检索结果-内蒙古大学图书馆

Conference on Electrical Insulation and Dielectric Phenomena, (CEIDP)

作者： Jierui Zhou Marina Dabaghian Anna Marie LaChance Jing Hao Wesley Zhong Luyi Sun Yang Cao Department of Electrical and Computer Engineering University of Connecticut Storrs CT USA Electrical Insulation Research Center Institute of Materials Science University of Connecticut Storrs CT USA Department of Chemical and Biomolecular Engineering University of Connecticut Storrs CT USA Polymer Program Institute of Materials Science University of Connecticut Storrs CT USA

Polymer-thin films are critical dielectric materials for capacitive energy storage in power and electronic systems. The rapid development of wide bandgap semiconductors urgently calls for polymers that can attain high energy density and high charge-discharge efficiency at elevated temperatures. However, high-temperature polymers usually suffer from compromised dielectric breakdown strength and soaring conduction loss due to the intrinsic constraint between their bandgaps and thermal stability. In this work, we propose a facile and high throughput interface engineering technique utilizing nanocoatings formed by montmorillonite (MMT) nanoclays, which can serve as an out-of-the-box solution to bypass this constraint. The highly ordered MMT-based nanocoatings with layered structure can significantly block the excessive charge injection at high electric fields and dissipate the charge carriers along the in-plane direction. The MMT-coated PI films exhibit improved breakdown strength, suppressed conduction loss, and boosted charging-discharging efficiency. This work holds the promise of improving the dielectric properties of polymers through surface engineering, enabling their application at concurrent electrical and thermal extremes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta-learning Spiking Neural Networks with Surrogate Gradient Descent

arXiv

引用

arXiv 2022年

作者： Stewart, Kenneth M. Neftci, Emre O. Department of Computer Science UC Irvine IrvineCA United States Department of Computer Science Department of Cognitive Sciences UC Irvine Peter Grünberg Institute – Neuromorphic Software Ecosystems Forschungszentrum Jülich Germany Faculty of Electrical Engineering and Information Technology RWTH Aachen Germany

Adaptive "life-long" learning at the edge and during online task performance is an aspirational goal of AI research. Neuromorphic hardware implementing Spiking Neural Networks (SNNs) are particularly attractive in this regard, as their real-time, event-based, local computing paradigm makes them suitable for edge implementations and fast learning. However, the long and iterative learning that characterizes state-of-the-art SNN training is incompatible with the physical nature and real-time operation of neuromorphic hardware. Bi-level learning, such as meta-learning is increasingly used in deep learning to overcome these limitations. In this work, we demonstrate gradient-based meta-learning in SNNs using the surrogate gradient method that approximates the spiking threshold function for gradient estimations. Because surrogate gradients can be made twice differentiable, well-established, and effective second-order gradient meta-learning methods such as Model Agnostic Meta Learning (MAML) can be used. We show that SNNs meta-trained using MAML match or exceed the performance of conventional Artificial Neural Networks (ANNs) meta-trained with MAML on event-based meta-datasets. Furthermore, we demonstrate the specific advantages that accrue from meta-learning: fast learning without the requirement of high precision weights or gradients. Our results emphasize how meta-learning techniques can become instrumental for deploying neuromorphic learning technologies on real-world problems. Copyright © 2022, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Role of deep learning in cognitive healthcare: Wearable signal analysis, algorithms, benefits, and challenges

引用

Digital Communications and Networks 2025年第3期11卷 642-670页

作者： Md. Sakib Bin Alam Aiman Lameesa Senzuti Sharmin Shaila Afrin Shams Forruque Ahmed Mohammad Reza Nikoo Amir H. Gandomi Department of Information Technology University of Information Technology and Sciences (UITS) Dhaka 1212 Bangladesh Department of Computer Science American International University - Bangladesh (AIUB) Dhaka 1229 Bangladesh Science and Math Program Asian University for Women Chattogram 4000 Bangladesh School of Mathematical Sciences Sunway University Bandar Sunway Petaling Jaya 47500 Selangor Darul Ehsan Malaysia Department of Mathematics and Physics North South University Dhaka 1229 Bangladesh Department of Civil and Architectural Engineering Sultan Qaboos University Muscat Oman Faculty of Engineering and Information Technology University of Technology Sydney Sydney NSW 2007 Australia University Research and Innovation Center (EKIK) Óbuda University 1034 Budapest Hungary Department of Computer Science Khazar University Mahsati 41 Baku Azerbaijan

Deep Learning (DL) offers promising solutions for analyzing wearable signals and gaining valuable insights into cognitive disorders. While previous review studies have explored various aspects of DL in cognitive healthcare, there remains a lack of comprehensive analysis that integrates wearable signals, data processing techniques, and the broader applications, benefits, and challenges of DL methods. Addressing this limitation, our study provides an extensive review of DL's role in cognitive healthcare, with a particular emphasis on wearables, data processing, and the inherent challenges in this field. This review also highlights the considerable promise of DL approaches in addressing a broad spectrum of cognitive issues. By enhancing the understanding and analysis of wearable signal modalities, DL models can achieve remarkable accuracy in cognitive healthcare. Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-term Memory (LSTM) networks have demonstrated improved performance and effectiveness in the early diagnosis and progression monitoring of neurological disorders. Beyond cognitive impairment detection, DL has been applied to emotion recognition, sleep analysis, stress monitoring, and neurofeedback. These applications lead to advanced diagnosis, personalized treatment, early intervention, assistive technologies, remote monitoring, and reduced healthcare costs. Nevertheless, the integration of DL and wearable technologies presents several challenges, such as data quality, privacy, interpretability, model generalizability, ethical concerns, and clinical adoption. These challenges emphasize the importance of conducting future research in areas such as multimodal signal analysis and explainable AI. The findings of this review aim to benefit clinicians, healthcare professionals, and society by facilitating better patient outcomes in cognitive healthcare.

关键词： cognitive healthcare Deep learning Wearable sensor Convolutional neural network Recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Cell2Sentence: teaching large language models the language of biology 24

Cell2Sentence: teaching large language models the language o...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Daniel Levine Syed Asad Rizvi Sacha Lévy Nazreen Pallikkavaliyaveetil David Zhang Xingyu Chen Sina Ghadermarzi Ruiming Wu Zihe Zheng Ivan Vrkic Anna Zhong Daphne Raskin Insu Han Antonio Henrique De Oliveira Fonseca Josue Ortega Caro Amin Karbasi Rahul M. Dhodapkar David Van Dijk Department of Computer Science Yale University New Haven CT School of Engineering Applied Science University of Pennsylvania Philadelphia PA School of Computer and Communication Sciences Swiss Federal Institute of Technology Lausanne Lausanne Switzerland Department of Computer Science Yale University New Haven CT and Department of Neuroscience Yale School of Medicine New Haven CT Department of Computer Science Yale University New Haven CT and Department of Neuroscience Yale School of Medicine New Haven CT and Wu Tsai Institute Yale University New Haven CT Google and Yale Institute for Foundations of Data Science New Haven CT and Department of Computer Science Yale University New Haven CT and Yale School of Engineering and Applied Science New Haven CT Roski Eye Institute University of Southern California Los Angeles CA and Department of Internal Medicine (Cardiology) Yale School of Medicine New Haven CT Department of Computer Science Yale University New Haven CT and Yale Institute for Foundations of Data Science New Haven CT and Wu Tsai Institute Yale University New Haven CT and Cardiovascular Research Center Yale School of Medicine New Haven CT and Interdepartmental Program in Computational Biology & Bioinformatics Yale University New Haven CT and Department of Internal Medicine (Cardiology) Yale School of Medicine New Haven CT

We introduce Cell2Sentence (C2S), a novel method to directly adapt large language models to a biological context, specifically single-cell transcriptomics. By transforming gene expression data into "cell sentences," C2S bridges the gap between natural language processing and biology. We demonstrate cell sentences enable the fine-tuning of language models for diverse tasks in biology, including cell generation, complex cell-type annotation, and direct data-driven text generation. Our experiments reveal that GPT-2, when fine-tuned with C2S, can generate biologically valid cells based on cell type inputs, and accurately predict cell types from cell sentences. This illustrates that language models, through C2S fine-tuning, can acquire a significant understanding of single-cell biology while maintaining robust text generation capabilities. C2S offers a flexible, accessible framework to integrate natural language processing with transcriptomics, utilizing existing models and libraries for a wide range of biological applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Prognostics and Health Management in Automated Driving Systems: Using Graph Neural Networks to Recognize Operational Contexts

Enhanced Prognostics and Health Management in Automated Driv...

引用

Prognostics and System Health Management Conference (PHM)

作者： Peng Su Yeqi Wang Conglei Xiang Erik Wendel Madhav Mishra DeJiu Chen Department of Engineering Design Mechatronics Division KTH Royal Institute of Technology Stockholm Sweden Embedded Systems Master Program of Electrical Engineering and Computer Science (EECS) School KTH Royal Institute of Technology Stockholm Sweden Digital Systems Division RISE Research Institutes of Sweden Gothenburg Sweden

ISBN: (数字)9798350360585

ISBN: (纸本)9798350360592

Prognostics and health management (PHM) is an engineering discipline that aims to maintain system behaviour and function and ensure mission success, safety and effectiveness. Addressing the challenges in prognostics and health management for modern intelligent systems, especially automated driving systems, is complex due to the contextual nature of faults. This complexity necessitates a thorough understanding of spatial, and temporal conditions, and relationships within operational scenarios and life-cycle stages. This paper introduces a framework designed to automatically recognize driving scenarios in automated driving systems using graph neural networks (GNNs). The framework extracts relational data from image frames, constructing graph-based models and transforming unstructured sensory data into structured data with diverse node types and relationships. A specific graph neural network processes the graph model to reveal and detect operational conditions and relationships. The proposed framework is evaluated using the KITTI dataset, demonstrating superior performance compared to conventional feed-forward networks such as MLP, particularly in handling relational data.

关键词： Graph neural networks Data models Safety Complexity theory Data mining Prognostics and health management Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A predictability-distinctiveness trade-off in the historical emergence of word forms 41

A predictability-distinctiveness trade-off in the historical...

引用

41st Annual Meeting of the cognitive science Society: Creativity + Cognition + Computation, CogSci 2019

作者： Xu, Aotao Ramiro, Christian Xu, Yang Computer Science Program University of Waterloo Canada Cognitive Science Program University of California Berkeley United States Department of Computer Science Cognitive Science Program University of Toronto Canada

ISBN: (纸本)0991196775

It has been proposed that language evolves under the joint constraints of communicative expressivity and cognitive ease. We explore this idea in the historical emergence of word forms. We hypothesize that new word forms that enter the lexicon should reflect a trade-off between predictability and distinctiveness. An emergent word form can be highly predictable if it efficiently reuses elements from the existing word forms, resulting in low cognitive load. An emergent word form should also be sufficiently distinctive from the existing lexicon, facilitating communicative expressivity. We test our hypothesis by examining the properties of 34,478 emergent word forms over the past 200 years of Modern English. We show how word forms at future time t + 1 are bounded statistically between n-gram generated word forms (highly predictable) and slang words that are outside the standard lexicon (highly distinctive) at time t. Our work supports the view of cognitive economy in lexical emergence. © cognitive science Society: Creativity + Cognition + Computation, CogSci *** rights reserved.

关键词： cognitive economy language evolution lexical emergence lexicon word form

来源：评论

学校读者我要写书评

暂无评论

Quantum Fourier Transform of Atrial Fibrillation

Quantum Fourier Transform of Atrial Fibrillation

引用

Quantum Computing and engineering (QCE), IEEE International Conference on

作者： Yu-Ching Chen Chih-Yu Chen Tsung-Wei Huang Chia-Ho Ou Master Program in Intelligent Computing and Big Data Chung Yuan Christian University Taoyuan Taiwan Quantum Information Center Chung Yuan Christian University Taoyuan Taiwan Department of Computer Science and Information Engineering National Pingtung University Pingtung Taiwan

ISBN: (数字)9798331541378

ISBN: (纸本)9798331541385

Electrocardiograms (ECGs) are crucial for detecting cardiac diseases like atrial fibrillation (AF). Traditional analysis methods like fast Fourier transform (FFT) face challenges with increasing data complexity. This study uses Taipei Veterans General Hospital data to explore quantum Fourier transform (QFT) for ECG analysis. Results show that QFT effectively analyzes ECG signals, matching FFT performance while benefiting from quantum computing's efficiency.

关键词： Heart Quantum computing Fast Fourier transforms Hospitals High performance computing Atrial fibrillation Machine learning Electrocardiography Real-time systems Signal analysis

来源：评论

学校读者我要写书评

暂无评论

Statistical 3D Device Simulation of Full Fluctuations of Gate-All-Around Silicon Nanosheet MOSFETs at Sub-3-nm Technology Nodes

Statistical 3D Device Simulation of Full Fluctuations of Gat...

引用

2022 International Symposium on VLSI Technology, Systems and Applications, VLSI-TSA 2022

作者： Kola, Sekhar Reddy Li, Yiming Chen, Chieh-Yang Chuang, Min-Hui National Yang-Ming Chiao Tung University Electrical Engineering and Computer Science International Graduate Program Hsinchu300 Taiwan National Yang-Ming Chiao Tung University Institute of Communications Engineering Hsinchu300 Taiwan National Yang-Ming Chiao Tung University Department of Electrical Engineering and Computer Engineering Hsinchu300 Taiwan National Yang-Ming Chiao Tung University Institute of Biomedical Engineering Hsinchu300 Taiwan National Yang-Ming Chiao Tung University Parallel and Scientific Computing Laboratory Hsinchu300 Taiwan

ISBN: (纸本)9781665409230

We for the first time study characteristic fluctuation of gate-all-around silicon nanosheet MOSFETs induced by random dopants fluctuation (RDF), interface trap fluctuation (ITF), and work function fluctuation (WKF), and their combinations. The explored devices affected by the WKF and its combination result in sizeable variability. Because of enigmatical interactions among the aforementioned random factors, overestimated variabilities occur if we only consider one random source each time, compared with the statistical 3D device simulation for full RDF, ITF and WKF at the same time. Notably, 10.78% and 103% overestimations are found for the threshold voltage and off-state current fluctuations. © 2022 IEEE.

关键词： Nanosheets

来源：评论

学校读者我要写书评

暂无评论

Application of the Internet of Everything in Educational Institutions

Application of the Internet of Everything in Educational Ins...

引用

2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021

作者： Yuan Chou, Tsung Lai, Wen-Hsing National Kaohsiung University of Science and Technology Ph.D.Program In Enginering Seience and Technology College of Enginering Kaohsiung Taiwan National Kaohsiung University of Science and Technology Dept. of Computer and Communication Engineering Kaohsiung Taiwan

ISBN: (纸本)9781665419512

Developments in network infrastructure and progress in sensor devices have brought the rise of the Internet of Everything (IoE). The technologies and applications are characterized by overall perception, tight connection, and intelligent responses. This study explored the application of the IoE in education such that these features can be utilized in educational institutions and areas designated for educational services. Focus was placed on the use of the Smart Manager in school attendance tracking, notification system, and security monitoring system for more broad and comprehensive campus safety. © 2021 IEEE.

关键词： Internet of Everything

来源：评论

学校读者我要写书评

暂无评论

Integration of Artificial Intelligence in Software Defined Networking Technology through Developing Machine Learning Algorithms

Integration of Artificial Intelligence in Software Defined N...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： Lamhot Naibaho Pulkit Raj Saxena Kuldeep Sharma Badria Sulaiman Alfurhood L. Pallavi Bhasker Pant English Language Education Study Program Faculty of Letters and Languages Christian University of Indonesia College of Computing Science and Information Technology Teer Thanker Mahaveer University Moradabad Uttar Pradesh India Department of Computer Science and Engineering Lovely Professional University Phagwara Jalandhar Punjab India Department of Computer Sciences College of Computer Information Sciences Princess Nourah Bint Abdulrahman University Saudi Arabia CSE B V Raju Institute of Technology Narsapur Telangana India Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India

A future networking design called "software-defined networking" combines network programmability with centralized administration (SDN). Network administration is currently handled by SDN, which, at the regulator, which acts as the cable network processor and divides the data plane into a control plane and a data aircraft. Recent breakthroughs in artificial intelligence (Al) have shown a stronger inclination for the science community to benefit from their ability to give learning capabilities and enhance Indicator. The author of this research provides a comprehensive analysis of initiatives underway to incorporate Al with SDN. The study concluded that the three primary Al thread where scientific research was centered were computer science, conceptual, and fuzzy reasoning systems. The authors of this paper explore the several fields in which these approaches may be used, their potential future applications, and the innovations made possible by the integration of AI-based methods into the SDN paradigm. By choosing the right SDN controller, any large organization may lower network complexity, implementation expenses, and maintenance costs. The focus of this article is software defined networking's benefits and downsides (SDN). Following is a basic explanation of artificial intelligence and a list of some of its most significant applications in SDN.

关键词：

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：