检索结果-内蒙古大学图书馆

International Conference on Big Data and smart Computing (BIGCOMP)

作者： Yoonjae Lee Kyung Seo Ki Gahgene Gweon Bugeun Kim Graduate School of Convergence Science and Technology Seoul National University South Korea Interdisciplinary Program in Artificial Intelligence Seoul National University South Korea Department of AI Chung-Ang University South Korea

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

The goal of financial QA is to generate solution equations by solving problems about financial reports. Current financial QA models can suffer from two issues: expression fragmentation and number redundancy. We conduct experiments to examine the impact of the two issues. The experimental results show that addressing the expression fragmentation issue in financial QA using EPT improves the execution accuracy by 0.09, and alleviating the number redundancy issue by removing redundant numbers in the input of the FinQANet generator improves the execution accuracy by 0.07.

关键词： Accuracy Computational modeling Redundancy Big Data Mathematical models Generators

来源：评论

学校读者我要写书评

暂无评论

MERNet: Multimodal Emotion Recognition in Conversation Network via Cross-Modal Knowledge Distillation and Contrastive Learning

MERNet: Multimodal Emotion Recognition in Conversation Netwo...

引用

International Conference on Big Data and smart Computing (BIGCOMP)

作者： Sooyeon Hwang Gahgene Gweon Eunseong Kwon Interdisciplinary Program in Artificial Intelligence Seoul National University South Korea Graduate School of Convergence Science and Technology Seoul National University South Korea Dept. of Computer Science and Engineering POSTECH South Korea

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

Multimodal Emotion Recognition in Conversation (ERC) is a task of predicting the emotion of each utterance in a conversation by utilizing both verbal and non-verbal modalities. However, existing approaches often struggle to bridge cross-modal gaps, resulting in misaligned features and frequent misclassification of minority emotions into semantically similar majority emotions. To address these challenges, we propose MERNet, a framework that employs cross-modal knowledge distillation and contrastive learning to align multimodal features and effectively distinguish subtle emotions in conversations. Our framework consists of two stages: 1) guiding non-verbal modalities with the text modality to transfer knowledge and align their features, and 2) applying contrastive learning with emotion labels as anchors to distinguish subtle differences between similar emotions and address the class imbalance problem. Experiments conducted on two benchmark datasets, IEMOCAP and MELD, demonstrate that our MERNet outperforms existing state-of-the-art models.

关键词： Knowledge engineering Bridges Emotion recognition Visualization Computational modeling Contrastive learning Benchmark testing Linguistics Big Data

来源：评论

学校读者我要写书评

暂无评论

3D Super Resolution for Non-Isotropic Medical Image Through Multi-Input 3D ResUnet

3D Super Resolution for Non-Isotropic Medical Image Through ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Youjin Seo ByeongChang Jeong Yeji Yoon Daegyeom Kim JuHong Min Cheol E. Han Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Korea University Sejong Sejong Republic of Korea Dept. of Electronics and Information Engineering Korea University Sejong Sejong Republic of Korea Dept. of Neurology Samsung Medical Center Sungkyunkwan University Seoul Republic of Korea

Fluid-attenuated inversion recovery imaging (FLAIR) is a magnetic resonance (MR) method that is frequently utilized to diagnose brain lesions. However, it usually provides transverse section imaging in high resolution but with very low resolution in the other axis. This non-isotropy huddles its wide utilization in research including machine learning. In this study, we applied a deep-learning based super resolution (SR) technique to convert non-isotropic FLAIR images into isotropic one. We proposed a multi-input 3D ResUnet that uses both FLAIR and T1-weighted MR images as its inputs. As a result, our proposed model successfully reconstructed isotropic FLAIR images (SSIM: 0.9947 $\pm 0.0009)$ , and out-performed the FLAIR only single-input 3D ResUnet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pseudomonas aeruginosa-derived DnaJ induces TLR2 expression through TLR10-mediated activation of the PI3K-SGK1 pathway in macrophages

引用

Microbes and Infection 2025年 105481页

作者： Lee, Jaehoo Jin, Yongxin Wu, Weihui Lee, Yeji Ha, Un-Hwan Department of Biotechnology and Bioinformatics Korea University Sejong 30019 South Korea Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Korea University Sejong 30019 South Korea State Key Laboratory of Medicinal Chemical Biology Key Laboratory of Molecular Microbiology and Technology of the Ministry of Education Department of Microbiology Nankai University Tianjin 300071 China

TLR2 is a key component of the innate immune system, responsible for recognizing Gram-positive bacterial components and initiating inflammatory signaling cascades that activate defense responses. However, little is known about the regulatory effects of Pseudomonas aeruginosa (P. aeruginosa) on TLR2 expression. In this study, we investigated the potential link between P. aeruginosa-derived DnaJ and TLR2 expression in macrophages, as well as the activation of downstream signaling pathways. Our findings revealed that DnaJ significantly induced TLR2 expression in a dose- and time-dependent manner, predominantly affecting TLR2 with minimal impact on other TLRs, such as TLR4 and TLR5, which detect bacterial PAMPs. The DnaJ-mediated TLR2 induction was driven by activation of the PI3K-SGK1 signaling pathway, with TLR10 playing a crucial role in facilitating these effects. This increase in TLR2 expression led to enhanced production of inflammatory cytokines in response to secondary Staphylococcus aureus infections, indicating a role in boosting host defense mechanisms. In conclusion, these findings suggest that P. aeruginosa-derived DnaJ promotes TLR2 expression via TLR10-mediated activation of the PI3K-SGK1 pathway, thereby enhancing host immune responses against Gram-positive bacterial infections. © 2025 Institut Pasteur

关键词： DnaJ Pseudomonas aeruginosa SGK1 TLR10 TLR2

来源：评论

学校读者我要写书评

暂无评论

VR-Based Implicit Authentication Using Electromyogram and Inertial Measurement Unit

VR-Based Implicit Authentication Using Electromyogram and In...

引用

International Conference on Cyberworlds

作者： Da-Young Yu Hyung-Tak Lee Youngsam Kim Jong-Hyuk Roh Soohyung Kim Jeonghun Ku Han-Jeong Hwang Dept. Electronics and Information Engineering Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Korea University Sejong Republic of Korea Dept. Electronics and Information Engineering Korea University Sejong Republic of Korea Electronics and Telecommunications Research Institute (ETRI) Daejeon Republic of Korea Department of Biomedical Engineering College of Medicine Keimyung University Daegu Republic of Korea

ISBN: (数字)9798331527174

ISBN: (纸本)9798331527181

Biometrics based on electromyogram (EMG) and inertial measurement unit (IMU) signals has received significant attention due to its resistance to forgery and tampering, as well as its relatively higher convenience and security compared to other biometric modalities. However, most EMG and IMU signal-based authentication methods require explicit authentication using unnatural gestures, which is not userfriendly. To address this, we collected EMG and IMU data during virtual reality (VR) rhythm game play, which does not require explicit gestures, and performed implicit authentication. Using a linear discriminant analysis (LDA) classifier, we achieved classification accuracies of 91.71% for human identification and 87.91% for human authentication. The result demonstrated the feasibility of a seamless and implicit authentication in VR environments.

关键词： Biometrics Solid modeling Measurement units Accuracy Authentication Inertial navigation Games Virtual reality Rhythm Electromyography

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Model of Amyloid-${\boldsymbol{\beta }}$ Diffusion Simulation

A Deep Learning Model of Amyloid-${\boldsymbol{\beta }}$ Dif...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： ByeongChang Jeong Daegyeom Kim Hyun-Ghang Jeong Cheol E. Han Dept. of Electronic and Information Engineering The Alzheimer's Disease Neuroimaging Initiative Korea University Sejong Republic of Korea The Alzheimer's Disease Neuroimaging Initiative Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Korea University Sejong Republic of Korea Dept. of Psychiatry The Alzheimer's Disease Neuroimaging Initiative Korea University College of Medicine Seoul Republic of Korea

Alzheimer's disease (AD) is a severe neurodegenerative disease characterized by ongoing brain tissue decline. Since amyloid- $\beta$ accumulation is supposed as a primary cause of AD progression, mathematical models have been recently employed to simulate amyloid- $\beta$ diffusion in our brain. These models require parameter estimation through observed data and an iterative process to update parameters, although increased complexity can hinder their optimization. To overcome these difficulties, we converted the mathematical model of amyloid- $\beta$ diffusion into a deep learning model, combining multi-layer perceptron (MLP) and graph convolutional neural network (GCN). The proposed model well predicted the change of accumulation level of amyloid- $\beta$ with a high accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pani/MoS₂ composite for an efficient catalyst for photocatalytic reduction and adsorption of chromium Cr (VI)

引用

Inorganic Chemistry Communications 2025年 178卷

作者： Sharma, Krishna Prasad Shin, Miyeon Awasthi, Ganesh Prasad Gwak, Nayeong Kim, Sung Hoon Yu, Changho Division of Convergence Technology Engineering Jeonbuk National University Jeonbuk State Jeonju 54896 South Korea Department of Energy Storage/Conversion Engineering (BK21 FOUR) Jeonbuk National University Jeonbuk State Jeonju 54896 South Korea Department of Electronics and Information Engineering Korea University Sejong 30019 South Korea Interdisciplinary Graduate Program for Artificial Intelligence Smart City Convergence Technology Korea University Sejong 30019 South Korea

The development and use of a cost-effective, eco-friendly catalyst for the efficient removal of Cr (VI) from wastewater are critical. In response, we have created a Pani/MoS2 composite for adsorption, utilizing a bina... 详细信息

The development and use of a cost-effective, eco-friendly catalyst for the efficient removal of Cr (VI) from wastewater are critical. In response, we have created a Pani/MoS₂ composite for adsorption, utilizing a binary organic–inorganic material produced through a combination of in-situ oxidative polymerization and hydrothermal reactions. This study highlights the significance of using a bifunctional organic–inorganic composite for Cr (VI) removal. The hydrothermally prepared Pani/MoS₂ material serves as a bifunctional catalyst, facilitating both adsorption and photocatalytic reduction. Comprehensive characterization, photocatalysis, and adsorption analyses of the Pani/MoS₂ composite provide valuable insights into its adsorption and reduction mechanisms. The results showed a reduction efficiency of 67.03% after 80 min and a removal efficiency of 73.60% at pH 3 after 24 h. Additionally, Pani/MoS₂ exhibited an adsorption capacity of 29.44 mg/g after 24 h. The hybrid organic–inorganic composite contains multiple adsorption sites, resulting in enhanced adsorption capacity. The adsorption process involves a variety of reactions, including electrostatic interactions, complexation reactions, physical and chemical adsorption, reduction reactions, and photocatalytic reduction, which incorporates simultaneous oxidation and reduction through electron-hole pairs. A study on the stability and the effect of radical scavengers demonstrated the comparable stability of Pani/MoS₂ and the role of radical interference during Cr (VI) adsorption. © 2025 Elsevier B.V.

关键词： Adsorption Composite Molybdenum disulfide Photocatalytic reduction Polyaniline

来源：评论

学校读者我要写书评

暂无评论

Effect of transauricular vagus nerve stimulation on stress regulation using electroencephalography

引用

Brain Stimulation 2025年第1期18卷 527-527页

作者： Lee, Yun-Sung Kim, Woo-Jin Hong, Ki Hwan Choi, Hyuk Song, Jae-Jun Hwang, Han-Jeong Korea University Republic of Korea Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Korea University Republic of Korea Neurive Co. Ltd Republic of Korea Graduate School of Medicine Korea University Republic of Korea Korea University Guro Hospital Republic of Korea

来源：评论

学校读者我要写书评

暂无评论

Caco-2 Cell-Derived Biomimetic Electrochemical Biosensor for Cholera Toxin Detection

SSRN

引用

SSRN 2022年

作者： Kim, Yonghwan Lee, Dongtak Seo, Youngjun Jung, Hyo Gi Jang, Jae Won Park, Dongsung Kim, Insu Lee, Gyudo Hwang, Kyo Seon Kim, Seung-Hyun Lee, Sang Won Lee, Jeong Hoon Yoon, Dae Sung School of Biomedical Engineering Korea University Seoul02841 Korea Republic of Interdisciplinary Program in Precision Public Health Korea University Seoul02841 Korea Republic of Department of Clinical Pharmacology and Therapeutics College of Medicine Kyung Hee University Seoul02447 Korea Republic of Department of Biotechnology and Bioinformatics Korea University Sejong30019 Korea Republic of Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Korea University Sejong30019 Korea Republic of School of Engineering Brown University ProvidenceRI02912 United States Department of Electrical Engineering and Computer Science University of California IrvineCA92697 United States Department of Electrical Engineering Kwangwoon University Seoul01897 Korea Republic of Astrion Inc Seoul02841 Korea Republic of

Cholera is a highly contagious and lethal waterborne disease induced by an infection with Vibrio cholerae (V. cholerae) secreting cholera toxin (CTx). Cholera toxin subunit B (CTxB) from the CTx specifically binds with monosialo-tetra-hexosyl-ganglioside (GM1) found on the exterior cell membrane of an enterocyte. Owing to the pathological process of CTx, a biomimetic electrochemical biosensor (CCB) was developed by applying GM1-expressing Caco-2 cell membrane (CCM) on the electrode surface of the biosensor for CTx detection. Briefly, the electrode surface was functionalized with CCM using the vesicle fusion method. The specific binding between GM1 and CTxB on the electrode surface was verified using confocal laser scanning microscopy and atomic force microscopy. The CTxB detection performances of the CCB, including sensitivity, selectivity, and long-term stability, were determined using electrochemical impedance spectroscopy (EIS). Based on the results, the CCB had an excellent limit of detection of ~11.46 nM and a detection range spanning 100 ng/mL - 1 mg/mL. Further, the CCB had high selectivity for the CTxB compared to different interfering molecules, which are abundant constituents of intestinal fluid and fecal matter in the human body. The long-term stability of the CCBs was also verified for 3 weeks using EIS. Overall, the CCB was found to have an excellent potential for application to point-of-care and cost-effective testing for CTxB detection in developing countries. © 2022, The Authors. All rights reserved.

关键词： Electrochemical impedance spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Elongation factor-G1A identified as a novel effector protein translocated into cells and a key modulator of Pseudomonas aeruginosa physiology and host cellular responses

引用

Microbial pathogenesis 2025年 205卷 107720页

作者： Yeji Lee Yongxin Jin Weihui Wu Un-Hwan Ha Department of Biotechnology and Bioinformatics Korea University Sejong 30019 Republic of Korea. State Key Laboratory of Medicinal Chemical Biology Key Laboratory of Molecular Microbiology and Technology of the Ministry of Education Department of Microbiology Nankai University Tianjin 300071 China. Department of Biotechnology and Bioinformatics Korea University Sejong 30019 Republic of Korea Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Korea University Sejong 30019 Republic of Korea. Electronic address: haunhwan@korea.ac.kr.

Pseudomonas aeruginosa has two closely related elongation factors, EF-G1A and EF-G1B, which share 90 % sequence similarity. Despite their high sequence homology, the role of EF-G in P. aeruginosa pathogenesis remains not fully understood. In our study, we found that compared to EF-G1B, EF-G1A expression reduced bacterial growth and twitching motility, while increasing swimming motility. Notably, EF-G1A was translocated into host cells in a T6SS-dependent manner. This translocation was significantly reduced, though not completely abolished, in strains with mutations in both the T6SS spike protein VgrG1a and the tube protein Hcp1, suggesting that while EF-G1A translocation is influenced by T6SS, additional components are also involved. Moreover, EF-G1A expression reduced T3SS-mediated morphological alterations, as evidenced by the downregulation of T3SS effectors such as ExoS and ExoT. EF-G1A was also found to suppress activation of the NF-κB signaling pathway, leading to decreased production of inflammatory cytokines including IL-6, IL-8, and TNFα. These findings highlight EF-G1A as a key modulator, affecting both P. aeruginosa physiology and host cellular responses, thereby providing new insights into the complex role of EF-G1A in bacterial pathogenesis.

关键词： Elongation factor-G1A Pseudomonas aeruginosa T3SS T6SS Translocation

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：