检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Yao, Yao Yang, Yifei Ma, Xinbei Yang, Dongjie Zhang, Zhuosheng Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan University Wuhan430072 China

How human cognitive abilities are formed has long captivated researchers. However, a significant challenge lies in developing meaningful methods to measure these complex processes. With the advent of large language models (LLMs), which now rival human capabilities in various domains, we are presented with a unique testbed to investigate human cognition through a new lens. Among the many facets of cognition, one particularly crucial aspect is the concept of semantic size—the perceived magnitude of both abstract and concrete words or concepts. This study seeks to investigate whether LLMs exhibit similar tendencies in understanding semantic size, thereby providing insights into the underlying mechanisms of human cognition. We begin by exploring metaphorical reasoning, comparing how LLMs and humans associate abstract words with concrete objects of varying sizes. Next, we examine LLMs’ internal representations to evaluate their alignment with human cognitive processes. Our findings reveal that multi-modal training is crucial for LLMs to achieve more human-like understanding, suggesting that real-world, multi-modal experiences are similarly vital for human cognitive development. Lastly, we examine whether LLMs are influenced by attention-grabbing headlines with larger semantic sizes in a real-world web shopping scenario. The results show that multi-modal LLMs are more emotionally engaged in decision-making, but this also introduces potential biases, such as the risk of manipulation through clickbait headlines. Ultimately, this study offers a novel perspective on how LLMs interpret and internalize language, from the smallest concrete objects to the most profound abstract concepts like ‘love’. The insights gained not only improve our understanding of LLMs but also provide new avenues for exploring the cognitive abilities that define human intelligence. Our code and dataset is publicly available at https://***/Zoeyyao27/LLM-Semantic-Size-Understanding. © 2025, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Non-invasive Cardiac Output Monitoring in Congenital Heart Disease

引用

Current Treatment Options in Pediatrics 2023年第4期9卷 247-259页

作者： Tandon, Animesh Bhattacharya, Sarnab Morca, Ayse Inan, Omer T Munther, Daniel S Ryan, Shawn D Latifi, Samir Q Lu, Nanshu Lasa, Javier J Marino, Bradley S Baloglu, Orkun Department of Heart Vascular and Thoracic Division of Cardiology and Cardiovascular Medicine Children’s Institute Cleveland Clinic Children’s Cleveland OH United States Cleveland Clinic Children’s Center for Artificial Intelligence (C4AI) Department of Heart Vascular and Thoracic Children’s Institute Cleveland Clinic Children’s Cleveland OH United States Department of Pediatrics Cleveland Clinic Lerner College of Medicine of Case Western Reserve University Cleveland OH United States Department of Biomedical Engineering Cleveland Clinic Lerner Research Institute and Case School of Engineering at Case Western Reserve University Cleveland OH United States Department of Electrical and Computer Engineering The University of Texas at Austin Austin 78712 TX United States Department of Integrated Hospital Care Division of Critical Care Children’s Institute Cleveland Clinic Children’s Cleveland OH United States School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA United States Department of Mathematics and Statistics Cleveland State University Cleveland 44115 OH United States Center for Applied Data Analysis and Modeling Cleveland State University Cleveland 44115 OH United States Department of Aerospace Engineering and Engineering Mechanics Texas Materials Institute The University of Texas at Austin Austin 78712 TX United States Department of Biomedical Engineering The University of Texas at Austin Austin 78712 TX United States Department of Mechanical Engineering Texas Materials Institute The University of Texas at Austin Austin 78712 TX United States Divisions of Cardiology and Critical Care Department of Pediatrics Children’s Medical Center UT Southwestern Medical Center Dallas TX United States

Purpose of review: Cardiac output (CO) is a fundamental physiological parameter that measures the volume of blood that is pumped by the heart per unit of time, and helps define how oxygen is delivered to the tissues of the human body. In this paper, we discuss current methods of continuous CO monitoring while defining low CO syndrome (LCOS) and how analytical tools may help improve CO management in the subpopulation of patients with congenital heart disease (CHD). Recent findings: Non-invasive methods of measuring CO have become increasingly available in recent years. Advantages of non-invasive over invasive techniques include decreased risk of procedural complications, decreased exposure to sedative and/or anesthetic agents, and increased patient comfort. Pediatric patient populations are particularly sensitive to the risks and complications of invasive techniques given the relative size of current technologies to pediatric vascular and cardiac dimensions. Summary: Novel device technologies, combined with emerging analytical techniques, may help improve measurement of CO in children and those with CHD, and allow earlier detection of LCOS. © 2023, The Author(s).

关键词： Cardiac index Cardiac output Congenital heart disease Non-invasive continuous cardiac output monitoring

来源：评论

学校读者我要写书评

暂无评论

The Security and Privacy of Mobile Edge Computing: An Artificial Intelligence Perspective

arXiv

引用

arXiv 2024年

作者： Wang, Cheng Yuan, Zenghui Zhou, Pan Xu, Zichuan Li, Ruixuan Wu, Dapeng Oliver Hubei Engineering Research Center on Big Data Security Key Laboratory of Distributed System Security of Hubei Province School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Software The Key Laboratory for Ubiquitous Network Service Software of Liaoning Province Dalian University of Technology Dalian116024 China Intelligent and Distributed Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science City University of Hong Kong Kowloon999077 Hong Kong

Mobile Edge Computing (MEC) is a new computing paradigm that enables cloud computing and information technology (IT) services to be delivered at the network’s edge. By shifting the load of cloud computing to individual local servers, MEC helps meet the requirements of ultralow latency, localized data processing, and extends the potential of Internet of Things (IoT) for end-users. However, the crosscutting nature of MEC and the multidisciplinary components necessary for its deployment have presented additional security and privacy concerns. Fortunately, Artificial Intelligence (ai) algorithms can cope with excessively unpredictable and complex data, which offers a distinct advantage in dealing with sophisticated and developing adversaries in the security industry. Hence, in this paper we comprehensively provide a survey of security and privacy in MEC from the perspective of ai. On the one hand, we use European Telecommunications Standards Institute (ETSI) MEC reference architecture as our based framework while merging the Software Defined Network (SDN) and Network Function Virtualization (NFV) to better illustrate a serviceable platform of MEC. On the other hand, we focus on new security and privacy issues, as well as potential solutions from the viewpoints of ai. Finally, we comprehensively discuss the opportunities and challenges associated with applying ai to MEC security and privacy as possible future research directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Multimodal Retrieval through Relations between Subjects and Objects in Lifelog Images 3

Multimodal Retrieval through Relations between Subjects and ...

引用

3rd Annual Workshop on the Lifelog Search Challenge, LSC 2020

作者： Chu, Tai-Te Chang, Chia-Chun Yen, An-Zi Huang, Hen-Hsen Chen, Hsin-Hsi National Taiwan University Department of Computer Science and Information Engineering Taipei Taiwan National Chengchi University MOST Joint Research Center for AI Technology and All Vista Department of Computer Science Taipei Taiwan MOST Joint Research Center for AI Technology and All Vista Healthcare Taiwan

ISBN: (纸本)9781450371360

With the development of wearable devices, people nowadays record their life experiences much easier than before. Lifelog retrieval becomes an emerging task. Because of the semantic gap between visual data and textual queries, retrieving lifelog images with text queries could be challenging. This paper proposes an interactive lifelog retrieval system that is aimed at retrieving more intuitive and accurate results. Our system is divided into the offline and the online parts. In the offline part, we aim to incorporate original visual and textual concepts from images into our system utilizing pre-trained word embedding. Moreover, we encode the information of relationships between subjects and objects in images by using a pre-trained relation graph generation model. In the online part, We provide an intuitive frontend with various metadata filters, which not only provides users with a convenient interface, but also a mechanism to exploit detail memory recall to users. In this case, users would clearly know the difference between the concepts in the clusters and efficiently browse the retrieved images clusters in a short time. Copyright © 2020 by the Association for Computing Machinery, Inc. (ACM).

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce NAS Space for Heterogeneous Pipeline of CNNs

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce ...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Huijuan Duan Danghui Wang Xingting Zhao Kuizhi Mei Jihe Wang School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

Efficiently deploying neural network models on heterogeneous edge systems faces unique challenges. Two major issues are underutilized pipelines caused by hardware heterogeneity and explosive growth of architecture search space. To address these challenges, we propose ExpoNAS, a framework enabling fast deployment-oriented neural architecture search on heterogeneous platforms. ExpoNAS evaluates model partitioning and deployability before search to meet accuracy and latency constraints. However, repeated partitioning leads to exponential growth in architecture search space. We first observe a strong correlation between operational exposure and accuracy improvement, and then we propose an exposure-based reduction technique that excludes the operations of low exposure. By removing these non-critical operations, the exposure-based pruning successfully reduces architecture search time. Our experiments on popular datasets show that the ExpoNAS pipelined design improves execution efficiency by a factor of 2 compared to traditional batch processing. Without compromising accuracy, ExpoNAS is able to reduce the architecture search time by 47.5% for discovering high-accuracy networks, compared to the SOTA NAS strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Linguistic Knowledge Transfer Learning for Speech Enhancement

arXiv

引用

arXiv 2025年

作者： Hung, Kuo-Hsuan Lu, Xugang Fu, Szu-Wei Tseng, Huan-Hsin Lin, Hsin-Yi Lin, Chii-Wann Tsao, Yu Department of Biomedical Engineering National Taiwan University Taipei Taiwan National Institute of Information and Communications Technology Japan NVIDIA Taipei Taiwan AI & ML Department Brookhaven National Laboratory UptonNY United States Department of Mathematics and Computer Science Seton Hall University South OrangeNJ07079 United States Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan

Linguistic knowledge plays a crucial role in spoken language comprehension. It provides essential semantic and syntactic context for speech perception in noisy environments. However, most speech enhancement (SE) methods predominantly rely on acoustic features to learn the mapping relationship between noisy and clean speech, with limited exploration of linguistic integration. While text-informed SE approaches have been investigated, they often require explicit speech-text alignment or externally provided textual data, constraining their practicality in real-world scenarios. Additionally, using text as input poses challenges in aligning linguistic and acoustic representations due to their inherent differences. In this study, we propose the Cross-Modality Knowledge Transfer (CMKT) learning framework, which leverages pre-trained large language models (LLMs) to infuse linguistic knowledge into SE models without requiring text input or LLMs during inference. Furthermore, we introduce a misalignment strategy to improve knowledge transfer. This strategy applies controlled temporal shifts, encouraging the model to learn more robust representations. Experimental evaluations demonstrate that CMKT consistently outperforms baseline models across various SE architectures and LLM embeddings, highlighting its adaptability to different configurations. Additionally, results on Mandarin and English datasets confirm its effectiveness across diverse linguistic conditions, further validating its robustness. Moreover, CMKT remains effective even in scenarios without textual data, underscoring its practicality for real-world applications. By bridging the gap between linguistic and acoustic modalities, CMKT offers a scalable and innovative solution for integrating linguistic knowledge into SE models, leading to substantial improvements in both intelligibility and enhancement performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SE(3) diffusion model with application to protein backbone generation

arXiv

引用

arXiv 2023年

作者： Yim, Jason Trippe, Brian L. De Bortoli, Valentin Mathieu, Emile Doucet, Arnaud Barzilay, Regina Jaakkola, Tommi Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Massachusetts United States Department of Statistics Columbia University New York United States Center for Sciences of Data French National Centre for Scientific Research Paris France Department of Engineering University of Cambridge Cambridge United Kingdom Department of Statistics University of Oxford Oxford United Kingdom

The design of novel protein structures remains a challenge in protein engineering for applications across biomedicine and chemistry. In this line of work, a diffusion model over rigid bodies in 3D (referred to as frames) has shown success in generating novel, functional protein backbones that have not been observed in nature. However, there exists no principled methodological framework for diffusion on SE(3), the space of orientation preserving rigid motions in R3, that operates on frames and confers the group invariance. We address these shortcomings by developing theoretical foundations of SE(3) invariant diffusion models on multiple frames followed by a novel framework, FrameDiff, for learning the SE(3) equivariant score over multiple frames. We apply FrameDiff on monomer backbone generation and find it can generate designable monomers up to 500 amino acids without relying on a pretrained protein structure prediction network that has been integral to previous methods. We find our samples are capable of generalizing beyond any known protein structure. Code: https://***/jasonkyuyim/se3_diffusion © 2023, CC BY.

关键词： Monomers

来源：评论

学校读者我要写书评

暂无评论

Generative Federated Learning with Small and Large Models In Consumer Electronics for Privacy preserving data Fusion in Healthcare Internet of Things

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Ghazal, Taher M. Islam, Shayla Hasan, Mohammad Kamrul Abu-Shareha, Ahmad A. Mokhtar, Umi A. Khan, M. Attique Baili, Jamel Saeed, Ali Q. Bhattt, Mohammed Wasim Ahmad, Munir Al-Ahliyya Amman University Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia (UKM) Department of Networks and Cybersecurity Hourani Center for Applied Scientific Research Amman Jordan UCSI University Institute of Computer Science and Digital Innovation Kuala Lumpur 56000 Malaysia Universiti Kebangsaan Malaysia (UKM) Center for Cyber Security Faculty of Information Science and Technology Malaysia Al-Ahliyya Amman University Hourani Center for Applied Scientific Research Department of Data Science and Artificial Intelligence Amman Jordan Prince Mohammad bin Fahd University Saudi Arabia King Khalid University College of Computer Science Department of Computer Engineering Abha 61413 Saudi Arabia Northern Technical University Computer Center Ninevah Iraq Korea University College of Informatics Seoul 02841 South Korea

Healthcare Internet of Things (HIoT) requires large-scale privacy features to ensure maximum security in sharing sensitive physiological data in consumer electronics. Recent approaches utilize the fusion concept to provide maximum privacy in health data sharing. Embedded signing data fusion with the health observed data ensures privacy preserved sharing across heterogeneous medical consumer devices for diagnosis. This article proposes a Dependency-correlated data Fusion Scheme (DcDFS) to maximize the privacy of the health data-sharing process. The proposed scheme prepares separate key signing procedures using triple-DES (data encryption standard) to embed with the accumulated health data. The fusion process is carried out by defining key headers and integrity footers for authentication and verification. Therefore, the fusion generates a combined sequence of linear authentication and validation procedures enclosing the health data. In this scheme, the role of federated learning is to prevent permuted sequences for the same health data. This research integrates Small Language Model (SLM) and Large Language Model (LLM) into the federated learning module to support secure, scalable, and intelligent healthcare data sharing. Their collaboration enhances context-aware training while preserving privacy across decentralized, encrypted environments. A similar sequence mapped between the header and footer is responsible for discarding unauthorized data handling. The learning process verifies the permutation for many-to-one header to footer and vice versa. Therefore, the proposed fusion scheme generates a linear dependency between the actual and security-related data for maximum privacy. The proposed scheme achieves the following: the computation time is confined by 12.424%, the privacy leakage by 12.923%, and the computation efficiency is improved by 11.46%, as observed under the maximum sequences. © 1975-2011 IEEE.

关键词： data Fusion Federated Learning Healthcare IoT Privacy-Preserving Triple DES

来源：评论

学校读者我要写书评

暂无评论

AgriField3D: A Curated 3D Point Cloud and Procedural Model dataset of Field-Grown Maize from a Diversity Panel

arXiv

引用

arXiv 2025年

作者： Kimara, Elvis Hadadi, Mozhgan Godbersen, Jackson Balu, Aditya Jubery, Talukder Li, Yawei Krishnamurthy, Adarsh Schnable, Patrick S. Ganapathysubramanian, Baskar Department of Computer Science Iowa State University Ames United States Translational AI Research and Education Center Ames United States Department of Mechanical Engineering Iowa State University Ames United States Plant Science Institute Iowa State University Ames United States Interdepartmental Genetics and Genomics Graduate Program Iowa State University Ames United States Department of Agronomy Iowa State University Ames United States

The application of artificial intelligence (ai) in three-dimensional (3D) agricultural research, particularly for maize, has been limited by the scarcity of large-scale, diverse datasets. While 2D image datasets are abundant, they fail to capture essential structural details such as leaf architecture, plant volume, and spatial arrangements that 3D data provide. To address this limitation, we present AgriField3D (website), a curated dataset of 3D point clouds of field-grown maize plants from a diverse genetic panel, designed to be ai-ready for advancing agricultural research. Our dataset comprises over 1,000 high-quality point clouds collected using a Terrestrial Laser Scanner, complemented by procedural models that provide structured, parametric representations of maize plants. These procedural models, generated using Non-Uniform Rational B-Splines (NURBS) and optimized via a two-step process combining Particle Swarm Optimization (PSO) and differentiable programming, enable precise, scalable reconstructions of leaf surfaces and plant architectures. To enhance usability, we performed graph-based segmentation to isolate individual leaves and stalks, ensuring consistent labeling across all samples. We also conducted rigorous manual quality control on all datasets, correcting errors in segmentation, ensuring accurate leaf ordering, and validating metadata annotations. The dataset further includes metadata detailing plant morphology and quality, alongside multi-resolution subsampled versions (100k, 50k, 10k points) optimized for various computational needs. By integrating point cloud data of field grown plants with high-fidelity procedural models and ensuring meticulous manual validation, AgriField3D provides a comprehensive foundation for ai-driven phenotyping, plant structural analysis, and 3D applications in agricultural research. © 2025, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Disentangling Genotype and Environment Specific Latent Features for Improved Trait Prediction using a Compositional Autoencoder

arXiv

引用

arXiv 2024年

作者： Powadi, Anirudha Jubery, Talukder Zaki Tross, Michael C. Schnable, James C. Ganapathysubramanian, Baskar Department of Electrical and Computer Engineering Iowa State University AmesIA5011 United States Translational AI Research and Education Center Iowa State University Ames Ames50011 United States Department of Agronomy and Horticulture University of Nebraska-Lincoln LincolnNE68588 United States Department of Mechanical Engineering Iowa State University AmesIA50011 United States Center for Plant Science Innovation University of Nebraska-Lincoln LincolnNE68588 United States

This study introduces a compositional autoencoder (CAE) framework designed to disentangle the complex interplay between genotypic and environmental factors in high-dimensional phenotype data to improve trait prediction in plant breeding and genetics programs. Traditional predictive methods, which use compact representations of high-dimensional data through handcrafted features or latent features like PCA or more recently autoencoders, do not separate genotype-specific and environment-specific factors. We hypothesize that disentangling these features into genotype-specific and environment-specific components can enhance predictive models. To test this, we developed a compositional autoencoder (CAE) that decomposes high-dimensional data into distinct genotype-specific and environment-specific latent features. Our CAE framework employs a hierarchical architecture within an autoencoder to effectively separate these entangled latent features. Applied to a maize diversity panel dataset, the CAE demonstrates superior modeling of environmental influences and 5-10 times improved predictive performance for key traits like Days to Pollen and Yield, compared to the traditional methods, including standard autoencoders, PCA with regression, and Partial Least Squares Regression (PLSR). By disentangling latent features, the CAE provides powerful tool for precision breeding and genetic research. This work significantly enhances trait prediction models, advancing agricultural and biological sciences. Copyright © 2024, The Authors. All rights reserved.

关键词： Prediction models

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：