检索结果-内蒙古大学图书馆

COD Optimization Prediction Model Based on CAWOA-ELM in Water Ecological Environment

JOURNAL OF CHEMISTRY 2021年第1期2021卷 p1-9页

作者： Jiang, Lili Yang, Liu Huang, Yang Wu, Yi Li, Huixian Shen, XiYan Bi, Meng Hong, Lin Yang, Yiting Ding, Zuping Chen, Wenjie Chongqing Technol & Business Univ Rongzhi Coll Chongqing Key Lab Spatial Data Min & Big Data Int Chongqing 401320 Peoples R China

The change of water quality can reflect the important indicators of ecological environment measurement. Sewage discharge is an important factor causing environmental pollution. Establishing an effective water ecological prediction model can detect changes in the ecological environment system quickly and effectively. In order to detect high error rate and poor convergence of the water ecological chemical oxygen demand (COD) prediction model, combining the limit learning machine (ELM) model and whale optimization algorithm, CAWOA is improved by the sin chaos search strategy, while the ELM optimizes the parameters of the algorithm to improve convergence speed, thus improving the generalization performance of the ELM. In the CAWOA, the global optimization results of the WOA are promoted by introducing a sin chaotic search strategy and adaptive inertia weights. On this basis, the COD prediction model of CAWOA-ELM is established and compared with similar algorithms by using the optimized ELM to predict the water ecological COD in a region. Finally, from the experimental results of the CAWOA-ELM algorithm, it has excellent prediction effect and practical application value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantifying night-time light change drivers in China's Yangtze River economic zone

引用

intERNATIONAL JOURNAL OF REMOTE SENSING 2024年第21期45卷 7856-7877页

作者： Kou, Pinglang Tao, Yuxiang Yunus, Ali P. Xu, Qiang Liu, Rui Jin, Zhao Liang, Wenli Xia, Ying Yuan, Shuang Chongqing Univ Posts & Telecommun Chongqing Engn Res Ctr Spatial Big Data Intelligen Chongqing Peoples R China Chongqing Univ Posts & Telecommun Key Lab Tourism Multisource Data Percept & Decis Minist Culture & Tourism TMDPD MCT Chongqing Peoples R China Indian Inst Sci Educ & Res Mohali Dept Earth & Environm Sciecnes Mohali Punjab India Chengdu Univ Technol State Key Lab Geohazard Prevent & Geoenvironm Prot Chengdu Peoples R China Chongqing Normal Univ Sch Geog & Tourism Chongqing Key Lab GIS Applicat Chongqing Peoples R China Inst Earth Environm Chinese Acad Sci State Key Lab Loess & Quaternary Geol Xian Peoples R China Xi An Jiao Tong Univ Inst Global Environm Change Xian Peoples R China Chongqing Univ Posts & Telecommun Chongqing Engn Res Ctr Spatial Big Data Intelligen Chongqing 400065 Peoples R China

Nighttime light (NTL) is a valuable data source for understanding urban sprawl and human activities. Radiometric quantification of NTL data can be used to explain the reasons for changes in NTL. We used average annual NTL data from 2013 to 2020 to investigate the magnitude and distribution of NTL change in the Yangtze River Economic Belt (YREB) in China. We found that NTL increased annually, with 93.06% of the area experiencing brightening. The annual NTL in 2020 was 2.42 times higher than that in 2013, and the NTL in the densely populated eastern provinces was 16.17 times higher than that in the west. Therefore, the east-west development of the research area is extremely uneven. Urbanization is often accompanied by dramatic NTL brightening, and the area of cropland being brightened is the largest of all landuse types. Urban development inevitably encroaches on cropland space. To address this issue, future policies should focus on sustainable regional development, for example encouraging urban densification development patterns. This will help to avoid the negative impact of urban expansion on the entire ecosystem.

关键词： Nighttime light land use urban densification urban sprawl Yangtze River Economic Belt

来源：评论

学校读者我要写书评

暂无评论

Selective Spectral-spatial Aggregation Transformer for Hyperspectral and LiDAR Classification

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2025年 22卷

作者： Ni, Kang Li, Zirun Yuan, Chunyang Zheng, Zhizhong Wang, Peng Nanjing Univ Posts & Telecommun Sch Comp Sci Nanjing 210023 Peoples R China Key Lab Spatial Temporal Big Data Anal & Applicat Shanghai 200063 Peoples R China Jiangsu Prov Engn Res Ctr Airborne Detecting & Int Nanjing 210049 Peoples R China Nanjing Univ Aeronaut & Astronaut Shenzhen Res Inst Shenzhen 518110 Peoples R China Key Lab Spatial Temporal Big Data Anal & Applicat Shanghai 200063 Peoples R China

Convolutional neural networks (CNNs) and transformers have achieved excellent classification performances in hyperspectral imagery (HSI) and light detection and ranging (LiDAR) land cover classification. However, for complex land covers, effectively characterizing the contextual information and spectral-spatial interaction features of HSI and LiDAR is crucial for improving classification accuracy. Motivated by this, this letter is dedicated to selective convolutional kernel mechanisms and spectral-spatial interactive transformer feature learning style, proposing a selective spectral-spatial aggregation transformer network, named S2ATNet. A convolution feature selected module (CFSM), which can dynamically capture the contextual features of various land covers, is first utilized in both of HSI and LiDAR branches. Afterward, a cascaded spatial-spectral learning and interactive fusion (CSLIF) block is designed for acquiring the nonlocal spatial-spectral characteristics in an interactive feature learning style. The learned features are fed into the max-average classification head (MACH) to obtain the final classification results. The effectiveness of the proposed S2ATNet is validated on two publicly available datasets. Codes are available at https://***/RSIP-NJUPT/***.

关键词： Convolutional neural networks (CNNs) hyperspectral imagery (HSI) and light detection and ranging (LiDAR) land cover classification spatial-spectral learning transformer

来源：评论

学校读者我要写书评

暂无评论

Mesh Segmentation for Individual Teeth Based on Two-Stream GCN With Self-Attention

引用

IEEE ACCESS 2024年 12卷 76735-76743页

作者： Liu, Shi-Jian Kang, Chao-ming Huang, Feng-Hua Zou, Zheng Fujian Univ Technol Fujian Prov Key Lab Big Data Min & Applicat Fuzhou 350118 Peoples R China Yango Univ Fujian Key Lab Spatial Informat Percept & Intellig Fuzhou 350015 Peoples R China Fujian Normal Univ Coll Comp & Cyber Secur Fuzhou 350117 Peoples R China

Dental triangular mesh is widely used in computer-aided oral medicine. Different from regular data such as digital images, the structure of triangular mesh is more complex, and traditional operations such as convolution cannot be directly applied. Therefore, the segmentation of patients' personalized teeth from mesh through deep learning is a hot topic in the current research field. Recently, a method named TSGCN presented the idea of learning coordinate features and normal features through a two-stream architecture based on Graph Convolutional Networks (GCN), which further improved the performance compared with other methods. However, its ability to extract and process global features still can be strengthened. To this end, a method named TSGCN-SA is proposed, whose core idea is to introduce the self-attention (SA) mechanism into TSGCN. Specifically, two SA modules are introduced, the first one is used to improve the global feature extraction ability in the coordinate stream. The second one plays an important role in the adaptive contribution adjustment of each stream during the feature fusion. Experiments based on the public dataset named 3DTeethSeg show that TSGCN-SA is superior to SOTAs in terms of segmentation performance due to the proposed SA modules, and the proposed method is competent in the task of individual tooth mesh segmentation.

关键词： Teeth Dentistry Transformers Feature extraction Faces Annotations Deep learning Tooth triangular mesh deep learning self-attention segmentation

来源：评论

学校读者我要写书评

暂无评论

Effects of carbon nanomaterials on the migration and fate of organic pollutants in the ecological environment

引用

FERROELECTRICS 2021年第1期570卷 206-217页

作者： Chen, Guobin Yuan, Hengyi Chongqing Technol & Business Univ Chongqing Key Lab Spatial Data Min & Big Data Int Rongzhi Coll Chongqing Peoples R China Jilin Engn Normal Univ Coll Mech Engn Changchun Jilin Peoples R China

The purpose of this study was to investigate the mechanism of adsorption reaction between heterocyclic organic compounds with different number of ring atoms and different atoms replacing carbon atoms and carbon nanotubes with different surface functional groups. Based on the current situation of research on adsorption of carbon nanomaterials adsorbing organic pollutants, the existing problems and limitations were analyzed by studying the properties and characterization of single-walled carbon nanotubes, oxidized single-walled carbon nanotubes and non-porous graphite powder, such as elemental analysis, transmission electron micrograph, zero charge point, etc. The three adsorption materials were investigated by batch experiment. Six compounds of thiophene, pyrimidine, benzene, aniline, 2-aminopyrimidine and 4,6-diaminopyrimidine were selected as the adsorbate for detecting adsorption capacity. The results showed that the affinity of different adsorbents on different adsorbents varied greatly. The adsorption capacity of heterocyclic compounds containing N and S was greatly enhanced by non-hydrophobic action. And the degree of oxidation of the adsorbent and the ph of the solution determined the adsorption capacity of the adsorbent for nitrogen-containing heterocyclic compounds. Therefore, in the ecological environment, the migration of hydrophilic organic pollutants in the environment can be reduced by the preparation of appropriate carbon nanotubes.

关键词： Carbon nanomaterials ecological environment organic pollution absorbent material

来源：评论

学校读者我要写书评

暂无评论

Network on chip for enterprise information management and integration in intelligent physical systems

引用

ENTERPRISE INFORMATION SYSTEMS 2021年第7期15卷 935-950页

作者： Chen, Guobin Li, Shijin Rongzhi Coll Chongqing Technol & Business Univ Chongqing Key Lab Spatial Data Min & Big Data Int Chongqing Peoples R China Yunnan Univ Finance & Econ Acad Affairs Off Kunming Yunnan Peoples R China

Recently, solution of discretisation operator technique with circular (DOTWC) approach, and runge-kutta implicit are presented for the Eigen efficient analysis, in this paper based on the various surveys it has been analysed that the efficiency is considered as low and computational burden terms to be high. Henceforth, the implicitly of the restarted Arnoldi (IRA) with intelligent physical system (IPS) with IOT algorithm is implemented for the computational Eigenvalues of critical solution operators in discretized matrices to optimise efficiency and computational burden. Furthermore, we have proposed the Advancement Deep Learning Reinforcement (ADLR) algorithms to improve the efficiency and existing of scalability of the intelligent physical system.

关键词： Eigen Efficient Analysis ira computational Algorithms intelligent Physical System and Deep Learning Reinforcement

来源：评论

学校读者我要写书评

暂无评论

Joint Spectral Regression Methods for Large-Scale Discriminant Analysis

引用

COMMUNICATIONS ON APPLIED MATHEMATICS AND COMPUTATION 2024年 1-24页

作者： Wu, Gang Yang, Wen Hainan Normal Univ Key Lab Data Sci & Intelligence Educ Minist Educ Haikou 571158 Hainan Peoples R China China Univ Min & Technol Sch Math Xuzhou 221116 Jiangsu Peoples R China Fuzhou Univ Int Studies & Trade Sch Big Data Fuzhou 350202 Fujian Peoples R China

Spectral regression discriminant analysis (SRDA) is one of the most popular methods for large-scale discriminant analysis. It is a stepwise algorithm composed of two steps. First, the response vectors are obtained from solving an eigenvalue problem. Second, the projection vectors are computed by solving a least-squares problem. However, the independent two steps can not guarantee the optimality of the two terms. In this paper, we propose a unified framework to compute both the response matrix and the projection matrix in SRDA, so that one can extract the discriminant information of classification tasks more effectively. The convergence of the proposed method is discussed. Moreover, we shed light on how to choose the joint parameter adaptively, and propose a parameter-free joint spectral regression discriminant analysis (JointSRDA-PF) method. Numerical experiments are made on some real-world databases, which show the numerical behavior of the proposed methods and the effectiveness of our strategies.

关键词： Dimension reduction Spectral regression discriminant analysis (SRDA) Joint principal component and discriminant analysis (JPCDA) algorithm Joint spectral regression discriminant analysis (JointSRDA)

来源：评论

学校读者我要写书评

暂无评论

A Semi-randomized Block Kaczmarz Method with Simple Random Sampling for Large-Scale Consistent Linear Systems

引用

COMMUNICATIONS ON APPLIED MATHEMATICS AND COMPUTATION 2024年 1-17页

作者： Wu, Gang Chang, Qiao Hainan Normal Univ Key Lab Data Sci & Smart Educ Minist Educ Haikou 571158 Hainan Peoples R China China Univ Min & Technol Sch Math Xuzhou 221116 Jiangsu Peoples R China Fuzhou Univ Int Studies & Trade Sch Big Data Fuzhou 350202 Fujian Peoples R China

The randomized block Kaczmarz (RBK) method is a randomized orthogonal projection iterative approach, which plays an important role in solving large-scale linear systems. A key point of this type of method is to select working rows effectively during iterations. However, in most of the RBK-type methods, one has to scan all the rows of the coefficient matrix in advance to compute probabilities or paving, or to compute the residual vector of the linear system in each iteration to determine the working rows. These are unfavorable for big data problems. To cure these drawbacks, we propose a semi-randomized block Kaczmarz (SRBK) method with simple random sampling for large-scale linear systems in this paper. The convergence of the proposed method is established. Numerical experiments on some real-world and large-scale data sets show that the proposed method is often superior to many state-of-the-art RBK-type methods for large linear systems.

关键词： Randomized Kaczmarz (RK) method Randomized block Kaczmarz (RBK) method Semi-randomized Kaczmarz (SRK) method Semi-randomized block Kaczmarz (SRBK) method Simple random sampling Large-scale linear system

来源：评论

学校读者我要写书评

暂无评论

Mid-Spine Belt of Beautiful China: future reversal of increasing vegetation greening in response to an evolving environment

引用

intERNATIONAL JOURNAL OF DIGITAL EARTH 2025年第1期18卷

作者： Fu, Jing Su, Baoling Qin, Jianxin Hu, Yong Hengyang Normal Univ Coll Geog & Tourism Hengyang 421002 Peoples R China Hunan Normal Univ Hunan Key Lab Geospatial Big Data Min & Applicat Changsha Peoples R China Int Ctr Space Technol Nat & Cultural Heritage HIST Hengyang Base Hengyang Peoples R China

SDG15 emphasizes the criticality of ecosystem sustainability. The interplay between vegetation and the environment plays a crucial role in maintaining ecological equilibrium. The Mid-Spine Belt of Beautiful China (MSBBC), a novel geographical designation, encompasses agro-pastoral production and living spaces in China. However, vegetation dynamics in the area remain incompletely characterized. Therefore, this study investigated spatiotemporal variations of NDVI in MSBBC from 2000 to 2022, introducing the V-statistic to simulate durations of future vegetation trends. Since 2000, a majority of the MSBBC has experienced vegetation improvement, with significant enhancement observed in 77.34% of the area. This trend is primarily driven by increased precipitation and wind speed under climate warming, coupled with increased afforestation efforts and reduced livestock populations. Conversely, areas presenting significant vegetation degradation account for only 1.07% of the total, mainly due to urbanization and economic progress, partially explained by decreased sunshine duration and relative humidity. Evidently, China's long-standing commitment to environmental preservation and ecological restoration has greatly mitigated degradation. Importantly, vegetation greening is projected to stagnate over the next decade. These findings deepen our understanding of ecosystem enhancement influenced by climatic and anthropogenic factors and provide a valuable reference for devising innovative approaches to remote sensing time series predictions.

关键词： NDVI time series spatiotemporal variability multiple determinants V-statistic sustainability

来源：评论

学校读者我要写书评

暂无评论

Non-linear relations between life expectancy, socio-economic, and air pollution factors: a global assessment with spatial disparities

引用

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH 2022年第35期29卷 53306-53318页

作者： Pu, Haixia Wang, Shaobin Wang, Zhaolin Ran, Zimi Jiang, Mengyu Chongqing Technol & Business Univ Ctr Populat Dev & Policy Res Chongqing 400067 Peoples R China Chinese Acad Sci Inst Geog Sci & Nat Resources Res A11 Datun Rd Beijing 100101 Anwai Peoples R China Chongqing Technol & Business Univ Sch Publ Adm Chongqing 400067 Peoples R China Chongqing Key Lab Spatial Data Min & Big Data Int Chongqing Peoples R China Changchun Normal Univ Coll Geog Sci Changchun 130032 Peoples R China

Influential factors of socio-economic and air pollution on life expectancy (LE) show complexity. The investigations of non-linear functions of LE, socio-economic, and air pollution factors have not been largely conducted, and spatial and temporal differences of the linear or non-linear relations between LE and the influential factors have been obscured across countries in the world. In this study, the non-linear relations between LE and factors of per capita gross national income (GNI(pc)), urban population rate (UPR), and fine-particulate (PM2.5) were estimated from 2000 to 2015 by using a generalized additive model (GAM). The collected data included the 219 countries and regions with sufficient data and covers the period 2000-2015. The results demonstrate that at the global level, the GNI(pc) plays a stable and significant non-linear role in LE, while the non-linear relationships between UPR, PM2.5, and LE are not significant. The temporal variation was further investigated that the non-linear effect of PM2.5 on LE is gradually strengthened, and the non-linear effect of UPR on LE shows a weakened trend. However, GNI(pc) always plays a significantly non-linear role in the LE level. Furthermore, the spatial difference in the non-linear relations among different continents is detected. In sum, it cannot be ignored the non-linear effects of socio-economic and air pollution factors on LE at a global scale and across different continents.

关键词： Life expectancy at birth Social-economic factors Air pollution spatial difference Generalized additive model

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：