-
Article
JAPO: learning join and pushdown order for cloud-native join optimization
In this paper, we introduce JAPO which learn the join and pushdown order through DRL. The main idea is that the DRL agent learns better decisions based on the experiences by monitoring the rewards and latencie...
-
Article
Introducing on-chain graph data to consortium blockchain for commercial transactions
-
Article
Open AccessPROST: quantitative identification of spatially variable genes and domain detection in spatial transcriptomics
Computational methods have been proposed to leverage spatially resolved transcriptomic data, pinpointing genes with spatial expression patterns and delineating tissue domains. However, existing approaches fall...
-
Article
The Microstructure Evolution and Mechanical Properties of Al2O3/ZrO2 Coatings with Different ZrO2 Contents: Guidelines to Prepare Eutectic Powders
The Al2O3/ZrO2 coatings (AZ-Cs) with different ZrO2 contents were prepared via Al-Zr(NO3)4 combustion-assisted thermal spraying (CATS) method, and its microstructure evolution, mechanical properties were analyzed...
-
Chapter and Conference Paper
Semi-supervised Class Imbalanced Deep Learning for Cardiac MRI Segmentation
Despite great progress in semi-supervised learning (SSL) that leverages unlabeled data to improve the performance over fully supervised models, existing SSL approaches still fail to exhibit good results when f...
-
Article
Open AccessSystematic comparison of somatic variant calling performance among different sequencing depth and mutation frequency
In the past decade, treatments for tumors have made remarkable progress, such as the successful clinical application of targeted therapies. Nowadays, targeted therapies are based primarily on the detection of ...
-
Article
Open AccessCancer type prediction based on copy number aberration and chromatin 3D structure with convolutional neural networks
With the developments of DNA sequencing technology, large amounts of sequencing data have been produced that provides unprecedented opportunities for advanced association studies between somatic mutations and ...
-
Chapter and Conference Paper
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition
Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them. In ...
-
Article
Open AccessDeepGene: an advanced cancer type classifier based on deep learning and somatic point mutations
With the developments of DNA sequencing technology, large amounts of sequencing data have become available in recent years and provide unprecedented opportunities for advanced association studies between somat...
