检索结果-内蒙古大学图书馆

CLEO: Applications and Technology in CLEO 2024, CLEO: A and T 2024 - Part of Conference on Lasers and Electro-Optics

作者： Li, Yuzhu Pillar, Nir Liu, Tairan Ma, Guangdong de Haan, Kevin Zhang, Yijie Correa, Adrian J. Wu, Yulun Bai, Bijie Yang, Xilin Qi, Yuxuan Wallace, William Dean Ozcan, Aydogan Electrical and Computer Engineering Department University of California Los AngelesCA90095 United States Bioengineering Department University of California Los AngelesCA90095 United States University of California Los AngelesCA90095 United States School of Physics Xi'an Jiaotong University Shaanxi Xi'an710049 China Department of Pathology Keck School of Medicine University of Southern California Los AngelesCA90033 United States Department of Mathematics University of California Los AngelesCA90095 United States Computer Science Department University of California Los AngelesCA90095 United States Department of Surgery University of California Los AngelesCA90095 United States

We present deep learning-based virtual staining of unlabeled lung and heart tissue sections to diagnose organ transplant rejection, achieving comparable diagnostic accuracy to histochemical staining methods, while sig... 详细信息

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Ab Initio Structure Solutions from Nanocrystalline Powder Diffraction Data via Diffusion Models

arXiv

引用

arXiv 2024年

作者： Guo, Gabe Saidi, Tristan Luca Terban, Maxwell W. Valsecchi, Michele Billinge, Simon J.L. Lipson, Hod Columbia University Department of Computer Science New YorkNY10027 United States Momentum Transfer Mannheim68169 Germany Columbia University Department of Chemical Engineering New YorkNY10027 United States Columbia University Department of Applied Physics and Applied Mathematics New YorkNY10027 United States Columbia University Department of Mechanical Engineering New YorkNY10027 United States Stanford University Department of Computer Science StanfordCA94305 United States

A major challenge in materials science is the determination of the structure of nanometer sized objects. Here we present a novel approach that uses a generative machine learning model based on diffusion processes that is trained on 45,229 known structures. The model factors both the measured diffraction pattern as well as relevant statistical priors on the unit cell of atomic cluster structures. Conditioned only on the chemical formula and the information-scarce finite-size broadened powder diffraction pattern, we find that our model, PXRDNET, can successfully solve simulated nanocrystals as small as 10 Å across 200 materials of varying symmetry and complexity, including structures from all seven crystal systems. We show that our model can successfully and verifiably determine structural candidates four out of five times, with average error among these candidates being only 7% (as measured by post-Rietveld refinement R-factor). Furthermore, PXRDNET is capable of solving structures from noisy diffraction patterns gathered in real-world experiments. We suggest that data driven approaches, bootstrapped from theoretical simulation, will ultimately provide a path towards determining the structure of previously unsolved nano-materials. Copyright © 2024, The Authors. All rights reserved.

关键词： Rietveld refinement

来源：评论

学校读者我要写书评

暂无评论

Sound propagation in realistic interactive 3D scenes with parameterized sources using deep neural operators

arXiv

引用

arXiv 2023年

作者： Borrel-Jensen, Nikolas Goswami, Somdatta Engsig-Karup, Allan P. Karniadakis, George Em Jeong, Cheol-Ho Department of Electrical and Photonics Engineering Acoustic Technology Technical University of Denmark Ørsteds Plads Kgs. Lyngby2800 Denmark Department of Applied Mathematics and Computer Science Technical University of Denmark Richard Petersens Plads Kgs. Lyngby2800 Denmark Division of Applied Mathematics Brown University 170 Hope Street ProvidenceRI02906 United States School of Engineering Brown University 170 Hope Street ProvidenceRI02906 United States

We address the challenge of acoustic simulations in 3D virtual rooms with parametric source positions, which have applications in virtual/augmented reality, game audio, and spatial computing. The wave equation can fully describe wave phenomena such as diffraction and interference. However, conventional numerical discretization methods are computationally expensive when simulating hundreds of source and receiver positions, making simulations with parametric source positions impractical. To overcome this limitation, we propose using deep operator networks to approximate linear wave-equation operators. This enables the rapid prediction of sound propagation in realistic 3D acoustic scenes with parametric source positions, achieving millisecond-scale computations. By learning a compact surrogate model, we avoid the offline calculation and storage of impulse responses for all relevant source/listener pairs. Our experiments, including various complex scene geometries, show good agreement with reference solutions, with root mean squared errors ranging from 0.02 Pa to 0.10 Pa. Notably, our method signifies a paradigm shift as – to our knowledge – no prior machine learning approach has achieved precise predictions of complete wave fields within realistic domains. © 2023, CC BY-NC-ND.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Higher-Accuracy Photonic Neural Networks via Duplication Schemes for Noise Reduction

Higher-Accuracy Photonic Neural Networks via Duplication Sch...

引用

International Conference on Photonics in Switching (PS)

作者： Gianluca Kosmella Jaron Sanders Bin Shi Ripalta Stabile Department of EE and M&CS Eindhoven University of Technology Eindhoven The Netherlands Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven The Netherlands Department of Electrical Engineering Eindhoven University of Technology Eindhoven The Netherlands

We present how feasible duplication schemes for reducing noise in optical neural networks achieve accuracy gains when compared to implementations without duplication. Performance gains are 7.4% at a practical chip siz...

关键词：

来源：评论

学校读者我要写书评

暂无评论

An overview of common emotion models in computer systems

An overview of common emotion models in computer systems

引用

Proceedings of the International Convention MIPRO

作者： M. Horvat A. Stojanović Ž . Kovač ević Department of Applied Computing Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Department of Computer Science and Information Technology Zagreb University of Applied Sciences Zagreb Croatia

ISBN: (数字)9789532331035

ISBN: (纸本)9781665484343

Emotions are an omnipresent and important factor in the interaction and communication between people. Since emotions are an indispensable part of human life, it would accelerate the progress of artificial intelligence and other fields of science that require data about emotions if they could be adequately described by computer systems. Today there are many different theories of affect, but few of them are used in affective computing. Other areas of computing also benefit from structured and expressive data models of the affective domain, such as human-computer interaction and brain-computer interfaces. Typical tasks include automated recognition and analysis of emotional states, mental fatigue, individual motivation, vigilance and stress resilience. In this paper four often used models of emotion and cognitive behavior are listed and their properties explained: discrete, dimensional, appraisal and action tendency models. For each model, algorithms are provided for similarity measures that can be used to determine the relatedness between different stimulation and estimation artefacts in their respective emotion spaces. The goal of this article is to help professionals find the optimal emotion model for their research and quickly become familiar with data modelling of affective states.

关键词： Emotion recognition Computational modeling Estimation Human factors Brain modeling Fatigue Extraterrestrial measurements

来源：评论

学校读者我要写书评

暂无评论

The role of implementing Machine Learning approaches in enhancing the effectiveness of HealthCare service 2

The role of implementing Machine Learning approaches in enha...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Umamaheswaran, S.K. Munagala, Nvlm Krishna Mishra, Deepti Othman, Bestoon Sinthu, S. Tripathi, Vikas Sri Sai Ram Engineering College Department of Mathematics TN Chennai India Gitam Deemed to Be University Department of Electrical Electronics and Communication Engineering Andhra Pradesh Visakhapatnam India G.L. Bajaj Institute of Technology and Management Department of Computer Science and Engineering UP Greater Noida India Erbil Polytechnic University Koya Technical Institute Erbil Iraq Nawroz University College of Administration and Economics Department of Business Administration Duhok Iraq Tamilnadu Karur India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9781665437899

'Machine Learning' (ML) is a useful technology for extracting information from 'Internet of Things' (IoT) data. These hybrid systems intelligently improve decision-making in a variety of fields, including education, business, healthcare as well as security. IoT can use machine learning to decipher hidden patterns in large amounts of data, allowing for better forecasting and recommendation engines. In healthcare, ML is utilised for disease assessment and treatment predictions, as well as target discovery and verification, pharmaceutical product development, biomarker recognition, and pathogenesis. Government expenditure on healthcare has achieved an all-time peak, despite the obvious need for improved patient-physician communication. In the areas of smartphone applications, computer appliances, online websites, cybersecurity, and other areas, such techniques have already been used. A 'health prediction system' deals with the problem of unexpected changes among hospital patient flows. Emergency occurrences such as 'ambulance arrivals during natural catastrophes' and 'motor vehicle accidents', as well as normal outpatient demand, generate demand for healthcare services in many hospitals. These healthcare related issues can be managed by using ML algorithms. In order to collect important information, this research paper has considered primary quantitative or survey method by considering 78 healthcare professionals to get proper information. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

ID-Yarn: Form-factoring an RFID Tag into a Yarn and How It Can Work Well 14

ID-Yarn: Form-factoring an RFID Tag into a Yarn and How It C...

引用

14th IEEE International Conference on RFID Technology and Applications, RFID-TA 2024

作者： Chen, Tianyang Liu, Yulong Li, Zhengzheng Jiang, Yuchen Yu, Mengxia Xu, Lulu Ye, Terry Tao Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Institute of Nanoscience and Applications Southern University of Science and Technology Shenzhen China Jiaxing Research Institute Southern University of Science and Technology Jiaxing China Department of Applied Physics Hong Kong Polytechnic University Hong Kong Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore School of Mechanical Electrical and Manufacturing Engineering Loughborough University Loughborough United Kingdom

ISBN: (纸本)9798331540227

We propose a novel design for RFID tags - ID-Yarn, in which an RFID tag is integrated into a yarn suitable for weaving, embroidery, or seam attachment to fabric. ID-Yarn comprises an RFID transponder chip soldered with a conductive filament onto the chip pads. The chip and the filament are then enveloped with non-conductive fibers, creating a yarn structure. The conductive filament within the ID-Yarn serves as a dipole antenna, and various dipole antenna configurations can be achieved by shaping the ID-Yarn into different geometries. We have introduced three dipole variations: a dipole with varied arms for conjugate-matching the chip impedance, a dipole with meander-lined arms, and a dipole with looped arms. Simulations and prototypes of these variations demonstrate the feasibility of ID-Yarns. Notably, the ID-Yarn shaped into a looped dipole geometry exhibits the best performance. © 2024 IEEE.

关键词： Linen

来源：评论

学校读者我要写书评

暂无评论

Fairness in Ranking: Robustness through Randomization without the Protected Attribute

Fairness in Ranking: Robustness through Randomization withou...

引用

International Conference on Data engineering Workshops

作者： Andrii Kliachkin Eleni Psaroudaki Jakub Mareček Dimitris Fotakis Department of Mathematics Università degli Studi di Padova Padua Italy School of Electrical & Computer Engineering National Technical University of Athens Greece Athena Research & Innovation Center in Information Communication & Knowledge Technologies Athens Greece The Department of Computer Science Czech Technical University in Prague the Czech Republic

ISBN: (数字)9798350384031

ISBN: (纸本)9798350384048

There has been great interest in fairness in machine learning, especially in relation to classification problems. In ranking-related problems, such as in online advertising, recommender systems, and HR automation, much work on fairness remains to be done. Two complications arise: first, the protected attribute may not be available in many applications. Second, there are multiple measures of fairness of rankings, and optimization-based methods utilizing a single measure of fairness of rankings may produce rankings that are unfair with respect to other measures. In this work, we propose a randomized method for post-processing rankings, which do not require the availability of the protected attribute. In an extensive numerical study, we show the robustness of our methods with respect to P-Fairness and effectiveness with respect to Normalized Discounted Cumulative Gain (NDCG) from the baseline ranking, improving on previously proposed methods.

关键词： Privacy Systematics Conferences Noise Machine learning Data engineering Robustness

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Neurological Diagnostics: Integrating 6G Technology with Deep Learning for Enhanced Detection of Multiple Sclerosis and Myelitis

Revolutionizing Neurological Diagnostics: Integrating 6G Tec...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Rana M. NourEldeen Rahma A. Elshshtawy Omnia A. Elgohary Fatma Alzahraa A. Wahba Marco K. Attia Zeinab B. Abo elazm Mohamed G. Khattap Hend Galal Eldeen Mohamed Ali Hassan Mariam Mostafa Nayra Ibrahim Reem Ramadan Yomna Refaat Mennatallah Khaled Ali Maher Mohamed Abd Elaziz Ahmed Gamal Abdellatif Ibrahim Radiology and Medical Imaging Faculty of Applied Health Sciences Galala University Suez Egypt Biomedical Informatics Faculty of Computer Science and Engineering Galala University Suez Egypt Artificial Intelligence Science Program Faculty of Computer Science and Engineering Galala University Suez Egypt Department of Electronics and Electrical Communications Engineering Air Defense College Alexandria Egypt

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

This paper proposes an alternative detection frame-work for multiple sclerosis (MS) and idiopathic acute transverse myelitis (ATM) within the 6G-enabled Internet of Medical Things (IoMT) environment. The developed framework relies on the implementation of a deep learning technique known as Dense Convolutional Networks (DenseNets) in the 6G-enabled IoMT to enhance prediction performance. To validate the performance of DenseNets, we compared it with other deep learning techniques, including Convolutional Neural Networks (CNN) and MobileNet, using real-world datasets. The experimental results show the high performance of DenseNets in predicting MS and ATM compared to other methods, achieving an accuracy of nearly 90 %.

关键词： 6G mobile communication Deep learning Multiple sclerosis Accuracy Internet of Medical Things Telecommunications Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

High-Capacity Freestanding Supercapacitor Electrode Based on Electrospun Ti3c2tx Mxene/Pani/Pvdf Composite

SSRN

引用

SSRN 2024年

作者： Mohammadi, Somayeh Ahmadi, Shayan Navid, Hamid Azadvari, Reza Sanaee, Zeinab Moeini, Mohammadreza Applied Engineering Science Research Center School of Engineering Science College of Engineering University of Tehran Tehran Iran Department of Chemistry Materials and Chemical Engineering ''GIULIO NATTA'' School of Industrial and Information Engineering Politecnico di Milano Milan Italy Energy Storage Laboratory School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran

In this study, a high-capacity freestanding supercapacitor electrode was developed by the electrospinning of a Ti3C2Tx MXene/Polyaniline (PANI)/Polyvinylidene fluoride (PVDF) composite. To benefit from the synergistic effect of highly conductive two-dimensional (2D) Ti3C2Tx MXene and pseudo-capacitive PANI, MXene/PANI composite was achieved through a facile synthesis. Ti3C2Tx MXene was produced through selective etching of Ti3AlC2 using hydrofluoric (HF) acid, which was then mixed by PANI Emeraldine salt in N-Methyl-2-Pyrrolidone (NMP). PVDF was added to the composite as a flexible binder to facilitate the electro-spinning and produce a freestanding electrode. The specific capacitance of the freestanding MXene/PANI/PVDF electrode is 740 Fg-1 at a scan rate of 2 mVs-1, and 895 Fg-1 at a charge-discharge current density of 0.5 Ag-1, which was significantly higher than the specific capacitance of MXene (67 Fg-1) and PANI (54 Fg-1) electrospun electrodes. © 2024, The Authors. All rights reserved.

关键词： Supercapacitor

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：