointly. The waveforms comprise radar and communication waveforms generated with GNU Radio to represent a heterogeneous wireless environment.

Read the full article here

RadarCommDataset: Radar & Communication Signal and Modulation Classification Dataset

A. Jagannath, J.Jagannath, “Dataset for Modulation Classification and Signal Type Classification for Multi-task and Single Task Learning”, Computer Networks (Elsevier), 2021.