News

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.

Rome Sentinel

Principal staff members Dr. Andrew Drozd and Dr. Jithin Jagannath, of ANDRO Computational Solutions, were recently awarded honors of distinction by the Institute of Electrical and Electronics Engineers (IEEE) for their years of service, contributing to technological excellence, and advancing innovation.

Drozd is the president of ANDRO, a scientific research and development business established 1994. Jagannath is the chief scientist of technology and director of ANDRO’s Marconi-Rosenblatt Artificial Intelligence and Machine Learning Innovation Lab.

Drozd’s credentials include professional engineering certifications from the international Association of Radio and Telecommunications Engineers (iNARTE); his past presidency of the IEEE Society on Electromagnetic Compatibility (EMC-S); past chairmanship of the IEEE EMC-S Standards Development and Education Committee; current membership on the FCC’s Communications, Security, Reliability, Interoperability Council (CSRIC VIII); membership in the Alpha Gamma Omicron Chapter of Kappa Delta Pi Honor Society in Scientific Education; chairmanship of the Project Fibonacci Foundation, Inc.; and as a 2019 inductee in the Rome Academy of Sciences Hall of Fame.

Jagannath was nominated by the IEEE Mohawk Valley Section for the Region 1 Award in Technical Innovation in the Industry/Government category. The IEEE Region 1 Board of Governors recently announced Jagannath as the 2021 recipient with the citation, “For innovative contributions in machine learning techniques for the wireless domain.”

Jagannath was recognized for scientific research leading to innovative and advanced technologies developed under several highly competitive, federally-funded projects over the past several years.

“ANDRO encourages membership and active participation in all aspects of the IEEE locally, regionally, and globally and is a strong supporter of its mission and vision to benefit society through science, technology, and engineering,” stated Drozd.

Read the full story here

A Rome-based startup subsidiary is aiming to improve the quality of life for individuals suffering from chronic back injuries and has received a patent for its spinal medical device.

AcceliPHI, LLC utilizes office and laboratory space at ANDRO Computational Solutions LLC at the Beeches Business Park. The subsidiary hopes to expand its prototyping labs within the coming 12-18 months.

“Over half of the United States population suffers from chronic back injuries causing pain and discomfort, including a considerable and growing population of patients with scoliosis,” stated AcceliPHi’s lead and primary inventor Evan Drozd.

“Although surgical and other therapeutic interventions can work, in many cases, such treatments can be limited or provide short term benefits, calling for new interventions to be examined,” added Drozd.

The patented prototype is in the process of being designed, fabricated, and tested in wearable form in cooperation with AcceliPHI’s medical and industry partners, offering a novel alternative for orthopedic surgeons, physical and occupational therapists, chiropractors, and other health specialists to help improve the quality of life for their patients, the company said in a release.

AcceliPHI is also in the process of exploring U.S. Food and Drug Administration approval, including conducting clinical trials, for future device distribution and sales.

According to Drozd, AcceliPHI will next study how the same technology, working in conjunction with biometric sensors, could be used in wearable form to treat other injury sites such as neck and limb joints, to augment existing therapeutic methods.

“Our five-year plan is to develop and deliver new wearables to market with the goal of expanding the versatility of options and alternatives to invasive
treatments and place more tools in the hands of health professionals to improve patient outcomes post-surgery or after other therapies have been exhausted,” Drozd said.

“The patient is our number-one priority, and we want to work with medical practitioners to understand how to optimize the treatment of patients’ pain points,” Drozd added.

AcceliPHI is also researching ways to scale the device for possible implantation using minimally invasive surgery to treat local vertebral, joint, or other body sites,” Drozd said.

Read the full story here

By Eric Reinhardt (ereinhardt@cnybj.com)

ROME, N.Y. — ANDRO Computational Solutions, LLC of Rome will use two new federal contracts — worth $150,000 each in their first phase — for work on new methods for enhancing wireless security.

The awards were based on research in wireless communications led by ANDRO’s Marconi-Rosenblatt artificial intelligence and machine learning (AI/ML) innovation lab, the firm said in a news release.

Established in 1994, ANDRO provides research, engineering, and technical services to defense and commercial industries. It’s currently headquartered in about a 20,000-square-foot space in the Beeches Business Park in Rome and had additional offices in Syracuse and Dayton, Ohio.

About the contracts

The U.S. Department of Homeland Security’s (DHS) science and technology (S&T) directorate awarded a phase I Small Business Innovation Research (SBIR) contract to ANDRO called Project Wi5G.

The project seeks to sustain “authenticated, secure” spectrum band sharing for Wi-Fi 6/6E and 5G cellular systems co-located and operating simultaneously within restricted federal networks. Wi-Fi 6/6E and 5G are the latest wireless-equipment standards for local broadband Internet and cellular access.

“The primary idea of authenticated spectrum sharing is to permit access to the Wi-Fi 6/6E and 5G radio frequency (RF) bands only to authorized users to protect privacy within a restricted federal network,” Jithin Jagannath, director of the AI/ML, said.

The phase I project was awarded $150,000 under the DHS SBIR program to conduct proof-of-concept research over a five-month period to address specific homeland-security technology needs, with second-phase funding for prototype development anticipated to be up to $750,000, ANDRO said.

“Investing in private sector innovation is a key factor in helping DHS keep pace with emerging threats and security challenges facing our nation,” Kathryn Coulter Mitchell, DHS senior official performing the duties of the undersecretary for science and technology, said. “The DHS SBIR Program provides the opportunity for S&T to partner with small businesses in advancing unique and innovative capabilities that address complex DHS technology needs.”

A second SBIR phase I award from the U.S. Department of Defense valued at $150,000 called DeepeRFind, seeks to develop new methods of enhancing the sensitivity of RF (radio frequency) signal fingerprinting techniques using deep learning — a machine-learning related approach. The fingerprinting technique enhances wireless security by enabling the accurate detection and classification of wireless signals.

“DeepeRFind has a wide range of applications in both tactical and commercial environments, considering the proliferation of wireless Internet of Things (IoT) devices,” Andrew Drozd, president of ANDRO, said.

The second phase funding for prototype development is anticipated to about $1 million.

“I am proud of ANDRO’s Marconi-Rosenblatt Artificial Intelligence and Machine Learning (AI/ML) Innovation Lab team for their accomplishments on these two fronts,” Drozd added.

He further mentioned that these opportunities will “considerably add” to the company’s portfolio of technologies and products and contribute to its plans for growth and near-term hiring needs, per the firm’s release.

Read the full story here