skip to main content

Search for: All records

Creators/Authors contains: "Wu, Guojun"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Lightweight neural networks refer to deep networks with small numbers of parameters, which can be deployed in resource-limited hardware such as embedded systems. To learn such lightweight networks effectively and efficiently, in this paper we propose a novel convolutional layer, namely Channel-Split Recurrent Convolution (CSR-Conv), where we split the output channels to generate data sequences with length T as the input to the recurrent layers with shared weights. As a consequence, we can construct lightweight convolutional networks by simply replacing (some) linear convolutional layers with CSR-Conv layers. We prove that under mild conditions the model size decreases with the rate of O( 1 ). Empirically we demonstrate the state-of-the-art T2 performance using VGG-16, ResNet-50, ResNet-56, ResNet- 110, DenseNet-40, MobileNet, and EfficientNet as backbone networks on CIFAR-10 and ImageNet. Codes can be found on Conv. 
    more » « less
  2. The DNA phosphorothioate (PT) modification existing in many prokaryotes, including bacterial pathogens and commensals, confers multiple characteristics, including restricting gene transfer, influencing the global transcriptional response, and reducing fitness during exposure to chemical mediators of inflammation. While PT-containing bacteria have been investigated in a variety of environments, they have not been studied in the human microbiome. Here, we investigated the distribution of PT-harboring strains and verified their existence in the human microbiome. We found over 2000 PT gene-containing strains distributed in different body sites, especially in the gastrointestinal tract. PT-modifying genes are preferentially distributed within several genera, including Pseudomonas, Clostridioides, and Escherichia, with phylogenic diversities. We also assessed the PT modification patterns and found six new PT-linked dinucleotides (CpsG, CpsT, ApsG, TpsG, GpsC, ApsT) in human fecal DNA. To further investigate the PT in the human gut microbiome, we analyzed the abundance of PT-modifying genes and quantified the PT-linked dinucleotides in the fecal DNA. These results confirmed that human microbiome is a rich reservoir for PT-containing microbes and contains a wide variety of PT modification patterns. 
    more » « less
  3. Public transits, such as buses and subway lines, offer affordable ride-sharing services and reduce the road network traffic, thus have significant impacts in mitigating the urban traffic congestion problem. However, it is non-trivial to evaluate a new transit plan, such as a new bus route or a new subway line, of its future ridership prior to actual deployment, since the travel preferences of passengers along the planned routes may vary. In this paper, we make the first attempt to model passengers' preferences of making various transit choices using a Markov Decision Process (MDP). Moreover, we develop a novel inverse preference learning algorithm to infer the passengers' preferences and predict the future human behavior changes, e.g., ridership, of a new urban transit plan before its deployment. We validate our proposed framework using a unique real-world dataset (from Shenzhen, China) with three subway lines opened during the data time span. With the data collected from both before and after the transit plan deployments, Our evaluation results demonstrated that the proposed framework can predict the ridership with only 19.8% relative error, which is 23%-51% lower than other baseline approaches. 
    more » « less