检索结果-内蒙古大学图书馆

25th International conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2024

ISBN: (纸本)9789819642069

The proceedings contain 55 papers. The special focus in this conference is on Parallel and Distributed Computing: Applications and Technologies. The topics include: A Meta-reinforcement Learning Framework for Adaptive Quadrotor UAV Attitude Control;Securing Energy Transactions for Electric Vehicles: The Blockchain Approach and Encrypted NFTs;optimizing Task Allocation in Heterogeneous Agent Manufacturing Systems;MPG: Multi-modal Personal Health Graph for Alzheimer’s Disease Diagnosis;SMAC: A Secure Multi-authority Access Control Scheme with Attribute Unification for Fog Enabled IoT in E-Health;Convolutional Neural Networks Parameter Training for SCM Algorithm Based on Hausdorff Difference;handling Non-stationarity with Distribution Shifts and Data Dependency in Time Series Forecasting;the Two-Stage stochastic Facility Location Game;regularized Non-monotone γ-weakly Submodular Maximization;fed-MoE: Efficient Federated Learning for Mixture-of-Experts Models via Empirical Pruning;WaitIO-Hybrid: Communication for Coupling MPI Programs Among Heterogeneous Systems;the Material Delivery Route Prediction Method Based on Deep Reinforcement Learning;privacy-Preserving in Medical image Analysis: A Review of methods and Applications;research on Task Migration Problem Based on Link Uncertainty in Adversarial Scenarios;optimizing Production Component Scheduling in Multivariate Industrial Networks with Dynamic Changes in Production Costs;multi-agent Collaboration for Time-Sensitive Tasks in Multiple Networked Adversarial Scenarios;containerized Data-Flow processing for Scalable Real-Time Analytics on Edge Devices;fast Approximation for Scheduling Malleable Jobs on Parallel Batch Machines with Rejection;real-Time and In-Situ Temperature Profiling for Determining Detonation of White Dwarf Mergers;accparser: A Standalone OpenACC Parser and Its Usage on Mapping OpenACC to OpenMP Directives;Out-of-Memory GPU Sorting Using Asynchronous CUDA Streams;long-Term and Periodicity-Aware Spatio

关键词：

来源：评论

学校读者我要写书评

暂无评论

Matching the statistical query lower bound for k-sparse parity problems with sign stochastic Gradient descent 24

Matching the statistical query lower bound for k-sparse pari...

引用

Proceedings of the 38th International conference on Neural Information processing Systems

作者： Yiwen Kou Zixiang Chen Quanquan Gu Sham M. Kakade Department of Computer Science University of California Los Angeles Los Angeles CA Kempner Institute at Harvard University Harvard University Cambridge MA

ISBN: (纸本)9798331314385

The k-sparse parity problem is a classical problem in computational complexity and algorithmic theory, serving as a key benchmark for understanding computational classes. In this paper, we solve the k-sparse parity problem with sign stochastic gradient descent, a variant of stochastic gradient descent (SGD) on two-layer fully-connected neural networks. We demonstrate that this approach can efficiently solve the k-sparse parity problem on a d-dimensional hypercube (k ≤ O (√d)) with a sample complexity of Õ(dk-1) using 2Θ(k) neurons, matching the established Ω(dk) lower bounds of statistical Query (SQ) models. Our theoretical analysis begins by constructing a good neural network capable of correctly solving the k-parity problem. We then demonstrate how a trained neural network with sign SGD can effectively approximate this good network, solving the k-parity problem with small statistical errors. To the best of our knowledge, this is the first result that matches the SQ lower bound for solving k-sparse parity problem using gradient-based methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Down-sampling template curve to accelerate LDDMM-curve with application to shape analysis of the corpus callosum

引用

HEALTHCARE TECHNOLOGY LETTERS 2021年第3期8卷 78-83页

作者： Huang, Weikai Tang, Xiaoying Southern Univ Sci & Technol Dept Elect & Elect Engn Shenzhen Guangdong Peoples R China

Large deformation diffeomorphic metric mapping for curve (LDDMM-curve) has been widely used in deformation based statistical shape analysis of the mid-sagittal corpus callosum. A main limitation of LDDMM-curve is that it is time-consuming and computationally complex. In this study, down-sampling strategies for accelerating LDDMM-curve are investigated and tested on two large datasets, one on Alzheimer's disease (155 Alzheimer's disease, 325 mild cognitive impairment and 185 healthy controls) and the other on first-episode schizophrenia (92 first-episode schizophrenia and 106 healthy controls). For both datasets a variety of down-sampling factors are tested in terms of registration accuracy, registration speed, and most importantly disease-related patterns. Experimental results revealed that down-sampling template curve by a factor of 2 can significantly reduce the running time of LDDMM-curve without sacrificing the registration accuracy. Also, the disease-induced patterns, or more specifically the group comparison results, were almost identical before and after down-sampling. It is also shown that there was no need to down-sample the target population curves but only the single template curve of the study of interest. Comprehensive analyses were conducted.

关键词： down-sampling template curve statistical analysis image registration Patient diagnostic methods and instrumentation neurophysiology diseases brain Biology and medical computing Computer vision and image processing techniques Other topics in statistics biomedical MRI Optical, image and video signal processing 106 healthy controls cognition 155 Alzheimer's disease Biomedical magnetic resonance imaging and spectroscopy 185 healthy controls LDDMM-curve deformation based statistical shape analysis medical image processing medical disorders target population curves Probability theory, stochastic processes, and statistics Medical magnetic resonance imaging and spectroscopy single template curve

来源：评论

学校读者我要写书评

暂无评论

Risk Evaluation and Detection of Information Hidden in Video Container Formats

Risk Evaluation and Detection of Information Hidden in Video...

引用

image processing and Media Computing (ICIPMC), International conference on

作者： Baohong Ling Yinyin Peng Donghui Hu Anhui Broadcasting Movie And Television College Hefei China Hefei University of Technology Hefei China

ISBN: (数字)9798350386660

ISBN: (纸本)9798350386677

The diversity of video file formats and the redundant space that exists in digital video file formats lead to risks from information that may be hidden in video container formats. Previous works concerning video steganalysis have focused primarily on information hidden using techniques based on the data used to encode video but have neglected information-hiding techniques based on the video container file formats themselves. In this paper, we propose a method to evaluate the risk of information being hidden in video container formats. The method can return a recommended risk level for manual steganalysis or automatic steganalysis. We then further propose two types of steganalysis methods to detect the information hidden in video container formats, including statistical pattern-based steganalysis and machine learning-based steganalysis. A case study and implementation are given for statistical pattern-based detection and machine learning-based detection, using FLV and PS video container formats as examples. The results of experiments concerning risk evaluation and these methods are given to show the effectiveness of the proposed information-hiding risk evaluation and detection methods.

关键词： image processing Manuals Containers Media

来源：评论

学校读者我要写书评

暂无评论

Optimizing Fuzzy System of Fuzzy Time Series for Hyper Spectral image Classification

Optimizing Fuzzy System of Fuzzy Time Series for Hyper Spect...

引用

2024 International conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Nidhya, M.S. Naval, Preeti Kumar, Ravindra Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Mathematics Jaipur India

ISBN: (纸本)9798350383348

This research paper examines the capability of fuzzy time collection for hyperspectral photograph classification. Fuzzy time series (FTS) is a time series in which fuzzy standards are used to model the styles within the facts. FTS can be used to explain complex temporal styles in the records, and as a consequence making it possible to categorize photographs more extraordinarily accurately., this look proposes an optimization method primarily based on genetic seek techniques. The optimization algorithm is designed to discover the high-quality FTS parameters that yield first-rate type accuracy. The efficacy of the proposed technique is evaluated on hyperspectral facts set with extraordinary experimental scenarios. The results of the test display that the proposed method can enhance the accuracy of photo classification and the use of FTS considerably. Hence, the proposed method gives a promising technique that can be used to classify hyperspectral snapshots efficiently. The paper affords an optimized fuzzy machine of fuzzy time collection for the hyperspectral photograph category. The proposed device consists of 3 levels: pre-processing, version creation, and optimization. Throughout the pre-processing level, statistical and spectral analyses are executed to acquire the applicable attributes for developing the fuzzy time collection. The model construction degree then uses the bushy time series to extract between-class separability for the photo type. It is followed utilizing the optimization stage, related to the software of differential evolution, to minimize the complexity of the proposed machine while still enhancing the type accuracy. The proposed machine has been correctly carried out to a real-international hyperspectral dataset and demonstrates widespread upgrades in class accuracy over existing methods. © 2024 IEEE.

关键词： accurately extraordinarily hyperspectral photographs primarily

来源：评论

学校读者我要写书评

暂无评论

An efficient method for Blind image Restoration using GAN

An efficient method for Blind Image Restoration using GAN

引用

2022 International conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2022

作者： Sophia, S.G.Gino Umar, Syed Visvas, N. B.S. Abdur Rahman University Department of CSE Chennai India

ISBN: (数字)9781665474139

ISBN: (纸本)9781665474139

The purpose of this project is to convert blind (or blurred) images to well-defined images using various stages of image processing such as preprocessing, image enhancement, segmentation and image restoration. The previous method involved Convolutional Neural Network (CNN) which was unable to identify noisy data appropriately using statistical methods. The main idea behind the project is to give a correct estimation of the image from a degraded version. In the proposed system incorporating Generative Adversarial Networks (GANs) to enhance the image thus, leading to a well-defined image for further study and development. There are some instances where the blind face (or blurred images) cannot be enhanced with human help so face image restoration is proposed to enhance such images in order to get clear images. © 2022 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Learning statistical and Physical Modeling for Consistency Human Motion Prediction

Learning Statistical and Physical Modeling for Consistency H...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Xunliang Huang Wenlong Wang Haoyong Li Fuming Wang Cheng Peng Haoyuan Sun Guangzhou Institute of Technology Xidian University Guangzhou China School of Artificial Intelligence Xidian University Xi’an China Academy of Advanced Interdisciplinary Research Xidian University Xi’an China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Diffusion denoising models have great potential in generating diverse and realistic human motions. However, despite the impressive performance of existing methods, they still face some issues. The diffusion process often significantly overlooks physical laws, leading to physically implausible motions and a lack of consistency. Additionally, there are complexities involved in the training process. To address these limitations, inspired by Newton’s laws of motion, we propose a diffusion model—SPDiff that combines statistical modeling to fit the data with physical modeling to explore the true sources of motion. SPDiff introduces acceleration into the diffusion process using Taylor expansion, ensuring the plausibility of joint torques and motion velocities. By integrating statistical and physical modeling and employing cross-attention mechanisms to fuse their results, SPDiff creates an end-to-end human motion prediction diffusion model that achieves state-of-the-art performance.

关键词： Training Noise reduction Diffusion processes stochastic processes Predictive models Taylor series Data models Reliability Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

2022 8th International conference on Information Technology and Nanotechnology, ITNT 2022

2022 8th International Conference on Information Technology ...

引用

8th International conference on Information Technology and Nanotechnology, ITNT 2022

ISBN: (纸本)9781665485715

The proceedings contain 177 papers. The topics discussed include: depth maps correction based on neighboring frames;adaptive traffic signal control based on maximum weighted traffic flow;restoration of spatially inhomogeneous images based on doubly stochastic filters;image processing algorithms for self-driving cars navigation;joint usage of neural networks and stochastic referencing of images while estimating defects in bridge structures;comparison of traffic signal control algorithms in a large-scale traffic simulation environment;comparison of methods for reconstructing intermediate video frames with a dynamic scene;the impact of intermediate video frames reconstruction step on the result of 3D reconstruction of objects;the effect of the integration of spectral channels and seasonal satellite images on the distinctiveness of coniferous and deciduous forests;vehicle trajectory planning in the problem of traffic flow control at signalized intersections;and investigation of segmentation methods for highlighting areas of interests on lung x-rays.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assessment of the Current Local Transport Situation via Online processing of Monitoring Data and its Application for Traffic Regulation

Assessment of the Current Local Transport Situation via Onli...

引用

International conference on Management of Large-Scale System Development (MLSD)

作者： Anatoliy A. Solovyev Andrey M. Valuev Laboratory of Dynamics of Man-Machine Systems Mechanical Engineering Research Institute named after A.A.Blagonravov of RAS Moscow Russia

ISBN: (数字)9798350375718

ISBN: (纸本)9798350375725

A new approach to adaptive traffic light control at an intersection is being developed by using automatic control methods while constantly monitoring local traffic flow. methods of providing it with the necessary data, both characterizing the current local situation and statistical dependencies for the stochastic dynamics of traffic flows, are considered. methods for obtaining estimates of the values of monitored local traffic indicators are determined. The experience of computer modeling using the proposed method shows the expected reduction in traffic delays, as well as the possibility of choosing the most effective control method for a specific traffic situation.

关键词： Roads Urban areas stochastic processes Process control Organizations Traffic control Regulation Road traffic Large-scale systems Monitoring

来源：评论

学校读者我要写书评

暂无评论

Human Body Action Recognition based on 3D Feature Fusion over RGB Scenes 11

Human Body Action Recognition based on 3D Feature Fusion ove...

引用

11th International conference on Information Technology, ICIT 2023

作者： Nsour, Heba Mustafa, Zaid Al-Sendah, Maria Al-Balqa Applied University Dept. of Computer Science Albalqa Jordan Al-Balqa Applied University Dept. of Computer Information Systems Albalqa Jordan Kuwait

ISBN: (纸本)9798350320060

Human body action recognition (HBAR) is an important area of research in machine learning and image processing due to its vast range of applications. Similarly, estimating various components of human anatomy from RGB scenes are essential to human action tracking. The present study involves the implementation of human key body point detection for pose estimation. During abstracted silhouettes and vital human points, the proposed system has extracted two main features, such as 3D features and distance features. Once the relevant attributes have been incorporated, executing precise tasks and strategies is critical to achieving maximum features. Therefore, we used the t- SNE-based data refinement technique for optimal feature selection. Finally, for training, a classification model random forest is utilized. The presented system is verified on a recognized benchmark dataset, i.e., the UCF sports database. The experimental settings have revealed that our proposed system has attained better performance and outperformed other present state-of-the-art methods regarding mean recognition rate. © 2023 IEEE.

关键词： stochastic systems

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：