检索结果-内蒙古大学图书馆

Innovations in High Speed Communication and Signal Processing (IHCSP), International Conference on

作者： Vikas Goel Ashutosh Sharma Raju Ranjan Amit Kumar Sharma Dept. of IT KIET Group of Institutions Ghaziabad India Dept. of Computer Application IMSUC-Ghaziabad Ghaziabad India School of Computing Science & Engineering Galgotia University Greater Noida India Dept. of CS&E Ch. Charan Singh University Campus Meerut India

As a new form of technology, blockchain has much to offer. The technology has a wide range of potential uses and advancements, depending on the field of application. However, further study is required to realise the potential of advanced technologies like Blockchain and smart contracts. There is a lot of potential for investigation because the technology is so new. This research looked at the origins of the Blockchain and analysed several different blockchain solutions. Ethereum was discovered to be the most often used platform for constructing distributed apps after being compared to other platforms. Therefore, a distributed smart energy microgrid application will be built on the Ethereum platform. There is a coin, or token, exclusive to each blockchain platform. Bitcoin's relationship to other cryptocurrencies was measured using the Karl Pearson correlation coefficient. The research concludes that ether's price is most sensitive to changes in the price of bitcoin. On a preferred Ethereum network, a distributed application for managing smart microgrids has been built. The smart contract constitutes the heart of this programme. As a result, we also take care of the smart contract's layout, coding, and optimization. In comparison to the original, less GAS is consumed by this smart contract. The entire distributed app has been built and thoroughly tested. Smart Energy Microgrid Distributed application framework results demonstrate that the application functioned as expected.

关键词： Surveys Analytical models Technological innovation Smart contracts Time series analysis Bitcoin Microgrids

来源：评论

学校读者我要写书评

暂无评论

Phase Difference Network for Efficient Differentiation of Hepatic Tumors with Multi-Phase CT

Phase Difference Network for Efficient Differentiation of He...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Yuanfeng Wu Geng Chen Zhan Feng Heng Cui Fan Rao Yangfan Ni Zhongke Huang Wentao Zhu Zhejiang Lab Hangzhou China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China Department of Radiology College of Medicine The First Affiliated Hospital Zhejiang University China Sir Run Run Shaw Hospital School of Medicine Zhejiang University Hangzhou China

Liver cancer has been one of the top causes of cancer-related death. For developing an accurate treatment strategy and raising the survival rate, the differentiation of liver cancers is essential. Multiphase CT recently acts as the primary examination method for clinical diagnosis. Deep learning techniques based on multiphase CT have been proposed to distinguish hepatic cancers. However, due to the recurrent mechanism, RNN-based approaches require expensive calculations whereas CNN-based models fail to explicitly establish temporal correlations among phases. In this paper, we proposed a phase difference network, termed as Phase Difference Network (PDN), to identify two liver cancer, hepatocellular carcinoma and intrahepatic cholangiocarcinoma, from four-phase CT. Specifically, the phase difference was used as interphase temporal information in a differential attention module, which enhanced the feature representation. Additionally, utilizing a multihead self-attention module, a transformer-based classification module was employed to explore the long-term context and capture the temporal relation between phases. Clinical datasets are used in experiments to compare the performance of the proposed strategy versus conventional approaches. The results indicate that the proposed method outperforms the traditional deep learning based methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The 3D projection function on NetPad 15

The 3D projection function on NetPad

引用

15th International Conference on computer science and Education, ICCSE 2020

作者： Zhou, Qixin Li, Chuanzhong Cai, Ruiqi Li, Miaoxuan Zhang, Chuanjun Guan, Hao Guangzhou University Institute of Computing Science and Technology Guangzhou China Guangzhou University School of Computer Science and Cyber Engineering Guangzhou China Guizhou Education University School of Mathematics and Big Data Guiyang China Chinese Academy of Science Chengdu Institute of Computer Application Chengdu China

ISBN: (纸本)9781728172675

Projection of 3D geometric graphics is an introduction to solid geometry, which has indispensable functional requirements for 3D Dynamic Geometry Software. To optimize the 3D dynamic geometry software in the construction of projection steps and support more types of projected objects, this paper presents a method of construction of 3D projection. The key steps as follows: Firstly, discretize the projection object. Secondly, transform the set of the discrete point according to the projection type selected by the user. Thirdly, construct a new geometric object as the projection using the set of transformed point. The experimental results show that using the method can support the projection of various geometric objects, dynamically show the projection process, and reduce the construction burden of the user. © 2020 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Learning synergistic attention for light field salient object detection

arXiv

引用

arXiv 2021年

作者： Zhang, Yi Chen, Geng Chen, Qian Sun, YuJia Xia, Yong Deforges, Olivier Hamidouche, Wassim Zhang, Lu France National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University China School of Information Science and Technology University of Science and Technology of China China School of Computer Science Inner Mongolia University China

In this work, we propose Synergistic Attention Network (SA-Net) to address the light field salient object detection by establishing a synergistic effect between multi-modal features with advanced attention mechanisms. Our SA-Net exploits the rich information of focal stacks via 3D convolutional neural networks, decodes the high-level features of multi-modal light field data with two cascaded synergistic attention modules, and predicts the saliency map using an effective feature fusion module in a progressive manner. Extensive experiments on three widely-used benchmark datasets show that our SA-Net outperforms 28 state-of-the-art models, sufficiently demonstrating its effectiveness and superiority. Our code is available at https://***/PanoAsh/ SA-Net. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Charging Out Rectangle: Quadrangle IoU for Scene Text Detection under Balanced Supervision 25

Charging Out Rectangle: Quadrangle IoU for Scene Text Detect...

引用

Proceedings of the 4th International Conference on computer, Artificial Intelligence and Control engineering

作者： Min Ma Xiangnan Zhang Wang Bin Qiuli Wang Kexing Che School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing Jiangsu China Key Laboratory of Intelligent Information Processing Corporation Key Laboratory of Aperture Array and Space Application The 38th Research Institute of China Electronics Technology Group Hefei Anhui China Government and Enterprise Division China Unicom Shandong Branch Jinan Shandong China School of Electronic Engineering Xidian University Xi' an Shaanxi China

ISBN: (纸本)9798400712647

In the past few years, text detection approaches have been able to cope with more and more challenging complex scenes. In this field, the arbitrary shape and various scale of text instances are the two most frequently mentioned topics. Among the existing methods, the bounding box prediction methods based on Intersection over Union (IoU) are efficient, but can only handle multi-oriented rectangles. Although arbitrary shape text detection methods have been proposed, these methods are often aimed at curved text. Besides, the post-processing is usually cumbersome. Considering that the affine transformation phenomenon caused by out-plane rotation is more frequent than curved text in real scenario, we design a quadrangle IoU (QIoU) loss to efficiently predict arbitrary convex quadrangle text. Furthermore, we analyze the challenge of variable scale in text detection from the perspective of unbalanced supervision information, and propose a cross-scale knowledge distillation (CSKD) method to improve the detection accuracy of large-scale text. An extensive ablation study demonstrates the effectiveness and superiority of the proposed strategies. During inferring, our method does not consume extra time. Using the basic feature pyramid network for feature extraction, our method achieves state-of-the-art results on several popular datasets for scene text detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling Fine-Grained Relations in Dynamic Space-Time Graphs for Video-Based Facial Expression Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Huang, Changqin Jiang, Fan Han, Zhongmei Huang, Xiaodi Wang, Shijin Zhu, Yanlai Jiang, Yunliang Hu, Bin Zhejiang Normal University Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Jinhua321004 China Charles Sturt University School of Computing Mathematics and Engineering AlburyNSW2640 Australia State Key Laboratory of Cognitive Intelligence Anhui Hefei230088 China Hangzhou Hikvision Digital Technology Co. Ltd Education Business Department Hangzhou310051 China Zhejiang Normal University School of Computer Science and Technology Jinhua321004 China Beijing Institute of Technology School of Medical Technology Beijing10081 China

Facial expressions in videos inherently mirror the dynamic nature of real-world facial events. Consequently, facial expression recognition (FER) should employ a dynamic graph-based representation to effectively capture the relational structure of facial expressions rather than relying on conventional grid or sequence methods. However, existing graph-based approaches have their limitations. Frame-level graph methods provide a coarse representation of the facial graph across time and space, while landmark-based graph methods need to introduce additional facial landmarks, resulting in a static graph structure. To address these challenges, we propose spatial-temporal relation-aware dynamic graph convolutional networks (ST-RDGCN). This fine-grained relation modeling approach enables the dynamic modeling of evolving facial expressions in videos through dynamic space-time graphs, eliminating the need for facial landmarks. ST-RDGCN encompasses three graph construction paradigms: dynamic independent space graph, dynamic joint space-time graph, and dynamic cross space-time graph. Furthermore, we propose a relation-aware space-time graph convolution (RSTG-Conv) operator to learn informative spatiotemporal correlations in dynamic space-time graphs. In extensive experimental evaluations, our ST-RDGCN demonstrates state-of-the-art performance on the five popular video-based FER datasets, achieving overall accuracy scores of 99.69%, 91.67%, 56.51%, 69.37%, and 49.03% on the CK+, Oulu-CASIA, AFEW, DFEW, and FERV39 k datasets, respectively. In particular, our ST-RDGCN outperforms the current best method by 3.6% in UAR on the most challenging FERV39 k dataset. Furthermore, our analysis reveals that the dynamic cross space-time graph scheme is the most effective among the three dynamic graph construction schemes. © 2010-2012 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Bloch Equation Enables Physics-informed Neural Network in Parametric Magnetic Resonance Imaging

arXiv

引用

arXiv 2023年

作者： Cai, Qingrui Zhu, Liuhong Zhou, Jianjun Qian, Chen Guo, Di Qu, Xiaobo National Integrated Circuit Industry Education Integration Innovation Platform School of Electronic Science and Engineering National Model Microelectronics College Xiamen University Xiamen361102 China Fudan University Xiamen361015 China Department of Electronic Science Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361102 China School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China

Magnetic resonance imaging (MRI) is an important non-invasive imaging method in clinical diagnosis. Beyond the common image structures, parametric imaging can provide the intrinsic tissue property thus could be used in quantitative evaluation. The emerging deep learning approach provides fast and accurate parameter estimation but still encounters the lack of network interpretation and enough training data. Even with a large amount of training data, the mismatch between the training and target data may introduce errors. Here, we propose one way that solely relies on the target scanned data and does not need a pre-defined training database. We provide a proof-of-concept that embeds the physical rule of MRI, the Bloch equation, into the loss of physics-informed neural network (PINN). PINN enables learning the Bloch equation, estimating the T2 parameter, and generating a series of physically synthetic data. Experimental results are conducted on phantom and cardiac imaging to demonstrate its potential in quantitative MRI. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Research and process optimization on frostless heat source tower heat pump system based on compound enthalpy enhancement

引用

International Journal of Refrigeration 2025年 177卷 320-337页

作者： Lei Li Huafu Zhang Zhentao Zhang Fuqiang Qi Qiu Tu Hongwei Wu Junling Yang Xuelai Zhang Mingxin He State Key Laboratory of Cryogenic Science and Technology Technical Institute of Physics and Chemistry Chinese Academy of Sciences 100190 PR China Shanghai Maritime University Merchant Marine College Shanghai 201306 PR China Department of Building Environment and Energy Application Ningbo University of Technology Ningbo City 315211 PR China University of Hertfordshire School of Engineering and Computer Science Hatfield AL10 9AB United Kingdom Beijing Brigeniues Energy & Environment Tech CO LTD Beijing 10089 PR China

Due to the problems of high pollution, strong corrosion and high regenerative energy consumption in traditional heat source tower, a compound enthalpy enhancement heat source tower heat pump system using potassium formate solution as antifreeze and integrated mechanical vapor compression solution regeneration system is propose. Using Aspen Plus simulations, this work systematically investigates the impacts of six key parameters: air inlet temperature, relative humidity, airflow velocity, solution-air temperature differential, antifreeze concentration, and spray density on heating performance and energy efficiency. The results demonstrate 15-20% efficiency improvements under elevated ambient temperatures (>15°C) and high humidity conditions (>70% RH). Optimal operational ranges are established as 1.9-2.3 m/s airflow velocity and 14-18 m³/(m²·h) spray density with >5°C thermal differential. The main contributions include developing an environmentally sustainable antifreeze solution implementation framework and establishing practical engineering guidelines for parameter optimization in cold climate applications. These findings provide critical insights for enhancing heat pump system efficiency while reducing corrosion risks and regeneration energy consumption by approximately 25-30% compared to conventional systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Impact of Special Characters on Password Security: a Comparative Analysis

引用

IEEE Network 2025年

作者： He, Daojing Liu, Zhiyong Chan, Sammy Zhou, Beibei Guizani, Mohsen Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Guizhou University State Key Laboratory of Public Big Data Guizhou China Research and Development Center Guangzhou Jingyuan Security Technology Co. Ltd Guangzhou China City University of Hong Kong Kowloon Department of Electrical Engineering Hong Kong Hong Kong Shanghai Urban Construction Vocational College School of Artificial Intelligence Application Shanghai China Machine Learning Department Abu Dhabi United Arab Emirates

Text-based password authentication remains essential for identity verification on internet platforms and blockchain systems. However, as computational power advances, security threats to user passwords have intensified, raising concerns about their effectiveness. While special characters (i.e., non-alphanumeric symbols, which include punctuation marks, mathematical symbols, and other non-letter/number characters like '.', '@', '#', '$', and similar) are often recommended to enhance password strength, the National Institute of Standards and Technology (NIST) prioritizes length over complexity, challenging their necessity. This study fills a critical gap in understanding user behavior regarding special character usage. By analyzing 15 datasets from Chinese, English, and German languages, we examined patterns of special character incorporation and their impact on password strength. Our findings indicate that users frequently employ predictable methods for including special characters, potentially compromising security, especially under stringent policies. We present three key contributions: (1) an analysis of special character usage patterns, (2) a quantitative assessment of strength differences using the PCFGv4.1 model, and (3) actionable recommendations for stakeholders to enhance password security practices. This research further advocates for aligning password policies with user behavior for more effective security. © 1986-2012 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

A Multi-Task Based Deep Learning Framework for MRI Couinaud Segmentation

SSRN

引用

SSRN 2023年

作者： Miao, Dong Zhao, Ying Ren, Xue Dou, Meng Yao, Yu Xu, Yiran Cui, Yingchao Liu, Ailian Chengdu Institute of Computer Application Chinese Academy of Sciences Sichuan Chengdu610200 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Department of Radiology The First Affiliated Hospital of Dalian Medical University Liaoning Dalian116000 China Dalian Engineering Research Center for Artificial Intelligence in Medical Imaging Liaoning Dalian116000 China School of Medical Imaging Dalian Medical University Liaoning Dalian116044 China

Bacground and Objectibve: The delineation of the liver into Couinaud segments constitutes an essential aspect of preoperative planning in hepatic surgery, given its complexity and the significantBacground and Objectibve: The delineation of the liver into Couinaud segments constitutes an essential aspect of preoperative planning in hepatic surgery, given its complexity and the significant anatomical variations present. Accurate segmentation underpins the customization of operative techniques, critically influencing the minimization of postoperative complications and the preservation of liver ***: This research introduces a novel approach to automating this segmentation by identifying seven key landmarks within the liver anatomy using portal venous phase images of contrast enhanced magnetic resonance imaging (CE-MRI). Through a multi-task learning framework, we synchronized the detection of landmarks with the segmentation process, which led to an accurate and robust delineation of the Couinaud ***: To validate the capability of our model comprehensively, we included a test dataset with multiple patient types—those with normal liver, diffuse liver diseases, and localized liver lesions—under varied imaging conditions encompassing two field strengths, two devices, and two contrast agents. Our model achieved an average Dice Similarity Coefficient (DSC) of 85.29%, which is 3.12% higher than the other best-performing ***: In conclusion, our research presents a pioneering automated approach for segmenting the liver into Couinaud segments through CE-MRI, correlating landmark detection with segmentation to enhance surgical planning precision. This method promises improved clinical outcomes by accurately adapting to anatomical variability and reducing potential postoperative complications anatomical variations present. © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance 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：