检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Xinghong Gu, Mingxuan Tang, Jiankai Sang, Yungang Xiang, Bingrui Zhang, Kong Zhang, Guanjie Wang, Xingyuan Guo, Xuhan Zhou, Linjie Wu, Wengang Mao, Yifei School of Sensing Science and Engineering School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu314200 China Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China College of Mathematics and Physics Beijing University of Chemical Technology Beijing100029 China State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Key Lab of Navigation and Location Services Shanghai Institute for Advanced Communication and Data Science Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China National Key Laboratory of Science and Technology on Micro/Nano Fabrication School of Integrated Circuits Peking University Beijing100871 China Beijing Advanced Innovation Center for Integrated Circuits Beijing100871 China Frontiers Science Center for Nano-optoelectronics Peking University Beijing100871 China

The miniaturization and integration of beam steering devices have consistently been the focus of the field. Conventional methods alter the eigenmode of the optical cavity by regulating the refractive index. Due to the weak nonlinear effect of the optical system, the device must be sufficiently large to achieve sufficient light modulation. The effective method for miniaturizing beam steering devices currently in use is based on metasurfaces. However, this type of device necessitates the input of a laser source, which precludes the simultaneous generation and control of light in a single device. Here we propose a miniaturized beam steering device that employs mode selection between different bound states in the continuum (BIC) states through phase change material. The device is capable of simultaneously achieving both light generation and beam steering (33°) in a single device with a size of only 25 μm and with a low threshold of 8.9 kW cm-2. Furthermore, it is possible to achieve a significant degree of dynamic wavelength tunability, with a range extending up to 296 nm. This method achieves high-efficient regulation of light properties by dynamically controlling the system’s topological charge, circumventing the problem of weak nonlinearity in traditional methods. Furthermore, the integration of phase change materials with nanolasers enables the direct alteration of lasing properties, which provides a novel idea for dynamic light control. The device process scheme based on phase change materials is straightforward, direct, and highly compatible, which will be advantageous for its intended application. Copyright © 2024, The Authors. All rights reserved.

关键词： Phase change materials

来源：评论

学校读者我要写书评

暂无评论

A Robust Zero Watermarking Algorithm for Medical Images Based on Tetrolet-DCT 1

引用

12th International Symposium on Cyberspace Safety and Security, CSS 2020

作者： Cui, Wenfeng Liu, Jing Li, Jingbing Fang, Yangxiu Xiao, Xiliang Bhatti, Uzair Aslam Nawaz, Saqib Ali School of Information and Communication Engineering Hainan University Hainan Haikou China State Key Laboratory of Marine Resource Utilization in the South China Sea Hainan University Hainan Haikou China Research Center for Healthcare Data Science Zhejiang Lab Zhejiang Hangzhou China Nanjing Normal University Nanjing China

ISBN: (数字)9783030736712

ISBN: (纸本)9783030736705

The rapid development of the information age of big data has promoted the development of traditional medicine and online diagnosis, as well as aroused concerns about the privacy of patient information. Aiming at the hidden dangers of copying, cutting, tampering, etc. in the dissemination of medical images, combined with the characteristics of medical images, this paper proposed a novel zero-watermarking algorithm based on Tetrolet-DCT, focusing on how to improve its security. Logistic map chaotic encryption is performed on the watermark, the Tetrolet-DCT transform is used to extract the visual feature of medical image, and the watermark information is embedded and extracted by combining the zero-watermarking technology. Experimental data show that the algorithm proposed in this paper can effectively extract the watermark without any changing of the medical image, and has a higher NC value under conventional attacks and geometric attacks. it has better invisibility and robustness. © 2021, Springer Nature Switzerland AG.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Zero-Watermarking Algorithm for Medical Images Based on Gabor-DCT 1

引用

12th International Symposium on Cyberspace Safety and Security, CSS 2020

作者： Xiao, Xiliang Liu, Jing Li, Jingbing Fang, Yangxiu Zeng, Cheng Hu, Jiabin Bhatti, Uzair Aslam School of Information and Communication Engineering Hainan University Hainan Haikou China State Key Laboratory of Marine Resource Utilization in the South China Sea Hainan University Hainan Haikou China Research Center for Healthcare Data Science Zhejiang Lab Zhejiang Hangzhou China Nanjing Normal University Nanjing China

ISBN: (数字)9783030736712

ISBN: (纸本)9783030736705

The development of digital age accelerated the development of digital medical systems, but it also inevitably brings security problems of the transmission and storage of medical images in the network. The wide use of digital watermarking technology in medical images has effectively improved such problems, but the research on the medical image watermarking algorithm is still less and immature. How to improve the invisibility and robustness of watermark information is a difficult problem in the medical image watermarking algorithm. In this paper, a zero watermarking algorithm for medical images based on Gabor-DCT is proposed. The watermark information first encrypted by a Logistic chaotic map and then combined with the medical image feature vector extracted by the Gabor-DCT algorithm to improve the robustness of the watermark information. At last, the watermark is extracted and embedded by zero watermark technology, which improved the invisibility of the watermark information. Experimental results show the proposed algorithm can effectively resist both common attacks and geometric attacks, and has good invisibility and robustness. © 2021, Springer Nature Switzerland AG.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep Fusion of Shifted MLP and CNN for Medical Image Segmentation

Deep Fusion of Shifted MLP and CNN for Medical Image Segment...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chengyu Yuan Hao Xiong Guoqing Shangguan Hualei Shen Dong Liu Haojie Zhang Zhonghua Liu Kun Qian Bin Hu Björn W. Schuller Yoshiharu Yamamoto Shlomo Berkovsky College of Computer and Information Engineering Henan Normal University China Key Laboratory of Artificial Intelligence and Personalized Learning in Education Henan China Big Data Engineering Lab of Teaching Resources & Assessment of Education Quality Henan China Centre for Health Informatics Australian Institute of Health Innovation Macquarie University Australia Key Laboratory of Brain Health Intelligent Evaluation and Intervention (BIT) Ministry of Education China School of Medical Technology Beijing Institute of Technology China School of Information Engineering Zhejiang Ocean University China GLAM – Group on Language Audio & Music Imperial College London U.K. Chair of Embedded Intelligence for Health Care and Wellbeing University of Augsburg Germany Educational Physiology Laboratory Graduate School of Education The University of Tokyo Japan

Medical image segmentation is an important task in modern analysis of medical images. Current methods tend to extract either local features with convolutions or global features with Transformers. However, few of them are able to effectively fuse global and local features to facilitate segmentation. In this work, we propose a novel hybrid network that involves three main branches: the Multi-Layer Perception (MLP) branch, the Convolutional Neural Network (CNN) branch, and a Fusion branch. The MLP and CNN branches aim to learn global and local features, respectively. To fuse these, the fusion branch introduces a novel hierarchical fusion that performs multi-layered fusions that generate high-level representations to enhance segmentation. Our evaluation with two datasets shows strong performance of the proposed method compared to state-of-the-art baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Robust Digital Watermarking for Medical Images Based on PHTs-DCT 1

引用

12th International Symposium on Cyberspace Safety and Security, CSS 2020

作者： Yi, Dan Liu, Jing Li, Jingbing Zhou, Jingjun Bhatti, Uzair Aslam Fang, Yangxiu Nawaz, Saqib Ali College of Information and Communication Engineering Hainan University Hainan Haikou China State Key Laboratory of Marine Resource Utilization in the South China Sea Hainan University Hainan Haikou China Research Center for Healtcare Data Science Zhejiang Lab Zhejiang Hangzhou China Nanjing Normal University Nanjing China

ISBN: (数字)9783030736712

ISBN: (纸本)9783030736705

In recent years, digital watermarking technology has been widely used to solve the protection of privacy issues in medical images. However, the existing algorithms are failed to solve the protection problems against geometric attacks. To solve this problem, a robust digital watermarking algorithm for medical images based on PHTs-DCT is proposed in this paper. For embedding watermark, DCT is applied to reduce the redundant data of the image, then the coefficients are calculated via PHTs and the DCT to construct a binary feature sequence. Moreover, the watermark information is encrypted by Logistic mapping, and the zero watermark is constructed and stored in a third party medical image protection database. Extensive experiments have shown that the proposed algorithm has good robustness to geometric attacks and common attacks, especially anti-translation, rotation, and compression attacks. © 2021, Springer Nature Switzerland AG.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Mandari: Multi-Modal Temporal Knowledge Graph-aware Sub-graph Embedding for Next-POI Recommendation

Mandari: Multi-Modal Temporal Knowledge Graph-aware Sub-grap...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiaoqian Liu Xiuyun Li Yuan Cao Fan Zhang Xiongnan Jin Jinpeng Chen School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing China The Technology Innovation Center of Cultural Tourism Big Data of Hebei Province Chengde China Hebei Normal University for Nationalities Chengde China Knowledge Discovery and Data Mining Research Center Zhejiang Lab Hangzhou China

Next-POI recommendation aims to explore from user check-in sequence to predict the next possible location to be visited. Existing methods are often difficult to model the implicit association of multi-modal data with user choices. Moreover, traditional methods struggle to fully explore the variation of user preferences at variable time intervals. To tackle these limitations, we propose a Multi-Modal Temporal Knowledge Graph-aware Sub-graph Embedding approach (Mandari). We first construct a novel Multi-Modal Temporal Knowledge Graph. Based on the proposed knowledge graph, we integrate multi-modal information and leverage the graph attention network to calculate sub-graph prediction probability. Next, we implement a temporal knowledge mining method to model the segmentation and periodicity of user check-in and obtain temporal prediction probability. Finally, we fuse temporal prediction probability with the previous sub-graph prediction probability to obtain the final result. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid malware detection approach with feedback-directed machine learning

引用

Science China(Information Sciences) 2020年第3期63卷 240-242页

作者： Zhetao LI Wenlin LI Fuyuan LIN Yi SUN Min YANG Yuan ZHANG Zhibo WANG Hunan Provincial Key Lab of Internet of Things and Information Security Xiangtan University The College of Information Engineering Xiangtan University Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences School of Computer Science Fudan University Shanghai Institute of Intelligent Electronics & Systems Shanghai Institute for Advanced Communication and Data Science School of Cyber Science and Engineering Wuhan University

Dear editor,In recent years, the number of mobile malware has increased at an alarming rate. According to a report from G data [1], there are approximately 9000 new Android malware instances each *** malicious applica... 详细信息

关键词： Hybrid malware detection approach with feedback-directed machine learning

来源：评论

学校读者我要写书评

暂无评论

A Semi-Supervised Approach with Error Reflection for Echocardiography Segmentation

arXiv

引用

arXiv 2024年

作者： Han, Xiaoxiang Liu, Yiman Shang, Jiang Li, Qingli Chen, Jiangang Hu, Menghan Zhang, Qi Zhang, Yuqi Wang, Yan School of Communication and Information Engineering Shanghai University Shanghai China Lab Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China Department of Pediatric Cardiology Shanghai Children’s Medical Center School of Medicine Shanghai Jiao Tong University Shanghai China Shanghai China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China

Segmenting internal structure from echocardiography is essential for the diagnosis and treatment of various heart diseases. Semi-supervised learning shows its ability in alleviating annotations scarcity. While existing semi-supervised methods have been successful in image segmentation across various medical imaging modalities, few have attempted to design methods specifically addressing the challenges posed by the poor contrast, blurred edge details and noise of echocardiography. These characteristics pose challenges to the generation of high-quality pseudo-labels in semi-supervised segmentation based on Mean Teacher. Inspired by human reflection on erroneous practices, we devise an error reflection strategy for echocardiography semi-supervised segmentation architecture. The process triggers the model to reflect on inaccuracies in unlabeled image segmentation, thereby enhancing the robustness of pseudo-label generation. Specifically, the strategy is divided into two steps. The first step is called reconstruction reflection. The network is tasked with reconstructing authentic proxy images from the semantic masks of unlabeled images and their auxiliary sketches, while maximizing the structural similarity between the original inputs and the proxies. The second step is called guidance correction. Reconstruction error maps decouple unreliable segmentation regions. Then, reliable data that are more likely to occur near high-density areas are leveraged to guide the optimization of unreliable data potentially located around decision boundaries. Additionally, we introduce an effective data augmentation strategy, termed as multi-scale mixing up strategy, to minimize the empirical distribution gap between labeled and unlabeled images and perceive diverse scales of cardiac anatomical structures. Extensive experiments on a public echocardiography dataset CAMUS, and a private clinical echocardiography dataset demonstrate the competitiveness of the proposed method. Copyright © 202

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

SOLVING CONTINUAL OFFLINE RL THROUGH SELECTIVE WEIGHTS ACTIVATION ON ALIGNED SPACES

arXiv

引用

arXiv 2024年

作者： Hu, Jifeng Huang, Sili Shen, Li Yang, Zhejian Hu, Shengchao Tang, Shisong Chen, Hechang Chang, Yi Tao, Dacheng Sun, Lichao School of Artificial Intelligence Jilin University China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University China MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China Shenzhen International Graduate School Tsinghua University China College of Computing and Data Science Nanyang Technological University Singapore Computer Science and Engineering Lehigh University United States

Continual offline reinforcement learning (CORL) has shown impressive ability in diffusion-based lifelong learning systems by modeling the joint distributions of trajectories. However, most research only focuses on limited continual task settings where the tasks have the same observation and action space, which deviates from the realistic demands of training agents in various environments. In view of this, we propose Vector-Quantized Continual Diffuser, named VQ-CD, to break the barrier of different spaces between various tasks. Specifically, our method contains two complementary sections, where the quantization spaces alignment provides a unified basis for the selective weights activation. In the quantized spaces alignment, we leverage vector quantization to align the different state and action spaces of various tasks, facilitating continual training in the same space. Then, we propose to leverage a unified diffusion model attached by the inverse dynamic model to master all tasks by selectively activating different weights according to the task-related sparse masks. Finally, we conduct extensive experiments on 15 continual learning (CL) tasks, including conventional CL task settings (identical state and action spaces) and general CL task settings (various state and action spaces). Compared with 16 baselines, our method reaches the SOTA performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

Elastic-plastic time-history analysis of steel-tube stiff-frame arch bridge without inner filling concrete 3

Elastic-plastic time-history analysis of steel-tube stiff-fr...

引用

2020 3rd International Symposium on Traffic Transportation and Civil Architecture, ISTTCA 2020

作者： Zhang, Ben Li, Li Su, Wenming School of Civil Engineering Chongqing Jiaotong University Chongqing400074 China China Railway Bridge Science Research Institute Ltd. Wuhan430034 China State Key Laborary for Health and Safety of Bridge Structures Wuhan430034 China Shandong Hi-Speed Engineering Testing Co. Ltd Jinan250000 China Key Lab. for Bridge Struct. Big Data Perf. Diagn. and Treatm. Improvement of Transp. Industry Jinan250000 China

Based on a case study of a typical arch bridge with hollow steel tube and stiffness frame located in the high intensity region of western China, this paper adopts the onlinear time- history method to analyze the structural response of the overall bridge elastic-plastic model under seismic action. Under the force of Wolong wave in Wenchuan Earthquake, the main load-bearing members of the structure have a good seismic performance. Only part of the columns on the main arch ring enter the plastic hinge state for energy dissipation, and the lower columns have a more obvious energy dissipation effect than the higher ones. The result indicates that the design idea of structure which is similar to that of strong column and weak beam in ductility design, has the characteristics of "strong arch and weak beam"and can therefore improve the ability of structure to resist collapse under earthquake action. © Published under licence by IOP Publishing Ltd.

关键词： Energy dissipation

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：