检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Bechler-Speicher, Maya Eliasof, Moshe Schönlieb, Carola-Bibiane Gilad-Bachrach, Ran Globerson, Amir Blavatnik School of Computer Science Tel-Aviv University Meta United States Department of Applied Mathematics and Theoretical Physics University of Cambridge United Kingdom Department of Bio-Medical Engineering Tel-Aviv University Edmond J. Safra Center for Bioinformatics Tel-Aviv University Google Research United States

Message-Passing Graph Neural Networks (GNNs) are known to have limited expressive power, due to their message passing structure. One mechanism for circumventing this limitation is to add unique node identifiers (IDs), which break the symmetries that underlie the expressivity limitation. In this work, we highlight a key limitation of the ID framework, and propose an approach for addressing it. We begin by observing that the final output of the GNN should clearly not depend on the specific IDs used. We then show that in practice this does not hold, and thus the learned network does not possess this desired structural property. Such invariance to node IDs may be enforced in several ways, and we discuss their theoretical properties. We then propose a novel regularization method that effectively enforces ID invariance to the network. Extensive evaluations on both real-world and synthetic tasks demonstrate that our approach significantly improves ID invariance and, in turn, often boosts generalization performance. © 2025, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring the Non-Thermal Effects of Electromagnetic Field on Biological Structures: Importance of Experimental Design and Measurement Conditions

SSRN

引用

SSRN 2023年

作者： Bajtos, Marek Carnecka, Lucia Dang, Nhat Gurhan, Hakki Pobocikova, Ivana Radil, Roman Janousek, Ladislav The Department of Electromagnetic and Biomedical Engineering Faculty of Electrical Engineering and Information Technology University of Zilina Univerzitna 8215 Zilina010 26 Slovakia The Department of Electrical Computer and Energy Engineering The University of Colorado Boulder BoulderCO80309 United States The Ann and H.J. Smead Department of Aerospace Engineering Sciences College of Engineering and Applied Science University of Colorado Boulder BoulderCO80309 United States The Department of Applied Mathematics Faculty of Mechanical Engineering University of Zilina Univerzitna 8215 Zilina010 26 Slovakia

This study delves into the non-thermal effects of electromagnetic fields (EMF) on living organisms, emphasizing experimental design, precise measurements, and simulation verification. Grounded in Ion Parametric Resonance theory, it investigates the interaction between time-varying EMF and the Earth's geomagnetic field. The research comprises experiments assessing the Earth's magnetic field at various locations using a magnetometer. These measurements reveal variations influenced by location and surrounding metallic elements. Complementary simulations confirm these measurements and assess high-permeability metal shielding's effectiveness in reducing geomagnetic field fluctuations within the experimental area. Crucial findings arise from experiments involving 50 Hz EMF exposure on Saccharomyces cerevisiae yeasts for seven hours. Statistical analysis supports the impact on yeast cells and identifies an optimal shielding setup for future low-frequency EMF experiments. This research provides valuable insights into EMF's effects on organisms, enhances experimental precision, and guides EMF exposure shielding strategies. © 2023, The Authors. All rights reserved.

关键词： Yeast

来源：评论

学校读者我要写书评

暂无评论

Electrically Programmable Non-Volatile Silicon Photonic Content Addressable Memory (CAM) Cell

Electrically Programmable Non-Volatile Silicon Photonic Cont...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Chuanyu Lian Hongyi Sun Yi-Siou Huang Steven A. Vitale Juejun Hu Ichiro Takeuchi Nathan Youngblood Christos Vagionas Carlos A. Ríos Ocampo Department of Materials Science & Engineering University of Maryland College Park MD USA Institute for Research in Electronics and Applied Physics University of Maryland College Park MD USA Advanced Materials and Microsystems Group MIT Lincoln Laboratory Lexington MA USA Department of Materials Science & Engineering MIT Cambridge MA USA Department of Physics Quantum Materials Center University of Maryland College Park MD USA Electrical & Computer Engineering Department The University of Pittsburgh Pittsburgh PA USA Department of Informatics Center for Interdisciplinary Research and Innovation Aristotle University of Thessaloniki Thessaloniki Greece

We experimentally demonstrate the first electrically programmable, non-volatile silicon photonic content addressable memory cell using Sb 2 Se3 phase change material on microring resonators, opening the path for light... 详细信息

ISBN: (纸本)9798350369311

关键词： Phase change materials Associative memory Nonvolatile memory Lasers and electrooptics Silicon photonics Table lookup Resonators Electro-optical waveguides

来源：评论

学校读者我要写书评

暂无评论

SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Zolman, Nicholas Fasel, Urban Nathan Kutz, J. Brunton, Steven L. Department of Mechanical Engineering University of Washington SeattleWA98195 United States Department of Aeronautics Imperial College LondonSW7 2AZ United Kingdom Department of Applied Mathematics University of Washington SeattleWA98195 United States Department of Electrical and Computer Engineering University of Washington SeattleWA98195 United States Data Science and Artificial Intelligence Department The Aerospace Corporation El SegundoCA90245 United States

Deep reinforcement learning (DRL) has shown significant promise for uncovering sophisticated control policies that interact in environments with complicated dynamics, such as stabilizing the magnetohydrodynamics of a tokamak fusion reactor or minimizing the drag force exerted on an object in a fluid flow. However, these algorithms require an abundance of training examples and may become prohibitively expensive for many applications. In addition, the reliance on deep neural networks often results in an uninterpretable, black-box policy that may be too computationally expensive to use with certain embedded systems. Recent advances in sparse dictionary learning, such as the sparse identification of nonlinear dynamics (SINDy), have shown promise for creating efficient and interpretable data-driven models in the low-data regime. In this work we introduce SINDy-RL, a unifying framework for combining SINDy and DRL to create efficient, interpretable, and trustworthy representations of the dynamics model, reward function, and control policy. We demonstrate the effectiveness of our approaches on benchmark control environments and challenging fluids problems. SINDy-RL achieves comparable performance to state-of-the-art DRL algorithms using significantly fewer interactions in the environment and results in an interpretable control policy orders of magnitude smaller than a deep neural network policy. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Neuroimaging Yolov8-Based Cad Framework for Anosmia Grading in Covid-19

A Neuroimaging Yolov8-Based Cad Framework for Anosmia Gradin...

引用

IEEE International Conference on Image Processing

作者： Hossam Magdy Balaha Mayada Elgendy Ahmed Alksas Mohamed Shehata Norah Saleh Alghamdi Fatma Taher Mohammed Ghazal Mahitab Ghoneim Eslam Hamed Fatma Sherif Ahmed Elgarayhi Mohammed Sallah Mohamed Abdelbadie Salem Elsharawy Kamal Harpal Sandhu Ayman El-Baz Department of Bioengineering J.B. Speed School of Engineering University of Louisville Louisville USA Physics Department Applied Theoretical Physics Research Group Faculty of Science Mansoura University Egypt Department of Computer Sciences College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Saudi Arabia The College of Technological Innovation Zayed University Dubai UAE Electrical Computer and Biomedical Engineering Depatrment Abu Dhabi University UAE Department of Radiology Faculty of Medicine Mansoura University Egypt Otolaryngology Department Faculty of Medicine Mansoura University Egypt Department of Physics College of Sciences University of Bisha Saudi Arabia

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

COVID-19, a respiratory illness caused by SARS-CoV-2, has brought attention to a common symptom: loss of smell and taste. Anosmia, a prevalent symptom of COVID-19, varies in severity from mild to severe, necessitating accurate diagnostic tools. The study proposes a novel framework for predicting COVID-19 anosmia severity utilizing YOLOv8 for classification and EigenCAM for interpretability. YOLOv8, optimized for object detection, is adapted for classification tasks using advanced architectural enhancements and mosaic augmentation. EigenCAM provides interpretability by highlighting image regions crucial for predictions, aiding clinical decision-making. Evaluation across multiple YOLOv8 model sizes using DTI and FLAIR modalities reveals robust performance, with the Large model excelling in DTI and the Nano model in FLAIR. Compared to our previous work, the framework significantly enhances accuracy and interpretability in predicting anosmia severity, marking a substantial advancement in medical image analysis. This study underscores the potential of deep learning for precise and interpretable medical diagnostics, offering insights into anosmia severity prediction.

关键词： COVID-19 Deep learning Solid modeling Adaptation models Accuracy Robustness Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

Assessing Employees’ Perspectives on Work-Life Equilibrium for Integrated Human Capital Governance

Assessing Employees’ Perspectives on Work-Life Equilibrium ...

引用

IEEE Students' Conference on Electrical, Electronics and computer science (SCEECS)

作者： Rakesh Kumar Garg Syed AtifJilani Sanjay Kumar Rai Shyam Ji Gupta Anil Kumar Department of Applied Science and Humanities ITS Engineering College Uttar Pradesh India Department of Business Administration Aligarh Muslim University West Bengal India Jaipuria Institute of Management Noida Uttar Pradesh India School of Computer Sciencs and Engineering Lovely Pofessional University Punjab India Mittal School of Business Lovely Pofessional University Punjab India

Purpose-Work-life balance enables individuals in an organization to harmonize their personal and professional spheres. It prompts employees to delineate these critical aspects of life and prioritize them accordingly. The primary aim of this study is to comprehend how employees perceive work-life balance within the context of holistic human capital management, considering various demographic variables. Additionally, the research seeks to investigate the extent of the impact of excessive workload and organizational policies on maintaining a healthy work-life *** Methodology-SPSS and MS Excel has been used for statistical analysis purpose. The statistical techniques used are Percentage Analysis, Regression Analysis, ANOVA and Chi-square test. The collected data from 236 respondents consists of top senior managers/middle managers and line managers, working in various organizations were *** and Findings-The data analysis reveals that a majority of participants are engaged in work for more than 50 hours per week. Furthermore, the analysis demonstrates a notable divergence in employee perceptions across various sectors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding Sign Language Recognition: An Overview

Understanding Sign Language Recognition: An Overview

引用

Electrical Electronics and Computing Technologies (ICEECT), International Conference on

作者： Shivani Saini Meenu Prjapati Bhupal Arya Ravinder Kumar Sharma Manoj Kumar Department of Mathematics Lovely Professional University Jalandhar India School of Applied & Life Sciences Uttranchal University Computer Science and Engineering RIT Roorkee Roorkee Institute of Technology Roorkee India Department of Mathematics Chandigarh University India India CSE RIT Roorkee Roorkee Institute of Technology Roorkee India

ISBN: (数字)9798350378092

ISBN: (纸本)9798350378108

Communication is only the way which is used by human to express their needs, feelings and thoughts to people mostly by speech. But this world also has the people with some disability like deaf and dumb people. For these people communication is not possible by speech. The only language which is used by deaf and dumb people to communicate with each other is Sign Language. Sign Language is completely different from generally spoken languages, it has its own grammar. Different body parts are involved in sign language but the important parameters are hand gestures, body movement and also facial expression. Many researches have been done in sign language recognition. But still Sign Language Recognition (SLR) is the most challenging area for practitioners and researchers, because sign language is not an international language. For e.g., Indian Sign Language is differed from Ethiopian Sign Language, Chinese Sign Language, American Sign Language and other country’s sign language. The SLR is mostly required because of its ability to remove the communication barrier for deaf and dumb people. This review paper contains various techniques of AI (Artificial Intelligence) used for SLR for human understanding that have employed in recent past. The main approaches are i) Vision based ii) Glove based. In vision-based approach one or more camera is used to capture the image sequence, and then image processing is used to recognize the signs. In glove-based approach instrumental gloves with sensor is used to track the hand movement

关键词： Support vector machines Sign language Image segmentation Tracking Reviews Image edge detection Feature extraction Classification algorithms Artificial intelligence Speech processing

来源：评论

学校读者我要写书评

暂无评论

Ultra-Low-Loss Silicon Nitride Photonics Based on Deposited Films Compatible with Foundries

arXiv

引用

arXiv 2023年

作者： Ji, Xingchen Okawachi, Yoshitomo Gil-Molina, Andres Corato-Zanarella, Mateus Roberts, Samantha Gaeta, Alexander L. Lipson, Michal Department of Electrical Engineering Columbia University New YorkNY10027 United States Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States Currently at John Hopcroft Center for Computer Science School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China

The fabrication processes of silicon nitride (Si3N4) photonic devices used in foundries require low temperature deposition, which typically leads to high propagation losses. Here, we show that propagation loss as low as 0.42 dB/cm can be achieved using foundry compatible processes by solely reducing waveguide surface roughness. By post-processing the fabricated devices using rapid thermal anneal (RTA) and furnace anneal, we achieve propagation losses down to 0.28 dB/cm and 0.06 dB/cm, respectively. These low losses are comparable to the conventional devices using high temperature, high-stress LPCVD films. We also tune the dispersion of the devices, and proved that these devices can be used for linear and nonlinear applications. Low threshold parametric oscillation, broadband frequency combs and narrow-linewidth laser are demonstrated. Our work demonstrates the feasibility of scalable photonic systems based on foundries. Copyright © 2023, The Authors. All rights reserved.

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

Design of an Automated Blockchain-Enabled Vehicle Data Management System

Design of an Automated Blockchain-Enabled Vehicle Data Manag...

引用

International Conference on Signal Processing and Information Security (ICSPIS)

作者： Debashis Das Sourav Banerjee Pushpita Chatterjee Uttam Ghosh Wathiq Mansoor Utpal Biswas Computer Science & Engineering University of Kalyani Kalyani India Computer Science & Engineering Kalyani Government Engineering College Kalyani India Computer Science & Engineering Howard University Washington DC USA School of Applied Computational Sciences Meharry Medical College Nashville TN USA Electrical Engineering Department University of Dubai Dubai UAE

ISBN: (纸本)9781665492669

The Internet of Vehicles (IoV) has a tremendous prospect for numerous vehicular applications. IoV enables vehicles to transmit data to improve roadway safety and efficiency. Data security is essential for increasing the security and privacy of vehicle and roadway infrastructures in IoV systems. Several researchers proposed numerous solutions to address security and privacy issues in IoV systems. However, these issues are not proper solutions that lack data authentication and verification protocols. In this paper, a blockchain-enabled automated data management system for vehicles has been proposed and demonstrated. This work enables automated data verification and authentication using smart contracts. Certified organizations can only access vehicle data uploaded by the vehicle user to the Interplanetary File System (IPFS) server through that vehicle user’s consent. The proposed system increases the security of vehicles and data. Vehicle privacy is also maintained here by increasing data privacy.

关键词： Data privacy Privacy Smart contracts Authentication Organizations Signal processing Safety

来源：评论

学校读者我要写书评

暂无评论

A Moonshot for AI Oracles in the sciences

arXiv

引用

arXiv 2024年

作者： Kaiser, Bryan Wu, Tailin Sonnewald, Maike Thackray, Colin Callis, Skylar Los Alamos National Laboratory X Computational Physics Division Los AlamosNM United States Westlake University Department of Engineering Hangzhou China University of California Davis Department of Computer Science DavisCA United States Harvard University John A. Paulson School of Engineering and Applied Sciences CambridgeMA United States

Nobel laureate Philip Anderson and Elihu Abrahams once stated that, "even if machines did contribute to normal science, we see no mechanism by which they could create a Kuhnian revolution and thereby establish a new physical law." In this Perspective, we draw upon insights from the philosophies of science and artificial intelligence (AI) to propose necessary conditions of precisely such a mechanism for generating revolutionary mathematical theories. Recent advancements in AI suggest that satisfying the proposed necessary conditions by machines may be plausible;thus, our proposed necessary conditions also define a moonshot challenge. We also propose a heuristic definition of the intelligibility of mathematical theories to accelerate the development of machine theorists. Copyright © 2024, The Authors. All rights reserved.

关键词： Philosophical aspects

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：