About 24 results
(0.09 seconds)
The Technology: Computationally efficient and scalable signal processing algorithm. This technology is a trainable algorithm for optimization-based template search that can be used to efficiently detect and recover signals from noisy high dimensional data. Unmet Need: Scalable algorithm to detect signals from noisy measurements. Accurate failure prediction in power grid components and other utilities. Uses state-of-the-art machine learning algorithms for predicting the risk of failures and prioritizing maintenance tasks. As a result, a need exists for proactive and predictive maintenance programs that can utilize existing data resources for electrical grid reliability. This technology is a semi-blind algorithm for detecting signals without channel-state information in multi-user hybrid massive multiple-input multiple-output (MIMO) systems that can be used for 5G broadband networks. This constraint could be overcome by adopting a hybrid architecture or using low-resolution ADCs, but both methods require large training overhead in their signal channel estimation algorithms. The matrix completion problem is solved using two iterative algorithms: regularized alternating least squares and bilinear generalized approximate message passing. 
