检索结果-内蒙古大学图书馆

Semantic segmentation of track image based on deep neural network

The Journal of China Universities of Posts and Telecommunications 2020年第5期27卷 23-33页

作者： Wang Zhaoying Zhou Junhua Liao Zhonghua Zhai Xiang Zhang Lianping School of Electronic Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China Beijing Complex Product Advanced Manufacturing Kngineering Research Center Beijing Simulation CenterBeijing 100854China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System EngineeringBeijing 100854China Alibaba Cloud Computing Beijing 100020China

In this paper,deep learning technology was utilited to solve the railway track recognition in intrusion detection *** railway track recognition can be viewed as semantic segmentation task which extends image processing to pixel level *** encoder-decoder architecture DeepLabv3+model was applied in this work due to its good performance in semantic segmentation *** images of the railway track collected from the video surveillance of the train cab were used as experiment dataset in this work,the following improvements were made to the *** first aspect deals with over-fitting problem due to the limited amount of training *** augmentation and transfer learning are applied consequently to rich the diversity of data and enhance model robustness during the training ***,different gradient descent methods are compared to obtain the optimal optimizer for training model *** third problem relates to data sample imbalance,cross entropy(CE)loss is replaced by focal loss(FL)to address the issue of serious imbalance between positive and negative *** of the improved DeepLabv3+model with above solutions is demonstrated by experiment results with different system parameters.

关键词： railway track recognition convolutional neural networks semantic segmentation DeepLabv3+

来源：评论

学校读者我要写书评

暂无评论

simulation Experiment Factor Screening Method Based on Combinatorial Optimization 21st

Simulation Experiment Factor Screening Method Based on Combi...

引用

21st Asia simulation Conference, AsiaSim 2022

作者： Zhang, Peng Li, Wei Chen, Qingao Tong, Jiahui Control and Simulation Center Harbin Institute of Technology Harbin China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9789811991974

When conducting complex simulation experiments, experimental factor screening is of great significance to improve the effectiveness and efficiency of the simulation. Aiming at the problems of unsatisfactory accuracy and efficiency of existing experimental factor screening methods, a simulation experiment factor screening method based on combinatorial optimization (EFS-CO) was designed. EFS-CO abstracts the experimental factor screening problem into a combinatorial optimization problem, designs the experimental factor evaluation criteria based on the support vector machine model, uses it as the fitness function of the genetic algorithm, and finally obtains the significant experimental factor. At the same time, to eliminate the influence of the randomness of the genetic algorithm on the screening results, the screening results of the experimental factors were determined based on the results of multiple experiments. Finally, the effectiveness of the method is verified by example analysis and comparing the results with the traditional experimental factor screening method. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

LEO Satellite Network Traffic Forecasting based on ARIMA-BPNN Model 3

LEO Satellite Network Traffic Forecasting based on ARIMA-BPN...

引用

3rd International Conference on Electronic Information Engineering and Computer Communication, EIECC 2023

作者： Han, Chi Xiong, Wei Yu, Ronghuan Fu, Jingyu Space Engineering University Science and Technology on Complex Electronic System Simulation Laboratory Beijing China Jiuquan Satellite Launch Center Jiuquan China

ISBN: (纸本)9798350359961

Satellite network traffic forecasting provides key information for routing and resource allocation, which is important for the efficient operation of satellite network. However, due to the self-similarity and long-range dependence (LRD) of satellite network traffic, traditional linear or non-linear network traffic forecasting models cannot achieve sufficient forecasting accuracy. A combined model of satellite network traffic forecasting based on BPNN and ARIMA is proposed. BPNN is adopted to forecast the residuals. EMD-ARIMA and BPNN forecasting results are combined to achieve satellite network traffic forecasting. Experimental results on the satellite network traffic data generated by the ON/OFF model show that forecast accuracy of the proposed method is better than traditional model, which verifies the effectiveness of the proposed satellite network traffic forecast model. © 2023 IEEE.

关键词： BP neural network empirical mode decomposition intrinsic mode function long-range dependence satellite network

来源：评论

学校读者我要写书评

暂无评论

Evaluating Metal-Support Interaction in Formaldehyde Oxidation Using Pd/TiO₂ Catalysts: The Key Role of Mono-Oxygen Vacancies

引用

Inorganic Chemistry 2025年 2025 May 14页

作者： Chen, Xudong Wang, Chunying Wang, Jingyi Wen, Wei Liu, Xiaofeng Li, Yaobin Shan, Wenpo He, Hong Center for Excellence in Regional Atmospheric Environment Key Laboratory of Urban Pollutant Conversion Institute of Urban Environment Chinese Academy of Sciences Xiamen 361021 China Zhejiang Key Laboratory of Pollution Control for Port-Petrochemical Industry Ningbo Urban Environment Observation and Research Station Institute of Urban Environment Chinese Academy of Sciences Ningbo 315800 China School of Resources & Chemical Engineering Sanming University Sanming 365004 China Faculty of Environmental Science and Engineering Kunming University of Science and Technology Kunming 650000 China State Key Joint Laboratory of Environment Simulation and Pollution Control Research Center for Eco-environmental Sciences Chinese Academy of Sciences Beijing 100085 China University of Chinese Academy of Sciences Beijing 100049 China

Metal-support interactions (MSI) have been widely recognized as playing a key role in regulating the catalytic activity in various reactions. However, clarifying the relationship linking catalyst defect structures, active sites, and catalytic performance for catalysts with a constructed MSI remains a challenge. Here, Pd/TiO₂ catalysts with adjustable MSI were designed and fabricated based on defect engineering. Comprehensive characterization analysis revealed that as the catalyst reduction temperature and defect content increase, the MSI gradually increases, subsequently enhancing the intrinsic activity of the catalyst to oxidize formaldehyde (HCHO). However, the activity of the catalyst exhibited a volcano-shaped trend, which was caused by the collapse of the support structure at a high reduction temperature. Through comparative analysis of the HCHO oxidation reaction and CO oxidation reaction activity tests, it was confirmed that the ratio of mono-oxygen vacancies to oxygen vacancy clusters (I₁/I₂) in this study system could reliably serve as a valid “descriptor” for HCHO oxidation apparent activity. © 2025 American Chemical Society.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced secondary pollution offset reduction of primary emissions during COVID-19 lockdown in China

引用

National science Review 2021年第2期8卷 51-59页

作者： Xin Huang Aijun Ding Jian Gao Bo Zheng Derong Zhou Ximeng Qi Rong Tang Jiaping Wang Chuanhua Ren Wei Nie Xuguang Chi Zheng Xu Liangduo Chen Yuanyuan Li Fei Che Nini Pang Haikun Wang Dan Tong Wei Qin Wei Cheng Weijing Liu Qingyan Fu Baoxian Liu Fahe Chai Steven J.Davis Qiang Zhang Kebin He School of Atmospheric Sciences Nanjing University Chinese Research Academy of Environmental Sciences Department of Earth System Science Tsinghua University State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua University Department of Earth System Science University of California Jiangsu Environmental Monitoring Center Jiangsu Provincial Academy of Environment Science Shanghai Environmental Monitoring Center Beijing Key Laboratory of Airborne Particulate Matter Monitoring Technology Beijing Municipal Environmental Monitoring Center

To control the spread of the 2019 novel coronavirus(COVID-19), China imposed nationwide restrictions on the movement of its population(lockdown) after the Chinese New Year of 2020, leading to large reductions in economic activities and associated emissions. Despite such large decreases in primary pollution, there were nonetheless several periods of heavy haze pollution in eastern China, raising questions about the well-established relationship between human activities and air quality. Here, using comprehensive measurements and modeling, we show that the haze during the COVID lockdown was driven by enhancements of secondary pollution. In particular, large decreases in NOx emissions from transportation increased ozone and nighttime NO3radical formation, and these increases in atmospheric oxidizing capacity in turn facilitated the formation of secondary particulate matter. Our results, afforded by the tragic natural experiment of the COVID-19 pandemic, indicate that haze mitigation depends upon a coordinated and balanced strategy for controlling multiple pollutants.

关键词： COVID-19 haze pollution ozone emission reduction secondary pollution

来源：评论

学校读者我要写书评

暂无评论

Cooperative jamming resource allocation based on integer-encoded directed mutation artificial bee colony algorithm 4

Cooperative jamming resource allocation based on integer-enc...

引用

4th IEEE International Conference on Electronic Information and Communication technology, ICEICT 2021

作者： Xia, Jiechen Ma, Jing Li, Yibing Song, Mingzhao Harbin Engineering University Harbin150001 China Key Laboratory of Advanced Marine Communication and Information Technology Ministry of Industry and Information Technology Science and Technology on Special System Simulation Laboratory Beijing100854 China

ISBN: (纸本)9781665432030

Electromagnetic countermeasure (ECM) is of extreme importance in modern warfare. In order to confront the threat of radar-net, cooperative jamming platform with multiple jammers is the main approach. A proper allocation of jamming resource is required before and during the process of interference. This paper proposes an artificial bee colony (ABC) based jamming resource allocation (JRA) algorithm with few parameter adjustments. The allocation strategy is encoded in integer to better handle the constraints of JRA problem. Furthermore, a genetic algorithm (GA) inspired solution update method is introduced in stages of algorithm to accelerate the convergence rate. simulation result shows that the proposed algorithm has a better performance in both rate and precision of convergence compared with tabu search artificial bee colony algorithm (TSABC) and ant colony optimization algorithm (ACO), which were adopted in previous related studies. ©2021 IEEE

关键词： Tabu search

来源：评论

学校读者我要写书评

暂无评论

Compensation method of GPS signal delay based on factor graph 4

Compensation method of GPS signal delay based on factor grap...

引用

4th IEEE International Conference on Electronic Information and Communication technology, ICEICT 2021

作者： Chen, Hangyu Ma, Jing Ye, Fang Harbin Engineering University Harbin150001 China Key Laboratory of Advanced Marine Communication and Information Technology Ministry of Industry and Information Technology Science and Technology on Special System Simulation Laboratory Beijing100854 China

ISBN: (纸本)9781665432030

In recent years, unmanned ground vehicles (UGVs) have been widely used in urban environments. The satellite positioning system plays an irreplaceable role in UGVs. However, the tall buildings in cities may cause interference to the transmission of satellite signals, which results in positioning delays, thus reducing the positioning accuracy of UGVs. To address this issue, a compensation method for information delay based on factor graph model is proposed in this paper. In the factor graph model utilized, the corresponding GPS factor node will not be generated when the GPS signal delay occurs at the current fusion time. The subsequent factor graph model is directly generated by the combined navigation system of visual odometry (VO) and inertial measurement unit (IMU). When the delayed GPS signal arrives, the measurement data of VO and IMU are used to compensate the delayed GPS positioning information. The compensated GPS positioning information is used to generate an additional factor node at the moment when the GPS signal actually arrives. This additional factor node is connected into the factor graph model for data fusion so that the delayed GPS positioning information can still be used to correct the positioning error. The method proposed in this paper effectively reduces the positioning error while taking into account the real-time performance. Experimental simulations show that the proposed method can reduce the positioning error while GPS signal delay occurs. ©2021 IEEE

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

The Star Scene Modeling and Generation for Hardware-in-the-loop simulation

The Star Scene Modeling and Generation for Hardware-in-the-l...

引用

2018 International Conference on Computational, Modeling, simulation and Mathematical Statistics(CMSMS 2018)

作者： Ying ZHANG Hui-jie DU Yu ZHANG Yi-yuan MA Hui-yang QU Science and Technology on Special System Simulation Laboratory Beijing Simulation Center National Key Laboratory of Intelligent Manufacture System Technology for Complicated Products

The star sensor simulation system is used to test the star sensor performance on the ground, which is designed for star identification and spacecraft attitude determination of the spacecraft. The computer star scene based on the astronomical star chat is generated for hardware-in-the-loop simulation of the star sensor simulation system using OpenGL. The results of star scene generation are shown in this paper and applied in the real time star sensor simulation.

关键词： Star scene Modeling simulation Astronomical chat

来源：评论

学校读者我要写书评

暂无评论

Research on requirement elicitation model of high-end equipment based on requirement classification under Internet and big data environment

Research on requirement elicitation model of high-end equipm...

引用

2016 4th International Conference on Machinery,Materials and Information technology Applications(ICMMITA 2016)

作者： Yu GUO Junting WU Ke-wei YANG Lixin Yu College of Information System and Management National University of Defense Technology Science and Technology on Special System Simulation Laboratory Beijing Simulation Center

ISBN: (纸本)9781510835467

Currently, Internet and big data as the representative of emerging technologies are widely penetrated into every aspect of the high-end equipment manufacturing industry. Considering the characteristics of multi-source, personalized and potential for high-end equipment, this paper focuses on requirement elicitation in the background of Internet, and proposes a high-end equipment requirement elicitation model based on requirement classification, which stands on the perspective of management to study the high-end equipment requirement elicitation. First, we classify the user's need, and then different technical means are taken orienting different types of needs. In this paper, according to users' master degree of requirement, requirements can be divided into instant user requirement and potential user requirement. For instant user requirement, we design a requirement interaction platform based on Internet;For potential user requirement, a requirement mining model based on the open source information of the Internet is established. Eventually, a complete user requirement program is integrated. In conclusion, the idea of classifying the requirements provides a new perspective on requirement elicitation of high-end equipment.

关键词： high-end equipment Internet requirement elicitation requirement classification

来源：评论

学校读者我要写书评

暂无评论

Profiling and analysis of object lazy allocation in Java programs

Profiling and analysis of object lazy allocation in Java pro...

引用

ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD)

作者： Jianjun Shi Weixing Ji Lulu Zhang Yujin Gao Han Zhang Duzheng Qing School of Computer Science Beijing Institute of Technology Beijing China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing China

Lazy allocation strategy allows the memory management system to defer the space allocation action of objects until they are being accessed. This paper investigates the potential benefits of a lazy allocator for Java applications. A heap tracing tool is implemented by instrumenting an existing Java virtual machine HotSpot, which records useful object manipulating events at runtime. By profiling and analyzing a large number of benchmarks, we show the potential dynamic memory management optimization opportunity in Java programs. We also designed a simulation system to demonstrate the actual effects of a lazy allocator.

关键词： Resource management Java Benchmark testing Memory management Virtual machining Color Runtime

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：