检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Hu, Xin Zhang, Lingling Liu, Jun Fan, Jinfu You, Yang Wu, Yaqiang Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University China Department of Control Science and Engineering Tongji University Shanghai China Department of Computer Science National University of Singapore Singapore Lenovo Research Beijing China

Diagram object detection is the key basis of practical applications such as textbook question answering. Because the diagram mainly consists of simple lines and color blocks, its visual features are sparser than those of natural images. In addition, diagrams usually express diverse knowledge, in which there are many low-frequency object categories in diagrams. These lead to the fact that traditional data-driven detection model is not suitable for diagrams. In this work, we propose a gestalt-perception transformer model for diagram object detection, which is based on an encoder-decoder architecture. Gestalt perception contains a series of laws to explain human perception, that the human visual system tends to perceive patches in an image that are similar, close or connected without abrupt directional changes as a perceptual whole object. Inspired by these thoughts, we build a gestalt-perception graph in transformer encoder, which is composed of diagram patches as nodes and the relationships between patches as edges. This graph aims to group these patches into objects via laws of similarity, proximity, and smoothness implied in these edges, so that the meaningful objects can be effectively detected. The experimental results demonstrate that the proposed GPTR achieves the best results in the diagram object detection task. Our model also obtains comparable results over the competitors in natural image object detection. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Interplays of liver fibrosis-associated microRNAs:Molecular mechanisms and implications in diagnosis and therapy

引用

Genes & Diseases 2023年第4期10卷 1457-1469页

作者： Hong Li Tingli Liu Yongchun Yang William C.Cho Robin J.Flynn Majid Fasihi Harandi Houhui Song Xuenong Luo Yadong Zheng State Key Laboratory of Veterinary Etiological Biology Key Laboratory of Veterinary Parasitology of Gansu ProvinceLanzhou Veterinary Research InstituteChinese Academy of Agricultural SciencesLanzhouGansu 730046China Key Laboratory of Applied Technology on Green-Eco-Healthy Animal Husbandry of Zhejiang Province Zhejiang Provincial Engineering Laboratory for Animal Health Inspection&Internet TechnologyZhejiang International Science and Technology Cooperation Base for Veterinary Medicine and Health ManagementChina-Australia Joint Laboratory for Animal Health Big Data AnalyticsCollege of Animal Science and Technology&College of Veterinary Medicine of Zhejiang A&F UniversityHangzhouZhejiang 311300China Department of Clinical Oncology Queen Elizabeth HospitalHong Kong SAR 999077China Department of Infection Biology Institute of Infection and Global HealthUniversity of LiverpoolLiverpool L35RFUK Graduate Studies Office Department of ResearchInnovation and Graduate StudiesWaterford Institute of TechnologyX91 K0EKIreland Research Center for Hydatid Disease in Iran Kerman University of Medical SciencesKerman ***Iran

microRNAs(miRNAs)are a class of non-coding functional small RNA composed of 21e23 nucleotides,having multiple associations with liver ***-associated miRNAs are roughly classified into pro-fibrosis or anti-fibrosis *** former is capable of activating hepatic stellate cells(HSCs)by modulating pro-fibrotic signaling pathways,mainly including TGF-b/SMAD,WNT/b-catenin,and Hedgehog;the latter is responsible for maintenance of the quiescent phenotype of normal HSCs,phenotypic reversion of activated HSCs(aHSCs),inhibition of HSCs proliferation and suppression of the extracellular matrix-associated gene ***,several miRNAs are involved in regulation of liver fibrosis via alternative mechanisms,such as interacting between hepatocytes and other liver cells via exosomes and increasing autophagy of ***,understanding the role of these miRNAs may provide new avenues for the development of novel interventions against hepatic fibrosis.

关键词： Diagnosis Hepatic stellate cell Liver fibrosis miRNA Therapy

来源：评论

学校读者我要写书评

暂无评论

Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning

arXiv

引用

arXiv 2022年

作者： Xu, Fangzhi Liu, Jun Lin, Qika Pan, Yudai Zhang, Lingling School of Computer Science and Technology Xi'an Jiaotong University Xi'an China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&d National Engineering Lab for Big Data Analytics Xi'an China

Machine reading comprehension has aroused wide concerns, since it explores the potential of model for text understanding. To further equip the machine with the reasoning capability, the challenging task of logical reasoning is proposed. Previous works on logical reasoning have proposed some strategies to extract the logical units from different aspects. However, there still remains a challenge to model the long distance dependency among the logical units. Also, it is demanding to uncover the logical structures of the text and further fuse the discrete logic to the continuous text embedding. To tackle the above issues, we propose an end-to-end model Logiformer which utilizes a two-branch graph transformer network for logical reasoning of text. Firstly, we introduce different extraction strategies to split the text into two sets of logical units, and construct the logical graph and the syntax graph respectively. The logical graph models the causal relations for the logical branch while the syntax graph captures the co-occurrence relations for the syntax branch. Secondly, to model the long distance dependency, the node sequence from each graph is fed into the fully connected graph transformer structures. The two adjacent matrices are viewed as the attention biases for the graph transformer layers, which map the discrete logical structures to the continuous text embedding space. Thirdly, a dynamic gate mechanism and a question-aware self-attention module are introduced before the answer prediction to update the features. The reasoning process provides the interpretability by employing the logical units, which are consistent with human cognition. The experimental results show the superiority of our model, which outperforms the state-of-the-art single model on two logical reasoning benchmarks. © 2022, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

MultiNet with Transformers: A Model for Cancer Diagnosis Using Images

arXiv

引用

arXiv 2023年

作者： Barzekar, Hosein Patel, Yash Tong, Ling Yu, Zeyun Big Data Analytics and Visualization Laboratory Department of Computer Science University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Department of Health Informatics and Administration University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Department of Biomedical Engineering University of Wisconsin-Milwaukee MilwaukeeWI53211 United States

Cancer is a leading cause of death in many countries. An early diagnosis of cancer based on biomedical imaging ensures effective treatment and a better prognosis. However, biomedical imaging presents challenges to both clinical institutions and researchers. Physiological anomalies are often characterized by slight abnormalities in individual cells or tissues, making them difficult to detect visually. Traditionally, anomalies are diagnosed by radiologists and pathologists with extensive training. This procedure, however, demands the participation of professionals and incurs a substantial cost. The cost makes large-scale biological image classification impractical. In this study, we provide unique deep neural network designs for multiclass classification of medical images, in particular cancer images. We incorporated transformers into a multiclass framework to take advantage of data-gathering capability and perform more accurate classifications. We evaluated models on publicly accessible datasets using various measures to ensure the reliability of the models. Extensive assessment metrics suggest this method can be used for a multitude of classification tasks. © 2023, CC BY.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Learnable Convolutional Attention Network for Knowledge Graph Completion

SSRN

引用

SSRN 2023年

作者： Shang, Bin Zhao, Yinliang Liu, Jun School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D Xi’an Jiaotong University Shaanxi Xi’an710049 China National Engineering Lab for Big Data Analytics Shaanxi Xi’an710049 China

Recently, graph convolutional networks (GCNs) and graph attention networks (GATs) have been widely used in knowledge graph completion (KGC), which aims to solve the incompleteness of knowledge graphs (KGs). However, GCNs based KGC models tend to stack redundant information when one entity have several noisy neighbors. GATs based KGC models may focus on certain neighbors and lead to weakening of structural information. Furthermore, relations in KGs have their specific semantics and should be considered when aggregating neighbor information (message passing). To address the above limitations, we propose a learnable convolutional attention network for knowledge graph completion named LCA-KGC. LCA-KGC introduces a knowledge graph convolutional attention network by using the convolution operation before the attention mechanism to ensure the structural information acquisition and avoid the redundant information stacking. Furthermore, to complete the autonomous switching of GNNs types and eliminate the necessity of pre-validating the local structure of KGs, LCA-KGC designs a learnable knowledge graph convolutional attention network by comprising three types of GNNs in one learnable formulation. Moreover, a learnable message function is proposed to emphasize relational semantics when aggregating neighbor information. Extensive experiments on standard KG datasets validate the effectiveness of the proposed innovations, and LCA-KGC achieves state-of-the-art (SOTA) performance compared to existing approaches (e.g., compared to SOTA approaches, LCA-KGC improves MRR from 0.360 to 0.372 on FB15k-237 dataset, and Hits@3 from 0.561 to 0.581 on YAGO3-10 dataset). © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging High-Order Similar Nodes and Structural Correlation for Attention-Based Graph Embedding

Leveraging High-Order Similar Nodes and Structural Correlati...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Jing-Hong Wang Chang-Xin Li Jia-Teng Yang College of Computer and Cyber Security Hebei Normal University Shijiazhuang China Hebei Key Laboratory of Network and Information Security Hebei Normal University Shijiazhuang China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Security Hebei Normal University Shijiazhuang China Hebei Polytechnic Institute Shijiazhuang China

Graph Attention Network (GAT) is a popular method for graph embedding as they effectively leverage attention mechanisms to aggregate first-order neighborhood node information. However, they have limitations in their ability to consider high-order neighborhood nodes and structural information. Directly incorporating high-order neighborhood node information into traditional GAT may result in over-smoothing. To address this challenge, in this paper, we propose a joint attention graph embedding model based on similar networks and structural correlation. secondly, we introduce the concept of structural correlation to the original graph attentional method, and consider not only node content feature but also joint node topological structure feature when calculating the attention score. Finally, the graph attention mechanism module performs feature extraction to generate embedding representations of the nodes. The proposed algorithm achieved an accuracy of 85.7%, 74.30%, and 84.10% on the Cora, Citeseer, and Pubmed datasets respectively in node classification tasks. This represents an improvement of 2.70%, 3.94%, and 2.60% respectively compared to the traditional graph attention model. It can be seen that the proposed method can obtain a better representation of node embedding.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Contamination, biofilm formation, virulence and molecular characterization of multi–drug resistant Staphylococcus aureus isolated from pork under low temperature in Zhejiang Province, China

SSRN

引用

SSRN 2025年

作者： Zhai, Ruidong Liang, Yilun Lei, Lei Xu, Xinlu Wu, Qin Han, Yue Deng, Simin Xu, Jiali Xia, Jing Yang, Yongchun Cocolin, Luca Simone Rantsiou, Kalliopi Cheng, Changyong Song, Houhui Key Laboratory of Applied Biotechnology on Animal Science & Veterinary Medicine of Zhejiang Province Zhejiang Engineering Research Center for Veterinary Diagnostics & Advanced Technology Zhejiang International Science and Technology Cooperation Base for Veterinary Medicine and Health Management Belt and Road International Joint Laboratory for One Health and Food Safety China-Australia Joint Laboratory for Animal Health Big Data Analytics College of Veterinary Medicine of Zhejiang Agricultural and Forestry University Zhejiang Province Hangzhou China Department of Agricultural Forest and Food Sciences University of Turin Torino Italy

Staphylococcus aureus is considered to be an increasingly food safety concern. Low temperature is usually used to limit bacterial reproduction on meat. The aim of this study was to investigate the contamination and characterization about S. aureus on pork under low temperature at cold storage warehouses in Zhejiang Province, China. A total of 344 samples were collected to detect S. aureus, and All 52 S. aureus were isolated from 11.6% samples with present in 18 batches from 13 cold storage warehouses, of note, 51.9% isolates was enterotoxigenic, and 71.2% isolates were multi-drug resistant strains with strong biofilm formation, notably, 13 MRSA. Moreover, all 52 isolates were classified into 10 clusters of RAPD with 13 SPA types, especially the new frequently Spa-t20663. And ST398, ST188, ST6 types were ranked among the top three accompanied by close genetic relationships with other food-borne S. aureus in China. In addition, high virulence isolates were observed on Galleria mellonella, and ST188 S. aureus with skin abscesses in rabbits. Findings from this study highlight the contamination, long-term survival, virulence and diverse molecular characteristics of multi-drug resistant S. aureus isolated from frozen pork. Therefore, integrated surveillance and control measures are urgent to mitigate the associated risk. © 2025, The Authors. All rights reserved.

关键词： Meats

来源：评论

学校读者我要写书评

暂无评论

Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer

arXiv

引用

arXiv 2023年

作者： Zhang, Zhihao Chen, Yiwei Zhang, Weizhan Yan, Caixia Zheng, Qinghua Wang, Qi Chen, Wangdu School of Computer Science and Technology Xi'an Jiaotong University Key Laboratory of Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi’an China School of Computer Science and Technology Xi'an Jiaotong University & National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China MIGU Video Shanghai China

Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, leading to the error accumulation problem. In this paper, we propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer, namely MFTR. Specifically, MFTR utilizes transformer-based networks to extract the long-range dependencies within each modality, then mine intra- and inter-modality relations to capture the combined impact of user historical inputs and video contents on future viewport selection. In addition, MFTR categorizes future tiles into two categories: user interested or not, and selects future viewport as the region that contains most user interested tiles. Comparing with predicting head trajectories, choosing future viewport based on tile's binary classification results exhibits better robustness and interpretability. To evaluate our proposed MFTR, we conduct extensive experiments on two widely used PVS-HM and Xu-Gaze dataset. MFTR shows superior performance over state-of-the-art methods in terms of average prediction accuracy and overlap ratio, also presents competitive computation efficiency. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Selenium nanoparticles alleviates cadmium induced hepatotoxicity by inhibiting ferroptosis and oxidative stress in vivo and in vitro

引用

Chemosphere 2024年 364卷 143004页

作者： Shao, Chunyan Luo, Tongwang Wang, Shujie Li, Zhuoyue Yu, Xiaoqiang Wu, Ya Jiang, Sheng Zhou, Bin Song, Quanjiang Song, Shengzhe Wang, Xiaodu Song, Houhui Shao, Chunyan Luo, Tongwang Wang, Shujie Li, Zhuoyue Yu, Xiaoqiang Wu, Ya Jiang, Sheng Zhou, Bin Song, Quanjiang Song, Shengzhe Wang, Xiaodu Song, Houhui Shao, Chunyan Luo, Tongwang Wang, Shujie Li, Zhuoyue Yu, Xiaoqiang Wu, Ya Jiang, Sheng Zhou, Bin Song, Quanjiang Song, Shengzhe Wang, Xiaodu Song, Houhui Shao, Chunyan Luo, Tongwang Wang, Shujie Li, Zhuoyue Yu, Xiaoqiang Wu, Ya Jiang, Sheng Zhou, Bin Song, Quanjiang Song, Shengzhe Wang, Xiaodu Song, Houhui Shao, Chunyan Luo, Tongwang Wang, Shujie Li, Zhuoyue Yu, Xiaoqiang Wu, Ya Jiang, Sheng Zhou, Bin Song, Quanjiang Song, Shengzhe Wang, Xiaodu Song, Houhui College of Veterinary Medicine Zhejiang A&F University Zhejiang Hangzhou311300 China Key Laboratory of Applied Technology on Green-Eco-Healthy Animal Husbandry of Zhejiang Province Zhejiang Hangzhou311300 China Zhejiang Provincial Engineering Research Center for Animal Health Diagnostics & Advanced Technology Zhejiang Hangzhou311300 China Zhejiang International Science and Technology Cooperation Base for Veterinary Medicine and Health Management Zhejiang Hangzhou311300 China China-Australia Joint Laboratory for Animal Health Big Data Analytics Zhejiang Hangzhou311300 China

Cadmium (Cd) is an important environmental toxicant that could cause serious damage to various organs including severe hepatotoxicity in intoxicated animals. Selenium has been reported to possess the protective effects against Cd toxicity, but the specific mechanism is still unclear. The purpose of this study was to explore the effects and mechanism of chitosan coated selenium nanoparticles (CS-SeNPs) against Cd-induced hepatotoxicity in animal and cellular models. ICR mice and rat hepatocyte BRL-3A cells were exposed to cadmium chloride (CdCl2) to evaluate the therapeutic efficiency of CS-SeNPs. Analysis of histopathological images, mitochondrial membrane potential (MMP) and ultramicrostructure, serum liver enzyme activities, ferroptosis-related indicators contents, and further molecular biology experiments were performed to investigate the underlying mechanisms. In vivo experiment results showed that CdCl2 caused significant pathological damage involving significant increase of liver index, contents of tissue MDA and serum ALT and AST, and significant decrease of serum GSH-Px activity. Moreover, CdCl2 exposure upregulated ACSL4 and HO-1 protein levels, downregulated GPX4, TfR1, ferritin protein levels in the liver. Notably, CS-SeNPs increased the expression level of GPX4 and ameliorated CdCl2-induced changes in above-mentioned indicators. In vitro experimental results showed that treatment with CS-SeNPs significantly elevated GSH-Px activity and GPX4 protein level, reversed CdCl2-induced expression of several ferroptosis-related proteins TfR1, FTH1 and HO-1, and repressed ROS production and increased MMP of the cells exposed to CdCl2. Our research indicated that CdCl2 induced hepatocyte injury by inducing ferroptosis, while CS-SeNPs can inhibit ferroptosis and reduce the degree of hepatocyte injury. This study is of great significance for further revealing the mechanism of Cd hepatotoxicity and expanding the clinical application of SeNPs. © 2024

关键词： Chlorine compounds

来源：评论

学校读者我要写书评

暂无评论

Improving Classification Performance of Motor Imagery BCI Through EEG data Augmentation with Conditional Generative Adversarial Networks

SSRN

引用

SSRN 2023年

作者： Choo, Sanghyun Park, Hoonseok Jung, Jae-Yoon Flores, Kevin Nam, Chang S. Computational Sciences and Engineering Division Oak Ridge National Laboratory Oak RidgeTN United States Department of Big Data Analytics Kyung Hee University Korea Republic of Department of Industrial and Management Systems Engineering Kyung Hee University Korea Republic of Department of Mathematics North Carolina State University RaleighNC United States Department of Industrial and Manufacturing Engineering Kettering University FlintMI United States

In brain-computer interface (BCI), building accurate electroencephalogram (EEG) classifiers for specific mental tasks is critical for BCI performance. The classifiers are developed by machine learning (ML) and deep learning (DL) techniques, requiring a large dataset for training to build reliable and accurate models. However, collecting large enough EEG datasets is difficult due to intra-/inter-subject variabilities and experimental costs. This leads to the data scarcity problem, which causes overfitting issues to training samples, resulting in reducing generalization performance. To solve the EEG data scarcity problem and improve the performance of the EEG classifiers, we propose a novel EEG data augmentation (DA) framework using conditional generative adversarial networks (cGANs). An experimental study is implemented with two public EEG datasets, including motor imagery (MI) tasks (BCI competition IV IIa and III IVa), to validate the effectiveness of the proposed EEG DA method for the EEG classifiers. To evaluate the proposed cGAN-based DA method, we tested six EEG classifiers for the experiment, including traditional MLs and state-of-the-art DLs with three existing EEG DA methods. Experimental results showed that most DA methods with proper DA proportion in the training dataset had higher classification performances than without DA. Moreover, applying the proposed DA method showed superior classification performance improvement than the other DA methods. This shows that the proposed method is a promising EEG DA method for enhancing the performances of the EEG classifiers in MI-based BCIs. © 2023, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：