检索结果-内蒙古大学图书馆

Design of Train Carriage Abnormal Noise Alarm System Based on Zigbee

Journal of Physics: Conference Series 2019年第1期1314卷

作者： Yongsheng Zhang Miaomiao Liu School of Computer and Information Technology Northeast Petroleum University Daqing Heilongjiang 163318 China Key Laboratory for Oil Big Data and Intelligent Analysis of Heilongjiang Province Daqing Heilongjiang 163318 China

In order to realize the timely and accurate alarm for abnormal conditions in train carriages, a scheme of abnormal noise alarm system based on zigbee is proposed. The overall system architecture as well as the hardware and software structure of each node is designed. Meanwhile, the workflow and implementation process of each module are elaborated in detail. The system includes five parts: sensor node, zigbee router, coordinator, video module and intelligent terminal. Firstly, the decibels collected by the sound sensor are processed through threshold judgment and sent to the coordinator through the zigbee router module. Secondly, the video module recognizes and analyzes the video of the alarming carriage by means of artificial intelligence. Finally, the detailed alarm information is sent to the intelligent terminal. The development cost of this system is low while its installation and maintenance is convenient. It improves the monitoring facilities of train carriages, which can not only guarantee the accuracy and real time of the warning, but also set the threshold value and delete alarm mark manually. It has strong expansibility and portability, which is of practical significance for improving the safety of train operation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LaG-DESIQUE: A local-and-global blind image quality evaluator without training on human opinion scores 6th

LaG-DESIQUE: A local-and-global blind image quality evaluato...

引用

6th CCF Academic Conference on big data, CCF big data 2018

作者： Liu, Ruyi Zhang, Yi Chandler, Damon M. Miao, Qiguang Liu, Tiange School of Computer Science and Technology Xidian University XianShaanxi710071 China Xian Key Laboratory of Big Data and Intelligent Vision XianShaanxi710071 China School of Electronic and Information Engineering Xian Jiaotong University XianShaanxi710049 China Department of Electrical and Electronic Engineering Shizuoka University HamamatsuShizuoka432-8561 Japan School of Information Science and Engingeering Yanshan University QinhuangdaoHebei066004 China

ISBN: (纸本)9789811329210

This paper extends our previous DESIQUE [1] algorithm to a local-and-global way (LaG-DESIQUE) to blindly measure image quality without training on human opinion scores. The local DESIQUE extracts block-based log-derivative features and evaluates image quality through measuring the multivariate Gaussian distance between selected natural and test image patches. The global DESIQUE extracts image-based log-derivative features and image quality is estimated based on a two-stage framework, which was trained on a set of regenerated distorted images with their quality scores estimated by MAD [2] algorithm. The overall quality is the weighted average of local and global DESIQUE scores. Test on several image databases demonstrates that LaG-DESIQUE performs competitively well in predicting image quality. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

A comparison of four global land cover maps on a provincial scale based on China’s 30 m GlobeLand30 4th

A comparison of four global land cover maps on a provincial ...

引用

4th International Conference on Geo-Informatics in Resource Management and Sustainable Ecosystem, GRMSE 2016

作者： Ye, Xiaohui Zhao, Jinling Huang, Linsheng Zhang, Dongyan Hong, Qi Anhui Engineering Laboratory of Agro-Ecological Big Data Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230039 China

ISBN: (纸本)9789811039652

To monitor the entire earth system, several global land cover mapping products have been produced based on different remote sensing imagery (e.g., AVHRR, MODIS, SPOT, HJ-1), including UMD Land Cover, Global Land Cover 2000, GlobCover 2009 and GlobeLand30. However, the application potential of those products has not been fully explored at a provincial scale. The primary objective of this study is to compare and investigate the potential of these products in Anhui Province, China. The area and spatial consistency were used to evaluate the four datasets based on China’s GlobeLand 30 due to 30 m spatial resolution and the total accuracy of 83.51%. The Pearson’s correlation coefficient (R) and the percentage disagreement (PD) were used to evaluate the area consistency. The spatial similarity coefficient (O) was here adopted in order to verify the accuracy of spatial positions. A total of eight cover classes including cropland, woodland, grassland, shrubland, wetland, water bodies, artificial surfaces and bareland were reclassified and mapped to perform the intercomparison. The analysis results show that the PD of GlobCover 2009 is respectively 15.36% and −8.43% for "cropland" and "woodland", while they are −20.20% and 2.10% for UMD. The "woodland" has better agreement percentage in comparison with "cropland". The O of UMD is the worst of 69.25%, indicating that the spatial consistency is weak for "cropland". Conversely, the O of GlobCover 2009 reaches up to 83.50%. © Springer Nature Singapore Pte Ltd. 2017.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-Metric Learning for Person Re-Identification

Deep Multi-Metric Learning for Person Re-Identification

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yongxin Ge Xinqian Gu Min Chen Hongxing Wang Dan Yang Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education (Chongqing University) Chongqing China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China School of Big Data & Software Engineering Chongqing University Chongqing China

In this paper, to exploit more discriminative information of the global-body and body-parts features, we present a novel deep multi-metric learning (DMML) network for person re-identification under the triplet framework. The main novelty of our learning framework lies in two aspects: 1) Unlike most existing metric learning-based approaches, which learn only one distance metric for comparison, our DMM-L method aims to learn different metrics for the global-body and body-parts features respectively by using convolutional neural network (CNN); 2) A new multi-metric loss function is proposed to train the DMML network, under which the distance of each negative pair is greater than that of each positive pair by a predefined margin, and the correlations of different metrics are maximized. Compared with the previous person re-identification methods that have shown state-of-the-art performances, our DMML approach can achieve competitive results on the challenging CUHK03, CUHKOl, VIPeR and iLIDS datasets.

关键词： Measurement Image color analysis Feature extraction Training Machine learning Kernel Learning systems

来源：评论

学校读者我要写书评

暂无评论

Maximum likelihood estimation based on random subspace EDA: Application to extrasolar planet detection 11th

Maximum likelihood estimation based on random subspace EDA: ...

引用

11th International Conference on Simulated Evolution and Learning, SEAL 2017

作者： Liu, Bin Chen, Ke-Jia School of Computer Science Nanjing University of Posts and Telecommunications NanjingJiangsu210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing NanjingJiangsu210023 China

ISBN: (纸本)9783319687582

This paper addresses maximum likelihood (ML) estimation based model fitting in the context of extrasolar planet detection. This problem is featured by the following properties: (1) the candidate models under consideration are highly nonlinear;(2) the likelihood surface has a huge number of peaks;(3) the parameter space ranges in size from a few to dozens of dimensions. These properties make the ML search a very challenging problem, as it lacks any analytical or gradient based searching solution to explore the parameter space. A population based searching method, called estimation of distribution algorithm (EDA), is adopted to explore the model parameter space starting from a batch of random locations. EDA is featured by its ability to reveal and utilize problem structures. This property is desirable for characterizing the detections. However, it is well recognized that EDAs can not scale well to large scale problems, as it consists of iterative random sampling and model fitting procedures, which results in the well-known dilemma curse of dimensionality. A novel mechanism to perform EDAs in interactive random subspaces spanned by correlated variables is proposed and the hope is to alleviate the curse of dimensionality for EDAs by performing the operations of sampling and model fitting in lower dimensional subspaces. The effectiveness of the proposed algorithm is verified via both benchmark numerical studies and real data analysis. © Springer International Publishing AG 2017.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Soft-gated warping-GAN for pose-guided person image synthesis 18

Soft-gated warping-GAN for pose-guided person image synthesi...

引用

Proceedings of the 32nd International Conference on Neural Information Processing Systems

作者： Haoye Dong Xiaodan Liang Ke Gong Hanjiang Lai Jia Zhu Jian Yin School of Data and Computer Science Sun Yat-sen University and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R. China School of Intelligent Systems Engineering Sun Yat-sen University School of Data and Computer Science Sun Yat-sen University School of Computer Science South China Normal University

Despite remarkable advances in image synthesis research, existing works often fail in manipulating images under the context of large geometric transformations. Synthesizing person images conditioned on arbitrary poses is one of the most representative examples where the generation quality largely relies on the capability of identifying and modeling arbitrary transformations on different body parts. Current generative models are often built on local convolutions and overlook the key challenges (e.g. heavy occlusions, different views or dramatic appearance changes) when distinct geometric changes happen for each part, caused by arbitrary pose manipulations. This paper aims to resolve these challenges induced by geometric variability and spatial displacements via a new Soft-Gated Warping Generative Adversarial Network (Warping-GAN), which is composed of two stages: 1) it first synthesizes a target part segmentation map given a target pose, which depicts the region-level spatial layouts for guiding image synthesis with higher-level structure constraints; 2) the Warping-GAN equipped with a soft-gated warping-block learns feature-level mapping to render textures from the original image into the generated segmentation map. Warping-GAN is capable of controlling different transformation degrees given distinct target poses. Moreover, the proposed warping-block is lightweight and flexible enough to be injected into any networks. Human perceptual studies and quantitative evaluations demonstrate the superiority of our Warping-GAN that significantly outperforms all existing methods on two large datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Traceable certificateless ring signature scheme for no full anonymous applications

引用

International Journal of Network Security 2018年第4期20卷 762-773页

作者： Gu, Ke Wang, LinYu Wu, Na Liao, NianDong School of Computer and Communication Engineering Changsha University of Science and Technology Wangjiali Rd Tianxin district Changsha Hunan Province410114 China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology China

With the rapid development of identity-based cryptography, several traceable (or linkable) identity-based ring signature (TIBRS) schemes have been proposed. Compared with ring signature based on public key cryptography, TIBRS can simplify public key management and be used for more applications. However, identity-based cryptography still has the problem of private key management and few traceable ring signature schemes are constructed in the standard model. In this paper, we present a fully traceable certificateless ring signature (TCRS) scheme in the standard model, which has a security reduction to the computational Diffie-Hellman (CDH) assumption. © 2018, Femto Technique Co., Ltd.

关键词： Public key cryptography

来源：评论

学校读者我要写书评

暂无评论

$\rho$ -Dominant Skyline Computation on data Stream

引用

IEEE Access 2018年 6卷 53201-53213页

作者： Zhiqiong Wang Junchang Xin Linlin Ding Jianmin Ba Xiaosong Gao Neusoft Institute of Intelligent Healthcare Technology Co. Ltd. Key Laboratory of Big Data Management and Analytics Shenyang China School of Information Liaoning University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China Sino-Dutch Biomedical and Information Engineering School Northeastern University Shenyang China

Skyline query is widely used in multi-standard decision making process. As the extension to skyline query, p-dominant skyline query controls the base of the result set by adjusting data proportion, which is suitable for the application on fast deciding data stream. However, skyline query on data stream cannot satisfy the need for skyline query of corresponding value ratio, and the traditional p-dominant skyline query cannot provide skyline query with frequent data update. As a result, a data stream-based algorithm that can achieve the goal of p-dominant skyline query is proposed. First, the definitions of full-dominant relationship and p-dominance are given, after which the definitions of p-dominant skyline and p-dominant skyline based on data stream are proposed. Second, by analyzing the characters of data stream-based p-dominant skyline, a new data filtering method is established. Based on the method, p-Dominant Skyline Query on data stream over Sliding Window (DSSW) is proposed in order to improve the efficiency of p-dominant skyline query. After that, we expend the p-dominant skyline query of data stream into n-of-N p-dominant skyline query and the (n1, n 2 )-of-Np-dominant skyline query in data stream. Finally, we prove that DSSW has obvious advantages in responding time and storage skyline space by comparing with the traditional p-dominant skyline query algorithms through abundant experiments.

关键词： IEEE merchandise Microsoft Windows Indexes Decision making Heuristic algorithms Computer science

来源：评论

学校读者我要写书评

暂无评论

Cascade control for supply air temperature in a variable air volume system

引用

IOP Conference Series. Earth and Environmental Science 2019年第1期238卷 012021-012021页

作者： Zhuang, Junhua Chen, Yimin Wu, Jie School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing China Department of Civil Architectural and Environmental Engineering Drexel University Philadelphia PA 19104 USA Beijing ZXT M&E Engineering Consultant Co. Ltd

Most supply air temperature in variable air volume systems is typically set at 55F(13 °C) that is design value in these systems. However, sometimes the load of cooling varies greatly in different zones, and it means the indoor temperature of low-load zones is lower than comfortable value, even if the supply air damper is at the minimum value that is not closed for minimum outside air requirement. Meanwhile, in transition season, the indoor temperature is also lower due to low outdoor temperature. These factors provided an opportunity to apply higher supply air temperature to reduce air handling unit (AHU) cooling load and box reheating. In this paper, a cascade control method is used to raise the supply air temperature. The external control loop controls the setting value of supply air temperature with the minimum supply air volume as the control target. And the internal control loop controls the supply air temperature by regulating valve. The cascade structure can solve the problem that the time constant of the system is too large. The simulation results show that the quality of control is good and the reheating can be cancelled.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Breast Cancer Diagnosis in Ultrasound Images Using Deep Learning with Feature Fusion and Attention Mechanism

引用

Academic radiology 2025年

作者： Sohaib Asif Yuqi Yan Bojian Feng Meiling Wang Yuxin Zheng Tian Jiang Ruyi Fu Jincao Yao Lujiao Lv Mei Song Lin Sui Zheng Yin Vicky Yang Wang Dong Xu Taizhou Key Laboratory of Minimally Invasive Interventional Therapy & Artificial Intelligence Taizhou Campus of Zhejiang Cancer Hospital (Taizhou Cancer Hospital) Taizhou Zhejiang 317502 China (S.A. Y.Y. B.F. L.S. D.X.) Center of Intelligent Diagnosis and Therapy (Taizhou) Hangzhou Institute of Medicine (HIM) Chinese Academy of Sciences Taizhou Zhejiang 317502 China (S.A. Y.Y. B.F. L.S. V.Y.W. D.X.) Wenling Institute of Big Data and Artificial Intelligence in Medicine Taizhou Zhejiang 317502 China (S.A. Y.Y. B.F. L.S. V.Y.W. D.X.) Department of Diagnostic Ultrasound Imaging & Interventional Therapy Zhejiang Cancer Hospital Hangzhou Institute of Medicine (HIM) Chinese Academy of Sciences Hangzhou Zhejiang 310022 China (S.A. Y.Y. B.F. T.J. J.Y. L.L. M.S. M.S. L.S. V.Y.W. D.X.). Department of Diagnostic Ultrasound Imaging & Interventional Therapy Zhejiang Cancer Hospital Hangzhou Institute of Medicine (HIM) Chinese Academy of Sciences Hangzhou Zhejiang 310022 China (S.A. Y.Y. B.F. T.J. J.Y. L.L. M.S. M.S. L.S. V.Y.W. D.X.) Zhejiang Provincial Research Center for Cancer Intelligent Diagnosis and Molecular Technology Hangzhou 310022 China (Y.Y. T.J. J.Y. L.S. D.X.). Second Clinical College Zhejiang University of Traditional Chinese Medicine Hangzhou China (M.W. Y.Z. Z.Y.). Hangzhou Fuyang Hospital of Orthopedics of Traditional Chinese Medicine Special Inspection Department Zhejiang China (R.F.). Zhejiang Provincial Research Center for Cancer Intelligent Diagnosis and Molecular Technology Hangzhou 310022 China (Y.Y. T.J. J.Y. L.S. D.X.) Key Laboratory of Head & Neck Cancer Translational Research of Zhejiang Province Hangzhou 310022 China (J.Y.). Zhejiang Provincial Research Center for Cancer Intelligent Diagnosis and Molecular Technology Hangzhou 310022 China (Y.Y. T.J. J.Y. L.S. D.X.). Electronic address: xudong@***.

RATIONALE AND OBJECTIVES:Early detection of malignant lesions in ultrasound images is crucial for effective cancer diagnosis and treatment. While traditional methods rely on radiologists, deep learning models can improve accuracy, reduce errors, and enhance efficiency. This study explores the application of a deep learning model for classifying benign and malignant lesions, focusing on its performance and interpretability. MATERIALS AND METHODS:In this study, we proposed a feature fusion-based deep learning model for classifying benign and malignant lesions in ultrasound images. The model leverages advanced architectures such as MobileNetV2 and DenseNet121, enhanced with feature fusion and attention mechanisms to boost classification accuracy. The clinical dataset comprises 2171 images collected from 1758 patients between December 2020 and May 2024. Additionally, we utilized the publicly available BUSI dataset, consisting of 780 images from female patients aged 25 to 75, collected in 2018. To enhance interpretability, we applied Grad-CAM, Saliency Maps, and shapley additive explanations (SHAP) techniques to explain the model's decision-making. A comparative analysis with radiologists of varying expertise levels is also conducted. RESULTS:The proposed model exhibited the highest performance, achieving an AUC of 0.9320 on our private dataset and an area under the curve (AUC) of 0.9834 on the public dataset, significantly outperforming traditional deep convolutional neural network models. It also exceeded the diagnostic performance of radiologists, showcasing its potential as a reliable tool for medical image classification. The model's success can be attributed to its incorporation of advanced architectures, feature fusion, and attention mechanisms. The model's decision-making process was further clarified using interpretability techniques like Grad-CAM, Saliency Maps, and SHAP, offering insights into its ability to focus on relevant image features for accurate classi

关键词： Attention mechanisms Deep learning Feature fusion Medical diagnostics Ultrasound imaging

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：