DeepSig Opens OmniSIG Hub for AI Radio Models
DeepSig, a leading company in AI for wireless communications, has launched the OmniSIG Model Hub, a new repository for AI models focused on radio systems.
The OmniSIG Model Hub is designed to support models that power DeepSig’s OmniSIG Engine. This hub serves as a centralized location where operators, developers, and researchers can store, manage, and retrieve both pre-trained and customized AI models. The OmniSIG Engine is known for its capability to detect and identify RF signals, enabling near-real-time, spectrum-aware reporting of anomalies, changes, and threats in radio frequency (RF) systems.
Extensive Model Collection
The repository already boasts numerous models that DeepSig has meticulously developed, tested, and validated. Users can now access OmniSIG capabilities beyond the standard models, including those for specific signal types such as push-to-talk radios and commercial drone signals. The hub facilitates easy model search based on criteria like signal type or frequency range, and offers a secure environment for managing and sharing both pre-trained and custom models.
Community Collaboration
A significant feature of the OmniSIG Model Hub is its community collaboration aspect. DeepSig believes this will greatly accelerate development, reduce training costs, and allow users to focus on fine-tuning models for particular needs.
“By offering a central model repository, we accelerate the ability of users to leverage powerful deep learning-driven AI and ML spectrum sensing with new signals and bands. This enables the development of spectrum-aware systems and applications more quickly, without the need to build, curate, and train their own models for various use cases. In the future, we envision DeepSig’s Model Hub extending to vetted OmniPHY AI models and collaboration for 5G, 6G, and RAN Digital Twin applications,” stated Tim O’Shea, CTO of DeepSig.
Support from NTIA
DeepSig was among the first recipients of a grant from the National Telecommunications and Information Administration’s Public Wireless Supply Chain Innovation Fund. This grant has bolstered the company's research and development efforts related to its generative AI and tools for modeling and measuring the wireless environment under real-world conditions, with a focus on Open RAN applicability.
