检索结果-内蒙古大学图书馆

International Conference on Big Data computing and Communications (BIGCOM)

作者： Xiaodong Wu Ronghai Wang Guoxin Lin School of Mathmatics and Computer Science Quanzhou Normal University Fujian Provincial Key Laboratory of Data-Intensive Computing Key Laboratory of Intelligent Computing and Information Processing Fujian Province University Fujian Provincial Big Data Research Institute of Intelligent Manufacturing Quanzhou China

Virtual Machine Consolidation (VMC) is an effective means to improve the resource utilization and reduce energy consumption of data centers. However, the VMC optimization that only considers energy consumption may lead to SLA (Service-Level Agreements) violations and thus fail to guarantee the QoS (Quality of Service) provided. Therefore, it is necessary to consider both energy saving and SLA violations in the process of VMC. In this paper, we propose an energy and SLA-aware VMC algorithm that considers both energy saving and SLA violation optimization in data centers. The proposed algorithm uses the local regression method to predict the utilization of virtual machines, based on which it determines whether the host will be overloaded, so as to make the decision of virtual machine migrations. The proposed VMC algorithm is evaluated with CloudSim toolkit. Simulation results demonstrate that our algorithm has good energy saving performance and can effectively reduce SLA violation in cloud data center. Considering energy consumption and SLA violation, the ESV can be reduced by 7.57% on average and 16.36% at most compared with other algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SELF-SUPERVISED DIFFUSION MRI DENOISING VIA ITERATIVE AND STABLE REFINEMENT

arXiv

引用

arXiv 2025年

作者： Wu, Chenxu Kong, Qingpeng Jiang, Zihang Kevin Zhou, S. School of Biomedical Engineering Division of Life Sciences and Medicine USTC China MIRACLE Center Suzhou Institute for Advance Research USTC China State Key Laboratory of Precision and Intelligent Chemistry USTC China Key Laboratory of Intelligent Information Processing of CAS Institute of Computing Technology CAS China

Magnetic Resonance Imaging (MRI), including diffusion MRI (dMRI), serves as a "microscope" for anatomical structures and routinely mitigates the influence of low signal-to-noise ratio scans by compromising temporal or spatial resolution. However, these compromises fail to meet clinical demands for both efficiency and precision. Consequently, denoising is a vital preprocessing step, particularly for dMRI, where clean data is unavailable. In this paper, we introduce Di-Fusion, a fully self-supervised denoising method that leverages the latter diffusion steps and an adaptive sampling process. Unlike previous approaches, our single-stage framework achieves efficient and stable training without extra noise model training and offers adaptive and controllable results in the sampling process. Our thorough experiments on real and simulated data demonstrate that Di-Fusion achieves state-of-the-art performance in microstructure modeling, tractography tracking, and other downstream tasks. Code is available at https://***/FouierL/Di-Fusion. Copyright © 2025, The Authors. All rights reserved.

关键词： signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Lifetime Prediction of Topcon Modules Based on Accelerated Damp Heat Life Tests

SSRN

引用

SSRN 2025年

作者： Ren, Xingang Duan, Junwei Yang, Lixia Xu, Tao Yu, Yuanjie Chen, Zhiliang Lv, Ruirui Ye, Feihong Wang, Gang Ahmed, Rida Jiang, Hao Yang, Lixia Huang, Zhixiang Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei230601 China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei230601 China CSI Cells Co. Ltd. Suzhou215129 China Anhui University of Chinese Medicine China Hong Kong Polytechnic University Hong Kong

Tunnel Oxide Passivation Contacts (TOPCon) solar cells have achieved high efficiency and become mainstream product in the global photovoltaic (PV) market. However, their long-term reliability, especially under high-temperature and high-humidity conditions, lacks sufficient field validation, and there is a lack of lifetime prediction models for TOPCon modules. To address this, we developed a robust accelerated aging model by integrating an improved Peck model with a sigmoidal degradation function, incorporating internal humidity and temperature as critical factors. The model employs a particle swarm optimization (PSO) algorithm to calibrate activation energy and humidity sensitivity parameters, enabling precise degradation trajectory simulation. Validated through a "fitting + testing" framework, the model achieves high accuracy (RMSE = 0.7%) in predicting power degradation under Damp Heat (DH), Highly Accelerated Stress Test (HAST), and modified Pressure Cooker Test (mPCT) conditions. Accelerated aging tests reveal that DH-induced degradation primarily reduces fill factor (FF) due to finger corrosion, with minimal impact on Voc and Isc. Experimental validation using a non-commercial corrosion-sensitive BOM combination shows that polyolefin elastomer (POE)-encapsulated modules exhibit superior corrosion resistance, projecting a service lifetime 23 years longer than EVA/EVA encapsulation in high-humidity regions like Hainan. This work bridges the gap in TOPCon module lifetime prediction under extreme environments, offering actionable insights for optimizing encapsulation materials and enhancing reliability. The model provides a scalable framework for evaluating module performance under site-specific climatic conditions, accelerating the development of durable PV technologies. © 2025, The Authors. All rights reserved.

关键词： Corrosion resistance

来源：评论

学校读者我要写书评

暂无评论

Deep Subdomain Alignment for Cross-domain Image Classification

Deep Subdomain Alignment for Cross-domain Image Classificati...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Yewei Zhao Hu Han Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China China University of the Chinese Academy of Sciences Beijing China

Unsupervised domain adaptation (UDA), which aims to transfer knowledge learned from a labeled source domain to an unlabeled target domain, is useful for various cross-domain image classification scenarios. A commonly used approach for UDA is to minimize the distribution differences between two domains, and subdomain alignment is found to be an effective method. However, most of the existing subdomain alignment methods are based on adversarial learning and focus on subdomain alignment procedures without considering the discriminability among individual subdomains, resulting in slow convergence and unsatisfactory adaptation results. To address these issues, we propose a novel deep subdomain alignment method for UDA in image classification, which consists of a Union Subdo-main Contrastive Learning (USCL) module and a Multi-view Subdomain Alignment (MvSA) strategy. USCL can create discriminative and dispersed subdomains by bringing samples from the same subdomain closer while pushing away samples from different subdomains. MvSA makes use of labeled source domain data and easy target domain data to perform target-to-source and target-to-target alignment. Experimental results on three image classifi-cation datasets (Office-31, Office-Home, Visda-17) demonstrate that our proposed method is effective for UDA and achieves promising results in several cross-domain image classification tasks. Our code will be available: https://***/zhaoyewei/DSACDIC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ptpfusion: A Progressive Infrared and Visible Image Fusion Network Based on Texture Preserving

SSRN

引用

SSRN 2024年

作者： Lu, Yixiang Zhang, Weijian Zhao, Dawei Qian, Yucheng Maksim, Davydau Gao, Qingwei The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China The Belarusian State University of Informatics and Radioelectronics Minsk Belarus State Grid Anhui Electric Power Research Institute China

Infrared and visible image fusion is to provide a more comprehensive image for downstream tasks by highlighting the main tar get and maintaining rich texture information. Image fusion methods based on deep learning suffer from insufficient multimodal information extraction and texture loss. In this paper, we propose a texture preserving progressive fusion network to extract comple mentary information from multimodal images (PTPFusion) to solve these issues. To reduce image texture loss, we design multiple consecutive texture-preserving blocks (TPB) to enhance fused texture. The TPB can enhance the features by using a parallel ar chitecture consisting with a residual block and a derivative operators. In addition, a novel cross-channel attention (CCA) fusion module is developed to obtain complementary information by modeling global feature interactions via cross-queries mechanism, followed by information fusion to highlight the feature of salient target. To avoid information loss, the extracted features at different stages are merged as the output of TPB. Finally, the fused image will be generated by the decoder. Extensive experiments on three datasets show that our proposed fusion algorithm is better than existing state-of-the-art methods. © 2024, The Authors. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Research on Data Augmentation for Garbage Classification with Target Detection Algorithm

Research on Data Augmentation for Garbage Classification wit...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Chen, Jiansong Zuo, Shikai Lin, Yun Tang, Kai Zou, Jianhang Feng, Naixing Cai, Yijun Xiamen University of Technology Smart Sensing Integrated Circuit Engineering Research Center of Universities in Fujian Province Xiamen361024 China Xiamen Wish Information Technology Co. Ltd Xiamen361006 China Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei China

ISBN: (纸本)9781665452366

Garbage classification is an essential work in daily life. With the development of artificial intelligence (AI), we have begun to use object detection to achieve garbage classification. However, the stacking and occlusion of garbage often make the detection performance unsatisfactory. In this paper, YOLOv5 algorithm is used for garbage detection and classification. YOLOv5 has three detection heads, which can detect objects at multiple scales. At the same time, Mosaic and Coarse Dropout image augmentation techniques are used to process our private data set of garbage, which improves the diversity of images. In this way, the target classification accuracy of the detection model can reach 75.7%, which is significantly improved compared with 69.9% without data augmentation. This paper provides a new technical support for the scene classification of stacked garbage based on deep learning. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Long-Short Term Policy for Visual Object Navigation

Long-Short Term Policy for Visual Object Navigation

引用

IEEE/RSJ International Conference on intelligent Robots and Systems (IROS)

作者： Yubing Bai Xinhang Song Weijie Li Sixian Zhang Shuqiang Jiang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (CAS) Beijing China University of Chinese Academy of Sciences Beijing China Institute of Intelligent Computing Technology CAS Suzhou

The goal of visual object navigation for an agent is to find the target objects accurately. Recent works mainly focus on the feature of embedding, attempting to learn better features with different variants, such as object distribution and graph representations. However, some typical navigation problems in complex environments, such as partially known and obstacle problems, may not be effectively addressed by previous feature embedding methods. In this paper, we propose a framework with a long-short objective policy, where the hidden states are classified according to the navigation objectives at that moment and separately rewarded. Specifically, we consider two objectives: the long-term objective is to go closer to the target, and the short-term objective is for obstacle avoidance and exploration. To alleviate the effect of long-term and short-term alternation, we build a state memory and propose an adjustment gate to update the state memory. Finally, all past hidden states are reweighted and combined for action prediction with an action-boosting gate. Experimental results on RoboTHOR show that the proposed method can significantly outperform the state-of-the-art.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fractional-Order Logarithmic Adaptive Filtering Algorithm Under $\alpha$-Stable Noise

A Fractional-Order Logarithmic Adaptive Filtering Algorithm ...

引用

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Dazhi Sun Canping Yu Li Li Yingsong Li Wudang Xiao Yong Chen Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China Aircraft Airworthiness Institute China Academy of Civil Aviation Science and Technology (Center of Aviation Safety Technology CAST) Beijing China

In practical applications, noise is more appropriately modelled as an a-stable random process than as a Gaussian process. To cope with a-stable noise, a fractional-order stochastic gradient descent (SGD) method is invented to adaptive filtering (AF) algorithms. When both input signal and noise follow α-stable random processes, the AF algorithms based on mean square error (MSE) criteria can be affected. Nevertheless, the fractional-order AF (FoAF) algorithm can effectively address this issue. For the purpose of better stability performance of the FoAF algorithm, different cost functions (CFs) are introduced into fractional-order SGD method. Based on the fractional-order derivative of a logarithmic CF (LCF), a fractional-order logarithmic adaptive filtering (FoLAF) algorithm is formed in this condition. Trials show that the FoLAF algorithm achieves faster convergence, excellent steady-state performance and superior tracking performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variable projection algorithms with sparse constraint for separable nonlinear models

引用

Control Theory and Technology 2024年第1期22卷 135-146页

作者： Hui-Lang Xu Guang-Yong Chen Si-Qing Cheng Min Gan Jing Chen College of Computer and Data Science Fuzhou UniversityFuzhou350116FujianChina Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhou350116FujianChina Key Laboratory of Intelligent Metro of Universities in Fujian Fuzhou UniversityFuzhou350116FujianChina Engineering Research Center of Big Data Intelligence Ministry of EducationFuzhou UniversityFuzhou350116FujianChina School of Science Jiangnan UniversityWuxi214122JiangsuChina

Separable nonlinear models are widely used in various fields such as time series analysis, system modeling, and machine learning, due to their flexible structures and ability to capture nonlinear behavior of data. However, identifying the parameters of these models is challenging, especially when sparse models with better interpretability are desired by practitioners. Previous theoretical and practical studies have shown that variable projection (VP) is an efficient method for identifying separable nonlinear models, but these are based on $L_2$ penalty of model parameters, which cannot be directly extended to deal with sparse constraint. Based on the exploration of the structural characteristics of separable models, this paper proposes gradient-based and trust-region-based variable projection algorithms, which mainly solve two key problems: how to eliminate linear parameters under sparse constraint;and how to deal with the coupling relationship between linear and nonlinear parameters in the model. Finally, numerical experiments on synthetic data and real time series data are conducted to verify the effectiveness of the proposed algorithms.

关键词： Variable projection(VP) Non-smooth constraint Separable nonlinear models

来源：评论

学校读者我要写书评

暂无评论

BRA-LADH: Bi-Level Routing Attention and Asymmetric Dual-Head Based Framework for Intestinal Polyp Detection

BRA-LADH: Bi-Level Routing Attention and Asymmetric Dual-Hea...

引用

Natural Language processing (ICNLP), International Conference on

作者： Xiaoying Pan Yaya Mu Sun Jia Han Chen Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an China School of Computing Xi'an University of Posts and Telecommunications Xi'an China

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

Colorectal cancer is a disease with a very high mortality rate, making timely diagnosis and prevention a crucial task. In clinical practice, the detection of intestinal polyps presents challenges due to their small size, complex background, and large span in target scale, making it difficult to accurately detect small targets. Existing detectors struggle to adaptively extract discriminative features, and their detection heads lack specificity, leading to difficulties in accurately identifying polyps against similar intestinal wall backgrounds. To address this issue, we propose a Bi-level Routing Attention and Asymmetric Dual-Head based framework for intestinal polyp detection(BRA-LADH). This approach enhances the detection capabilities of the branches through strategies such as global information fusion and adaptive sample selection. It dynamically sets thresholds for each target, ultimately solving the problems of missed and false detections caused by high similarity between the foreground and background and large variations in target scale, thus improving detection accuracy. Qualitative and quantitative experiments on three datasets demonstrate that this method outperforms existing ones, showing strong stability and generalization performance.

关键词： Training Head Prevention and mitigation Detectors Routing Feature extraction Stability analysis Magnetic heads Natural language processing Lesions

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：