Qing Yu 교수

Since deep learning models have been implemented in many commercial applications, it is important to detect out-of-distribution (OOD) inputs correctly to maintain the performance of the models, ensure the quality of the collected data, and prevent the applications from being used for other-than-intended purposes. In this work, we propose a two-head deep convolutional neural network (CNN) and maximize the discrepancy between the two classifiers to detect OOD inputs. We train a two-head CNN consis

Biomass plays a crucial role in mitigating the concerns associated with increasing fossil fuel combustion. Among various types of biomass, forest biomass has attracted considerable attention given its abundance and variations. In this work, an overview is presented on different pathways available to convert forest biomass into bioenergy. Direct use of forest biomass could reduce carbon dioxide emissions associated with conventional energy production systems. However, there are certain drawbacks

Photodynamic therapy (PDT) has recently been considered a potential tumor therapy due to its time-space specificity and non-invasive advantages. PDT can not only directly kill tumor cells by using cytotoxic reactive oxygen species but also induce an anti-tumor immune response by causing immunogenic cell death of tumor cells. Although it exhibits a promising prospect in treating tumors, there are still many problems to be solved in its practical application. Tumor hypoxia and immunosuppressive mi

Yu et al., (2022). TransBigData: A Python package for transportation spatio-temporal big data processing, analysis and visualization. Journal of Open Source Software, 7(71), 4021, https://doi.org/10.21105/joss.04021

As the outcomes of rapid urbanization, the spatial separation of homes and workplaces extends the commuting distance and complicates the commuting demand of residents. To promote urban livability and sustainability, it becomes crucially important to understand the commuting patterns by decomposing and simplifying the diverse commuting demand. In this paper, a methodology framework is proposed to describe the spatial structure of commuting demand in a city using mobile phone data. Four steps are

The purpose of this study was to investigate the anaerobic digestion (AD) of rice straw at different temperatures in a 300 m3 bioreactor. The results showed that the biogas yield was 401.9 m3/ton (dry straw weight) in this AD system. The contents of total solids, volatile solids, chemical oxygen demand, pH, NH4+-N, and volatile fatty acids were all in the optimal range, indicating that the entire AD system was stable and efficient. In addition, the phylum Bacteroidetes was the main type of bacte

Abstract Text classification is a typical application of natural language processing. At present, the most commonly used text classification method is deep learning. Meanwhile there are many difficulties in natural language processing, such as metaphor expression, semantic diversity and grammatical specificity. To solve these problems, this paper proposes the structure of BERT-BiGRU model. First, use the BERT model instead of the traditional word2vec model to represent the word vector, the word

Universal domain adaptation (UniDA) has been proposed to transfer knowledge learned from a label-rich source domain to a label-scarce target domain without any constraints on the label sets. In practice, however, it is difficult to obtain a large amount of perfectly clean labeled data in a source domain with limited resources. Existing UniDA methods rely on source samples with correct annotations, which greatly limits their application in the real world. Hence, we consider a new realistic settin