检索结果-内蒙古大学图书馆

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Tang, Xuan Zheng, Xiao Wang, Xiujun Huang, Jun Anhui University of Technology School of Computer Science and Technology Maanshan China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Maanshan China

ISBN: (纸本)9798350303636

As the Industrial Internet becomes an integral part of the steel industry, the next question is naturally how to combine powerful computing power as well as data sharing capabilities for effective detection of surface defects in strip steel. However, existing classification algorithms focus on the accuracy of the classification without considering how to protect the privacy of the manufacturer or the company, as the data is uploaded to the cloud and easily discovered by attackers. To address this problem, in this paper, we propose a privacy-preserving classification scheme that provides both privacy protection and improved classification accuracy in the industrial Internet. Specifically, our approach first adaptively encrypts the original steel image using a homomorphic encryption scheme. The homomorphic encryption scheme is followed by designing a convolutional neural network which can handle the encrypted images well and provide better classification accuracy. In addition, the execution efficiency of our method can be further improved under the edge computing architecture by using distributed computing with cloud-edge architecture. Experiments conducted on real image datasets of strip steel surface show that the encryption scheme not only protects the privacy of manufacturers or companies contained in the steel images and guarantees classification accuracy, but also outperforms existing methods in terms of efficiency. © 2023 IEEE.

关键词： Convolution neural network Defect category detection Edge computing Homomorphic encryption Privacy-preserving Strip steel

来源：评论

学校读者我要写书评

暂无评论

Social-Aware Group Display Configuration in VR Conference 38

Social-Aware Group Display Configuration in VR Conference

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Hsu, Bay-Yuan Shen, Chih-Ya Yuan, Hao Shan Lee, Wang-Chien Yang, De-Nian Department of Industrial Engineering and Engineering Management National Tsing Hua University China Department of Computer Science National Tsing Hua University China Institute of Information Systems and Applications National Tsing Hua University China Department of Computer Science and Engineering Pennsylvania State University United States Institute of Information Science Academia Sinica Taiwan Research Center of Information Technology Innovation Academia Sinica Taiwan

ISBN: (纸本)1577358872

Virtual Reality (VR) has emerged due to advancements in hardware and computer graphics. During the pandemic, conferences and exhibitions leveraging VR have gained attention. However, large-scale VR conferences, face a significant problem not yet studied in the literature - displaying too many irrelevant users on the screen which may negatively impact the user experience. To address this issue, we formulate a new research problem, Social-Aware VR Conference Group Display Configuration (SVGD). Accordingly, we design the Social Utility-Aware VR Conference Group Formation (SVC) algorithm, which is a 2-approximation algorithm to SVGD. SVC iteratively selects either the P-Configuration or S-Configuration based on their effective ratios. This ensures that in each iteration, SVC identifies and chooses the solution with the highest current effectiveness. Experiments on real metaverse datasets show that the proposed SVC outperforms 11 baselines by 75% in terms of solution quality. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

EDSep: An Effective Diffusion-Based Method for Speech Source Separation

EDSep: An Effective Diffusion-Based Method for Speech Source...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Dong, Jinwei Wang, Xinsheng Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China Audio Speech and Language Processing Group School of Computer Science Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350368741

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to speech separation has encountered challenges, notably slow convergence and suboptimal separation outcomes. To address these issues and enhance the efficacy of diffusion-based speech separation, we introduce EDSep, a novel single-channel method grounded in score matching via stochastic differential equation (SDE). This method enhances generative modeling for speech source separation by optimizing training and sampling efficiency. Specifically, a novel denoiser function is proposed to approximate data distributions, which obtains ideal denoiser outputs. Additionally, a stochastic sampler is carefully designed to resolve the reverse SDE during the sampling process, gradually separating speech from mixtures. Extensive experiments on databases such as WSJ0-2mix, LRS2-2mix, and VoxCeleb2-2mix demonstrate our proposed method's superior performance over existing diffusion and discriminative models, validating its efficacy. © 2025 IEEE.

关键词： diffusion score matching speech separation stochastic differential equation

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Classification and Diagnosis of Alzheimer's from Baseline MRI Scans

CNN-Based Classification and Diagnosis of Alzheimer's from B...

引用

iNnovative Informatics of Biskra (ISNIB), International Symposium on

作者： Manel Femmam Amel Saraoui Abdeljalil Naceri Maroua Grid Mohamed Elkabir Fareh Sami Slimani Computer Science Department Laboratory of Science for mathematics computer science and engineering applications University Center of Barika Barika Algeria Computer Science Department LINFI Laboratory Biskra University Biskra Algeria

ISBN: (数字)9798331509576

ISBN: (纸本)9798331509583

The diagnosis of neurodegenerative diseases like Alzheimer's remains a medical challenge, relying heavily on physicians' interpretation of symptoms. Early detection and man-agement are critical for improving patient outcomes, but there is a lack of automated tools to assist in decision-making. This project aims to address this gap a framework for detecting Alzheimer's disease from MRI scans. A convolutional neural network (CNN) is used in the proposed method to classify images into four categories: No Dementia (ND), Very Mild Dementia (VMD), Mild Dementia (MD), and Moderate Dementia (MOD). Leveraging the proven capabilities of CNNs in medical image classification, a tailored architecture was designed and implemented. The model delivered strong performance, demonstrating its potential for early detection of Alzheimer's. This system could be used in clinical settings to assist physicians in identifying cases of Alzheimer's disease and improving diagnostic efficiency.

关键词： Deep learning Magnetic resonance imaging Medical services Brain modeling Transformers Convolutional neural networks Alzheimer's disease Informatics Medical diagnostic imaging Overfitting

来源：评论

学校读者我要写书评

暂无评论

Analytical Study of the Features and Parameters of Off-Angle Iris Image vs. Deep Learning Model

Analytical Study of the Features and Parameters of Off-Angle...

引用

2024 International Conference on Decision Aid sciences and applications, DASA 2024

作者： Suleiman, Aghiad Khedr Shafek, Darin Mahfuri, Mahmoud Khishe, Mohammad Saeed, Ali Ghwanmeh, Sameh Alma'Moon University College Cybersecurity and Cloud Computing Technologies Engineering Dept. Baghdad Iraq Alma'Moon University College Computer Engineering Techniques Dept. Baghdad Iraq International University for Science and Technology Computer and Information Technology Department Syria Innovation Center for Artificial Intelligence Applications Yuan Ze University Taiwan Jadara Research Center Jadara University Jordan Jordan Computer Center Northern Technical University Ninevah Iraq College of Computer Information Technology Computer Science Dept American University in the Emirates United Arab Emirates

ISBN: (纸本)9798350369106

This paper presents an analytical study and a technique for extracting the features of a common case of images of the iris called off-angle iris which was taken for persons identification systems. The main problem when using biological iris measurements to identify the persons is the difficulty of identifying and extracting features of the iris. This problem is increasing when dealing with off-angle iris and it leads to decreased system accuracy and increased system rate error. In return, all the transfer learning techniques face difficulties in the case of heavily degraded data and partially occluded, and off-angle. A new method has a whole new methodology to deal with the image as it is without transformation processes. A new algorithm has been included for extracting features of the iris through the pupil switching points. The most discriminating points of the iris depend on the biological human eye statistics and analytical study. It has been trained and tested on the common images of the off-angle iris database so-called: 'CASIA Iris 1.0'. It has been implemented in the MATLAB environment. The results showed the efficiency of this technique, high precision and more importantly low failed acceptance rate. It emphasized that it is adaptive as well as efficiency improvement of the system. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Tensor MIMO Perfect-Equalizer Design Using New Projection-Based Method and Approximation-Error Analysis

引用

IEEE Systems Journal 2024年第1期18卷 668-679页

作者： Chang, Shih-Yu Wu, Hsiao-Chun Kao, Yi-Chih San Jose State University Department of Applied Data Science San JoseCA95192 United States Louisiana State University School of Electrical Engineering and Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center for Ai Applications Chungli32003 Taiwan National Yang Ming Chiao Tung University Network and System Division Information Technology Service Center Hsinchu30010 Taiwan

As real environments are quite complex, multiple-input-multiple-output (MIMO) channels should be characterized by the multidimensional-multirelational models. Tensor linear algebra has been emerging as a powerful and promising tool for such MIMO channel modeling and estimation. However, to the best of our knowledge, there hardly exists any algebraic framework of MIMO channel equalization when the channel is modeled as an arbitrary-dimensional transfer tensor (a tensor whose entries are all rational z-functions). In this work, we first propose a new method based on the projection, namely, 'projection-based method,' to determine whether a given transfer tensor is a full-rank tensor or not and carry out the inversion of an invertible transfer tensor. Our idea is employing the projection subspace of the system transfer tensor to simplify the pertinent inversion process. Second, we design the finite-impulse-response (FIR) realization to approximate the inverse of an arbitrary transfer tensor such that all entries of the approximated inverse transfer tensor are finite-degree polynomials of z. Third, we also analyze the computational and memory complexities required by our proposed new projection-based method for checking the full-rank condition of a given transfer tensor and for undertaking the tensor inversion. Our developed new theories and analysis in this work can be applied to determine the FIR model-orders of an approximated inverse MIMO transfer tensor often encountered in signal processing, control, communications, etc. © 2007-2012 IEEE.

关键词： FIR filters

来源：评论

学校读者我要写书评

暂无评论

Bipartite Consensus Control of Multi-agent Systems with Region-Dependent Intermittent Communication

Bipartite Consensus Control of Multi-agent Systems with Re...

引用

International Conference on Guidance, Navigation and Control, ICGNC 2024

作者： Wang, Ruotong Sun, Jian Zhang, Jianxin Ding, Xueyan Wang, Guangpeng Wu, Yanming School of Computer Science and Engineering Dalian Minzu University Dalian116000 China Research Center of Multimodal Information Perception and Intelligent Processing Dalian116000 China School of Automation Shenyang Aerospace University Shenyang110136 China

ISBN: (纸本)9789819622115

This article explores the consensus control of multi-agent systems, focusing on intermittent communication in dependent regions. Based on this, a novel region-dependent intermittent scheme is introduced, which employs system dynamics for its implementation on agents. The communication scheme divides a nonnegative real region into three subregions, and among them, the operation intervals and the nonoperating intervals represent the functions of the predefined sub-region and the error state, respectively. Based on the above scheme, a new region-dependent intermittent control protocol is designed, and the conditions are provided to prove the consensus. This region-dependent method can accept more nonoperating time than the existing time-dependent methods, and the simulation experiments are also carried out. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Consensus Intermittent Communication Multi-Agent Systems

来源：评论

学校读者我要写书评

暂无评论

Single-shot single-beam coherent Raman scattering thermometry based on optically induced air lasing

引用

Light(science & applications) 2024年第12期13卷 3253-3260页

作者： Xu Lu Yewei Chen Francesco Mazza Siyi He Zihan Li Shunlin Huang Quanjun Wang Ning Zhang Bo Shen Yuzhu Wu Jinping Yao Ya Cheng State Key Laboratory of High Field Laser Physics Shanghai Institute of Optics and Fine MechanicsChinese Academy of SciencesShanghai 201800China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China Faculty of Aerospace Engineering Delft University of TechnologyKluyverweg 12629 HS DelftThe Netherlands Institute of Modern Optics Nankai UniversityTianjin 300350China School of Microelectronics Shanghai UniversityShanghai 200444China

Thermometric techniques with high accuracy,fast response and ease of implementation are desirable for the study of dynamic combustion environments,transient reacting flows,and non-equilibrium ***,single-shot singlebeam coherent Raman scattering(SS-CRS)thermometry is developed,for the first time to our knowledge,by using air lasing as a *** show that the air-lasing-assisted CRS signal has a high signal-to-noise ratio enabling single-shot measurements at a 1 kHz repetition *** SS-CRS thermometry consistently exhibits precision of<2.3%at different temperatures,but the inaccuracy grows with the increase in *** high measurement repeatability,1 kHz acquisition rate and easy-to-implement single-beam scheme are achieved thanks to the unique temporal,spectral and spatial characteristics of air *** work opens a novel avenue for high-speed CRS thermometry,holding tremendous potential for fast diagnostics of transient reacting flows and plasmas.

关键词： scattering lasing beam

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Motion Intention Detection for Robotic Rehabilitation: Evaluating Classification and Regression Algorithms

引用

SN computer science 2024年第8期5卷 1057页

作者： Khan, Abdul Manan Khan, Fatima Dwivedi, Anshu Kumar Semwal, Vijay Bhaskar Martha, Sheshikala Bijalwan, Vishwanath Department of Aerospace Engineering University of Bristol Bristol United Kingdom Graduate School of Cancer Science and Policy National Cancer Center Ilsan South Korea School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of CSE Maulana Azad National Institute of Technology Bhopal India School of Computer Science & amp Artificial Intelligence SR University Warangal Warangal India Department of Electrical and Electronics Engineering University of West London London United Kingdom

Rehabilitation robots have shown significant efficacy in restoring lost motor functions in stroke survivors by providing compliant assistance during rehabilitation tasks. However, accurately understanding the desired motion intention (DMI) of the subjects is a significant challenge in providing effective robotic assistance. This work aims to determine the desired motion intention (DMI) for compliant robotic assistance through the analysis of upper limb motions using electroencephalography (EEG) signals. A group of fifteen individuals who were in good health carried out six distinct exercises. These movements were categorized using decision trees, random forest, and deep learning algorithms. Using deep learning, we achieved the highest accuracy rates, reaching 82% for movement-to-movement classification and 90% for movement-to-rest classification. The random forest method achieved superior performance compared to the other algorithms in regression tests, with an accuracy rate of 83%. The results demonstrate the effectiveness of our proposed EEG-based classification and regression techniques in detecting DMI for robotic help in *** study was conducted with a small sample size, exclusively involving healthy subjects, which is a critical factor to consider. This may limit the generalizability of the results, particularly when populations with motor impairments are taken into account. However, the study offers valuable insights into the potential of the EEG-based models for real-time rehabilitation applications despite this limitation. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： C-RNN Deep learning Desired motion intention EEG signals Machine learning Rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Offline Handwritten Signature Analysis for Age Classification using Deep Features 4

Offline Handwritten Signature Analysis for Age Classificatio...

引用

4th International Conference for Emerging Technology, INCET 2023

作者： Kumar, Sathish Gornale, Shivanand Patil, Abhijit Rashmi, S. Rani Channamma University Department of Computer Science Belagavi India Gulbarga University PG Center Halhalli Department of Computer Science Line 3 Kalaburagi India West Virginia University Department of Mechanical and Aerospace Engineering MorgantownWV United States

ISBN: (纸本)9798350335750

Handwritten Signatures are prominent and convincing behavioral biometric data, used in many authentication application areas such as commercial, financial data, document analysis, health care, and forensic science etc. Different writing styles, cursive characters, and inconsistency in the shapes make it tougher to identify the writer from a handwritten signature. This problem remains still a challenging task, because of the considerable intra-class variations in handwriting. The proposed work focuses on the classification of the age using the different handwritten signatures collected from male and female writers of different age groups (adolescents (18-60)). In-house of total 6010 signatures were collected from 610 individuals. Experiments were carried out using well known deep neural architecture namely VGG16 model. Classification task carried out in end-to-end framework. The proposed work achieves comparatively better results than the existing methods respectively. © 2023 IEEE.

关键词： Classification (of information)

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：