检索结果-内蒙古大学图书馆

6th International Conference on information Science and Control Engineering (ICISCE)

作者： Yang, Mengji Zhang, Haiqing Bouras, Abdelaziz Tang, Yiqian He, Yu Li, DaiWei Yu, Xi Chengdu Univ Sch Informat Sci & Engn Chengdu Peoples R China Chengdu Univ Informat Technol Dept Software Engn Chengdu 610103 Sichuan Peoples R China Qatar Univ Comp Sci Dept ictQATAR Box 2731 Doha Qatar Key Lab Pattern Recognit & Intelligent Informat P Chengdu Peoples R China

ISBN: (纸本)9781728157122

Crop diseases are a major global threat to food security. Because the lack of agriculture experts or necessary facilities, it is difficult to determine the type of disease, as well as the degree of disease in time, which became the major factor affecting in crop production. In recent years, with the development of the transfer learning in deep learning domain, the experience of experts can be simulated to detect crop diseases in time. In this paper, we have proposed an improved transfer learning method based on ResNet 50 in crop disease diagnosis. The AI Challenger 2018 dataset has been deeper analyzed, the degree of crops diseases are detected. Comparing with non-transfer learning, the proposed transfer learning method achieved better results, which can significantly improve accuracy results by 5.1%similar to 1.87% with reducing half of the running time.

关键词： crop disease deep learning transfer learning ResNet 50

来源：评论

学校读者我要写书评

暂无评论

Multi-Task GANs for View-Specific Feature Learning in Gait recognition

引用

IEEE TRANSACTIONS ON informatION FORENSICS AND SECURITY 2019年第1期14卷 102-113页

作者： He, Yiwei Zhang, Junping Shan, Hongming Wang, Liang Fudan Univ Shanghai Key Lab Intelligent Informat Proc Shanghai 200433 Peoples R China Fudan Univ Sch Comp Sci Shanghai 200433 Peoples R China Rensselaer Polytech Inst Dept Biomed Engn Ctr Biotechnol & Interdisciplinary Studies Troy NY 12180 USA Chinese Acad Sci Inst Automat Ctr Res Intelligent Percept & Comp Natl Lab Pattern Recognit Beijing 100190 Peoples R China

Gait recognition is of great importance in the fields of surveillance and forensics to identify human beings since gait is the unique biometric feature that can be perceived efficiently at a distance. However, the accuracy of gait recognition to some extent suffers from both the variation of view angles and the deficient gait templates. On one hand, the existing cross-view methods focus on transforming gait templates among different views, which may accumulate the transformation error in a large variation of view angles. On the other hand, a commonly used gait energy image template loses temporal information of a gait sequence. To address these problems, this paper proposes multi-task generative adversarial networks (MGANs) for learning view-specific feature representations. In order to preserve more temporal information, we also propose a new multi-channel gait template, called period energy image (pEI). Based on the assumption of view angle manifold, the MGANs can leverage adversarial training to extract more discriminative features from gait sequences. Experiments on OU-ISIR, CASIA-B, and USF benchmark data sets indicate that compared with several recently published approaches, pEI + MGANs achieves competitive performance and is more interpretable to cross-view gait recognition.

关键词： Gait recognition cross-view generative adversarial networks surveillance

来源：评论

学校读者我要写书评

暂无评论

Analysis of Seasonal Daytime Urban Thermal Environment Dynamics in a Tropical Coastal City Based on the Spatiotemporal Fusion Model

引用

ADVANCES IN METEOROLOGY 2020年第1期2020卷

作者： Yao, Yuan Lu, Yiling Zhang, Fang Liu, Lulu Liao, Min Chengdu Univ Sch Architecture & Civil Engn Chengdu 610106 Peoples R China Chengdu Univ Inst Higher Educ Sichuan Prov Key Lab Pattern Recognit & Intelligent Informat P Chengdu 610106 Peoples R China Xinjiang Univ Coll Resources & Environm Sci Urumqi 830046 Peoples R China

This study investigated the seasonal variations of daytime urban thermal environment (UTE) based on land surface temperature (LST) in Shenzhen of 2015. The spatial and temporal adaptive reflectance fusion model (STARFM) was used for retrieving seasonal daytime LST at high spatiotemporal resolution by combining MODIS and HJ-1B LST data. Next, the relationship between the land cover and daytime in each season was examined. Finally, daytime LST patterns were classified, and the effects of seasonal variations of high-grade daytime LSTs were analyzed with landscape metrics. The results showed that (1) the STARFM is capable of generating seasonal daytime LST data at high spatiotemporal resolution. (2) Daytime LSTs were generally higher in the western parts of Shenzhen in spring and summer. (3) Daytime LST in each land cover type showed an increasing trend form winter to summer and decreased from summer to autumn. The highest and lowest daytime LSTs in each season were observed in ISAs and water bodies. (4) Landscape metrics provided a quantitative method for describing seasonal variations in daytime LSTs, and it was found that seasons influenced the intensity and extent of daytime LSTs in Shenzhen. These findings may be helpful for urban planners developing regional urban strategies to improve daytime urban thermal comfort conditions.

关键词： Seasonality Coastal City

来源：评论

学校读者我要写书评

暂无评论

Block sparse representation for pattern classification: Theory, extensions and applications

引用

pattern recognitION 2019年 88卷 198-209页

作者： Wang, Yulong Tang, Yuan Yan Li, Luoqing Zheng, Xianwei Chengdu Univ Sch Informat Sci & Engn Chengdu Sichuan Peoples R China Chengdu Univ Inst Higher Educ Sichuan Prov Key Lab Pattern Recognit & Intelligent Informat P Chengdu Sichuan Peoples R China Univ Macau Fac Sci & Technol Macau Peoples R China Hubei Univ Fac Math & Stat Wuhan Hubei Peoples R China Foshan Univ Sch Math & Big Data Foshan Guangdong Peoples R China

By exploiting the low-dimensional structure of high-dimensional data, sparse representation based classifiers (SRC) has recently attracted massive attention in pattern recognition. In this paper, we study a natural generalization of SRC, i.e., block sparse representation based classifiers (BSRC), which takes into account the block structure of the dictionary. Our contributions are two-fold: (1) we provide theoretical guarantees for BSRC and theoretically show that BSRC performs perfect classification for any test sample under both cases of independent subspaces and arbitrary subspaces settings;(2) we extend BSRC and propose three robust BSRC methods based on M-estimators originating in robust statistics. This is motivated by the observation that many previous representation based classifiers utilize the mean square error (MSE) criterion as the loss function, which is sensitive to outliers and complicated noises in reality. In contrast, M-estimators has shown much stronger robustness than MSE against gross corruptions. We demonstrate the efficacy of the proposed methods through experiments on both synthetic and real-world databases for block sparse recovery, handwritten digit recognition and robust face recognition. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Representation based classifier Block sparsity Subspace M-estimator

来源：评论

学校读者我要写书评

暂无评论

Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation 9

Enhancing Context Modeling with a Query-Guided Capsule Netwo...

引用

Conference on Empirical Methods in Natural Language processing / 9th International Joint Conference on Natural Language processing (EMNLp-IJCNLp)

作者： Yang, Zhengxin Zhang, Jinchao Meng, Fandong Gu, Shuhao Feng, Yang Zhou, Jie Univ Chinese Acad Sci Beijing Peoples R China Chinese Acad Sci ICT CAS Inst Comp Technol Key Lab Intelligent Informat Proc Beijing Peoples R China Tencent Inc Pattern Recognit Ctr WeChat AI Shenzhen Guangdong Peoples R China

ISBN: (纸本)9781950737901

Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations. The widely used method for document-level translation usually compresses the context information into a representation via hierarchical attention networks. However, this method neither considers the relationship between context words nor distinguishes the roles of context words. To address this problem, we propose a query-guided capsule networks to cluster context information into different perspectives from which the target translation may concern. Experiment results show that our method can significantly outperform strong baselines on multiple data sets of different domains.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Thermal inspection for viscous dissipation slip flow of hybrid nanofluid (TiO2-Al2O3/C2H6O2) using cylinder, platelet and blade shape features

引用

SCIENTIFIC REpORTS 2023年第1期13卷 1-11页

作者： Yang, Hong Hayat, Umer Shaiq, Shakil Shahzad, Azeem Abbas, Tasawar Naeem, Muhammad Khan, Sami Ullah labidi, Taher Kolsi, Lioua Zahid, Manzoor Ahmad Chengdu Univ Sch Comp Sci Chengdu Peoples R China Chengdu Univ Key Lab Pattern Recognit & Intelligent Informat Pr Chengdu Peoples R China Univ Engn & Technol Dept Basic Sci Taxila 47050 Pakistan Sahara Univ Dept Math Narowal 51600 Pakistan Univ Wah Dept Math Wah Cantt 47040 Pakistan COMSATS Univ Islamabad Sahiwal Campus Dept Math Sahiwal 57000 Pakistan Namal Univ Dept Math Mianwali 42250 Pakistan Prince Sattam Bin Abdulaziz Univ Coll Comp Engn & Sci Dept Software Engn POB 151 Al Kharj 11942 Saudi Arabia Sfax Univ Miracl Lab Sfax Tunisia Univ Hail Coll Engn Dept Mech Engn Hail City 2440 Saudi Arabia Univ Monastir Dept Energy Engn Lab Metrol & Energy Syst Monastir 5000 Tunisia

Hybrid nanofluid are the modified class of nanofluids with extra high thermal performances and present different applications in automotive cooling, heat transfer devices, solar collectors, engine applications, fusion processes, machine cutting, chemical processes etc. This thermal research explores the heat transfer assessment due to hybrid nanofluid with of different shape features. The thermal inspections regarding the hybrid nanofluid model are justified with aluminium oxide and titanium nanoparticles. The base liquid properties are disclosed with ethylene glycol material. The novel impact of current model is the presentation of different shape features namely platelets, blade and cylinder. Different thermal properties of utilized nanoparticles at various flow constraints are reported. The problem of hybrid nanofluid model is modified in view of slip mechanism, magnetic force and viscous dissipation. The heat transfer observations for decomposition of TiO2-Al2O3/C2H6O2 is assessed by using the convective boundary conditions. The shooting methodology is involved for finding the numerical observations of problem. Graphical impact of thermal parameters is observed for TiO2-Al2O3/C2H6O2 hybrid decomposition. The pronounced observations reveal that thermal rate enhanced for blade shaped titanium oxide-ethylene glycol decomposition. The wall shear force reduces for blade shaped titanium oxide nanoparticles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coreferential Reasoning Learning for Language Representation

Coreferential Reasoning Learning for Language Representation

引用

Conference on Empirical Methods in Natural Language processing (EMNLp)

作者： Ye, Deming Lin, Yankai Du, Jiaju Liu, Zhenghao Li, peng Sun, Maosong Liu, Zhiyuan Tsinghua Univ Dept Comp Sci & Technol Beijing Peoples R China Tsinghua Univ Inst Artificial Intelligence Beijing Peoples R China Beijing Natl Res Ctr Informat Sci & Technol Beijing Peoples R China Tsinghua Univ State Key Lab Intelligent Technol & Syst Beijing Peoples R China Beijing Acad Artificial Intelligence Beijing Peoples R China Tencent Inc Pattern Recognit Ctr WeChat AI Beijing Peoples R China

ISBN: (纸本)9781952148606

Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLp tasks with appropriate fine-tuning. However, most existing language representation models cannot explicitly handle coreference, which is essential to the coherent understanding of the whole discourse. To address this issue, we present CorefBERT, a novel language representation model that can capture the coreferential relations in context. The experimental results show that, compared with existing baseline models, CorefBERT can achieve significant improvements consistently on various downstream NLp tasks that require coreferential reasoning, while maintaining comparable performance to previous models on other common NLp tasks. The source code and experiment details of this paper can be obtained from https://***/thunlp/CorefBERT.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

An Independent Component Analysis Classification for Complex power Quality Disturbances With Sparse Auto Encoder Features

引用

IEEE ACCESS 2019年 7卷 20961-20966页

作者： Shi, Xiaoying Yang, Hui Xu, Zhibang Zhang, Xiujun Farahani, Mohammad Reza Nanchang Univ Sch Mechatron Engn Nanchang 330031 Jiangxi Peoples R China East China Jiaotong Univ Sch Elect & Automat Engn Nanchang 330013 Jiangxi Peoples R China Chengdu Univ Inst Higher Educ Sichuan Prov Key Lab Pattern Recognit & Intelligent Informat P Chengdu 610106 Sichuan Peoples R China Iran Univ Sci & Technol Dept Appl Math Tehran 16844 Iran

This paper introduces a method to detect multiple power quality (pQ) disturbances of power system features based on an independent component analysis (ICA) and a sparse auto encoder (SAE). Seven basic single pQ disturbances are extracted as typical features from numerous training samples of pQ disturbances by the SAE method, which can automatically gain the training features rather than manually selecting features as in the conventional approaches. An ICA is adapted to conduct basic separate signals from the blind original disturbance sources. The experimental results indicate that the proposed method has not only achieved a significant improvement for detecting single pQ disturbances but is also effective for detecting and classifying multiple pQ disturbances.

关键词： Multiple power quality disturbances (pQDs) sparse auto encoder (SAE) blind original signal independent component analysis (ICA) complex fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Lesion Detection From Fundus Images

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2019年第6期38卷 1501-1512页

作者： Wang, Renzhen Chen, Benzhi Meng, Deyu Wang, Lisheng Xi An Jiao Tong Univ Inst Informat & Syst Sci Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ Minist Educ Key Lab Intelligent Networks & Network Secur Xian 710049 Shaanxi Peoples R China Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Dept Automat Shanghai 200240 Peoples R China

Early diagnosis and continuous monitoring of patients suffering from eye diseases have been major concerns in the computer-aided detection techniques. Detecting one or several specific types of retinal lesions has made a significant breakthrough in computer-aided screen in the past few decades. However, due to the variety of retinal lesions and complex normal anatomical structures, automatic detection of lesions with unknown and diverse types from a retina remains a challenging task. In this paper, a weakly supervised method, requiring only a series of normal and abnormal retinal images without need to specifically annotate their locations and types, is proposed for this task. Specifically, a fundus image is understood as a superposition of background, blood vessels, and background noise (lesions included for abnormal images). Background is formulated as a low-rank structure after a series of simple preprocessing steps, including spatial alignment, color normalization, and blood vessels removal. Background noise is regarded as stochastic variable and modeled through Gaussian for normal images and mixture of Gaussian for abnormal images, respectively. The proposed method encodes both the background knowledge of fundus images and the background noise into one unique model, and corporately optimizes the model using normal and abnormal images, which fully depict the low-rank sub-space of the background and distinguish the lesions from the background noise in abnormal fundus images. Experimental results demonstrate that the proposed method is of fine arts accuracy and outperforms the previous related methods.

关键词： Computer-aided detection weakly supervised learning retinal lesions low-rank structure mixture of Gaussian

来源：评论

学校读者我要写书评

暂无评论

An observer deployment algorithm for information source positioning based on Naive Bayes

引用

INTERNATIONAL JOURNAL OF MODERN pHYSICS C 2020年第8期31卷

作者： Zhang Hong Guo Bing Shen Yan Shen Yun-Cheng Duan Xu-Liang Dong Xiang-Qian Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Chengdu Univ Coll Informat Sci & Engn Chengdu 610106 Peoples R China Chengdu Univ Informat Technol Sch Control Engn Chengdu 610225 Peoples R China Chengdu Univ Key Lab Pattern Recognit & Intelligent Informat P Inst Higher Educ Sichuan Prov Chengdu 610106 Peoples R China

The accurate positioning of the propagation and diffusion source points of personal information is of great practical significance for the protection of personal information security. Currently, a popular method is to locate the data diffusion source point by deploying a certain number of observers and collecting the data propagation information from observers. In view of the deployment of observers, it was found that there is an important correlation between the observer deployment location and the data propagation time delay by analyzing the relationship between the positioning accuracy of information sources and the deployment location of observers, and then an optimal deployment strategy based on Naive Bayes model (NBM) was proposed. At last, it was verified that the proposed deployment strategy can significantly improve the positioning accuracy of information source by comparing the model network with the actual network, which is of great significance for the security control of personal information propagation.

关键词： personal information observer deployment location information source Naive Bayes

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：