Explore how Bayesian optimization enhances signal processing applications by providing efficient algorithm design solutions in the signal processing toolbox.

Inspired by the capabilities of transformer models, we introduce a novel method named Multivariate Time-Series Imputation with Transformers (MTSIT). This entails an unsupervised autoencoder model featuring a transformer encoder, leveraging unlabeled observed data for simultaneous reconstruction and imputation of multivariate time-series.

Our method overcomes 3D underwater imaging challenges by offering high-frame-rate video 3D imaging (>100 fps), providing uncertainty measures for estimates, and extending applicability to various obscurant media imaging.

Pretrained audio neural networks (PANNs) are trained on 5800 hours of AudioSet data that can be used to recognize hundreds of sound types in the natural world.

Focus stacking is an effective approach to extending the depth of field of a camera, yet is challenging with regard to 1) controlling focal planes in forming a stack and 2) fusing the focal stack into composites free from defocusing, i.e., all-in-focus. We propose a deep learning all-in-focus imaging pipeline as a novel solution for focus stacking.

Addressing underwater image challenges, our method MLLE enhances color, contrast, and details efficiently. Outperforming competitors, it processes 1024×1024×3 images in under 1s on a single CPU. Experiments show improved underwater image segmentation, keypoint detection, and saliency detection.

Beamforming is a widely used signal processing technique to steer, shape, and focus an electromagnetic wave using an array of sensors toward a desired direction.

Millimeter wave (mmWave) communications provide a promising solution to meet the proliferating demand for high data rate because of large bandwidth. The current “boomingly” deployed fifth generation communication system (5G) has not actually touched the dominant frequency band of mmWave and thus can hardly enjoy its merit on dramatically boosting transmission rate, which motivates us to conduct research on the ultimate implementation of mmWave communications.

A coarse-to-fine SR CNN (CFSRCNN) consisting of a stack of feature extraction blocks (FEBs), an enhancement block (EB), a construction block (CB) and, a feature refinement block (FRB) is proposed to learn a robust SR model.

To handle the various types of tasks in the upcoming cellular services, we can design the system with both cloud and edge computing capabilities, where the computational tasks can be partially offloaded to the ENs and the CP.