检索结果-内蒙古大学图书馆

International Conference on networking and network Applications (NaNA)

作者： Hong Xia Jing Xu Qingyi Dong Hui Jia Yanping Chen Xi’an Key Laboratory of Big Data and Intelligent Computing Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an Shaanxi China

ISBN: (数字)9798350376777

ISBN: (纸本)9798350376784

In the Mobile Edge computing (MEC) environment, the prediction efficiency is low when user recommendation is based on Quality of Service (QoS) data due to network environment and other factors. Traditional methods use Collaborative Filtering (CF) or tensor decomposition methods to mine the relationship between historical QoS data for prediction, but there are problems with prediction accuracy and efficiency. Given this, this paper proposes an efficient QoS data prediction method (CTT) combining tensor kernel paradigm-tensor decomposition. The method first introduces the tensor kernel norm to approximate the tensor rank function to better capture the spatio-temporal correlation of real QoS data; Second, tensor decomposition is combined to address inefficiencies. Experimental results on the public QoS dataset WS-Dream show that the method significantly improves the runtime while guaranteeing prediction accuracy and applies to scenarios with different data missing densities.

关键词： Tensors Accuracy Runtime Multi-access edge computing Computational modeling Quality of service Predictive models

来源：评论

学校读者我要写书评

暂无评论

A Nonconformal SETI-DP Method for Transient Thermal Simulation

引用

IEEE Transactions on Components, Packaging and Manufacturing Technology 2025年

作者： Feng, Naixing Li, Hongyang Huang, Zhixiang Liu, Qi Qiang Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education The Information Materials and Intelligent Sensing Laboratory of Anhui Province The Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes Hefei China Hangzhou Dianzi University School of Electronics and Information Engineering Hangzhou310018 China

This paper proposes a novel nonconformal meshbased dual-primal spectral element tearing and interconnecting (SETI-DP) method designed for the efficient transient simulation of complex large-scale heat conduction problems utilizing a domain decomposition method (DDM). This method allows for the division of complex, large-scale problems into smaller subdomain problems. By applying Robin-type transmission conditions at the subdomain interfaces, rapid convergence of the global interface iterative solution is achieved for arbitrary non-conformal subdomain problems. This non-conformal DDM approach supports independent meshing of subdomains, eliminating the need to generate a globally continuous mesh for large-scale problems, thereby significantly enhancing meshing efficiency. In addition, this non-conformal meshing strategy enables high-contrast spatial discretization and mixed-order spectral interpolation between different subdomains. This significantly increases meshing flexibility, minimizes the number of degrees of freedom (DoF) in multi-scale problems, and reduces computational costs. In addition, by developing a subdomain-coupled time iteration scheme, the global corner problem of residual transfer is explicitly given, which greatly improves the versatility and flexibility of the algorithm. Finally, to demonstrate the accuracy, efficiency, and robustness of our algorithm, we conduct benchmark tests on several representative examples. © 2011-2012 IEEE.

关键词： Domain decomposition methods

来源：评论

学校读者我要写书评

暂无评论

A Method to Verify Internal Parameters of Camera Calibration in World Coordinate System 6

A Method to Verify Internal Parameters of Camera Calibration...

引用

6th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2023

作者： Xing, Zheng Wang, Qingchun Li, Yingsong Qi, Junwei College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Shanghai Yanding Information Technology Co. Ltd. Shanghai201210 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (纸本)9798350399059

Aiming at the problem that reprojection error (RE) cannot reflect the camera calibration accuracy intuitively, this paper proposes a method to verify the camera calibration results in world coordinate system. Firstly, the checkerboard calibration target is photographed with the camera under test, and the internal parameters and distortion parameters of the camera are calculated by using the pinhole model and the Kannala-Brandt (KB) fisheye model, respectively. Then, the same camera is used to shoot two targets in the field of view (FOV), and the pixel coordinates of the two target points are detected from the image. Thirdly, the inverse projection model is used to calculate the distance between the two objects and the angle between the camera and the two objects, and the real distance and angle are compared. The experimental results show that the average distance errors of the pinhole model and the KB fisheye model are 0.34% and 0.35%, respectively, and the angle errors are 0.40% and 0.12%, respectively, which proves that the verification method can effectively characterize the calibration accuracy of the camera. © 2023 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

3D Vision Transformer for Postoperative Recurrence Risk Prediction of Liver Cancer

3D Vision Transformer for Postoperative Recurrence Risk Pred...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2021

作者： Li, Fan Zhou, Xueying Gao, Xizhan Zhao, Hui Niu, Sijie School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing Jinan250022 China

ISBN: (纸本)9789811669620

Hepatocellular carcinoma (HCC) is a kind of malignant tumor with a high fatality rate, and it has a serious impact on the patient’s normal life. Although the diagnostic scheme for liver cancer has been gradually improved in recent years, the prognosis of patients with liver cancer is still not very ideal. Due to the high recurrence rate and poor prognosis after surgery, intrahepatic metastasis plays an important role in the survival cycle of patients with liver cancer, which is also a significant guiding factor in the selection of preoperative treatment and the planning of postoperative follow-up. In this paper, a classification method based on 3D Vision Transformer is proposed to determine whether intrahepatic metastasis occurs after the operation. Specifically, in this study, 161 patients who were diagnosed as HCC by puncture pathology or clinical diagnosis and received Transcatheter Arterial Chemoembolization (TACE) treatment were selected as the study subjects, and the patients were divided into non-metastasis group (79 cases) and intrahepatic metastasis group (82 cases). By comparing 3D Vision Transformer with the 3D forms of multiple deep learning classification models, the predictive value of 3D Vision Transformer in predicting intrahepatic metastasis after transarterial chemoembolization in HCC patients was verified. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

A dwell point detection algorithm for smart pen 2

A dwell point detection algorithm for smart pen

引用

2nd International Conference on Computer Graphics, Image and Virtualization, ICCGIV 2022

作者： Kong, DeHui University of Jinan School of Information Science and Engineering Jinan250022 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan250022 China

ISBN: (纸本)9781665492508

This paper presents a dwell point detection algorithm for smart pen. The main innovations of the method are: (a) The tracking of a smart pen is achieved by a common monocular camera. (b) A method of vertex adsorption is proposed. (c) The definition of a dwell point is introduced, and the auxiliary line intent is calculated by detecting the dwell point. Compared to the collision body detection method in Unity3D, the method in this paper improves the accuracy of doing auxiliary line intent and the smoothness of user operation. The effectiveness of the method is demonstrated by the use of the method in a smart pen interacting with a Unity3D-based three-dimensional geometry teaching system. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Survey of FPGA-Based Deep Learning Acceleration Research

A Survey of FPGA-Based Deep Learning Acceleration Research

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2021

作者： Lv, Ziyi Zhang, Jing School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing Jinan250022 China

ISBN: (纸本)9789811669620

In a range of fields such as emotion detection, medical image processing and speech recognition, deep learning has recently achieved good results. With the pursuit of more precise results, many scholars try to add more new type network layers to increase the size of the neural network. However, this will lead to deeper and more intricate network models, and training and evaluating models requires intensive CPU calculations and tremendous computing resources which cannot be achieved by general purpose processors. Nowadays, some hardware accelerators such as Field Programmable Gate Array (FPGA) have been employed to accelerate the neural network, and FPGA with reconfigurability and low power consumption are currently applied to improve throughput of deep learning networks at a reasonable price. In this paper, the typical technologies and methods of accelerating deep learning network on FPGA in recent years are reviewed and analyzed with their advantages and disadvantages, and feasible research suggestions for the next research direction are given. It is expected that it will have a certain reference value for researchers in the field of deep learning acceleration and hardware optimization. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Attention-Aware U-Net network for Segmentation of Retinopathy Region

Attention-Aware U-Net Network for Segmentation of Retinopath...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2021

作者： Kong, Wenyang Li, Fan Xing, Ruiwen Gao, Xizhan Zhao, Hui Su, Jie Niu, Sijie School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing Jinan250022 China

ISBN: (纸本)9789811669620

The important function of the computer-aided analysis platform for OCT (Optical Coherence Tomography) retinal images is image segmentation and the accuracy of the segmentation results affects the diagnosis of the disease area. In this paper, we improve the U-Net network by introducing attention mechanism and residual learning for segmenting retinal image lesions. Based on the original U-Net architecture, we embed the Squeeze-and-excitation module into the residual learning branch of the residual structure to replace the backbone network of U-Net. As a result, our improved method not only retains the advantages of fast convergence of network and Solve the problem of the weakening of the neural network's ability to extract features in the deep level, but also considers the correlation between attention learning channels, enhances useful features, and suppresses noise features. The data set used for training and testing of the method in this paper contains 2944 images from 23 patients diagnosed with ocular CSC (Central Serous Chorioretinopathy). We performed 4 sets of cross-validation on this dataset. According to experimental data, the method proposed in this paper can get better segmentation results. Compared with seven methods, our improved method can achieve competitive segmentation results, which is helpful for clinical disease diagnosis. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Multimodal intention understanding method based on NHMM 2

Multimodal intention understanding method based on NHMM

引用

2nd International Conference on Computer Graphics, Image and Virtualization, ICCGIV 2022

作者： Liu, Hao University of Jinan School of Information Science and Engineering Jinan250022 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan250022 China

ISBN: (纸本)9781665492508

This paper proposes a multimodal intention understanding method based on NHMM. Due to the declining expression ability of the elderly, single-mode input during human-computer interaction may reduce the accuracy of robot intention understanding and cannot meet the requirements of helping the elderly. Therefore, in the aspect of intention understanding, this paper uses multi-modal input of voice, gesture and posture to obtain the user's multi-dimensional information as much as possible. Each modal information is processed to obtain three intention sets, and then fused to obtain the fused intention set, By combining the improvement of the core formula of hidden Markov model (HMM) with Bayes, the intention with the highest probability in the fusion intention set is calculated as the result of intention understanding. The results show that the accuracy of this method is 97.7% in the state of user natural interaction, and compared with the other four intention understanding methods, this method is more effective for intention extraction under fuzzy input. © 2022 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Multiple Random Feature Superpixel-Based Fuzzy Clustering for Image Segmentation 9

Multiple Random Feature Superpixel-Based Fuzzy Clustering fo...

引用

9th International Conference on information, Cybernetics, and Computational Social Systems, ICCSS 2023

作者： Zhang, Chuanbin Chen, Long Tian, Yifei Shi, Zhaoyin Wang, Yingxu University of Macau Department of Computer and Information Science China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan China

ISBN: (纸本)9798350342239

Random feature maps attempt to approximate the kernel method with low computational complexity, and they are efficient and effective algorithms for dealing with the non-linear structure of data. Nevertheless, the existing random feature-based methods are sensitive to hyper-parameters, and their performances are affected by the randomness in feature maps. To improve the robustness of random feature maps and further speed up kernel-based image segmentation algorithms, a multiple random feature superpixel-based fuzzy clustering is proposed in this paper. First, we generate a group of random features from the original image via a novel multiple random feature scheme. Then, we use the superpixel segmentation to reduce the scale of multiple random features. The final segmentation results are obtained by performing the multi-view fuzzy clustering on the multiple random feature superpixels. Experiments on two shared benchmark data sets verify the superiority of our approach. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Non-Destructive Judgment of Watermelon Ripeness Based on Multi-Feature Fusion of Image

Non-Destructive Judgment of Watermelon Ripeness Based on Mul...

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Hongbao Shi Jun Liu Yimei Huang Jinping Li Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and Engineering University of Jinan Jinan China

ISBN: (数字)9798350356328

ISBN: (纸本)9798350356335

The nondestructive judgment of watermelon ripeness is a key issue in everyday life. Whether watermelons are ripe or not affects the interests of watermelon farmers and consumers. So far, acoustic, electrical, machine vision and other methods have been applied to the nondestructive judgment of agricultural product ripeness, but the equipment used in the lab, such as spectrometers and laser Doppler vibrometers, is expensive, difficult to carry, and has limited practical value in daily life. Based on practical experience, the ripeness of watermelons can be judged by observing specific physical characteristics, such as the rind's glossiness, texture, fuzz on the fruit stalk and navel. In this study, images of the watermelon's texture, fuzz and navel were captured using a smartphone. We utilized ResN et with an embedded Coordinate Attention mechanism and Swin-Transformer networks to independently analyze the ripeness of each feature. Then we combined the output prediction scores using post-fusion technology, with the highest weighted prediction score judging the final ripeness assessment. Our method achieved a 90.2% accuracy rate on the test set. The experiments demonstrate that a deep learning model utilizing multi-feature fusion of image data can reliably and accurately identify watermelon ripeness, even under varying image conditions.

关键词： Deep learning Laser theory Accuracy Vibrometers Machine vision Morphology Knowledge discovery Mobile handsets Reliability Guidelines

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：