检索结果-内蒙古大学图书馆

Research on the Application of User Recommendation Based on the Fusion Method of spatially Complex Location Similarity

引用

COMPLEXITY 2021年第1期2021卷

作者： Wang, Lili Shi, Ting Li, Shijin Chongqing Finance & Econ Coll Big Data Integrat Ecol & Environm Chongqing Key Lab Spatial Data Min Chongqing 401320 Peoples R China Yunnan Business Informat Engn Sch Kunming 677000 Yunnan Peoples R China Yunnan Univ Finance & Econ Acad Affairs Off Kunming 650221 Yunnan Peoples R China

Since the user recommendation complex matrix is characterized by strong sparsity, it is difficult to correctly recommend relevant services for users by using the recommendation method based on location and collaborative filtering. The similarity measure between users is low. This paper proposes a fusion method based on KL divergence and cosine similarity. KL divergence and cosine similarity have advantages by comparing three similar metrics at different K values. Using the fusion method of the two, the user's similarity with the preference is reused. By comparing the location-based collaborative filtering (LCF) algorithm, user-based collaborative filtering (UCF) algorithm, and user recommendation algorithm (F2F), the proposed method has the preparation rate, recall rate, and experimental effect advantage. In different median values, the proposed method also has an advantage in experimental results.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Study on the prediction method of grasshopper occurrence risk in Inner Mongolia based on the maximum entropy model during the growing period

引用

JOURNAL OF ECONOMIC ENTOMOLOGY 2024年第3期117卷 843-857页

作者： Wen, Fu Liu, Ronghao Garcia y Garcia, Axel Ye, Huichun Lu, Longhui Qimuge, Eerdeng Sun, Zhongxiang Nie, Chaojia Han, Xuemei Zhang, Yue Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China Taiyuan Univ Technol Coll Water Resources Sci & Engn Taiyuan 030024 Peoples R China Univ Minnesota Dept Agron & Plant Genet St Paul MN 55108 USA Univ Minnesota Southwest Res & Outreach Ctr Lamberton MN 56152 USA Aerosp Informat Res Inst Chinese Acad Sci Key Lab Digital Earth Sci Beijing 100094 Peoples R China Hainan Aerosp Informat Res Inst Key Lab Earth Observat Hainan Prov Sanya 572029 Peoples R China Grassland Workstat Xilingol League Xilinhot 026000 Peoples R China China Agr Museum Beijing 100125 Peoples R China Xinjiang Univ Sch Geol & Min Engn Urumqi 830046 Peoples R China

Grasshoppers represent a significant biological challenge in Inner Mongolia's grasslands, severely affecting the region's animal husbandry. Thus, dynamic monitoring of grasshopper infestation risk is crucial for sustainable livestock farming. This study employed the Maxent model, along with remote sensing data, to forecast Oedaleus decorus asiaticus occurrence during the growing season, using grasshopper suitability habitats as a base. The Maxent model's predictive accuracy was high, with an AUC of 0.966. The most influential environmental variables for grasshopper distribution were suitable habitat data (34.27%), the temperature-vegetation dryness index during the spawning period (18.81%), and various other meteorological and vegetation factors. The risk index model was applied to calculate the grasshopper distribution across different risk levels for the years 2019-2022. The data indicated that the level 1 risk area primarily spans central, eastern, and southwestern Inner Mongolia. By examining the variable weights, the primary drivers of risk level fluctuation from 2019 to 2022 were identified as accumulated precipitation and land surface temperature anomalies during the overwintering period. This study offers valuable insights for future O. decorus asiaticus monitoring in Inner Mongolia.

关键词： Maxent insect dynamics predictive modeling remote sensing influencing factor

来源：评论

学校读者我要写书评

暂无评论

Impact of urbanization factors on mortality due to unintentional injuries using panel data regression model and spatial-temporal analysis

引用

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH 2020年第3期27卷 2945-2954页

作者： Pu, Haixia Li, Bin Luo, Dongqi Wang, Shaobin Wang, Zhaolin Zhao, Wei Zheng, Lingyu Duan, Ping Chongqing Technol & Business Univ Res Ctr Econ Upper Reaches Yangtze River Minist Educ Chongqing 400067 Peoples R China Chongqing Technol & Business Univ Key Res Base Humanities Minist Educ Chongqing 400067 Peoples R China Chongqing Technol & Business Univ Coll Tourism & Land Resources Chongqing 400067 Peoples R China Chongqing Key Lab Spatial Data Min & Big Data Int Chongqing Peoples R China Chinese Acad Sci Inst Geog Sci & Nat Resources Res Beijing 100101 Peoples R China Yunnan Normal Univ Coll Tourism & Geog Sci Kunming 650500 Yunnan Peoples R China

Unintentional injuries pose a great risk for human health in China. Few studies have focused on unintentional injuries at national level from urbanization perspective. The panel data of mortality rate of transportation accidents (TA), fall and drowning and sinking (DS) is investigated, and urbanization development index is collected. Global Moran's I and linear regression of panel data are applied to determine the spatial distribution and spatial influencing factors of unintentional injuries. The results are the following: (1) The unintentional injury such as TA, fall, and DS shows clear non-uniformity of spatial distribution and relative immobility through time. (2) A 10,000 tons increase in SO2 emission amount (SO2 EA) and emission of smoke and dust (ESD) can result in 15.7 and 12.5 increases in TA death in eastern region, respectively. Meanwhile, A 10,000 tons increase in NOx emission amount can cause 15.1 increase in TA death in western region. For every 100 billion yuan increase in GDP, the fall death can reduce by 8.4 in central region. One bed increase in number of hospital beds per 10,000 population (NHBP) is favorable for decreasing in fall death by 16.7 in eastern region. However, increase in number of workers enjoying industrial injury (NEWII) does not reduce the fall death in eastern region. (3) For every 1 ten thousand people increase in number of students in ordinary high schools (NSOHS) is conductive to reducing DS death by 7.8 in the western region. Our findings show that there exist spatial differences for urbanization influencing TA, fall, and DS death in eastern, western, and central regions. This study is expected to provide a reference for unintentional injuries control in those three regions.

关键词： Unintentional injuries Spatio-temporal distribution Urbanization Global Moran's I Linear regression of panel data

来源：评论

学校读者我要写书评

暂无评论

A Forest Leaf Area Index Inversion Scheme Using Polarimetric SAR

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2023年 61卷 1页

作者： Fu, Wenxue Wang, Jian Guo, Huadong Chinese Acad Sci Int Res Ctr Big Data Sustainable Dev Goals Beijing 210094 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 210094 Peoples R China Anhui Univ Sci & Technol Sch Spatial Informat & Geomat Engn Huainan 232000 Peoples R China

A novel forest leaf area index (LAI) inversion scheme using polarimetric synthetic aperture radar (PolSAR) images is proposed. The advantage of inversion using synthetic aperture radar (SAR) images over conventional optical methods is the ability to perform all-weather and all-time forest observation, especially in the tropical rainforest area. In this article, leaves were assumed to be isotropic media, while branches were assumed to be anisotropic with a certain orientation. We first investigated the specific extinction coefficients of propagation through leaves and branches, respectively. Then, a method was employed to separate the attenuation of leaves and branches. Subsequently, an inversion scheme model for LAI inversion using PolSAR images was designed based on the linear relationship between the LAI, and the products of forest height and extinction coefficient. Finally, an experiment was performed using L-band Satelite Argentino de Observacion COn Microondas (SAOCOM) spaceborne SAR image pairs. The forest height and extinction coefficients according to H and V polarizations were retrieved using the oriented volume over ground (OVoG) model. The linear relation between the LAI, and the products of forest height and extinction coefficient were verified using the data measured in situ, and the coefficient of determination (R-2) was 0.64. Finally, the temporal decorrelation and the extinction component caused by the oriented elements were analyzed.

关键词： Extinction coefficient forest leaf area index (LAI) oriented volume over ground (OVoG) model polarimetric synthetic aperture radar (PolSAR)

来源：评论

学校读者我要写书评

暂无评论

Frequency Bias Causes Overestimation of Climate Change Impacts on Global Flood Occurrence

引用

GEOPHYSICAL RESEARCH LETTERS 2024年第16期51卷 e2024GL108855-e2024GL108855页

作者： Zhao, Fang Lange, Stefan Goswami, Bedartha Frieler, Katja East China Normal Univ Sch Geog Sci Minist Educ Key Lab Geog Informat Sci Shanghai Peoples R China Minist Nat Resources Key Lab Spatial temporal Big Data Anal & Applicat Shanghai Peoples R China Leibniz Assoc Potsdam Inst Climate Impact Res PIK Potsdam Germany Int Inst Appl Syst Anal IIASA Biodivers & Nat Resources Program Water Secur Res Grp Laxenburg Austria Univ Tubingen Machine Learning Climate Sci Tubingen Germany

The frequency change of 100-year flood events is often determined by fitting extreme value distributions to annual maximum discharge from a historical base period. This study demonstrates that this approach may significantly bias the computed flood frequency change. An idealized experiment shows frequency bias exceeding 100% for a 50-year base period. Further analyses using Monte Carlo simulations, mathematical derivations, and hydrological model outputs reveal that bias magnitude inversely relates to base period length and is weakly influenced by the generalized extreme value distribution's shape parameter. The bias, persisting across different estimation methods, implies floods may exceed local defenses designed based on short historical records more often than expected, even without climate change. We introduce a frequency bias adjustment method, which significantly reduces the projected rise in global flood occurrence. This suggests a substantial part of the earlier projected increase in flood occurrence and impacts is not attributable to climate change. We report a previously overlooked bias in a common method for projecting the frequency of extreme floods, like 100-year events. This method typically uses a short period of historical data for two primary purposes: first, to define local thresholds for extreme floods, such as 100-year events, and second, to serve as a base for projecting future changes in flood occurrences. Our study, utilizing random data, demonstrates that this method can lead to inaccurate projections, increasing the number of expected extreme floods in future years and decreasing them in historical baseline years, even when no change is indicated by the data. Additionally, we find that the longer the historical period used, the smaller the bias. By simulating the characteristics of real hydrological model projections with artificial data, we are able to estimate a bias similar to that observed in these projections, and thus propose a simple

关键词：

来源：评论

学校读者我要写书评

暂无评论

Matching end-of-life household vehicle generation and recycling capacity in Chinese cities: A spatio-temporal analysis for 2022-2050

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2023年第1期899卷 165498页

作者： Ren, Shuliang Huang, Zhou Bao, Yi Yin, Ganmin Yang, Jingfan Shan, Xv Peking Univ Inst Remote Sensing & Geog Informat Syst Sch Earth & Space Sci Beijing 100871 Peoples R China Peking Univ Beijing Key Lab Spatial Informat Integrat & Its Ap Beijing 100871 Peoples R China Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China State Key Lab Media Convergence Prod Technol & Sys Beijing Peoples R China

End-of-life vehicles (ELVs) present both opportunities and challenges for the environment and the economy, where effective recycling management plays a decisive role. Recently, the primary focus of recycling manage-ment has shifted from simply meeting demand to refining and optimizing processes at the city-scale. However, the mismatch in recycling capacity has become a significant obstacle to maximizing environmental and economic benefits. To reveal this issue and propose improvements in the context of China, this study simulates end-of-life internal combustion engine vehicles (ICEVs) and new energy vehicles (NEVs) at the city-scale from 2021 to 2050, and analyzes their spatio-temporal pattern and recycling capacity matching. The results indicate that the number of ELVs in China will continue to increase, peaking between 3.5 and 3.7 million. This growth will be mainly driven by third-to fifth-tier cities, as well as central and southwestern cities. Regarding recycling capacity matching, most cities possess excess dismantling capacity, while first-tier cities face coordination problems in battery collection. spatial coordination across cities or provinces is a viable approach for dismantling enterprises and should be prioritized over indiscriminate deregistration or establishing new facilities. The absence of initiative within the recycling system results in uncoordinated battery collection. Implementing a recycling -sharing mechanism and establishing a reuse market can effectively tackle this problem by leveraging market incentives. These analyses provide practical suggestions to maximize the environmental and economic benefits of resource recycling, thereby contributing to the UN's 2030 Sustainable Development Goals (SDGs).

关键词： End-of-life vehicles Material flow analysis spatial-temporal patterns Over capacity City scale

来源：评论

学校读者我要写书评

暂无评论

Research on Improved Chaotic Particle Optimization Algorithm Based on Complex Function

引用

FRONTIERS IN PHYSICS 2020年 8卷

作者： Xia, Xiangli Li, Shijin Chongqing Technol & Business Univ Rongzhi Coll 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

In order to improve the performance of Particle Swarm Optimization (PSO) algorithm in solving continuous function optimization problems, a chaotic particle optimization algorithm for complex functions is proposed. Firstly, the algorithm uses qubit Bloch spherical coordinate coding scheme to initialize the initial position of the population. This coding method can expand the ergodicity of the search space, increase the diversity of the population, and further accelerate the convergence speed of the algorithm. Secondly, Logistic chaos is used to search the elite individuals of the population, which effectively prevents the PSO algorithm from falling into local optimization, thus obtaining higher quality optimal solution. Finally, complex functions are used to improve chaotic particles to further improve the convergence speed and optimization accuracy of PSO algorithm. Through the optimization tests of four complex high-dimensional functions, the simulation results show that the improved algorithm is more competitive and its overall performance is better, especially suitable for the optimization of complex high-dimensional functions.

关键词： PSO algorithm complex function chaos search convergence rate improve chaotic particles

来源：评论

学校读者我要写书评

暂无评论

Analysis of Geometric Characteristics and Coverage for Moon-Based/Spaceborne Bistatic SAR Earth Observation

引用

REMOTE SENSING 2023年第8期15卷 2151-2151页

作者： Zhang, Ke Guo, Huadong Jiang, Di Han, Chunming Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Technol Geo Spatial Informat Proc & Applic Beijing 100094 Peoples R China

With the rapid development of Earth system science, a new understanding of the complete Earth system has highlighted the crucial importance of integrated observations, especially in research involving large-scale geoscience phenomena. As an active sensor with all-time and all-weather capabilities, synthetic aperture radar (SAR) has been widely used in recent decades for Earth observation. However, the existing spaceborne, airborne, and ground-based SAR systems have difficulty providing temporally consistent and spatially continuous Earth observation data on a global scale. As Earth's only natural satellite, the Moon is a very promising Earth observation platform. By deploying a transmitter on the Moon and a receiver on the high-orbit satellite, a Moon-based/spaceborne bistatic synthetic aperture radar (MS-BiSAR) can be formed. In this paper, the MS-BiSAR geometric model of Earth observation was established using ephemeris and orbit propagators with reference system transformations, and three different MS-BiSAR configurations were used to calculate and analyze their geometric characteristics and Earth observation coverage. The results show that with the advantage of wide swaths, continuous observation capabilities, and large coverage, such an MS-BiSAR could significantly contribute to monitoring and understanding large-scale geoscience phenomena.

关键词： Moon-based Earth observation bistatic SAR observation geometry

来源：评论

学校读者我要写书评

暂无评论

A high-resolution dataset of water bodies distribution over the Tibetan Plateau

引用

SCIENTIFIC data 2024年第1期11卷 453页

作者： Chen, Zhengchao Guo, Linan Wu, Yanhong Zhang, Bing Chen, Pan Yang, Xuan Guo, Jiawei Chinese Acad Sci State Key Lab Remote Sensing Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China China Univ Min & Technol Beijing Beijing 100083 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Shenzhen Inst Adv Technol Chinese Acad Sci Ctr Geospatial Informat Shenzhen 518055 Peoples R China Aerosp Informat Res Inst Chinese Acad Sci China Remote Sensing Satellite Ground Stn Beijing 100094 Peoples R China

Water body (WB) extraction is the basic work of water resources management. Tibetan Plateau is one of the largest alpine lake systems in the world. However, research on the characteristics of water bodies (WBs) is mainly focused on large and medium WBs due to spatial resolution. This research presents a dataset containing a 2-m resolution map of WBs in 2020 based on Gaofen-1 data, and morphometric and landscape indices of WBs across the Tibetan Plateau. The Swin-UNet model is well performed with overall accuracy at 98%. The total area of WBs is 56354.6 km2 across Tibetan Plateau in 2020. The abundance compared with that from size-abundance relationship indicate WBs in the Tibetan Plateau conformed to the classic power scaling law. We evaluate the influence of spatial-resolution in WB extraction, which shows the dataset could be valuable to fill the gap of existing WBs map, especially for small waters. The dataset is valuable for revealing the spatial patterns of WBs, and understanding the impacts of climate change on water resources in Plateau.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Temporal convolution network based on attention mechanism for well production prediction

引用

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING 2022年第0期218卷

作者： Zhen, Yan Fang, Junyi Zhao, Xiaoming Ge, Jiawang Xiao, Yifei Southwest Petr Univ Sch Earth Sci & Technol Chengdu Sichuan Peoples R China Southwest Petr Univ Nat Gas Geol Key Lab Sichuan Prov Chengdu Sichuan Peoples R China Spatial Informat Technol & Big Data Min Res Ctr Chengdu Sichuan Peoples R China

Well production forecasting has a very important guiding significance for oilfield production and management. The traditional BP neural network is difficult to deal with the data with time continuity, and the recurrent neural network (RNN) has some shortcomings such as vanishing gradients and exploding gradients. In order to avoid these problems and further improve the accuracy of neural network models in well production prediction. In this study, a prediction model combining temporal convolutional network (TCN) and attention mechanism is pro-posed. TCN is able to obtain more sensory fields to solve longer time series with fewer network layers by causally expanding convolution. And the residual connectivity in the model structure enables the model to transfer in-formation across layers to solve the problem of network degradation caused by overly deep networks. The attention mechanism can reinforce the influence of important features on the prediction results to improve the prediction accuracy of the model. To evaluate the effectiveness of the model, the TCN-attention model was used to forecast the oil production of four producing wells, and the prediction results were compared with those of LSTM, TCN, RNN, and ARIMA. The results showed that TCN-Attention outperformed the other models in the prediction of the four wells in all evaluation metrics. The method proposed in this paper has excellent data fitting ability, can provide accurate prediction results, and have a certain application value in oilfield production.

关键词： TCN Attention mechanism Production forecasting Deep learning Time series

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：