检索结果-内蒙古大学图书馆

2021 IEEE India Geoscience and Remote Sensing Symposium, InGARSS 2021

作者： Kowkabi, Fatemeh Keshavarz, Ahmad Kumar, Lalit Islamic Azad University College of Engineering Marvdasht Branch Department of Electrical Engineering Marvdasht Iran Persian Gulf University IoT and Signal Processing Research Group Ict Research Institute Faculty of Intelligent Systems Engineering and Data Science Bushehr*** Iran EastCoast Geospatial Consultants ArmidaleNSW2350 Australia

ISBN: (纸本)9781665442497

Hyperspectral images have wide application in different commercial and military missions. However, these images suffer from the low spatial resolution, and hence, spectral unmixing has been proposed as a suitable technique to solve this deficiency. Recently, some preprocessing modules have been proposed which use the combination of spatial and spectral information of image pixels with the purpose of improving endmember extraction and spectral unmixing in hyperspectral images. In this paper, we propose a statistical preprocessing algorithm using weighted extended cumulative entropy (WECE) as the Edge Detection algorithm to identify spectrally pure pixels and KL distance estimation using the mean and covariance values of pure oversegments and their neighbors to find the spatially homogenous and spectrally pure pixels for the next endmember extraction algorithms. Moreover, the average of KL distances are applied due to the reduction of noise power and local spectral variability. The performance of the novel statistical preprocessing algorithm has been compared with the sate-of-the-art in terms of RMSE reconstruction and average SAD errors on two real hyperspectral images known as HYDICE urban and AVIRIS Indian Pines in combination with several endmember extraction (EE) algorithms and its efficiency is evaluated. © 2021 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Performance improvement by enhancing spatial parallelism on FPGA for HPC applications

Performance improvement by enhancing spatial parallelism on ...

引用

IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS)

作者： Yuka Sano Taisuke Boku Mitsuhisa Sato Miwako Tsuji Norihisa Fujita Ryohei Kobayashi Degree Programs in Systems and Information Engineering University of Tsukuba Japan Center for Computational Sciences University of Tsukuba Japan Faculty of Health Data Science Juntendo University Japan Center for Computational Science RIKEN Japan

In today’s HPC systems, GPUs with high computational performance and memory bandwidth under relatively low power consumption are the leading players. However, GPU-based acceleration is designed to excel when utilizing many computation cores and performing SIMD/STMD manner of synchronized computation over a large number of uniform data array elements. Therefore, it may not fully exploit its computational performance in calculations with low parallelism, complex operations involving conditional branching, or parallel applications with frequent inter-node communication to interrupt continuous computing on GPU devices. One of the alternative solutions for accelerated computing is FPGA (Field Programmable Gate Array), especially with recent advancements in devices containing a large number of logic elements, high memory bandwidth, and even multiple channels of high-speed optical interconnection interfaces, reaching up to 100 Gbps for each. The performance of an FPGA is based on pipeline parallelism, enabling the computation stream to continue even with conditional branches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resilience analysis of maritime transportation networks:a systematic review

引用

Transportation Safety and Environment 2024年第4期6卷 1-13页

作者： Di Zhang Jiale Tao Chengpeng Wan Liang Huang Ming Yang State Key Laboratory of Maritime Technology and Safety Wuhan University of TechnologyWuhan 430063China School of Transportation and Logistics Engineering Wuhan University of TechnologyWuhan 430063China Intelligent Transportation Systems Research Center Wuhan University of TechnologyWuhan 430063China Inland Port and Shipping Industry Research Co. Ltd.of Guangdong ProvinceShaoguan 512100China Sanya Science and Education Innovation Park Wuhan University of TechnologySanya 572000China Safety and Security Science Section Faculty of TechnologyPolicy and ManagementDelft University of TechnologyDelft 2600GBNetherlands Australia Maritime College University of TasmaniaLauncestonTasmania 7005Australia

As supply chains in today’s world become more complex and fragile,enhancing the resilience of maritime transport is increasingly *** COVID-19 epidemic in 2020 exposed the vulnerability of existing supply chains,causing substantial impacts such as supply shortages,procurement constraints,logistics delays and port congestion,highlighting the need to build resilient maritime transportation networks(MTNs)and reigniting research on the resilience of maritime *** on science mapping,we quantitatively analysed the domain of resilience of *** mainly study the resilience of MTNs from the following aspects:the construction of MTNs and their topological characterization,vulnerability-orientated resilience analysis of MTNs,recovery-orientated resilience analysis of MTNs,investment decision-orientated resilience analysis of MTNs,climate change-orientated resilience analysis of MTNs and pandemic-orientated resilience analysis of *** study reviews recent advances in MTN resilience research,highlighting research topics,shortcomings and future research agenda.

关键词： maritime transportation networks(MTNs) science mapping approach maritime transport resilience

来源：评论

学校读者我要写书评

暂无评论

Visual–Semantic Graph Matching Net for Zero-Shot Learning

引用

IEEE Transactions on Neural Networks and Learning systems 2024年第6期36卷 10171-10185页

作者： Bowen Duan Shiming Chen Yufei Guo Guo-Sen Xie Weiping Ding Yisong Wang School of Computer Science and Technology and the Institute for Artificial Intelligence Guizhou University Guiyang Guizhou China Department of Computer Vision Mohamed bin Zayed University of AI Abu Dhabi United Arab Emirates Intelligent Science and Technology Academy CASIC Beijing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Artificial Intelligence and Computer Science Nantong University Nantong China Faculty of Data Science City University of Macau Macau China

Zero-shot learning (ZSL) aims to leverage additional semantic information to recognize unseen classes. To transfer knowledge from seen to unseen classes, most ZSL methods often learn a shared embedding space by simply aligning visual embeddings with semantic prototypes. However, methods trained under this paradigm often struggle to learn robust embedding space because they align the two modalities in an isolated manner among classes, which ignore the crucial class relationship during the alignment process. To address the aforementioned challenges, this article proposes a visual-semantic graph matching net (VSGMN), which leverages semantic relationships among classes to aid in visual-semantic embedding. VSGMN uses a graph build net (GBN) and a graph matching net (GMN) to achieve two-stage visual-semantic alignment. Specifically, GBN first uses an embedding-based approach to build visual and semantic graphs in the semantic space and align the embedding with its prototype for first-stage alignment. In addition, to supplement unseen class relationships in these graphs, GBN also builds the unseen class nodes based on semantic relationships. In the second stage, GMN continuously integrates neighbor and cross-graph information into the constructed graph nodes and aligns the node relationships between the two graphs under the class relationship constraint. Extensive experiments on three benchmark datasets demonstrate that VSGMN achieves superior performance in both conventional and generalized ZSL (GZSL) scenarios. The implementation of our VSGMN and experimental results are available at github: https://***/dbwfd/VSGMN .

关键词： Semantics Visualization Zero shot learning Prototypes Vectors Manifolds Graph neural networks Benchmark testing Training Space mapping

来源：评论

学校读者我要写书评

暂无评论

Enabling surrogate-assisted evolutionary reinforcement learning via policy embedding

arXiv

引用

arXiv 2023年

作者： Tang, Lan Li, Xiaxi Zhang, Jinyuan Li, Guiying Yang, Peng Tang, Ke Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Faculty of engineering Shenzhen MSU-BIT university Shenzhen518172 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China

Evolutionary Reinforcement Learning (ERL) that applying Evolutionary Algorithms (EAs) to optimize the weight parameters of Deep Neural Network (DNN) based policies has been widely regarded as an alternative to traditional reinforcement learning methods. However, the evaluation of the iteratively generated population usually requires a large amount of computational time and can be prohibitively expensive, which may potentially restrict the applicability of ERL. Surrogate is often used to reduce the computational burden of evaluation in EAs. Unfortunately, in ERL, each individual of policy usually represents millions of weights parameters of DNN. This high-dimensional representation of policy has introduced a great challenge to the application of surrogates into ERL to speed up training. This paper proposes a PE-SAERL Framework to at the first time enable surrogate-assisted evolutionary reinforcement learning via policy embedding (PE). Empirical results on 5 Atari games show that the proposed method can perform more efficiently than the four state-of-the-art algorithms. The training process is accelerated up to 7x on tested games, comparing to its counterpart without the surrogate and PE. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Methods for Kernel Initialization of Convolutional Neural Network Model Applied to Plant Disease Classification

Adaptive Methods for Kernel Initialization of Convolutional ...

引用

Electrical, Electronic and Information sciences (eStream), Open Conference of

作者： Saloua Lagnaoui Khaoula Boumais Saad El Fallah Zakariae En-Naimani Khalid Haddouch Dalius Matuzevičius Laboratory Engineering Systems and Applications ENSA Sidi Mohamed Ben Abdellah University Fez Morocco Laboratory AI Data Science and Emerging Systems Sidi Mohammed ben Abdallah University ENSA Fez Morocco Systems and Sustainable Environment Laboratory Faculty of Engineering Sciences Private University of Fez Fez Morocco Laboratory Computer Science AI and Cyber Security ENSET University of Hassan II Casablanca Mohammedia Morocco Department of Electronic Systems Faculty of Electronics Vilnius Gediminas Technical University Vilnius Lithuania

ISBN: (数字)9798350352412

ISBN: (纸本)9798350352429

Convolutional Neural Networks are instrumental in artificial intelligence, especially in image processing, where their ability to autonomously learn hierarchical features has led to significant breakthroughs. However, the success of these models is intricately tied to the judicious choice of hyperparameters, which include the configuration of convolutional layers, activation functions, and kernel initialization methods. This research explores kernel initialization methods in Convolutional Neural Network models, seven diverse initialization methods (Glorot Uniform, Ones initialization, Zero initialization, Constant initialization, Random initialization, HeNormal initialization, and Orthogonal initialization) are comprehensively compared. The primary objective is to showcase the sensitivity of Convolutional Neural Networks to these various initialization techniques. The study not only aims to reveal the nuanced impact of kernel initialization but also introduces an adaptive method to enhance model performance. By delving into the intricacies of initialization methods, this research contributes to the improvement of Convolutional Neural Networks effectiveness, especially in critical applications like Plant Disease classification.

关键词： Training Plant diseases Adaptation models Sensitivity Neural networks Convolutional neural networks Kernel

来源：评论

学校读者我要写书评

暂无评论

The graphene squeeze-film microphone

arXiv

引用

arXiv 2024年

作者： Abrahams, M.P. Martinez, J. Steeneken, P.G. Verbiest, G.J. Department of Precision and Microsystems Engineering Delft University of Technology Mekelweg 2 Delft2628 CD Netherlands Multimedia Computing Group Intelligent Systems Department Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2628 XE Netherlands

Most microphones operate by detecting the sound-pressure induced motion of a membrane. In contrast, here we introduce a microphone that operates by monitoring the sound-pressure-induced modulation of the compressibility of air. By driving a graphene membrane at its resonance frequency, the gas, that is trapped in a squeeze-film beneath it, is compressed at high frequency. Since the stiffness of the gas film depend on the air pressure, the resonance frequency of the graphene is modulated by variations in sound pressure. We demonstrate that this squeeze-film microphone principle can be used to detect sound and music by tracking the membrane's resonance frequency using a phase-locked loop (PLL). Since the sound detection principle is different from conventional devices, the squeeze-film microphone potentially offers advantages like increased dynamic range, and a lower susceptibility to pressure-induced failure and vibration-induced noise. Moreover, it might be made much smaller, as demonstrated by the microphone in this work that operates using a circular graphene membrane with an area that is more than a factor 1000 smaller than that of MEMS microphones. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

OptiPMB: Enhancing 3D Multi-Object Tracking with Optimized Poisson Multi-Bernoulli Filtering

arXiv

引用

arXiv 2025年

作者： Ding, Guanhua Xia, Yuxuan Guan, Runwei Wu, Qinchen Huang, Tao Ding, Weiping Sun, Jinping Mao, Guoqiang School of Electronic Information Engineering Beihang University Beijing100191 China Department of Automation Shanghai Jiaotong University Shanghai200240 China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Guangzhou511455 China College of Science and Engineering James Cook University SmithfieldQLD4878 Australia School of Artificial Intelligence and Computer Science Nantong University Nantong226019 China Faculty of Data Science City University of Macau 999078 China Research Laboratory of Smart Driving and Intelligent Transportation Systems Southeast University Nanjing210096 China

Accurate 3D multi-object tracking (MOT) is crucial for autonomous driving, as it enables robust perception, navigation, and planning in complex environments. While deep learning-based solutions have demonstrated impressive 3D MOT performance, model-based approaches remain appealing for their simplicity, interpretability, and data efficiency. Conventional model-based trackers typically rely on random vector-based Bayesian filters within the tracking-by-detection (TBD) framework but face limitations due to heuristic data association and track management schemes. In contrast, random finite set (RFS)-based Bayesian filtering handles object birth, survival, and death in a theoretically sound manner, facilitating interpretability and parameter tuning. In this paper, we present OptiPMB, a novel RFS-based 3D MOT method that employs an optimized Poisson multi-Bernoulli (PMB) filter while incorporating several key innovative designs within the TBD framework. Specifically, we propose a measurement-driven hybrid adaptive birth model for improved track initialization, employ adaptive detection probability parameters to effectively maintain tracks for occluded objects, and optimize density pruning and track extraction modules to further enhance overall tracking performance. Extensive evaluations on nuScenes and KITTI datasets show that OptiPMB achieves superior tracking accuracy compared with state-of-the-art methods, thereby establishing a new benchmark for model-based 3D MOT and offering valuable insights for future research on RFS-based trackers in autonomous driving. Copyright © 2025, The Authors. All rights reserved.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

High-Quality Sonar Image Generation Algorithm Based on Generative Adversarial Networks

High-Quality Sonar Image Generation Algorithm Based on Gener...

引用

第40届中国控制会议

作者： Zhengyang Wang Qingchang Guo Min Lei Shuxiang Guo Xiufen Ye College of Intelligent Systems Science and Engineering Harbin Engineering University Department of Intelligent Mechanical Systems Engineering Faculty of EngineeringKagawa University

In this paper,we propose a high-quality sonar image generation model based on generative adversarial networks,which is used to generate user-controlled high-resolution and high-quality sonar images,so that the targets in these images have more obvious features and can be further used in engineering applications such as target detection and image *** a result of the development of underwater detection technology,sonar target detection technology is widely used in various engineering *** resolution and high-quality underwater sonar images have become an indispensable part of underwater ***,due to the high cost of sonar and the high cost of marine experiments,sonar datasets are *** then,few sonar data can be obtained,and most images have no target and have more noise so that they cannot be used for underwater *** recent years,using generative adversarial networks to generate images has gradually become an important method of solving the problem of data *** there are still some shortcomings—the images produced are poor and the resolution is *** overcome the issue of poor image quality and low resolution caused by gradient disappearing and sudden change in the training process,we,therefore,use a controllable multi-layer transposed convolutional layer and gradient correction term to improve image resolution and image quality.A simple network structure does not make the model difficult to train,and the user may change the size of the generated image by simply changing the convolution parameter i to achieve the objective of improving the ***,the gradient correction term added in the training phase will always restrict the gradient to a certain *** a certain degree,the problems of gradient disappearing and gradient sudden change in model training can be overcome,thereby providing a guarantee for the production of high-quality *** demonstrate that this method will successfully

关键词： Generative Adversarial Networks Sonar Image Generation Trarnsposed Convolution Gradient Correction Term Underwater Detection

来源：评论

学校读者我要写书评

暂无评论

Tiny noise, big mistakes: adversarial perturbations induce errors in brain–computer interface spellers

引用

National science Review 2021年第4期8卷 78-90页

作者： Xiao Zhang Dongrui Wu Lieyun Ding Hanbin Luo Chin-Teng Lin Tzyy-Ping Jung Ricardo Chavarriaga Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and Technology School of Civil Engineering and Mechanics Huazhong University of Science and Technology Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Swartz Center for Computational Neuroscience Institute for Neural ComputationUniversity of California San Diego Center for Advanced Neurological Engineering Institute of Engineering in Medicine University of California San Diego ZHAW Data Lab Zürich University of Applied Sciences

An electroencephalogram(EEG)-based brain–computer interface(BCI) speller allows a user to input text to a computer by thought. It is particularly useful to severely disabled individuals, e.g. amyotrophic lateral sclerosis patients, who have no other effective means of communication with another person or a *** studies so far focused on making EEG-based BCI spellers faster and more reliable; however, few have considered their security. This study, for the first time, shows that P300 and steady-state visual evoked potential BCI spellers are very vulnerable, i.e. they can be severely attacked by adversarial perturbations,which are too tiny to be noticed when added to EEG signals, but can mislead the spellers to spell anything the attacker wants. The consequence could range from merely user frustration to severe misdiagnosis in clinical applications. We hope our research can attract more attention to the security of EEG-based BCI spellers, and more broadly, EEG-based BCIs, which has received little attention before.

关键词： electroencephalogram brain-computer interfaces BCI spellers adversarial examples

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：