检索结果-内蒙古大学图书馆

Research Square 2021年

作者： Liu, Shutian Xie, Xiansheng Wang, Xiaochuan Feng, Xinxin Hou, Xianda Wang, Shuojin Lin, keyu Huang, Mei Jia, Shugang Hou, Yanlin Dou, Sen Guangxi Geographical Indication Crops Research Centre of Big Data Mining and Experimental Engineering Technology Nanning Normal University Nanning530001 China Guangxi Key Laboratory of Earth Surface Processes and Intelligent Simulation Nanning Normal University Nanning530001 China School of Geography and Planning Nanning Normal University Nanning530001 China College of Resource and Environmental Science Jilin Agricultural University Changchun130118 China

Soils are an important pool for storing organic carbon. Soil organic carbon (SOC) content is generally considered as an important indicator to evaluate farmland soil quality. The loss of SOC causes soil degradation and reduces the sustainability of farmland. In order to reveal the distribution pattern of SOC in the coastal monsoon area of eastern China, and to clarify the macro dominant factors of SOC accumulation caused by temperature and precipitation, this paper analyzed the distribution pattern of SOC in the coastal monsoon area of eastern China by using the SOC data collected from the national soil testing and formula fertilization data set, and discussed the effects of temperature and precipitation on SOC content. According to the provincial administrative divisions, the distribution of SOC in the coastal monsoon areas of eastern China from Heilongjiang Province to Hainan Province was calculated. According to the annual average temperature 20.95℃, annual average precipitation 0~400 mm, 400~800 mm, > 800 mm, the study area was divided into different regions, and the effects of annual average temperature and annual average precipitation on SOC content were studied. In the region with annual average temperature less than 10.18℃, the temperature had a negative correlation with the accumulation of organic carbon, and the ratio of precipitation and temperature had a positive correlation with the accumulation of SOC;In the region of 10.18℃~20.95℃, the annual average temperature and annual average precipitation had a significant positive correlation, and the ratio of precipitation and temperature had a positive correlation with the accumulation of SOC;In the region >20.95℃, the temperature had a negative correlation with the accumulation of organic carbon, and the ratio of precipitation and temperature was not related to the accumulation of SOC. In the range of 0 ~ 400 mm of annual average precipitation, the temperature had a positive correlation with the accumulation

关键词： Temperature

来源：评论

学校读者我要写书评

暂无评论

Deep Domain Adaptation for Pavement Crack Detection

arXiv

引用

arXiv 2021年

作者： Liu, Huijun Yang, Chunhua Li, Ao Huang, Sheng Feng, Xin Ruan, Zhimin Ge, Yongxin College of Computer Science Chongqing University Chongqing400044 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China Chongqing City Management College Chongqing401331 China Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing University Chongqing400044 China College of Computer Science And Engineering Chongqing University of Technology Chongqing400054 China Co. Ltd Chongqing400060 China

Deep learning-based pavement cracks detection methods often require large-scale labels with detailed crack location information to learn accurate predictions. In practice, however, crack locations are very difficult to be manually annotated due to various visual patterns of pavement crack. In this paper, we propose a Deep Domain Adaptation-based Crack Detection Network (DDACDN), which learns domain invariant features by taking advantage of the source domain knowledge to predict the multi-category crack location information in the target domain, where only image-level labels are available. Specifically, DDACDN first extracts crack features from both the source and target domain by a two-branch weights-shared backbone network. And in an effort to achieve the cross-domain adaptation, an intermediate domain is constructed by aggregating the three-scale features from the feature space of each domain to adapt the crack features from the source domain to the target domain. Finally, the network involves the knowledge of both domains and is trained to recognize and localize pavement cracks. To facilitate accurate training and validation for domain adaptation, we use two challenging pavement crack datasets CQU-BPDD and RDD2020. Furthermore, we construct a new large-scale Bituminous Pavement Multi-label Disease dataset named CQU-BPMDD, which contains 38994 high-resolution pavement disease images to further evaluate the robustness of our model. Extensive experiments demonstrate that DDACDN outperforms state-of-the-art pavement crack detection methods in predicting the crack location on the target domain. Copyright © 2021, The Authors. All rights reserved.

关键词： Crack detection

来源：评论

学校读者我要写书评

暂无评论

A robust and generalized framework for adversarial graph embedding

arXiv

引用

arXiv 2021年

作者： Li, Jianxin Fu, Xingcheng Peng, Hao Wang, Senzhang Zhu, Shijie Sun, Qingyun Yu, Philip S. He, Lifang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China State Key Laboratory of Software Development Environment Beihang University Beijing100083 China School of Computer Science and Engineering Central South University Changsha410083 China Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States Department of Computer Science and Engineering Lehigh University BethlehemPA18015 United States

Graph embedding is essential for graph mining tasks. With the prevalence of graph data in real-world applications, many methods have been proposed in recent years to learn high quality graph embedding vectors various types of graphs. However, most existing methods usually randomly select the negative samples from the original graph to enhance the training data without considering the noise. In addition, most of these methods only focus on the explicit graph structures and cannot fully capture complex semantics of edges such as various relationships or asymmetry. In order to address these issues, we propose a robust and generalized framework for adversarial graph embedding based on generative adversarial networks. Inspired by generative adversarial network, we propose a robust and generalized framework for adversarial graph embedding, named AGE. AGE generates the fake neighbor nodes as the enhanced negative samples from the implicit distribution, and enables the discriminator and generator to jointly learn each node's robust and generalized representation. Based on this framework, we propose three models to handle three types of graph data and derive the corresponding optimization algorithms, i.e., UG-AGE and DG-AGE for undirected and directed homogeneous graphs, respectively, and HIN-AGE for heterogeneous information networks. Extensive experiments show that our methods consistently and significantly outperform existing state-of-the-art methods across multiple graph mining tasks, including link prediction, node classification, and graph reconstruction. Copyright © 2021, The Authors. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Does ad-context matter on the effectiveness of online advertising? 30

Does ad-context matter on the effectiveness of online advert...

引用

30th International Conference on Software engineering and knowledge engineering, SEKE 2018

作者： Sun, Caihong Zhang, Meina Zuo, Meiyun Key Laboratory of Data Engineering and Knowledge Engineering School of Information Renmin University of China Beijing China

ISBN: (纸本)1891706446

In this paper, we focus on examining the effects of Ad-context on the click-Through rate (CTR) for the online advertising. Many researches have shown that ad-context congruity is a key factor to CTR, but the features of ad-context are rarely introduced in CTR prediction algorithms. By leveraging data from various sources, and using text mining and sentiment analysis techniques, our proposed approach extracts three types of features (i.e. users, advertisements and ad-context features) to predict CTR. User features describe "Who" is browsing the webpage, advertisement features depict "How" an ad serving is, and ad-context features include "What" the product is, "Where" an ad displays, as well as the "Mood" of the context. Experiment results show that our proposed approach outperforms the benchmark models by introducing ad-context features. Novel ad-context features we proposed make good contributions to the prediction of CTR. The research highlights the power of ad-context in online advertising CTR prediction. Moreover it gives an insight into supporting effective advertising and improving users' satisfaction. © 2018 Universitat zu Koln. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

STL-FNN:An Intelligent Prediction Model of Daily Theft Level

STL-FNN:An Intelligent Prediction Model of Daily Theft Level

引用

作者： Shaochong Shi Peng Chen Zhaolong Zeng Xiaocheng Hu Department of Information Technology and Cyber Security People’s Public Security University of China Key Laboratory of Security Technology & Risk Assessment Ministry of Public Security National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data China Academy of Electronics and Information Technology

Theft is a long-standing crime against property,which exists alongside the development of private *** the time pattern of thefts could be found out well,police officers can take preventive measures in advance to control the occurrence of theft ***,thieves are smart enough to pick targets *** makes it difficult for police to predict accurately when and where the offenders would commit *** this paper,STL-FNN is proposed based on a seasonal trend decomposition procedure based on loess(STL) and Full Connected Neural Network(FNN),which is designed to predict daily theft level in order to find out when criminals are most likely to commit *** empirical case of prediction of daily theft level in City B shows that the STL-FNN model is better than the other five traditional models for prediction of the long-term sequence(365 days).This model is expected to have high potential application value in the schedule of anti-theft activities planned by polices.

关键词： Crime prediction STL-FNN Daily theft level

来源：评论

学校读者我要写书评

暂无评论

Probabilistic methods for approximate archetypal analysis

arXiv

引用

arXiv 2021年

作者： Han, Ruijian Osting, Braxton Wang, Dong Xu, Yiming Department of Statistics The Chinese University of Hong Kong Hong Kong Department of Mathematics University of Utah Salt Lake City United States School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen China Scientific Computing and Imaging Institute University of Utah Salt Lake City United States

Archetypal analysis is an unsupervised learning method for exploratory data analysis. One major challenge that limits the applicability of archetypal analysis in practice is the inherent computational complexity of the existing algorithms. In this paper, we provide a novel approximation approach to partially address this issue. Utilizing probabilistic ideas from high-dimensional geometry, we introduce two preprocessing techniques to reduce the dimension and representation cardinality of the data, respectively. We prove that provided the data is approximately embedded in a low-dimensional linear subspace and the convex hull of the corresponding representations is well approximated by a polytope with a few vertices, our method can effectively reduce the scaling of archetypal analysis. Moreover, the solution of the reduced problem is near-optimal in terms of prediction errors. Our approach can be combined with other acceleration techniques to further mitigate the intrinsic complexity of archetypal analysis. We demonstrate the usefulness of our results by applying our method to summarize several moderately large-scale datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Correction: Chromosome-level genome provides insights into environmental adaptability and innate immunity in the common dolphin (Delphinus delphis)

引用

BMC genomics 2024年第1期25卷 499页

作者： Kui Ding Qinzeng Xu Liyuan Zhao Yixuan Li Zhong Li Wenge Shi Qianhui Zeng Xianyan Wang Xuelei Zhang Key Laboratory of Marine Eco-Environmental Science and Technology First Institute of Oceanography Ministry of Natural Resources Qingdao China. Laboratory for Marine Ecology and Environmental Science Qingdao Marine Science and Technology Center Qingdao China. Key Laboratory of Marine Ecological Conservation and Restoration Third Institute of Oceanography Ministry of Natural Resources Xiamen China. Key Laboratory of Marine Ecological Conservation and Restoration Third Institute of Oceanography Ministry of Natural Resources Xiamen China. wangxianyan@***. Key Laboratory of Marine Eco-Environmental Science and Technology First Institute of Oceanography Ministry of Natural Resources Qingdao China. zhangxl@***. Laboratory for Marine Ecology and Environmental Science Qingdao Marine Science and Technology Center Qingdao China. zhangxl@***. National Engineering Laboratory for Integrated Aero-Space-GroundOcean Big Data Application Technology Xi'an China. zhangxl@***.

来源：评论

学校读者我要写书评

暂无评论

An approach to the applicability evaluation of moving target tracking algorithm 2nd

An approach to the applicability evaluation of moving target...

引用

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Xi, Runping Xue, Shaohui Han, Qianqian Chen, Jiaxin School of Computer Science Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory of Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China Shaanxi Provincial Key Laboratory of Speech and Image Information Processing Xi’an710129 China

ISBN: (纸本)9783030317256

Objective and effective algorithm performance evaluation results are an important basis for the selection of tracking algorithms. Problems in the existing performance evaluation of moving target tracking algorithms include an enlarge number of trials, and in particular, failure to consider the influence of algorithm performance on the multifactor combination scenario. This study proposes a method based on the orthogonal test to evaluate algorithms. First, the factors and levels of the tracking algorithm are analyzed, and an orthogonal test dataset is constructed by using an orthogonal table. Second, the experiments of the performance evaluation are arranged with the dataset and the results are analyzed via range analysis. Finally, evaluation results show that the strong– weak sequence of factors affect the performance of the algorithm and the combination of levels form the factors that can achieve enhanced algorithm performance. Experimental results show that the proposed method can evaluate algorithms comprehensively, objectively, and effectively with decreased test and data volume. © Springer Nature Switzerland AG 2019.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

data Analysis of Portfolio Optimization using Artificial Neural Network in China's Stock Market* 5

Data Analysis of Portfolio Optimization using Artificial Neu...

引用

5th IEEE International Conference on big data Intelligence and Computing, dataCom 2019

作者： Wang, Chia-Hung Lee, Chia-Jung Fujian University of Technology College of Information Science and Engineering Fuzhou City350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications No. 33 South University Road University Town Fujian Province Fuzhou City350118 China Soochow University School of Big Data Management No. 70 Linhsi Road Shihlin District Taipei City11102 Taiwan

ISBN: (纸本)9781728141176

This paper presents a neural network model for studying the portfolio optimization in China's stock market. An investment scheme is proposed by using an artificial intelligence algorithm based on the trained neural network. In the empirical study, six key indicators of historical transaction data for stocks are used as the input characteristics of our neural network model, which are the opening price, the closing price, the trading volume, the highest and lowest price on the day, and Week time scale. Besides, we use Python technology to process the collected stock data and develop the learning process of the studied neural network for predicting the closing price for the next period. Based on the presented data analysis in the paper, the investors of the stock market in China could make a rational decision-making on the portfolio optimization. © 2019 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A Reliable Calibration of HII Galaxies Hubble Diagram with Cosmic Chronometers and Artificial Neural Network

arXiv

引用

arXiv 2022年

作者： Zhang, Jian-Chen Jiao, Kang Zhang, Tingting Zhang, Tong-Jie Yu, Bo Institute for Frontiers in Astronomy Astrophysics of Beijing Normal University Beijing100875 China Department of Astronomy Beijing Normal University Beijing100875 China College of Computer and Information Engineering Dezhou University Dezhou253023 China Institute for Astronomical Science Dezhou University Dezhou253023 China Dipartimento di Fisica e Astronomia "Augusto Righi" Alma Mater Studiorum Università di Bologna via Piero Gobetti 93/2 BolognaI-40129 Italy College of Command and Control Engineering PLA Army Engineering University Nanjing210000 China School of Mathematics and Big Data Dezhou University Dezhou253023 China Shandong Provincial Key Laboratory of Biophysics Institute of Biophysics Dezhou University Dezhou253023 China

The L − σ relation of HII galaxies (HIIGx) calibrated by a distance indicator is a reliable standard candle for measuring the Hubble constant H0. The most straightforward calibration technique anchors them with the first tier of distance ladders from the same galaxies. Recently another promising method that uses the cosmological model-independent Cosmic Chronometers (CC) as a calibrator has been proposed. We promote this technique by removing the assumptions about the cosmic flatness and using a non-parametric Artificial Neural Network for the data reconstruction process. We observe a correlation between the cosmic curvature density parameter and the slope of the L−σ relation, thereby improving the reliability of the calibration. Using the calibrated HIIGx Hubble diagram, we obtain a Type Ia Supernovae Hubble diagram free of the conventional assumption about H0. Finally we get a value of H0 = 65.9+3.0−2.9 km s−1 Mpc−1, which is compatible with latest Planck18 measurement. © 2022, CC BY.

关键词： Supernovae

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：