检索结果-内蒙古大学图书馆

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Ye, Feiyang Lin, Baijiong Cao, Xiaofeng Zhang, Yu Tsang, Ivor W. Department of Computer Science and Engineering Southern University of Science and Technology China Australian Artificial Intelligence Institute University of Technology Sydney Australia The Hong Kong University of Science and Technology Guangzhou China School of Artificial Intelligence Jilin University China Shanghai Artificial Intelligence Laboratory China Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9781643685489

In this paper, we study the Multi-Objective Bi-Level Optimization (MOBLO) problem, where the upper-level subproblem is a multi-objective optimization problem and the lower-level subproblem is for scalar optimization. Existing gradient-based MOBLO algorithms need to compute the Hessian matrix, causing the computational inefficient problem. To address this, we propose an efficient first-order multi-gradient method for MOBLO, called FORUM. Specifically, we reformulate MOBLO problems as a constrained multi-objective optimization (MOO) problem via the value-function approach. Then we propose a novel multi-gradient aggregation method to solve the challenging constrained MOO problem. Theoretically, we provide the complexity analysis to show the efficiency of the proposed method and a non-asymptotic convergence result. Empirically, extensive experiments demonstrate the effectiveness and efficiency of the proposed FORUM method in different learning problems. In particular, it achieves state-of-the-art performance on three multi-task learning benchmark datasets. © 2024 The Authors.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Combined Effect of Concept Drift and Class Imbalance on Model performance During Stream Classification

引用

computers, Materials & Continua 2023年第4期75卷 1827-1845页

作者： Abdul Sattar Palli Jafreezal Jaafar Manzoor Ahmed Hashmani Heitor Murilo Gomes Aeshah Alsughayyir Abdul Rehman Gilal Department of Computer and Information Sciences Universiti Teknologi PETRONAS(UTP)Seri Iskandar32610Malaysia Centre for Research in Data Science UTPPerak32610Malaysia High Performance Cloud Computing Centre(HPC3) UTPPerak32610Malaysia School of Engineering and Computer Science Victoria University of WellingtonWellington6012New Zealand AI Institute University of Waikato WellingtonHamilton3240New Zealand Anti-Narcotics Force Ministry of Narcotics ControlIslamabad46000Pakistan College of Computer Science and Engineering Taibah UniversityMadinah42353Saudi Arabia

Every application in a smart city environment like the smart grid,health monitoring, security, and surveillance generates non-stationary datastreams. Due to such nature, the statistical properties of data changes overtime, leading to class imbalance and concept drift issues. Both these issuescause model performance degradation. Most of the current work has beenfocused on developing an ensemble strategy by training a new classifier on thelatest data to resolve the issue. These techniques suffer while training the newclassifier if the data is imbalanced. Also, the class imbalance ratio may changegreatly from one input stream to another, making the problem more *** existing solutions proposed for addressing the combined issue of classimbalance and concept drift are lacking in understating of correlation of oneproblem with the other. This work studies the association between conceptdrift and class imbalance ratio and then demonstrates how changes in classimbalance ratio along with concept drift affect the classifier’s *** analyzed the effect of both the issues on minority and majority classesindividually. To do this, we conducted experiments on benchmark datasetsusing state-of-the-art classifiers especially designed for data stream ***, recall, F1 score, and geometric mean were used to measure theperformance. Our findings show that when both class imbalance and conceptdrift problems occur together the performance can decrease up to 15%. Ourresults also show that the increase in the imbalance ratio can cause a 10% to15% decrease in the precision scores of both minority and majority *** study findings may help in designing intelligent and adaptive solutionsthat can cope with the challenges of non-stationary data streams like conceptdrift and class imbalance.

关键词： Classification data streams class imbalance concept drift class imbalance ratio

来源：评论

学校读者我要写书评

暂无评论

Complex Permeability Determination for EE Core Based on Flexible PCB Fixture and Magnetic Flux Path Length Analysis 2

Complex Permeability Determination for EE Core Based on Flex...

引用

2nd China Power Supply Society Electromagnetic Compatibility Conference, CPEMC 2024

作者： Jie, Huamin Zhao, Zhenyu Chang, Yongqi Wang, Changdong Jiang, Shiqi Gao, Richard Xian-Ke See, Kye Yak School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Department of Electrical and Computer Engineering National Univeristy of Singapore Singapore Singapore Department of Control Science and Engineering Harbin Institute of Technology Harbin China School of Electronics and Information Engineering Harbin Institute of Technology Harbin China School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China Institute of High Performance Computing A*STAR Singapore Singapore

ISBN: (纸本)9798331509552

The complex permeability of magnetic cores acts as a vital factor in electromagnetic interference (EMI) filtering choke design and optimization. Many efforts have been reported for toroid cores, but fewer target those with other shapes, such as EE, EI, UU, and UI cores. Owing to their commonly used in planar EMI filters, determining the complex permeability of them is of significance. Targeting EE cores, this paper presents a flexible printed circuit board (PCB)-based fixture adapter tailored designed for performing the measurement, while the corresponding core permeability can be calculated through magnetic flux path length analysis. The experiments validate the effectiveness and accuracy of the proposed methods, spanning a wide frequency range up to 120 MHz. ©2024 IEEE.

关键词： Magnetic flux

来源：评论

学校读者我要写书评

暂无评论

An Investigation into Power Aware Aspects of Rendering 3D Models on Multi-Core Processors

An Investigation into Power Aware Aspects of Rendering 3D Mo...

引用

2022 International Conference on Machine Learning and Data engineering, ICMLDE 2022

作者： Konnurmath, Guruprasad Chickerur, Satyadhyan School of Computer Science and Engineering KLE Technological University Hubballi580031 India Centre for High Performance Computing K L e Technological University Hubballi580031 India

Graphics Processing Units (GPUs) are designed to process numerically intensive applications and specially customized with additional computational power to achieve efficient rendering of 3D applications. Shaders are basically the computer programs that run on graphics rendering pipeline and inform about how to process and render each pixel, to perform efficient rendering of 3D applications. Shaders included in our Geometric complexity, texture resolution, per-pixel lighting. These shaders expose GPUs to suffer more power utilization during rendering process. In this paper, initially GPU power usage is investigated at run-time for rendering configuration to define shader parameters on a 3D scene and then power prediction model is proposed at different shader calls on GPU to generate power-aware dynamically reconfigurable rendering model. In the implementation process we integrate the TensorFlow management library routines and dynamic voltage and frequency scheduling (DVFS) mechanism to improve efficiency in rendering process and reach optimal power savings. To analyze the power efficiency of GPUs, shader parameters such as geometric complexity, texture resolution, per-pixel lighting, filtering that expose more towards power consumption are experimented with common GPU workloads during rendering process, then frequency and voltage is altered based on the framerate monitoring. Also in addition to this the frame rate is monitored and maintained in such a way that GPU frequency is adjusted in parallel if the framerate is within the acceptable range so that unnecessary power usage is reduced. During the experimental tests a lower limit of 30 frames per second and upper limit of 60 frames per second is configured. The GPU frequency is reduced if the existing framerate is greater than upper configured limit and frequency range is increased if framerate is below the configured lower limit. Compared with the previous state of art, results show power savings around 40% and imp

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Resfusion: denoising diffusion probabilistic models for image restoration based on prior residual noise 24

Resfusion: denoising diffusion probabilistic models for imag...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhenning Shi Haoshuai Zheng Chen Xu Changsheng Dong Bin Pan Xueshuo Xie Along He Tao Li Huazhu Fu College of Computer Science Nankai University School of Statistics and Data Science Nankai University Haihe Lab of ITAI College of Computer Science Nankai University and Haihe Lab of ITAI Institute of High Performance Computing A*STAR

ISBN: (纸本)9798331314385

Recently, research on denoising diffusion models has expanded its application to the field of image restoration. Traditional diffusion-based image restoration methods utilize degraded images as conditional input to effectively guide the reverse generation process, without modifying the original denoising diffusion process. However, since the degraded images already include low-frequency information, starting from Gaussian white noise will result in increased sampling steps. We propose Resfusion, a general framework that incorporates the residual term into the diffusion forward process, starting the reverse process directly from the noisy degraded images. The form of our inference process is consistent with the DDPM. We introduced a weighted residual noise, named resnoise, as the prediction target and explicitly provide the quantitative relationship between the residual term and the noise term in resnoise. By leveraging a smooth equivalence transformation, Resfusion determine the optimal acceleration step and maintains the integrity of existing noise schedules, unifying the training and inference processes. The experimental results demonstrate that Resfusion exhibits competitive performance on ISTD dataset, LOL dataset and Raindrop dataset with only five sampling steps. Furthermore, Resfusion can be easily applied to image generation and emerges with strong versatility. Our code and model are available at https://***/nkicsl/Resfusion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Alleviating data insufficiency for Chinese sign language recognition

引用

Visual Intelligence 2023年第1期1卷 1-9页

作者： Xue, Wanli Liu, Jingze Yan, Siyi Zhou, Yuxi Yuan, Tiantian Guo, Qing School of Computer Science and Engineering Tianjin University of Technology Tianjin China Technical College for the Deaf Tianjin University of Technology Tianjin China Institute of High Performance Computing (IHPC) Agency for Science Technology and Research (A*STAR) Singapore Singapore Singapore Centre for Frontier AI Research (CFAR) Agency for Science Technology and Research (A*STAR) Singapore Singapore

Continuous Chinese sign language recognition (CCSLR) methods have shown their strong ability to learn excellent model architectures from datasets. However, due to data insufficiency, it is difficult to complete the CCSLR task. In this work, we focus on a simple but important solution to alleviate data insufficiency: how to refine the model architecture of a CCSLR network to improve the robustness of feature processing by using some better-quality non-Chinese sign language datasets. To this end, a simple empirical study was first conducted to verify the feasibility of knowledge transfer in the CCSLR task. Surprisingly, just by pre-training of our recognition model on a foreign sign language dataset, we can refine the model architecture and improve its robustness significantly. To make it more practical, the key issue of how to fine-tune the existing feature processing models for effective guidance should be carefully investigated. Then, we propose a novel scheme for fine-tuning of pre-trained models named FTP, which updates the spatial feature extractor initialized by a pre-trained backbone and freezes the temporal feature extractor implemented by a better shareable transformer encoder. Compared with the baseline method, our FTP method can achieve significant performance improvement on the public dataset USTC-CCSL. © The Author(s) 2023.

关键词： computer vision Continuous Chinese sign language recognition (CCSLR) Fine-tuning Pre-training

来源：评论

学校读者我要写书评

暂无评论

Accelerating fluid flow in Quantum computing using GPU

Accelerating fluid flow in Quantum Computing using GPU

引用

computer, Electronics & Electrical engineering & their Applications (IC2E3), International Conference on

作者： Joel Dandin Satyadhyan Chickerur School of Computer Science and Engineering KLE Technological University Hubballi India Centre for High Performance Computing School of Computer Science and Engineering KLE Technological University Hubballi India

In the last few years, quantum computing has evolved as the next big technological breakthrough. Many big companies are actively researching this area and have built open-source frameworks which can be used to develop solutions for problems that connect be solved by classical computers. One such problem is the solution of Navier-Stokes equations which takes exponential time for simulation but using quantum computers, they can be solved in polynomial time. But the current state of quantum computation does not enable everyone to test their implementation on a real quantum computer. In this situation, a simulator enables rapid prototype and testing techniques and algorithms for when the real quantum computer is ready. This paper focuses on simulating fluid flow algorithms using a quantum framework, such as Navier- Stokes equations, with the lattice Boltzmann method (LBM) used to numerically solve the relevant system of equations on both CPU and GPU to speed up the process. The quantum framework used in this paper is Qiskit, an open-source software development kit created by IBM that allows developers to create and test quantum algorithms. NVIDIA cuQuantum is an SDK of optimized libraries and tools for expediting quantum computing operations used in this paper to solve the fundamental problem of modeling large-size quantum circuits using the power of GPU

关键词：

来源：评论

学校读者我要写书评

暂无评论

WeakPolyp-SAM: Segment Anything Model-driven weakly-supervised polyp segmentation

引用

Knowledge-Based Systems 2025年 322卷

作者： Zhao, Yiming Zhou, Tao Gu, Yunqi Zhou, Yi Zhang, Yizhe Wu, Ye Fu, Huazhu School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science and Engineering Southeast University Nanjing211189 China Institute of High Performance Computing A*STAR Singapore

Accurate polyp segmentation is essential for early detection of polyps, which is of significant clinical importance for the prevention of colorectal cancer. Although various fully-supervised deep learning techniques have been developed for polyp segmentation, pixel-wise annotation by physicians during diagnosis is both time-consuming and expensive. Meanwhile, visual foundation models such as the Segment Anything Model (SAM) have demonstrated remarkable performance in general segmentation tasks. However, directly applying SAM to medical segmentation may not yield satisfactory results due to the lack of medical knowledge. In this paper, we propose a novel SAM-driven weakly-supervised polyp segmentation framework (termed WeakPolyp-SAM), which enables a collaborative learning process between our segmentation network and SAM to boost the model performance. Specifically, we propose a Cross-aware Feature Aggregation Network (CFANet) to effectively aggregate cross-level features and leverage global cues for weakly-supervised polyp segmentation. Within CFANet, we propose a Cross-level Fusion Module (CFM) that integrates the adjacent features to enhance the representation capabilities of different resolution features. Additionally, a Local-and-global Context Decoder (LCD) is presented to capture richer features across multiple levels. Moreover, we present a box-augmentation strategy that combines the segmentation maps generated by CFANet with scribble annotations to create more precise prompts. These prompts are then fed into SAM, generating segmentation SAM-driven masks, which provide additional supervision to effectively train CFANet. Furthermore, we present an image-level filtering mechanism to filter out unreliable masks. Experimental results demonstrate that our WeakPolyp-SAM outperforms state-of-the-art weakly-supervised segmentation methods. The scribble-annotated datasets and code will be released at https://***/taozh2017/WeakPolyp-SAM. © 2025 Elsevier B.V.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Two-Level Scheduling Technology for Heterogeneous Clusters Using Analytical Hierarchy Processes 6

Two-Level Scheduling Technology for Heterogeneous Clusters U...

引用

6th IEEE International Conference on computer and Communication Systems, ICCCS 2021

作者： Zhao, Tianhai Gu, Jianhua Zhang, Xiaoyuan Northwestern Polytechnical University School of Computer Science and Engineering Center for High Performance Computing Xi'an Shanxi China

ISBN: (纸本)9780738126043

The cluster system presents multi-level and complex heterogeneous features with GPUs computing. Job scheduling technology determines computing resource utilization and throughput of the cluster system. On the basis of heterogeneous cluster system, the two-level scheduling technology is proposed in this paper. In the first level, a job priority scheduling algorithm based on user value is designed at the cluster level using analytical hierarchy processes. The second level of scheduling is to act on the computing nodes that contain GPUs, and design a scheduling algorithm based on GPU sharing policy that manages GPU jobs in a more fine-grained manner. Through experiments, it shows that the job priority scheduling algorithm based on user value can ensure that jobs with high user value are executed first, and fairness is guaranteed. The scheduling algorithm based on GPU sharing technology can significantly improve the utilization of GPU and video memory, reducing the average waiting time of jobs by 55.54% and the average turnaround time of jobs by 28.83%. © 2021 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

LSA-PINN: Linear Boundary Connectivity Loss for Solving PDEs on Complex Geometry

LSA-PINN: Linear Boundary Connectivity Loss for Solving PDEs...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jian Cheng Wong Pao-Hsiung Chiu Chinchun Ooi My Ha Dao Yew-Soon Ong Institute of High Performance Computing Agency for Science Technology and Research Singapore School of Computer Science and Engineering Nanyang Technological University Singapore

We present a novel loss formulation for efficient learning of complex dynamics from governing physics, typically described by partial differential equations (PDEs), using physics-informed neural networks (PINNs). In our experiments, existing versions of PINNs are seen to learn poorly in many problems, especially for complex geometries, as it becomes increasingly difficult to establish appropriate sampling strategy at the near boundary region. Overly dense sampling can adversely impede training convergence if the local gradient behaviors are too complex to be adequately modelled by PINNs. On the other hand, if the samples are too sparse, existing PINNs tend to overfit the near boundary region, leading to incorrect solution. To prevent such issues, we propose a new Boundary Connectivity (BCXN) loss function which provides linear local structure approximation (LSA) to the gradient behaviors at the boundary for PINN. Our BCXN-loss implicitly imposes local structure during training, thus facilitating fast physics-informed learning across entire prob-lem domains with order of magnitude sparser training samples. This LSA-PINN method shows a few orders of magnitude smaller errors than existing methods in terms of the standard L2-norm metric, while using dramatically fewer training samples and iterations. Our proposed LSA-PINN does not pose any requirement on the differentiable property of the networks, and we demonstrate its benefits and ease of implementation on both multi-layer perceptron and convolutional neural network versions as commonly used in current PINN literature.

关键词：

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：