OmniSIG™ Sensor

The OmniSIG sensor provides a new class of RF sensing and awareness using DeepSig’s pioneering application of Artificial Intelligence (AI) to radio systems. Going beyond the capabilities of existing spectrum monitoring solutions, OmniSIG is able to not only detect and classify signals, but also understand the spectrum environment to inform contextual analysis and decision making. Compared to traditional approaches, OmniSIG provides higher sensitivity and accuracy, is more robust to harsh impairments and dynamic spectrum environments, and requires less computational resources and dynamic range allowing for an order of magnitude improvement in speed and device requirements. The OmniSIG software can be deployed and scaled on a wide range of target devices ranging from low-SWaP mobile and embedded systems, to mobile personal computers, to cloud and datacenter environments. It provides a web-based UI as well as an open low-latency streaming interface and control API for seamless integration into customer systems and applications.

Capabilities

The OmniSIG sensor is able to perform detection and classification of RF emissions across very large bandwidths of spectrum on the order of milliseconds, giving it the ability to report anomalies, changes, or threats in near real-time. It works with both wide- and narrow-band signals, and delivers accurate results for highly dynamic signals and within harsh or contested environments. Detection and recognition has been validated across a wide range of signal types, including numerous QAM, PAM, FSK, analog single carrier modulations, multi-carrier modulation schemes, cellular and infrastructure signals (e.g., GSM, LTE, CDMA2000, WCDMA, WiMAX), ISM-band signals (e.g., WiFi, BlueTooth), and mobile radio services (e.g., P25, GMR, PTT), and can be readily extended to include additional signals and protocols based on customer requirements and applications. It is robust to interference, both intentional and unintentional, and to other impairments including those caused by receiver hardware.

Deploying with OMNISIG

The OmniSIG sensor is a software product that customers can integrate into their own systems or third-party platforms. The OmniSIG software is highly flexible, and can be targeted to a wide variety of processing platforms and elements. It supports numerous both standard and custom radio interfaces, and can be easily deployed, scaled and updated using containerization such as Docker. We have worked with numerous customers to help identify and configure off-the shelf hardware items which can host the software accommodating existing software radio receivers and compute platforms.

The OmniSIG software is typically deployed on a general purpose processor such as an x86 or ARM core, and can accelerate core signal processing throughput and efficiency using Graphics Processing Units (GPUs) including integrated NVIDIA Tegra cores or discrete GPU cards, Tensor and Vector processing accelerators, and FPGA resources. The OmniSIG sensor typically operates in a streaming fashion, ingesting radio samples from a radio receiver interface, such as UHD or standardized packet formats like VITA-49. The web-based user interface can be used from any device with a browser, including mobile handsets, or alternatively controlled over ZMQ or WebSocket APIs, and finally the OmniSIG software provides a near real time stream of output inference metadata in JSON or other form to help provide visibility, analytics, and rapid notification of spectrum events.

Theory of Operation

DeepSig’s revolutionary approach to signal processing applies machine learning directly to time-series radio samples and channel measurements allowing it to learn from data. By creating algorithms that learn from raw signal data and effects, DeepSig’s systems achieve significantly better performance than traditional simplified analytic models or purely feature-based methods.

Our approach allows us to optimize the system as a whole for a particular set of performance requirements rather than optimizing individual components, as is the practice in existing methodologies. This allows us to rapidly adapt to new data and signatures, obtain computationally efficient inference engines and account for a wide range of effects and environments quickly.

Performance

The sensing techniques used within the OmniSIG sensor have demonstrated an improvement of 4 to 10 dB higher sensitivity than existing state-of-the-art methods in many cases. In some instances, it can provide 10x or higher reductions in computational complexity and throughput through reduced sample precision & dynamic range, increased parallelism, and algorithmic efficiency enabling reductions in antenna size and both processor and receiver expenses. OmniSIG also produces accurate sensing results with substantially reduced data requirements and dwell times, providing further power reductions and throughput increases on equivalent processors and allowing for more rapid scanning and detection. Sensing can be easily parallelized, scaled to application needs, and deployed on everything from cloud compute clusters to mobile ARM processors.

inquiries

To learn more about using OmniSIG in your applications, please contact us!