By 
On August 3, Herndon, VA-based Expedition Technology (EXP), a leader in the development and deployment of novel solutions supporting the defense and intelligence communities, announced it recently received three small business innovation research (SBIR) awards from the U.S. Army and the U.S. Navy’s Office of Naval Research. Each of these Phase I SBIR engagements leverages EXP’s domain and subject matter expertise to explore the identification and implementation of solutions that use leading edge technologies like artificial intelligence (AI) and machine learning (ML) to improve communications and signal processing performance in the field.
The electromagnetic spectrum on today’s battlefield includes emissions from U.S. and allied forces, enemy forces, and civilian telecommunications infrastructure. This environment requires the ability to rapidly scan large swaths of the radio frequency (RF) spectrum and automatically characterize emissions by frequency and modulation type. The current process relies on libraries and lookup tables, a linear approach unable to meet performance expectations. Under its “AI/ML for RF Modulation Recognition” SBIR topic, the Army has tasked EXP to demonstrate the application of AI and ML techniques to signal modulation and recognition to identify threat signals of interest in near-real-time.
RF spectrum use varies as a function of time, space, and frequency, resulting in a highly dynamic environment that challenges traditional methods of spectrum monitoring and evaluation and makes it difficult to detect anomalous spectrum use. Most activity, however, is routine and potentially predictable, providing an opportunity for limited available resources to focus attention on new or unusual features. The Office of Naval Research has engaged EXP via the “RF Spectrum Patterns of Life” SBIR topic to develop an automated system that detects, characterizes, and learns RF emitter behaviors and patterns of life to separate the novel and unexpected from the normal across a wide range of signal types.
The increasing military use of highly adaptive transmit signals means receivers need to respond to an unpredicted range of pulsed signals. Unfortunately, by the time the signal has been detected and characterized to be of interest, the data samples may no longer be present or available for further analysis. A forensic memory system offers a way to look back in time and access the signal data, but the cost and complexity of current options and the resultant architectures are prohibitive to apply across the full spectrum. Through its “Forensic Memory for Self-Cued, Data-Thinning Receivers” SBIR topic, the Office of Naval Research has selected EXP to develop a practical solution that doesn’t require massive RAM, cost, or power consumption to operate. To meet this objective, the EXP solution will capture and hold the digital representation of the entire spectrum long enough to extract the data associated with detected signals and cue digital signal processors to perform deeper analysis.
“As the communications spectrum gets more crowded, complex, dynamic, and adaptive, analyzing and characterizing signals to identify and respond to threats in an accurate and timely fashion becomes increasingly challenging. Legacy hardware and software solutions either aren’t up to the task, perform too slowly, or cost too much, placing missions and lives at risk,” said Marc Harlacher, EXP’s president and CEO. “We believe next generation solutions powered by AI, ML, and other technologies can produce improved outcomes through pattern recognition, data reduction, and automation to optimize resource utilization and detect and resolve threats and anomalies more effectively. We look forward to demonstrating this successfully in the lab and ultimately on Army and Navy Programs of Record.”
Source: Expedition Technology
Help IC News continue to bring you breaking news from across the IC and IC contracting landscape. Join our paid subscribers today.
