• What we'll do
Go beyond working with public datasets and enter the realm of Intelligent Multi-Sensor Analytics (IMSA). In the first half of this presentation, we’ll introduce concepts and methods for using deep learning in multi-sensor systems and applications. There are many resources and examples available for learning how to leverage deep learning with public datasets. However, few resources exist to demonstrate how to combine and use these techniques to process multi-sensor data. We will introduce some examples of using deep learning to process radio frequency (RF) signals, intelligent video analytics (IVA) from traffic cameras, and more. We'll also introduce methods for adapting existing deep learning frameworks for multiple sensor signal types (for example, RF, video, and radar). We'll share examples of leveraging IMSA in smart city, telecommunications, and security applications.
During the second half of the presentation, we will introduce new concepts and algorithms that apply deep learning specifically to radio frequency (RF) data to advance the state of the art in signal processing and digital communications. With the ubiquity of wireless devices, the crowded RF spectrum poses challenges for cognitive radio and spectral monitoring applications. Furthermore, the RF modality presents unique processing challenges due to the complex-valued data representation, large data rates, and unique temporal structure. We'll present innovative deep learning architectures to address these challenges, which are informed by the latest academic research and our extensive experience building RF processing solutions. We'll also outline various strategies for pre-processing RF data to create feature-rich representations that can significantly improve performance of deep learning approaches in this domain. We'll discuss various use-cases for RF processing engines powered by deep learning that have direct applications to telecommunications, spectral monitoring, and the Internet of Things.
David Ohm, PhD is president and co-founder of KickView Corporation and has extensive experience developing innovative capabilities combining of sensor signal processing and deep learning. KickView is a Denver based company creating intelligent processing solutions that automate large scale sensor processing tasks. KickView delivers intelligent multi-sensor analytics solutions at the edge of the network for smart city, security and telecommunications applications. Our intelligent multi-sensor analytics (IMSA) software platform provides customers with greater levels of automation, understanding and operational efficiency.
Krishna Karra is a research engineer at KickView Corporation. He has extensive experience with software-defined radios, signal processing, and deep learning. He published a paper at IEEE DySpan 2017 Battle of the ModRecs hosted by DARPA, demonstrating a deep learning technique to perform blind modulation recognition of communications signals. Krish
• What to bring
Yourselves! Enjoy the food, drinks, education, and networking!
• Important to know