检索结果-内蒙古大学图书馆

International Conference on Vacuum Nanoelectronics (IVNC)

作者： Richard G. Forbes Sergey V. Filippov Anatoly G. Kolosko Eugeni O. Popov University of Surrey Advanced Technology Institute & School of Computer Science and Electronic Engineering Guildford Surrey UK Division of Plasma Physics Atomic Physics and Astrophysics Ioffe Institute St Petersburg Russia

This presentation is part of a long-term project to put field electron emission (FE) onto a better scientific basis, by seeking reliable quantitative agreement between theory and experiment, especially as regards emission-current values. The main paper aims are: (1) to respond to remarks made in recent papers [1], [2]; (2) to restate the thinking behind our 2022 methodology [3] for choosing between different FE models using experiments; (3) to assess progress; and (4) to make further suggestions about improved approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory Prediction

arXiv

引用

arXiv 2023年

作者： Sun, Ge Wang, Sheng Zhu, Lei Liu, Ming Ma, Jun Division of Emerging Interdisciplinary Areas The Hong Kong University of Science and Technology Hong Kong Guangzhou China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Accurate prediction of pedestrian trajectories is crucial for improving the safety of autonomous driving. However, this task is generally nontrivial due to the inherent stochasticity of human motion, which naturally requires the predictor to generate multi-modal prediction. Previous works leverage various generative methods, such as GAN and VAE, for pedestrian trajectory prediction. Nevertheless, these methods may suffer from mode collapse and relatively low-quality results. The denoising diffusion probabilistic model (DDPM) has recently been applied to trajectory prediction due to its simple training process and powerful reconstruction ability. However, current diffusion-based methods do not fully utilize input information and usually require many denoising iterations that lead to a long inference time or an additional network for initialization. To address these challenges and facilitate the use of diffusion models in multi-modal trajectory prediction, we propose GDTS, a novel Goal-Guided Diffusion Model with Tree Sampling for multi-modal trajectory prediction. Considering the "goal-driven" characteristics of human motion, GDTS leverages goal estimation to guide the generation of the diffusion network. A two-stage tree sampling algorithm is presented, which leverages common features to reduce the inference time and improve accuracy for multi-modal prediction. Experimental results demonstrate that our proposed framework achieves comparable state-of-the-art performance with real-time inference speed in public datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence based Models to Support Water Quality Prediction using Machine Learning Approach

Artificial Intelligence based Models to Support Water Qualit...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： P. William Oluwadare Joshua Oyebode Gandikota Ramu Manish Gupta Dibyhash Bordoloi Anurag Shrivastava Department of Information Technology Sanjivani College of Engineering Savitribai Phule Pune University Pune India Civil and Environmental Engineering Afe Babalola University Ado-Ekiti Ekiti State Nigeria Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad Division of Research and Development Lovely Professional University Phagwara India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu India

The purpose of this study is to simulate the propagation of bio-contamination risk in Water Distribution System (WDS). This will be accomplished by putting an emphasis on source identification and response modelling. This will be accomplished in the WDS via the process of simulating the bio-contamination risk propagation under real environmental circumstances. This will be done in order to accomplish this goal. Due to the failure to take into consideration the ability for the bulk of the pollutants to undergo chemical degradation and the neglecting of dynamic responses, an overestimation of the population that is exposed has resulted. The study presented here takes into account the connected change in a variety of water quality indicators that are caused by the mixing of the pollutants. These measurements include the total organic carbon content, pH, and alkalinity. In practise, the baseline requirements for each of the aforementioned metrics are set at the beginning of the regular WDS monitoring. Contamination is then indicated by considerable deviations from the base line. The study's goal was to determine whether it is feasible to develop a smart monitoring system powered by artificial intelligence (AI) that would successfully enable water operators to ensure near real-time quality control for the early detection of chemical and/or biological pollution and risk management. The study's goal was to see whether it was possible to develop an artificial intelligence (AI)-based smart monitoring system. The study's purpose was to investigate the viability of building a sophisticated monitoring system that would allow water operators to perform quality control in near real time. Artificial Neural Networks (ANN) and other sophisticated pattern recognizers like Support Vector Machines (SVMs) are examples of cutting-edge sensor technologies that have been implemented as solutions to identify anomalies and estimate the severity of such irregularities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spectral Characterization of a Terahertz Vortex Beam Generated Via a Two-Photon Lithography Printed Spiral Phase Plate

Spectral Characterization of a Terahertz Vortex Beam Generat...

引用

Photonics North

作者： Andreea Aura Paraipan Diana Gonzalez-Hernandez Innem V. A. K. Reddy Giacomo Balistreri Luca Zanotto Mostafa Shalaby Roberto Morandotti Carlo Liberale Luca Razzari Centre Energie Matériaux Telecommunications (INRS-EMT) Institut National de la Recherche Scientifique Varennes QC Canada Biologcal and Environmental Science Biological and Environmental Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwai Kingdom of Saudi Arabia Deparment of Electrical Engineering University of Buffalo Buffalo New York USA Swiss Terahertz Research-Zürich Zürich Switzerland Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) ThuwaI Kingdom of Saudi Arabia

ISBN: (数字)9798350366365

ISBN: (纸本)9798350366372

A terahertz (THz) vortex beam is generated through a spiral phase plate fabricated via two-photon polymerization lithography (TPL). TPL is a three-dimensional (3D) printing technique that exhibits high resolution and low surface roughness enabling the fabrication of high-frequency THz devices. The SPP is characterized via a scanless THz time-domain imaging (TDI) technique that allows to obtain a coherent hyperspectral analysis of the generated vortex beam. Numerical simulations are also conducted for comparison with experiments, revealing a good agreement.

关键词： Terahertz wave imaging Spirals Lithography Three-dimensional printing Numerical simulation Surface roughness Rough surfaces

来源：评论

学校读者我要写书评

暂无评论

GAN-enabled framework for fire risk assessment and mitigation of building blueprints 30

GAN-enabled framework for fire risk assessment and mitigatio...

引用

30th International Conference on Intelligent Computing in engineering 2023, EG-ICE 2023

作者： Ye, Mao Chen, Long Milne, Alistair Hillier, John Sølvsten, Simon Wuhan Zhongyuan Electronic Group Co. Ltd. China Department of Computer Science Loughborough University United Kingdom School of Architecture Building and Civil Engineering Loughborough University United Kingdom School of Business and Economics Loughborough University United Kingdom Department of Geography and Environment Loughborough University United Kingdom Department of Sociology Environmental and Business Economics University of Southern Denmark Denmark

Fire risk posed by residential buildings endangers individuals' lives and safety but also severely impacts economic activities of a society. Consequently, minimising the risk of fire and reduce losses through the development of effective solutions for fire risk assessment and mitigation was, is and will remain crucial. This paper proposes a systematic framework for assessing and mitigating fire risk in buildings that incorporates hybrid of computer vision and artificial intelligence techniques. This framework relies on the automatic blueprint interpretation and can handle both manual and digital blueprints relying on the connectivity analysis of room layout. A well-trained connectivity-constrained generative adversarial network (cc-GAN) has been developed to redesign the original building blueprints to meet fire safety criteria. Overall, our work aims to offer building designers and engineers a practical tool for enhancing the fire safety performance of building layouts. © 2023 30th EG-ICE: International Conference on Intelligent Computing in engineering 2023. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Battle Against Fluctuating Quantum Noise: Compression-Aided Framework to Enable Robust Quantum Neural Network

Battle Against Fluctuating Quantum Noise: Compression-Aided ...

引用

Design Automation Conference

作者： Zhirui Hu Youzuo Lin Qiang Guan Weiwen Jiang Electrical and Computer Engineering Department George Mason University Fairfax VA US Quantum Science and Engineering Center George Mason University Fairfax VA US Earth and Environmental Sciences Division Los Alamos National Laboratory NM US Department of Computer Science Kent State University Kent OH

Recently, we have been witnessing the scale-up of superconducting quantum computers; however, the noise of quantum bits (qubits) is still an obstacle for real-world applications to leveraging the power of quantum computing. Although there exist error mitigation or error-aware designs for quantum applications, the inherent fluctuation of noise (a.k.a., instability) can easily collapse the performance of error-aware designs. What’s worse, users can even not be aware of the performance degradation caused by the change in noise. To address both issues, in this paper we use Quantum Neural Network (QNN) as a vehicle to present a novel compression-aided framework, namely QuCAD, which will adapt a trained QNN to fluctuating quantum noise. In addition, with the historical calibration (noise) data, our framework will build a model repository offline, which will significantly reduce the optimization time in the online adaption process. Emulation results on an earthquake detection dataset show that QuCAD can achieve 14.91% accuracy gain on average in 146 days over a noise-aware training approach. For the execution on a 7-qubit IBM quantum processor, ibm-jakarta, QuCAD can consistently achieve 12.52% accuracy gain on earthquake detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fused Fuzzy Deep Learning and Information Steganography for Privacy Preservation in Medical Consumer electronics

引用

IEEE Transactions on Consumer electronics 2025年

作者： Chen, Jingxue Zhao, Pengbiao Deng, Erqiang Khan, Fazlullah Alturki, Ryan Alshawi, Bandar Xiong, Hu School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China the School of Computer Science Faculty of Science and Engineering University of Nottingham Ningbo China Zhejiang Ningbo315104 China the KKR and KSR institute of technology and sciences Andhra Pradesh Guntur India the Division of Research and Development Lovely Professional University Phagwara India the University Centre of Research and Development Chandigarh University Mohali India the Department of Computer and Network Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia the Department of Software Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia

—Medical Consumer electronics (MCE) have greatly facilitated people’s lives, allowing patients to obtain personal medical information including medical images. These medical images obtained from MCE need to be processed using segmentation, diagnosis, recognition to obtain useful information. Deep learning plays an important role in medical image segmentation and recognition. However, other personal information about the patient, such as previous cases, is often required to determine the final diagnosis. However, sending personal information and medical images generated through MCE to the clinic directly exposes patient privacy. Therefore, in this paper, we propose a digital medical image privacy protection framework based on information steganography with fuzzy deep learning. The proposed framework transforms patient privacy information into invisible noise and hides it in the deep covert space of the image. This method plays a crucial role in ensuring patient privacy and data security. Furthermore, this method can ensure a high level of image segmentation accuracy that supports the development of personalized medical services. The experimental results show that the proposed framework can embed patient information in medical images without affecting the segmentation task, and effectively protect privacy. Finally, the proposed framework provides new possibilities and impetus for the popularization of MCE. © 2025 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Research and Implement a Virtual Reality System for Parkinson's Disease Rehabilitation Training 8

Research and Implement a Virtual Reality System for Parkinso...

引用

8th International Conference on Virtual Reality, ICVR 2022

作者： Li, Ming-Nan Gao, He-Bei Shi, Hao-Wen Pan, Zhi-Geng Wang, Peng-Jun Li, Hong College of Computer Science and Artificial Intelligence Wenzhou University Wenzhou China Hangzhou Normal University Division of Health Sciences Hangzhou China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China College of Electrical and Electronic Engineering Wenzhou University Wenzhou China

ISBN: (数字)9781665479110

ISBN: (纸本)9781665479110

Rehabilitation training systems using virtual reality (VR) techniques offer a cost-effective alternative to conventional training methods. This paper investigated the implementation of VR in motor function rehabilitation training. We describe our experience in researching and developing VR-based rehabilitation training systems for the patient with early state of Parkinson's Disease (PD). By analyzing the correlation of Virtual Reality feature and the dysfunction of Parkinson's disease a rehabilitation training system framework is proposed in this work. In this paper, we propose a rehabilitation training system framework by analyzing the correlation between virtual reality features and Parkinson's disease dysfunction. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

QAUST:Protein Function Prediction Using Structure Similarity,Protein Interaction,and Functional Motifs

引用

Genomics, Proteomics & Bioinformatics 2021年第6期19卷 998-1011页

作者： Fatima Zohra Smaili Shuye Tian Ambrish Roy Meshari Alazmi Stefan T.Arold Srayanta Mukherjee P.Scott Hefty Wei Chen Xin Gao Computational Bioscience Research Center(CBRC) ComputerElectrical and Mathematical Sciences and Engineering(CEMSE)DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955Saudi Arabia Department of Biology Southern University of Science and Technology of China(SUSTC)Shenzhen 518055China Department of Computational Medicine and Bioinformatics University of MichiganAnn ArborMI 48109USA College of Computer Science and Engineering University of Ha’ilHa'il 55476Saudi Arabia Biological and Environmental Sciences and Engineering(BESE)Division King Abdullah University of Science and Technology(KAUST)Thuwal 23955Saudi Arabia Department of Molecular Bioscience University of KansasLawrenceKS 66047USA

The number of available protein sequences in public databases is increasing ***,a sig-nificant percentage of these sequences lack functional annotation,which is essential for the understanding of how bio-logical systems ***,we propose a novel method,Quantitative Annotation of Unknown STructure(QAUST),to infer protein functions,specifically Gene Ontology(GO)terms and Enzyme Commission(EC)*** uses three sources of information:structure information encoded by global and local structure similarity search,biological network information inferred by protein–protein interaction data,and sequence information extracted from functionally discriminative sequence *** three pieces of information are combined by consensus averaging to make the final *** approach has been tested on 500 protein targets from the Critical Assessment of Functional Annotation(CAFA)benchmark *** results show that our method provides accurate functional annotation and outperforms other prediction methods based on sequence similarity search or *** further demonstrate that a previously unknown function of human tripartite motif-containing 22(TRIM22)protein predicted by QAUST can be experimentally validated.

关键词： Protein function prediction GO term EC number Protein structure similarity Functionally discriminative motif

来源：评论

学校读者我要写书评

暂无评论

USING THE GAF TRANSFORM AND MODIS TIME-SERIES TO PERFORM LANDCOVER CLASSIFICATION AND CHANGE DETECTION

USING THE GAF TRANSFORM AND MODIS TIME-SERIES TO PERFORM LAN...

引用

2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

作者： Grobler, T.L. Kleynhans, W. Salmon, B.P. Dept of Mathematical Sciences Computer Science Division Stellenbosch University Private Bag X1 Matieland7602 South Africa Department of Electrical Electronic and Computer Engineering University of Pretoria Pretoria0002 South Africa School of Engineering University of Tasmania HobartTAS7001 Australia

The Gramien Angular Field (GMF) transform encodes time-series into images so that image based classification approaches can be exploited to perform time-series classification. Settlement expansion is one of the most pervasive forms of landcover change in sub-saharan Africa. In this paper, we show that the GAF transform outperforms the conventional techniques we compared against when it is employed in conjunction with Moderate Resolution Imaging Spectroradiometer (MODIS) time-series to detect settlement expansion in the Gauteng province of South Africa. © 2021 IEEE.

关键词： Expansion

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：