检索结果-内蒙古大学图书馆

A Synchronous Parallel Method with Parameters Communication Prediction for Distributed Machine Learning 19th

A Synchronous Parallel Method with Parameters Communication...

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yanguo Xue, Meiting Xu, Peiran Shi, Yukun Zeng, Kaisheng Zhang, Jilin Yue, Lupeng School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China National University of Defense Technology Changsha China School of Cyberspace HangZhou Dianzi University Hangzhou China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9783031545306

With the development of machine learning technology in various fields, such as medical care, smart manufacturing, etc., the data has exploded. It is a challenge to train a deep learning model for different application domains with large-scale data and limited resources of a single device. The distributed machine-learning technology, which uses a parameter server and multiple clients to train a model collaboratively, is an excellent method to solve this problem. However, it needs much communication between different devices with limited communication resources. The stale synchronous parallel method is a mainstream communication method to solve this problem, but it always leads to high synchronization delay and low computing efficiency as the inappropriate delay threshold value set by the user based on experience. This paper proposes a synchronous parallel method with parameters communication prediction for distributed machine learning. It predicts the optimal timing for synchronization, which can solve the problem of long synchronization waiting time caused by the inappropriate threshold settings in the stale synchronous parallel method. Moreover, it allows fast nodes to continue local training while performing global synchronization, which can improve the resource utilization of work nodes. Experimental results show that compared with the delayed synchronous parallel method, the training time and quality, and resource usage of our method are both significantly improved. © ICST Institute for Computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

FISS GAN:A Generative Adversarial Network for Foggy Image Semantic Segmentation

引用

IEEE/CAA Journal of Automatica Sinica 2021年第8期8卷 1428-1439页

作者： Kunhua Liu Zihao Ye Hongyan Guo Dongpu Cao Long Chen Fei-Yue Wang School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510006China State Key Laboratory of Automotive Simulation and Control and the Department of Control Science and Engineering Jilin University(Campus Nanling)Changchun 130025China Mechanical and Mechatronics Engineering Department at the University of Waterloo 200 University Avenue West WaterlooON N2L 3G1Canada State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

Because pixel values of foggy images are irregularly higher than those of images captured in normal weather(clear images),it is difficult to extract and express their *** method has previously been developed to directly explore the relationship between foggy images and semantic segmentation *** investigated this relationship and propose a generative adversarial network(GAN)for foggy image semantic segmentation(FISS GAN),which contains two parts:an edge GAN and a semantic segmentation *** edge GAN is designed to generate edge information from foggy images to provide auxiliary information to the semantic segmentation *** semantic segmentation GAN is designed to extract and express the texture of foggy images and generate semantic segmentation *** on foggy cityscapes datasets and foggy driving datasets indicated that FISS GAN achieved state-of-the-art performance.

关键词： Edge GAN foggy images foggy image semantic segmentation GAN semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

High Efficiency Formamidinium-Cesium Perovskite-Based Radio-Photovoltaic Cells

引用

Energy & Environmental Materials 2024年第1期7卷 160-167页

作者： Runlong Gao Rui Chen Pengying Wan Xiao Ouyang Qiantao Lei Qi Deng Xinyu Guan Guangda Niu Jiang Tang Wei Chen Zonghao Liu Xiaoping Ouyang Linyue Liu Sino-French Institute of Nuclear Engineering and Technology Sun Yat-Sen UniversityZhuhai 519082China State Key Laboratory of Intense Pulsed Radiation Simulation and Effect Northwest Institute of Nuclear TechnologyXi'an 710024China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China School of Microelectronics Xi'an Jiaotong UniversityXi'an 710049China Key Laboratory of Beam Technology of Ministry of Education College of Nuclear Science and TechnologyBeijing Normal UniversityBeijing 100875China Shanghai Institute of Applied Physics Chinese Academy of SciencesShanghai 201800China

Radio-photovoltaic cell is a micro nuclear battery for devices operating in extreme environments,which converts the decay energy of a radioisotope into electric energy by using a phosphor and a photovoltaic *** phosphors with high light yield and good environmental stability have been developed,but the performance of radio-photovoltaic cells remains far behind expectations in terms of power density and power conversion efficiency,because of the poor photoelectric conversion efficiency of traditional photovoltaic converters under low-light *** paper reports an radio-photovoltaic cell based on an intrinsically stable formamidinium-cesium perovskite photovoltaic converter exhibiting a wide light wavelength response from 300 to 800 nm,high open-circuit voltage(V_(oc)),and remarkable efficiency at low-light *** a He ions accelerator is adopted as a mimickedαradioisotope source with an equivalent activity of 0.83 mCi cm^(-2),the formamidinium-cesium perovskite radio-photovoltaic cell achieves a V_(oc)of 0.498 V,a short-circuit current(J_(sc))of 423.94 nA cm^(-2),and a remarkable power conversion efficiency of 0.886%,which is 6.6 times that of the Si reference radio-photovoltaic cell,as well as the highest among all radio-photovoltaic cells reported so *** work provides a theoretical basis for enhancing the performance of radio-photovoltaic cells.

关键词： formamidinium-cesium perovskite phosphor photovoltaic converter power conversion efficiency radio-photovoltaic cell

来源：评论

学校读者我要写书评

暂无评论

What have we known so far for fluorescence staining and quantification of microplastics:A tutorial review

引用

Frontiers of Environmental science & engineering 2022年第1期16卷 37-50页

作者： Shengdong Liu Enxiang Shang Jingnan Liu Yining Wang Nanthi Bolan MBKirkham Yang Li Key Laboratory of Water and Sediment Sciences of Ministry of Education State Key Laboratory of Water Environment SimulationSchool of EnvironmentBeijing Normal UniversityBeijing 100875China College of Science and Technology Hebei Agricultural UniversityHuanghua 061100China School of Agriculture and Environment The University of Western AustraliaPerthWA 6001Australia The UWA Institute of Agriculture The University of Western AustraliaPerthWA 6001Australia Global Innovative Centre for Advanced Nanomaterials College of EngineeringScience and EnvironmentUniversity of NewcastleCallaghanNSW 2308Australia Department of Agronomy Throckmorton Plant Sciences CenterKansas State UniversityManhattanKS 66506USA

Understanding the fate and toxicity of microplastics(MPs,<5 mm plastic particles)is limited by quantification *** paper summarizes the methods in use and presents new ***,sampling and pretreatment processes ofMPs,including sample collection,digestion,density separation,and quality control are *** the promising and convenient staining procedures and quantification methods for MPs using fluorescence dyes are *** factors that influence the staining of MPs,including their physicochemical properties,are summarized to provide an optimal operation *** general,the digestion step is crucial to eliminate natural organic matter(NOM)to avoid interference in *** was reported to be the most appropriate solvent,and 10–20μg/mL are recommended as optimal dye *** addition,a heating and cooling procedure is recommended to maintain the fluorescence intensity of MPs for two *** staining,a fluorescence microscope is usually used to characterize the morphology,mass,or number of MPs,but compositional analysis cannot be determined with *** fluorescence staining methods have been implemented to study MP abundance,transport,and toxicity and have been combined with other chemical characterization techniques,such as Fourier transform infrared spectroscopy and Raman *** studies are needed to focus on the synthesis of novel dyes to avoid NOM’s *** need to be combined with other spectroscopic techniques to characterize plastic composition and to develop image-analysis *** stability of stained MPs needs to be improved.

关键词： Plastic particles Fluorescence dyes Identification Concentration quantification

来源：评论

学校读者我要写书评

暂无评论

Photocatalytic Degradation of Tetracycline Over Bimetallic Layered Double Hydroxides-Mxenes Heterostructures Under Visible Light

SSRN

引用

SSRN 2024年

作者： Yao, Jixin Liu, Yong Tong, Xiaowei Lu, Shibin Meng, Ying Li, Guang Anhui Province Key Laboratory of Simulation and Design for Electronic Information System Universities Joint Key Laboratory of Photoelectric Detection Science and Technology in Anhui Province Hefei Normal University Hefei230601 China School of Materials Science and Engineering Anhui Key Laboratory of Information Materials and Devices Key Laboratory of Structure and Functional Regulation of Hybrid Materials Ministry of Education Institute of Physical Science and Information Technology Anhui University Hefei230601 China School of Electronic Engineering Huainan Normal University Huainan232038 China

Layered double hydroxides (LDHs) are widely used in photocatalytic degradation of antibiotic pollutants under ultraviolet (UV)-light, but their efficiency under visible light is hampered by large band gaps and layer agglomeration. To address these challenges, we have successfully developed innovative bimetallic NiCo LDHs-MXenes heterostructures (LDHs-MXenes) for enhanced degradation of tetracycline (TC) pollutants under visible light conditions. As-prepared LDHs-MXenes photocatalysts (20 mg) show exceptional performance, achieving ~97.4% TC degradation efficiency (20 mg L-1, 100 mL) within just 50 minutes under a 300 W Xe lamp. This significant enhancement underscores the synergistic effects derived from the combination of LDHs and MXenes nanosheets. © 2024, The Authors. All rights reserved.

关键词： Heterojunctions

来源：评论

学校读者我要写书评

暂无评论

Enhancing Reconstruction Reaction Kinetics by Inner Electric Potential engineering for High-Performance Aqueous Supercapacitors

SSRN

引用

SSRN 2023年

作者： Du, Zhengyan Meng, Zeshuo Hao, Zeyu Yu, Shansheng Hu, Xiaoying Tian, Hongwei Key Laboratory of Automobile Materials of MOE School of Materials Science and Engineering Jilin University Changchun130012 China College of Science Laboratory of Materials Design and Quantum Simulation Changchun University Changchun130022 China

For the materials with localized electronic structure characteristics, it is a significant challenge to enhance their reconstruction capabilities in the development of next-generation high-performance energy storage electrode materials. However, existing strategies overly emphasize the interaction between advantageous guest and host materials to achieve co-optimization of electronic structures, without addressing the intrinsic issues of the host material. Herein, we propose a novel concept of internal potential engineering, which aims to optimize the internal potential by directly adjusting the electronic structure of the host material. As a proof of concept, the charge distribution of Fe5Ni4S8 is directly modulated using surface groups, resulting in the optimization of Fe5Ni4S8 internal potential and significantly enhancing the intensity of its surface reconstruction reaction. Compared to unmodulated counterpart, the optimized Fe5Ni4S8 exhibits a high specific capacitance of 724.4 F g-1 at a current density of 1 A g-1, and the assembled asymmetric supercapacitor achieves a maximum energy density of 41.35 Wh kg-1. This study provides a promising pathway for the design of electrode materials with optimized dynamic reconstruction rates and high energy density. © 2023, The Authors. All rights reserved.

关键词： Reaction kinetics

来源：评论

学校读者我要写书评

暂无评论

Large Language Models can be Guided to Evade AI-Generated Text Detection

arXiv

引用

arXiv 2023年

作者： Lu, Ning Liu, Shengcai He, Rui Ong, Yew-Soon Wang, Qi Tang, Ke Guangdong Key Laboratory of Brain-Inspired Intelligent Computation China Department of Computer Science and Engineering Southern University of Science and Technology China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Singapore Singapore

Large language models (LLMs) have shown remarkable performance in various tasks and have been extensively utilized by the public. However, the increasing concerns regarding the misuse of LLMs, such as plagiarism and spamming, have led to the development of multiple detectors, including fine-tuned classifiers and statistical methods. In this study, we equip LLMs with prompts, rather than relying on an external paraphraser, to evaluate the vulnerability of these detectors. We propose a novel Substitution-based In-Context example Optimization method (SICO) to automatically construct prompts for evading the detectors. SICO is cost-efficient as it requires only 40 human-written examples and a limited number of LLM inferences to generate a prompt. Moreover, once a task-specific prompt has been constructed, it can be universally used against a wide range of detectors. Extensive experiments across three real-world tasks demonstrate that SICO significantly outperforms the paraphraser baselines and enables GPT-3.5 to successfully evade six detectors, decreasing their AUC by 0.5 on average. Furthermore, a comprehensive human evaluation show that the SICO-generated text achieves human-level readability and task completion rates, while preserving high imperceptibility. Finally, we propose an ensemble approach to enhance the robustness of detectors against SICO attack. Copyright © 2023, The Authors. All rights reserved.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Organic–inorganic hybrid perovskite scintillators for mixed field radiation detection

引用

InfoMat 2022年第9期4卷 97-108页

作者： Mengling Xia Guangda Niu Linyue Liu Runlong Gao Tong Jin Pengying Wan Weicheng Pan Xianpeng Zhang Zuoxiang Xie Sam Teale Zenghua Cai Jiajun Luo Shan Zhao Haodi Wu Shiyou Chen Zhiping Zheng Qingguo Xie Xiaoping Ouyang Edward HSargent Jiang Tang Wuhan National Laboratory for Optoelectronics(WNLO) WuhanChina School of Optical and Electronic Information Huazhong University of Science and Technology(HUST)WuhanChina State Key Laboratory of Intense Pulsed Radiation Simulation and Effect Northwest Institute of Nuclear TechnologyXi'anChina School of Nuclear Science and Technology Xi'an Jiaotong UniversityXi'anChina Department of Electrical and Computer Engineering University of TorontoTorontoOntarioCanada School of Microelectronics Fudan UniversityShanghaiChina College of Life Science and Technology Huazhong University of Science and TechnologyWuhanChina

Sensitive and fast detection of neutrons and gamma rays is vital for homeland security,high-energy physics,and proton ***-neutron detectors rely on light organic scintillators,andγ-ray detectors use heavy inorganic scintillators and *** mixed-field detection using a single material is highly challenging due to their contradictory *** we report hybrid perovskites(C_(8)H_(12)N)_(2)Pb(Br_(0.95)Cl_(0.05))_(4)that combine light organic cations and heavy inorganic skeletons at a molecular level to achieve unprecedented performance for mixed-field radiation *** neutron absorption due to a high density of hydrogen,strong radiative recombination within the highly confined[PbX_(6)]^(4-)layer,and sub-nanometer distance between absorption sites and radiative centers,enable a light yield of 41000 photons/MeV,detection pulse width of 2.97 ns and extraordinary linearity response toward both fast neutrons andγ-rays,outperforming commonly used fast-neutron *** energy spectrum,time-of-flight based fast-neutron/γ-ray discrimination and neutron yield monitoring were all successfully achieved using(C_(8)H_(12)N)_(2)Pb(Br_(0.95)Cl_(0.05))_(4)*** further demonstrate the monitoring of reaction kinetics and total power of a nuclear fusion *** envision that molecular hybridized scintillators open a new avenue for mixed-field radiation detection and imaging.

关键词： fast neutron mixed-field radiation detection organic-inorganic hybrid perovskite

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Vehicle Positioning Method Based on Multi-Resolution Point Cloud Histogram 5

Research on Intelligent Vehicle Positioning Method Based on ...

引用

5th CAA International Conference on Vehicular Control and Intelligence, CVCI 2021

作者： Meng, QingYu Guo, HongYan Guo, JingZheng Jilin University Department of Control Science and Engineering ChangChun China State Key Laboratory of Automotive Simulation and Control Jilin University ChangChun China

ISBN: (纸本)9781665408462

Precise positioning is the basic condition for intelligent vehicles to complete perception, decision making and control tasks. In response to this challenge, in this article, lidar simultaneous localization and mapping (SLAM) is taken as the research object, and a SLAM system is designed that integrates motion compensation and ground information removal functions. A loop-closure detection method with a multiresolution point cloud histogram mode is proposed, which can effectively reduce the accumulation of positioning errors during the driving of the intelligent vehicles. We conduct experiments on the well-known KITTI dataset and compare the results with those of state-of-the-art systems. The experiments confirm that the lidar SLAM system designed in this article can provide accurate and effective positioning information for intelligent vehicles. © 2021 IEEE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Positive and unlabeled learning with controlled probability boundary fence 24

Positive and unlabeled learning with controlled probability ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Changchun Li Yuanchao Dai Lei Feng Ximing Li Bing Wang Jihong Ouyang College of Computer Science and Technology and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore

Positive and Unlabeled (PU) learning refers to a special case of binary classification, and technically, it aims to induce a binary classifier from a few labeled positive training instances and loads of unlabeled instances. In this paper, we derive a theorem indicating that the probability boundary of the asymmetric disambiguation-free expected risk of PU learning is controlled by its asymmetric penalty, and we further empirically evaluated this theorem. Inspired by the theorem and its empirical evaluations, we propose an easy-to-implement two-stage PU learning method, namely Positive and Unlabeled Learning with Controlled Probability Boundary Fence (PUL-CPBF). In the first stage, we train a set of weak binary classifiers concerning different probability boundaries by minimizing the asymmetric disambiguation-free empirical risks with specific asymmetric penalty values. We can interpret these induced weak binary classifiers as a probability boundary fence. For each unlabeled instance, we can use the predictions to locate its class posterior probability and generate a stochastic label. In the second stage, we train a strong binary classifier over labeled positive training instances and all unlabeled instances with stochastic labels in a self-training manner. Extensive empirical results demonstrate that PUL-CPBF can achieve competitive performance compared with the existing PU learning baselines.

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：