检索结果-南通市图书馆

Boosting Adversarial Training with Learnable Distribution

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第3期78卷 3247-3265页

作者： Kai Chen Jinwei Wang James Msughter Adeke Guangjie Liu Yuewei Dai School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing210044China key laboratory of Intelligent Support technology for Complex Environments Ministry of EducationNanjing210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Nanjing Center for Applied Mathematics Nanjing211135China

In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural networks.Adversarial training is one of the most potent methods to defend against adversarial attacks.However,the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial training.This paper proposes a learnable distribution adversarial training method,aiming to construct the same distribution for training data utilizing the Gaussian mixture model.The distribution centroid is built to classify samples and constrain the distribution of the sample features.The natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the model.The proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial training.This algorithm gradually increases the accuracy and robustness of the model by scaling perturbation.Finally,the proposed method outputs the predicted labels and the distance between the sample and the distribution centroid.The distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model defense.The effectiveness of the proposed method is demonstrated through comprehensive experiments.

关键词： Adversarial training feature space learnable distribution distribution centroid

An Improved HVQ Algorithm for Compression and Rendering of space Environment Volume Data with Multi-correlated Variables

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

空间科学学报 2023年第4期43卷 780-785页

作者： BAO Lili CAI Yanxia WANG Rui ZOU Yenan SHI Liqin State key laboratory of space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190 key laboratory of science and technology on environmental space situation awareness Chinese Academy of SciencesBeijing 100190 University of Chinese Academy of sciences Beijing 100049

Volume visualization can not only illustrate overall distribution but also inner structure and it is an important approach for space environment research.space environment simulation can produce several correlated variables at the same time.However,existing compressed volume rendering methods only consider reducing the redundant information in a single volume of a specific variable,not dealing with the redundant information among these variables.For space environment volume data with multi-correlated variables,based on the HVQ-1d method we propose a further improved HVQ method by compositing variable-specific levels to reduce the redundant information among these variables.The volume data associated with each variable is divided into disjoint blocks of size 43 initially.The blocks are represented as two levels,a mean level and a detail level.The variable-specific mean levels and detail levels are combined respectively to form a larger global mean level and a larger global detail level.To both global levels,a splitting based on a principal component analysis is applied to compute initial codebooks.Then,LBG algorithm is conducted for codebook refinement and quantization.We further take advantage of progressive rendering based on GPU for real-time interactive visualization.Our method has been tested along with HVQ and HVQ-1d on high-energy proton flux volume data,including>5,>10,>30 and>50 MeV integrated proton flux.The results of our experiments prove that the method proposed in this paper pays the least cost of quality at compression,achieves a higher decompression and rendering speed compared with HVQ and provides satisficed fidelity while ensuring interactive rendering speed.

关键词： Compressed volume rendering Multi-correlated variables space environment Vector quantization GPU programming

space Environment Measurements and Applications on the Tianhe Core Module of China space Station

在线全文

学校读者我要写书评

暂无评论

空间科学学报 2022年第4期42卷 744-753页

作者： LIU Siqing SUN Yueqiang ZHONG Qiuzhen WEI Fei LIN Ruilin LI Zhitao REN Tingling LI Yongping ZHANG Xianguo ZHANG Shenyi LUO Bingxian CHANG Zhen WANG Chunqin PENG Songwu AI Jiangzhao State key laboratory of space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190 key laboratory of science and technology on environmental space situation awareness Chinese Academy of SciencesBeijing 100190 University of Chinese Academy of sciences Beijing 100049

Tianhe Core Module of China space Station(CSS)equips a set of instruments consisting of a Particle Fluxes and Solar Activity Detector(PFSAD)and two Atmospheric Density Multi-directional Detectors(ADMDs).The PFSAD is to measure X-rays from the Sun and energetic particles in the low-latitude and low altitude regions,including electrons,protons,and helium ions.The ADMDs are to measure thermospheric atmospheric density.The instruments provide real-time data of the orbital space environment,including solar flares,energetic particle variation and thermospheric density enhancement.All the data contribute to the CSS space weather service for mission control and astronaut’s safety.The paper gives preliminary analyses of the space environment measurements from the PFSAD and the ADMDs.By further analysis,the 1024-channel fine spectra of the solar X-ray can be used to study the mechanism of solar flares and their impacts on the Earth’s atmosphere.Data accumulation will be helpful for analyzing mid-term and long-term variations of the South Atlantic Anomaly and atmosphere density.Furthermore,the data are useful to calibrate previous empirical models and establish new models to study the space environment.

关键词： space environment Tianhe core module China space Station(CSS)

Image Feature Extraction and Matching of Augmented Solar Images in space Weather

在线全文

学校读者我要写书评

暂无评论

空间科学学报 2023年第5期43卷 840-852页

作者： WANG Rui BAO Lili CAI Yanxia State key laboratory of space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190 University of Chinese Academy of sciences Beijing 100049 key laboratory of science and technology on Environment space situation awareness Chinese Academy of SciencesBeijing 100190

Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speeded-up robust features algorithm,binary robust invariant scalable keypoints algorithm,and oriented fast and rotated brief algorithm.The performance of these algorithms was estimated in terms of matching accuracy,feature point richness,and running time.The experiment result showed that no algorithm achieved high accuracy while keeping low running time,and all algorithms are not suitable for image feature extraction and matching of augmented solar images.To solve this problem,an improved method was proposed by using two-frame matching to utilize the accuracy advantage of the scale-invariant feature transform algorithm and the speed advantage of the oriented fast and rotated brief algorithm.Furthermore,our method and the four representative algorithms were applied to augmented solar images.Our application experiments proved that our method achieved a similar high recognition rate to the scale-invariant feature transform algorithm which is significantly higher than other algorithms.Our method also obtained a similar low running time to the oriented fast and rotated brief algorithm,which is significantly lower than other algorithms.

关键词： Augmented reality Augmented image Image feature point extraction and matching space weather Solar image

Meteoroid and space Debris Risk Assessment for Satellites Orbiting the Earth/Moon

在线全文

学校读者我要写书评

暂无评论

空间科学学报 2023年第4期43卷 724-735页

作者： FENG Shuai WANG Ronglan National space science Center Chinese Academy of SciencesBeijing 100190 University of Chinese Academy of sciences Beijing 100049 State key laboratory of space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190 key laboratory of science and technology on environmental space situation awareness Chinese Academy of SciencesBeijing 100190

Interplanetary meteoroids and space debris can impact satellites orbiting the Earth or spacecraft traveling to the Moon.Targeting China space Station(CSS),7 satellites selected from the constellation of Beidou Navigation Satellite System Phase III(BDS-3),and 3 spacecraft orbiting the Moon,we have adopted in the paper the Meteoroid Engineering Model 3,Divine-Staubach meteoroid environment model,and Jenniskens-McBride meteoroid steam model to analyze the meteoroid environment with the mass range of 10–6~10 g.Orbital Debris Engineering Model 3.1 space debris model is used to analyze the orbital debris environment faced by these satellites.The flux of space debris with a size larger than 100μm is compared with that of the meteoroids.The results show that the space debris flux encountered by China space Station is much higher than that of the meteoroids with sizes in the above range.And quite the opposite,the meteoroids flux impacting the 7 satellites from the BDS-3 is higher.Upon adopting the double-layer Whipple protection measure,the catastrophic collision flux of these satellites encountering meteoroids is about 10–6 times of that without protection,or even less,implying that the Whipple protection effectively guarantees the safety of the satellites in orbit.Besides,it is also found that the flux of the high-density meteoroid population encountered by each satellite is greater than that of the low-density population,whereas the impact velocity is lower for each satellite.These results can aid the orbit selection and the protection design for satellites and spacecraft.

关键词： Meteoroid environment model space debris model Ballistic limit equation Impact risk assessment

Contribution of the Chinese Meridian Project to space environment research:Highlights and perspectives

在线全文

学校读者我要写书评

暂无评论

science China Earth sciences 2023年第7期66卷 1423-1438页

作者： Chi WANG Jiyao XU Libo LIU Xianghui XUE Qinghe ZHANG Yongqiang HAO Gang CHEN Hui LI Guozhu LI Bingxian LUO Yajun ZHU Jiangyan WANG State key laboratory of space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190China University of Chinese Academy of sciences Beijing 100049China key laboratory of Earth and Planetary Physics Institute of Geology and GeophysicsChinese Academy of SciencesBeijing 100029China School of Earth and space sciences University Science and Technology of ChinaHefei 230026China Shandong Provincial key laboratory of Optical Astronomy and Solar-Terrestrial Environment Institute of Space SciencesShandong UniversityWeihai 264209China School of Earth and space sciences Peking UniversityBeijing 100191China Department of space Physics School of Electronic InformationWuhan UniversityWuhan 430072China key laboratory of science and technology on environmental space situation awareness National Space Science CenterChinese Academy of SciencesBeijing 100190China

The Chinese Meridian Project(CMP)is devoted to establishing a comprehensive ground-based monitoring network for China’s space weather research.CMP is a major national science and technology infrastructure project with the participation of more than 10 research institutions and universities led by the National space science Center of the Chinese Academy of sciences.CMP is planned to be constructed in two phases:CMP phasesⅠandⅡ.The first phase(CMP-Ⅰ)started construction in2008 and completed in 2012,after which it entered the operation stage.The 10-year observation of CMP-Ⅰhas made significant scientific discoveries and achievements in the research fields of the middle and upper atmospheric fluctuations,metal layers in the mesosphere and lower thermosphere,ionospheric disturbances and irregularities,geomagnetic disturbances,and influences of solar activity.The review summarizes the main observations and research achievements,space weather forecast modeling and methods based on CMP-Ⅰover the past 10 years,and presents a future extension perspective along with the construction of CMP-Ⅱ.

关键词： Chinese Meridian Project Ground-based observation network space weather Solar-terrestrial physics

Development of High-energy Particle Detectors for space Exploration

在线全文

学校读者我要写书评

暂无评论

空间科学学报 2022年第6期42卷 1171-1184页

作者： YANG Zhe SHEN Guohong JING Tao National space science Center Chinese Academy of SciencesBeijing 100190 University of Chinese Academy of sciences Beijing 100049 Beijing key laboratory of space Environment Exploration Beijing 100190 key laboratory of science and technology on space Environment situational awareness Chinese Academy of SciencesBeijing 100190

space environment exploration is a hot topic globally.The scope of space exploration ranges from near-Earth space to the moon,other planets in the solar system,and even the heliosphere and interplanetary space.It is used for various crucial applications,including aerospace technology development,space weather research,understanding the origin and evolution of the universe,searching for extraterrestrial life,and finding human livable places.Although China’s space environment exploration started late,its progress has been rapid.China is gradually narrowing the gap with advanced countries and may eventually lead the world in space research.This article briefly reviews the development history of China’s space environmental detectors.

关键词： High-energy particle detectors Near-Earth space exploration Lunar exploration space environment

Analysis of the correlation between horizontal wind and 11-year solar activity over Langfang, China

在线全文

学校读者我要写书评

暂无评论

Earth and Planetary Physics 2021年第3期5卷 270-279页

作者： Bing Cai QingChen Xu Xiong Hu Xuan Cheng JunFeng Yang Wen Li key laboratory of science and technology on environmental space situation awareness National Space Science CenterChinese Academy of SciencesBeijing 100190China College of Earth sciences University of Chinese Academy of SciencesBeijing 100049China

In this study,long term observations of medium frequency(MF)radar at Langfang site(39.4°N,116.7°E)from 2009 to 2020 have been used to analyze the dependence of the 11-year solar cycle on horizontal winds in the local mesosphere and lower thermosphere(MLT).The results show that the zonal wind is positively correlated with solar activity during spring at 80–84 km,and during summer at 80–82 km;the meridional wind is positively correlated with solar activity during spring at 84–88 km and during summer at 84–90 km.In contrast,the results show no correlation between the horizontal wind and solar activity in autumn and winter.We attempt to explain the correlations in terms of the changes in stratospheric temperature and the net flux of gravity waves during solar activities.In addition,annual and semiannual oscillations of the zonal/meridional wind were found by using the least squares fitting method on daily horizontal winds,which show negative correlations with solar activity at heights of 80–90 km.

关键词： MF radar MLT horizontal wind solar cycle

Impacts of CMEs on Earth Based on Logistic Regression and Recommendation Algorithm

在线全文

学校读者我要写书评

暂无评论

space(science & technology) 2022年第1期2022卷 351-362页

作者： Yurong Shi Jingjing Wang Yanhong Chen Siqing Liu Yanmei Cui Xianzhi Ao National space science Center Chinese Academy of SciencesBeijingChina key laboratory of science and technology on environmental space situation awareness Chinese Academy of SciencesBeijingChina University of Chinese Academy of sciences BeijingChina

Coronal mass ejections(CMEs)are one of the major disturbance sources of space weather.Therefore,it is of great significance to determine whether CMEs will reach the earth.Utilizing the method of logistic regression,we first calculate and analyze the correlation coefficients of the characteristic parameters of CMEs.These parameters include central position angle,angular width,and linear velocity,which are derived from the Large Angle and Spectrometric Coronagraph(LASCO)images.We have developed a logistic regression model to predict whether a CME will reach the earth,and the model yields an F1 score of 30%and a recall of 53%.Besides,for each CME,we use the recommendation algorithm to single out the most similar historical event,which can be a reference to forecast CMEs geoeffectiveness forecasting and for comparative analysis.

关键词： Earth forecasting weather