检索结果-内蒙古大学图书馆

17th International Conference on intelligent Computing, ICIC 2021

作者： Niu, Tingting Zhang, Xiaolong Deng, Chunhua Chen, Ruoqin School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Institute of Big Data Science and Engineering Wuhan University of Science and Technology Wuhan China Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan China Tianyou Hospital Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9783030845285

Aiming at the problem of poor medical image recognition accuracy caused by the large individual differences in liver pathological images and the large single feature size, a liver image classification method based on dual-channel recalibration and feature fusion is proposed. Firstly, we construct a dual-channel recalibration model based on attention mechanism, suppress useless features and calculate different feature channel weights, and embed them into the Inception_ResNet_V2 network structure. Secondly, we design fully connected layers on the basis of two-dimensional and three-dimensional convolutional neural networks, then add feature fusion layers to obtain deep semantic information in different dimensions. Finally, we use pre-training models to initialize the network structure and input the fused features into the XGBoost classifier for classification prediction. Experiments have been carried out with liver cancer race imaging datasets and a hospital patient dataset. Experimental results show that this method is superior to previous ones. © 2021, Springer Nature Switzerland AG.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Low-Latency, Predictable, and High-Precision Networking for Cooperative Vehicle Infrastructure system

SSRN

引用

SSRN 2022年

作者： Lin, Chi Wu Yu, Chang Wang, Ning Institute of Intelligent System School of Software Dalian University of Technology Dalian China Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan Computer Science & Research Rowan University GlassboroNJ United States

Traditionally, infrastructural architects and road design have independently analyzed respective subsystems' needs in customary transportation. The two's inability to cooperate has culminated in possible safety issues, lousy road congestion, and unnecessary resource utilization. Moreover, challenges concerning sensor arrangement, data collecting, wireless communications, multi-source data fusion, analytical methodologies, and the development of decision-making processes might occur when cooperative vehicle infrastructure systems are used. In recent decades, Cooperative vehicle infrastructure systems(CVIS) have been suggested to assure intelligent transportation's effectiveness, effectiveness, and durability by integrating cars and infrastructures. A cooperative vehicle infrastructure system represents a novel business structure linked to businesses like autos, semiconductors, relevant information, and road infrastructure. Informatics, machine intelligence, telecommunications, data fusion, and intelligent monitoring are all included in this domain. Recent generations of networking technologies are pushing the boundaries of what became achievable utilizing cooperative vehicle infrastructure systems. Especially cooperative vehicle infrastructure systems, such instance, factory automation, Mixed Reality, and Touchscreen Network need ultra-low delay evaluated in single-digit milliseconds and cannot accept any fluctuation. Higher financial literacy requires an increased cloudification of application scenarios that require precise service level requirements for cooperative vehicle infrastructure systems. Almost all of those apps are mission-critical and therefore can risk perhaps a data packet being interrupted. Consequently, emerging applications need network infrastructure capable of delivering high-precision and predictable levels of service and accompanying assurances bordering on predictability. Cooperative vehicle infrastructure systems will require reassessing the f

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

MS-Glance: Bio-Inspired Non-Semantic Context Vectors and Their Applications in Supervising Image Reconstruction

MS-Glance: Bio-Inspired Non-Semantic Context Vectors and The...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Ziqi Gao Wendi Yang Yujia Li Lei Xing S. Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advance Research USTC Suzhou Jiangsu China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology China Department of Radiation Oncology Stanford University Stanford CA USA Key Laboratory of Precision and Intelligent Chemistry USTC CAS Hefei Anhui

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Non-semantic context information is crucial for visual recognition, as the human visual perception system first uses global statistics to process scenes rapidly before identifying specific objects. However, while semantic information is increasingly incorporated into computer vision tasks such as image reconstruction, non-semantic information, such as global spatial structures, is often overlooked. To bridge the gap, we propose a biologically informed non-semantic context descriptor, MS-Glance, along with the Glance Index Measure for comparing two images. A Global Glance vector is formulated by randomly retrieving pixels based on a perception-driven rule from an image to form a vector representing non-semantic global context, while a local Glance vector is a flattened local image window, mimicking a zoom in observation. The Glance Index is defined as the inner product of two standardized sets of Glance vectors. We evaluate the effectiveness of incorporating Glance supervision in two reconstruction tasks: image fitting with implicit neural representation (INR) and undersampled MRI reconstruction. Extensive experimental results show that MS-Glance outperforms existing image restoration losses across both natural and medical images. The code is available at https://***/Z7Gao/MSGlance.

关键词： Computer vision Visualization Magnetic resonance imaging Fitting Vectors Image restoration Indexes Image reconstruction Biomedical imaging Visual perception

来源：评论

学校读者我要写书评

暂无评论

Abnormal Traffic Detection of Industrial Edge Network Based on Deep Nature Learning 7th

Abnormal Traffic Detection of Industrial Edge Network Based ...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Liu, Qi Zhang, Bowen Zhao, Jianming Zang, Chuanzhi Wang, Xibo Li, Tong School of Information Science and Engineering Shenyang University of Technology Shenyang110870 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China State Grid Liaoning Electric Power Research Institute Shenyang110004 China

ISBN: (纸本)9783030786113

In view of the network and application security risks in the field of industrial Internet edge computing, a method for classifying abnormal traffic of industrial edge network based on Convolution Neural Network (CNN) is presented, which is designed by using feature self-learning through analyzing the substantial flow content and protocol hierarchy characteristics of edge network packets. Authors present an abnormal traffic detection model for industrial edge network based on CNN, by using the preprocessed raw traffic data as sample data to directly learn features. The experimental results show that the average accuracy of the trained and optimized model is 98.76%, which can meet the practical application standard of the industrial edge network anomaly traffic detection task. © 2021, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Robust Camera-LiDAR Fusion Framework for 3D Object Detection in High-Dust Environments

A Robust Camera-LiDAR Fusion Framework for 3D Object Detecti...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Mingyuan Wang Wentao Liu Bin Zhou Zhangyu Wang Runsen Liu Hanyu Wang Sate Key Lab of Intelligent Transportation System The Key Laboratory of Autonomous Transportation Technology for Special Vehickes Ministry of Industry and Information Technology School of Transportation Science and Engineering Beihang University Beijing China Technology and Development Center of Hefei Metro Research Institute Co. Ltd. Hefei Metro Research Institute Co. Ltd. Hefei China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

The fusion of camera and LiDAR features in the Bird's Eye View (BEV) perspective has become a prevalent solution for 3D detection in autonomous driving due to its simplicity and efficiency. However, in challenging environments like mining areas with dusty roads, existing BEV -based fusion networks struggle due to dust occlusion and misidentification of dust as obstacles. To address this, we propose a robust fusion framework that integrates fine-grained depth supervision and channel-wise attention mechanisms. Combined with a temporal multi-frame mechanism, our framework effectively mitigates issues caused by dust occlusion and misidentification. We validated our method's detection accuracy on a self-constructed mining road dataset, achieving 89.6% mAP, surpassing BEVFusion's 88.3% mAP. Tests on sensor occlusion and failure further demonstrated its robustness in adverse conditions typical of unstructured road scenarios.

关键词： Three-dimensional displays Attention mechanisms Laser radar Roads Channel estimation Object detection Feature extraction Robustness Informatics Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Novel Anomaly Detection Algorithm Based on OCSVM for Lower Limb Exoskeleton system

A Novel Anomaly Detection Algorithm Based on OCSVM for Lower...

引用

Chinese Control and Decision Conference, CCDC

作者： Li-Gang Liu Shi-Jie Wei Xu Zhong Jie Yao Bi Zhang Xin-Gang Zhao State Key Lab of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes of Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China College of Information Science and Engineering Northeastern University Shenyang China Handan Purificalion Equipment Research Institute Hebei Handan China School of Intelligent Medicine China Medical University Shenyang China

ISBN: (纸本)9781665478977

This paper presents a novel anomaly detection algorithm for lower limb exoskeleton system, which based on the gait characteristics of human walking on a Hat ground. This algorithm is suitable for lower limb exoskeleton system which can obtain the angles of hip, knee and ankle in real time. Previous studies have shown that the traditional balance evaluation methods such as zero moment point (ZMP), center of press (COP) and base of support (BOS) are difficult to solve and rely on accurate plantar pressure sensors. Therefore, through the analysis of the characteristics of human body stability, this paper uses the position relationship between the center line of feet (CLOF) and center of mass (COM) as the evaluation index of human body balance. To verify the correctness of this index, the forward, backward, left and right lateral abnormal data of human body are collected by inertial navigation, and the algorithm is used to train the anomaly classifier. Finally, through the test of normal sample and abnormal sample data, the classification accuracy is 99.821% and 99.297% respectively. In the next step, the algorithm will be used to control the balance recovery of the lower limb exoskeleton system.

关键词： Pressure sensors Presses Exoskeletons Stability criteria Inertial navigation Robot sensing systems Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A DFT+U study about agglomeration of Au atoms on reduced surface of rutile TiO2 (110)

引用

Materials Chemistry and Physics 2021年 271卷 124944-124944页

作者： Li, Lei Li, Wenshi Zhu, Canyan Mao, Ling-Feng Institute of Intelligent Structure and System & School of Electronics and Information Engineering Soochow University Suzhou215006 China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China

The sintering deactivates CO oxidation in a single Au catalyst. Understanding the mechanism of sintering at a reduced atmosphere seems important for improving sintering resistance. Here, we employ the first principle calculations to evaluate the barrier energy of Au atoms on reduced rutile TiO2 (110) surface and to demonstrate a favorable channel for their diffusion at an early stage in sintering. In the current DFT + U calculations, 16 structural configurations with oxygen vacancies and Au atoms are considered. This shows that Au atoms prefer to mobilize on fivefold-coordinated Ti (Ti5c) row rather than moving perpendicularly from this Ti5c row to a twofold-coordinated O (O2c) row. We regard a trap center involving a complex of Au‒oxygen vacancy on an O2c row as the initial nucleation site during sintering. It will capture the unstable Au atom on a Ti5c row, and hence, a highly stable Au dimer would be produced as the primary nucleation pattern. © 2021 Elsevier B.V.

关键词： Sintering

来源：评论

学校读者我要写书评

暂无评论

Application of Iterative Learning Control in X-Y Precision Planar Motion Platform

Application of Iterative Learning Control in X-Y Precision P...

引用

2021 China Automation Congress, CAC 2021

作者： Yan, Hongyu Jia, Danping Zhang, Tao Zhang, Hualiang Xiong, Yingjie Lu, Xu Liu, Yang School of Artificial Intelligence Shenyang University of Technology Shenyang China School of Information Science and Engineering Shenyang University of Technology Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China School of Electrica l Engineering Dalian University of Technology Dalian China College Of Information Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781665426473

The size of the tracking error is one of the important indicators to measure the control system of the X-Y Precision Planar Motion Platform. Iterative learning control (ILC) can obtain higher tracking accuracy through multiple iterations. However, it is found in experiments that the tracking error of the XY precision motion stage using ordinary PD-type iterative learning will eventually fluctuate in a relatively range, and some high-frequency Noise will seriously affect the stability of the system after many iterations. Aiming at the above problems, a PD-type variable gain open-closed loop ILC with a low-pass filter is proposed. This control scheme can effectively remove high-frequency noise and reduce tracking errors. Finally, a hardware-in-the-loop real-time simulator is used to conduct a comparative experiment. Through comparison with PID controller and ordinary PD-type ILC, the experimental consequence show that this arithmetic has a smaller tracking error than the other two algorithms. © 2021 IEEE

关键词： Low pass filters

来源：评论

学校读者我要写书评

暂无评论

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Jinan250353 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Jinan250014 China The Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Application of Graph-Curvature Features in Auxiliary Diagnosis for Histopathological Image Identification of Gastric Cancer

SSRN

引用

SSRN 2023年

作者： He, Ruilin Li, Chen Yang, Xinyi Yang, Jinzhu Jiang, Tao Grzegorzek, Marcin Sun, Hongzan Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Liaoning Shenyang China School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu China International Joint Institute of Robotics and Intelligent Systems Chengdu University of Information Technology Chengdu China Institute for Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland Shengjing Hospital of China Medical University Shenyang China School of Computer Science and Engineering

Background: Histopathology diagnosis is often regarded as the final diagnostic method for malignant tumors, but it has some drawbacks. This paper explores a computer-aided diagnostic method that can identify benign and malignant gastric cancer with histopathology images. Method: This article obtains the most suitable process through multiple experiments, compared multiple methods and features for classification. Firstly, the U-net is applied to segment the image. Next, the nucleus is extracted from the segmented image and the Minimum Spanning Tree (MST) diagram structure is drawn. The third step is to extract the graph-curvature features of histopathology image according to the MST image. Finally, by inputting graph-curvature features into the classifier, the recognition results for benign or malignant can be obtained. Result: During the experiment, we use various methods for comparison. In the image segmentation stage, U-net, watershed algorithm and Otsu threshold segmentation methods are used respectively. Combined with multiple indicators, we find that the U-net method is the most suitable for segmentation of histopathology images. In the feature extraction stage, in addition to extracting graph-edge feature and graph-curvature feature, several basic image features are also extracted, including Red, Green, Blue feature, Gray-Level Co-occurrence Matrix feature, Histogram of Oriented Gradient feature, and Local Binary Pattern feature. In the classifier design stage, we experimented with various methods, such as Support vector machine (SVM), Random forest, Artificial Neural Network, K Nearest Neighbors, VGG-16 and Inception-V3. Through the comparison and analysis, the classification results with an accuracy of 98.57% can be obtained by inputting the graph-curvature feature into SVM classifier. Conclusion: This paper has created a unique feature, graph-curvature feature based on MST to represent and analyze histopathology images. This graph-based feature can be used

关键词： Local binary pattern

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：