检索结果-内蒙古大学图书馆

Multi-scale network for single image deblurring based on ensemble learning module

Multimedia Tools and Applications 2025年第11期84卷 9045-9064页

作者： Wu, WenBo Pan, Yun Su, Na Wang, JingTao Wu, ShaoChuan Xu, ZeKun Yu, YouJian Liu, YaPeng State Key Laboratory of Media Convergence and Communication Communication University of China Beijing100024 China School of Computer and Cyberspace Security Communication University of China Beijing100024 China School of Electronics and Information Engineering Harbin Institute of Technology Harbin150080 China College of Computer and Control Engineering Northeast Forestry University Harbin150040 China School of Computer and Information Engineering Tianjin Chengjian University Tianjin300384 China School of Computer Science and Technology Anhui University Hefei230601 China

In this paper, we have identified two primary issues with current multi-scale image deblurring methods. On the one hand, the blurring scale is ignored. On the other hand, the context information of images is not fully utilized, and the spatial detail information of images is lost. To better solve the above problems, on top of that, this paper proposes a multi-scale network for single image deblurring. The designed network contains two parts: 1) Ensemble Learning Model: The Weak Learning Model in this module connects multiple weak learners in series to increase network depth. Moreover, through multi-scale feature ensemble module, the output features and intermediate features of different weak learner are integrated, and finally strong learner is used to enhance the features with semantic information at different scales;2) Spatial Feature Enhancement Module: This module can preserve spatial detail information of images and compensate for the disadvantages of losing image spatial details due to continuous downsampling in the Ensemble Learning Model structure. Our proposed deblurring model has been extensively evaluated on several benchmark datasets, and the model achieves superior performance compared to the most advanced deblurring methods. In particular, the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values are 33.57 dB and 0.965 on the GoPro dataset, respectively, with PSNR and SSIM improving by 0.49 dB and 0.002 over NAFNet, and 0.65 dB and 0.004 over Restormer. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Slicing Based Task Admission Scheduling Strategy in Multi-Access Edge Computing

引用

IEEE Internet of Things Journal 2025年第11期12卷 16067-16078页

作者： Liao, Zhuofan Tang, Yanpu Tang, XiaoYong Huang, Jiawei Changsha University of Science and Technology School of Computer and Communication Engineering Changsha410114 China Central South University School of Information Science and Engineering Changsha410083 China

The rise of Multi-access Edge Computing (MEC) speeds up mobile user services and resolves service delays caused by long-distance transmission to cloud servers. However, in task-intensive scenarios, edge server processing limitations lead to buffer congestion, increasing latency and reducing Quality of Service (QoS). Furthermore, the challenges of edge server task processing are increased by the varying deadline requirements of different tasks, the time variability of task arrivals, and the real-time fluctuations of the network. In this work, we propose an Adaptive Slicing based Task Admission scheduling strategy (ASTA) to address these issues. ASTA consists of an adaptive time slice adjustment algorithm (named ASTA-I) and a task admission scheduling algorithm (named ASTA-II). ASTA-I dynamically adjusts time slices based on real-time network conditions and task flow. ASTA-II first adjusts task priorities dynamically by considering factors such as data volume, deadlines, network conditions, and buffer locations. After that, ASTA-II formulates different scheduling strategies based on changes in task priorities. These strategies are formulated to improve the throughput efficiency of edge servers and enhance the average response speed of tasks. Simulation results show that compared with the existing O2A and OTDS in different scenarios, the proposed ASTA can reduce the average number of waiting requests in the edge server buffer by 19.53% 57.73% and 20.42% 50.26%, and accelerates the average response speed of tasks by about 39.76% and 32.41%. © 2014 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Breaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition

Breaking Through the Spike: Spike Window Decoding for Accele...

引用

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

作者： Zhang, Wei Zhang, Tian-Hao Luo, Chao Zhou, Hui Yang, Chao Qian, Xinyuan Yin, Xu-Cheng *** GROUP Shanghai China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9798350368741

Recently, end-to-end automatic speech recognition has become the mainstream approach in both industry and academia. To optimize system performance in specific scenarios, the Weighted Finite-State Transducer (WFST) is extensively used to integrate acoustic and language models, leveraging its capacity to implicitly fuse language models within static graphs, thereby ensuring robust recognition while also facilitating rapid error correction. However, WFST necessitates a frame-by-frame search of CTC posterior probabilities through autoregression, which significantly hampers inference speed. In this work, we thoroughly investigate the spike property of CTC outputs and further propose the conjecture that adjacent frames to non-blank spikes carry semantic information beneficial to the model. Building on this, we propose the Spike Window Decoding algorithm, which greatly improves the inference speed by making the number of frames decoded in WFST linearly related to the number of spiking frames in the CTC output, while guaranteeing the recognition performance. Our method achieves SOTA recognition accuracy with significantly accelerates decoding speed, proven across both AISHELL-1 and large-scale In-House datasets, establishing a pioneering approach for integrating CTC output with WFST. © 2025 IEEE.

关键词： automatic speech recognition spike window decoding wfst

来源：评论

学校读者我要写书评

暂无评论

M2PAIR: A High-Quality Acoustic Impulse Response Computation Model

M2PAIR: A High-Quality Acoustic Impulse Response Computation...

引用

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

作者： Li, Zhiyu Zhao, Xinpei Wang, Jing Qian, Xinyuan Xie, Xiang School of Information and Electronics Beijing Institute of Technology Beijing China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9798350368741

Acoustic Impulse Response (AIR) provides crucial spatial information about the environment, significantly enhancing audio immersion. However, achieving high perceptual quality while computing AIR in real-time for interactive audio-video media (IAVM) presents a challenging problem. This study proposes the Mesh to Parametric AIR (M2PAIR), a method for computing AIR designed for IAVM. M2PAIR integrates neural networks with psychoacoustics. It takes the 3D scene mesh, the listener positions, and the sound source positions as inputs, utilizes perceptual parameters as intermediaries, and computes the desired high-quality AIR signal based on these parameters. Experimental results demonstrate that M2PAIR improves the perceptual quality of AIR output compared to existing methods while reducing the model complexity. Additionally, it meets the requirements of IAVM, including real-time computation, high sampling rates, and flexible duration for the output AIR. © 2025 IEEE.

关键词： Acoustic Impulse Response Auralization Deep Learning Interactive Media Psychoacoustics

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Review: Advancing Cognitive Computingthrough Theory of Mind Integration and Deep Learning in Artificial Intelligence 24

Comprehensive Review: Advancing Cognitive Computingthrough T...

引用

8th International Conference on computer science and Application engineering, CSAE 2024

作者： Liu, Shuyan Wang, Kangsheng School of Information Science and Engineering Yunnan University Yunnan Kunming China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9798400718090

In this article, we will review our advances in intelligence modeling the mind and explore various efforts to mimic the processes that would allow humans to perform cognition files and line widgets of processing. It presents ideas and stresses how understanding cognitive functions is vital for AI progress. Three principal modeling strategies are examined: cognitive mind modeling, assignation mind modeling, and intelligent body mind modeling. In the article, he explores a few theories, such as symbol systems and the ACT-R framework. It further argues that learning seems limited in encoding models of the mind, citing its successes in language-oriented tasks and its limitations in translating basic mechanisms like reward to model-level language and data from neuroscience. Additionally, it investigates ways of assessing and enhancing learning theory of mind abilities based on tasks that utilize end-to-end function. The review reiterates the need for an improved understanding of human-level thought processing to develop intelligent systems that can better discern intentions and feelings. It provides some ideas on evaluating this based on deep learning approaches. The review argues that viewing learning through the lens of systems yields new insights into human thought and social behavior that could enable the development of novel and more adaptive AI technologies. © 2024 Copyright held by the owner/author(s).

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced rate capability and cycle stability of Ti2C MXene for sodium storage through an aniline molecules welding strategy

引用

Tungsten 2025年第1期7卷 161-171页

作者： Hao Chen Ya-Qin Wang Dong-Ting Zhang Bei Zhao Min-Peng Li Chen-Yang Li Tian-Peng Xu Mao-Cheng Liu State Key Laboratory of Advanced Processing and Recycling of Non-Ferrous Metals Lanzhou University of Technology School of Materials Science and Engineering Lanzhou University of Technology School of Computer and Communication Technology Lanzhou University of Technology

MXenes obtained significant attention in the field of energy storage devices due to their characteristic layered structure,modifiable surface functional groups,large electrochemically active surface,and regulable interlayer ***,the self-restacking and sluggish ions diffusion kinetics performance of MXenes during the alkali metal ions insertion/extraction process severely impedes their cycle stability and rate *** paper proposes an aniline molecule welding strategy for welding p-phenylenediamine（PPDA） into the interlayers of Ti2C through a dehydration condensation *** welded PPDA molecules can contribute pillar effect to the layered structure of *** pillar effect effectively maintains the structural stability during the sodium ions insertion/extraction process and effectively expands the interlayer spacing of Ti2C from 1.16 to 1.38 nm,thereby enhancing ions diffusion kinetics performance and improving the long-term cycle *** Ti2C-PPDA demonstrates outstanding Na+storage capability,exhibiting a specific capacity of 100.2 mAh·g-1at a current density of 0.1 A·g-1over 960 cycles and delivering a remarkable rate capability 81.2 mAh·g-1at a current density of 5 A·*** study demonstrates that expanding interlayer spacing is a promising strategy to enhance the Na+storage capacity and improve long-term cycling stability,which provides significant guidance for the design of two-dimensional Na+storage materials with high-rate capability and cycle stability.

关键词： Ti_2C Expanding interlayer spacing Sodium ions storage Diffusion kinetics Rate capability

来源：评论

学校读者我要写书评

暂无评论

MCDGMatch: Multilevel Consistency Based on Data-augmented Generalization for Remote Sensing Image Classification

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12470-12484页

作者： Liu, Pingping Liu, Xiaofeng Liu, Zetong Li, Haodong Zhou, Qiuzhan Jilin University School of Computer Science and Technology Changchun130012 China Jilin University School of Communication Engineering Changchun130012 China

The exponential growth of remote sensing image data and the high cost of manual annotation have led to insufficient labeled data, limiting classification performance. Semisupervised methods can address this issue, but most existing approaches lack multi-level consistency constraints in both embedding space and prediction probabilities, resulting in weak feature expressiveness. Additionally, the fine-grained characteristics of remote sensing images, amplified by data augmentation, are often overlooked, leading to overfitting and inaccurate decision boundaries. To address these issues, we propose a multi-level consistency solution that operates at both the embedding space and prediction probability levels. First, we refine the traditional data augmentation strategy and propose a mutual constraint loss function based on this refinement. Second, to address the intra-class variability of remote sensing images, we introduce a novel metric loss function to constrain the embedding space, taking into account both intra-sample consistency and intersample variability. Experimental results on three remote sensing image datasets demonstrate that our proposed method achieves significant performance e improvements compared to existing semi-supervised methods. © 2008-2012 IEEE.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Leakage Localization of Gas Pipelines Based on Modal Acoustic Emission and Cross-power Spectrum Peak Optimization

引用

IEEE Sensors Journal 2025年第11期25卷 19982-19992页

作者： Zhang, Wenbiao Gong, Kezheng Cui, Xiwang North China Electric Power University School of Control and Computer Engineering Beijing102206 China Beijing Information Science and Technology University School of Instrument Science and OptoElectronics Engineering Beijing100192 China

Leakage accidents in natural gas pipelines bring huge property losses and pose serious safety risks. Therefore, faster and more accurate leakage localization is of great significance. In this paper, a new method based on modal acoustic emission (MAE) and peak optimization of cross-power spectrum is proposed to enhance the performance of leakage localization. When a pipeline leakage occurs, the sensors installed on the pipelines receive the acoustic emission (AE) signals, which have various modes. Instead of extracting a single mode through complex algorithms, the proposed method directly extracts the cross-power spectrum of a specified mode by choosing the appropriate window function and window parameters to locate the leakage with velocity information from dispersion curves. Gaussian, Hamming and Blackman window functions are compared in the extraction of the cross-power spectrum of L(0,1) mode, among which the Blackman window function is found to be the most effective. The artificial fish swarm algorithm combined with the iteration criterion for peak optimization is used to obtain suitable window parameters. Finally, the localization error of the above method is less than 5.2%. In addition, the performance of the iteration criterion for peak optimization of cross-power spectrum combined with other intelligent swarm algorithms are investigated. The results show that the maximum errors of other intelligent methods are still less than 9%, demonstrating the great compatibility of the proposed method. © 2001-2012 IEEE.

关键词： Acoustic emissions

来源：评论

学校读者我要写书评

暂无评论

Joint Task Offloading and Resource Allocation Strategy for Space-Air-Ground Integrated Vehicular Networks

引用

清华大学学报自然科学版（英文版） 2025年第3期30卷 1027-1043页

作者： Yuanshuo Gang Yuexia Zhang Zhihai Zhuo School of Information and Communication Engineering Beijing Information Science and Technology UniversityBeijing 100101China Key Laboratory of Modern Measurement and Control Technology Ministry of EducationBeijing Information Science and Technology UniversityBeijing 100101China

Space-Air-Ground integrated Vehicular Network(SAGVN)aims to achieve ubiquitous connectivity and provide abundant computational resources to enhance the performance and efficiency of the vehicular ***,there are still challenges to overcome,including the scheduling of multilayered computational resources and the scarcity of spectrum *** address these problems,we propose a joint Task Offloading(TO)and Resource Allocation(RA)strategy in SAGVN(namely JTRSS).This strategy establishes an SAGVN model that incorporates air and space networks to expand the options for vehicular TO,and enhances the edge-computing resources of the system by deploying edge *** minimize the system average cost,we use the JTRSS algorithm to decompose the original problem into a number of subproblems.A maximum rate matching algorithm is used to address the channel allocation and the Lagrangian multiplier method is employed for computational *** acquire the optimal TO decision,a differential fusion cuckoo search algorithm is *** simulation results demonstrate the significant superiority of the JTRSS algorithm in optimizing the system average cost.

关键词： edge computing Resource Allocation(RA) Space-Air-Ground integrated Vehicular Network(SAGVN) Task Offloading(TO)

来源：评论

学校读者我要写书评

暂无评论

A Decoupling-Type Strategy for the Allen-Cahn Equation on Curved Surfaces

引用

Journal of Mathematical Research with Applications 2025年第1期45卷 73-83页

作者： Xiaoman XIE Qing PAN School of Computer and Communication Engineering Changsha University of Science & Technology

In this paper, we construct an efficient decoupling-type strategy for solving the Allen-Cahn equation on curved surfaces. It is based on an FEM-EIEQ(Finite Element Method and explicit-Invariant Energy Quadratization) fully discrete scheme with unconditional energy stability. Spatially the FEM is adopted, using a triangular mesh discretization strategy that can be adapted to complex regions. Temporally, the EIEQ approach is considered, which not only linearizes the nonlinear potential but also gives a new variable that we combine with the nonlocal splitting method to achieve the fully decoupled computation. The strategy can successfully transform the Allen-Cahn system into some completely independent algebraic equations and linear elliptic equations with constant coefficients, we only need to solve these simple equations at each time step. Moreover, we conducted some numerical experiments to demonstrate the effectiveness of the strategy.

关键词： FEM-EIEQ Allen-Cahn equation surface

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：