In this paper, we present a general numerical platform for designing accurate, efficient, and stable numerical algorithms for incompressible hydrodynamic models that obeys the thermodynamical laws. The obtained numerical schemes are automatically linear in time. It decouples the hydrodynamic variable and other state variables such that only small-size linear problems …
View synthesis is usually done by an autoencoder, in which the encoder maps a source view image into a latent content code, and the decoder transforms it into a target view image according to the condition. However, the source contents are often not well kept in this setting, which leads …
This paper presents a layer-2 micropayment pool design which supports high-throughput blockchain off-chain payment, designed specifically for the use case of rewarding users who share redundant bandwidth to assist video stream delivery. We analyze the validity and effectiveness of the proposed micropayment pool. Our analysis results demonstrate that the proposed …
Single image super-resolution (SISR), which aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) observation, has been an active research topic in the area of image processing in recent decades. Particularly, deep learning-based super-resolution (SR) approaches have drawn much attention and have greatly improved the reconstruction performance on …
We propose in this work a multi-view learning approach for audio and music classification. Considering four typical low-level representations (i.e. different views) commonly used for audio and music recognition tasks, the proposed multi-view network consists of four subnetworks, each handling one input types. The learned embedding in the subnetworks are …
In recent years, epidemic modeling in complex networks has found many applications, including modeling of information or gossip spread in online social networks, modeling of malware spread in communication networks, and the most recent model of the COVID-19 pandemic. If the information disseminated is accurate, for example, maximizing its distribution …
Deep convolutional neural networks have shown outstanding performance in medical image segmentation tasks. The usual problem when training supervised deep learning methods is the lack of labeled data which is time-consuming and costly to obtain. In this paper, we propose a novel uncertainty-guided semi-supervised learning based on a student-teacher approach …
Missing values exist in nearly all clinical studies because data for a variable or question are not collected or not available. Inadequate handling of missing values can lead to biased results and loss of statistical power in analysis. Existing models usually do not consider privacy concerns or do not utilise …
We present robust high-performance implementations of signal-processing tasks performed by a high-throughput wildlife tracking system called ATLAS. The system tracks radio transmitters attached to wild animals by estimating the time of arrival of radio packets to multiple receivers (base stations). Time-of-arrival estimation of wideband radio signals is computationally expensive, especially …
Hospitals around the world collect massive amounts of physiological data from their patients every day. Recently, there has been an increase in research interest to subject this data to statistical analysis to gain more insights and provide improved medical diagnoses. Such analyses require complex computations on large volumes of data, …