检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhuo Huang Miaoxi Zhu Xiaobo Xia Li Shen Jun Yu Chen Gong Bo Han Bo Du Tongliang Liu Sydney AI Centre The University of Sydney National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University JD Explore Academy Department of Automation University of Science and Technology of China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Department of Computer Science Hong Kong Baptist University

Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is available, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards a Deep Learning Pain-Level Detection Deployment at UAE for Patient-Centric-Pain Management and Diagnosis Support: Framework and Performance Evaluation

引用

Procedia computer science 2023年 220卷 339-347页

作者： Leila Ismail Muhammad Danish Waseem Clouds and Distributed Computing and Systems (CLOUDS) Lab School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne Australia. Intelligent Distributed Computing and Systems (INDUCE) Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University UAE. National Water and Energy Center United Arab Emirates University UAE.

The outbreak of the COVID-19 pandemic revealed the criticality of timely intervention in a situation exacerbated by a shortage in medical staff and equipment. Pain-level screening is the initial step toward identifying the severity of patient conditions. Automatic recognition of state and feelings help in identifying patient symptoms to take immediate adequate action and providing a patient-centric medical plan tailored to a patient's state. In this paper, we propose a framework for pain-level detection for deployment in the United Arab Emirates and assess its performance using the most used approaches in the literature. Our results show that a deployment of a pain-level deep learning detection framework is promising in identifying the pain level accurately.

关键词： computer Vision Deep Learning Image Processing Machine Learning Pain Detection Patient-Centric Smart healthcare eHealth

来源：评论

学校读者我要写书评

暂无评论

Development of a deep learning system for preventive detection of heart failure due to pulmonary disease

Development of a deep learning system for preventive detecti...

引用

International Conference on software Process Improvement (CIMPS)

作者： Axel Frederick Félix Jiménez Isaul Ibarra Belmonte Vania Stephany Sánchez Lee Uziel Jaramillo Avila Ezra Federico Parra González Computer Systems Engineering National Polytechnic Institute Zacatecas México Software Engineer Center for Research in Mathematics Zacatecas Zacatecas México Computer Science Department Center for Research in Mathematics Zacatecas Zacatecas México

ISBN: (纸本)9798350398977

In the context of addressing the problem of people who do not undergo a diagnosis of heart failure due to pulmonary conditions on time, a solution to this problem would allow early preventive detection to avoid the development of severe disease efficiently. Our approach employs the use of medical data retrieved from the user to determine and predict whether there is a likelihood of a potential condition. To solve this problem, according to a users medical measurement history, a deep learning model can be implemented to determine a preventive diagnosis or otherwise to follow up on an already detected condition. By posing the problem as a classification task, it can be taken advantage of a deep learning model focused on heart failure or pulmonary conditions to make a preliminary diagnosis and determine if there are signs of any symptomatology.

关键词： Cardiovascular diseases Diseases Deep learning Medical diagnostic imaging Lung Prediction algorithms Medical services

来源：评论

学校读者我要写书评

暂无评论

Adaptive Student Inference Network for Efficient Single Image Super-Resolution

Adaptive Student Inference Network for Efficient Single Imag...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Kang Miao Zhao Zhang Jiahuan Ren Mingbo Zhao Haijun Zhang Richang Hong School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China School of Information Science and Technology Donghua University Shanghai China Department of Computer Science Harbin Institute of Technology (Shenzhen) Shenzhen China

Recent advances in single image super-resolution (SISR) have achieved remarkable performance through deep learning. However, the high computational cost hinders the deployment of SISR models on edge devices. Instead of proposing new SISR models, a new trend is emerging to improve network efficiency by reducing parameters, FLOPs, and inference time through slight modifications to the original models. However, recent methods usually focus on reducing only one of three metrics, i.e., FLOPs, parameters and inference time, which inevitably increases the other two metrics. In this paper, we propose a novel Adaptive Student Inference Network (ASIN) on popular SISR models, which aims at reducing FLOPs and inference time while maintaining the number of parameters and restoring clearer high-resolution images. Specifically, our ASIN divides a SISR model into three components (head, body and tail) and adopts various strategies for each part. For head and tail parts, to ensure the restored images contain more detailed information, a novel auxiliary Enhanced Teacher Network (ETNet) is designed, which is trained with the ground-truth images to obtain more prior knowledge to guide student network to extract more accurate textures using a new knowledge distillation method. For the body part, owing to the varying difficulties of the reconstructions in different regions, we propose an Adaptive Depth Predicted Module (ADPM) to dynamically shorten average depth of network to reduce the computational cost of overall network. Extensive experiments on two datasets demonstrate the effectiveness and state-of-the-art performance of our ASIN compared to its counterparts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Near-Far Field Channel Estimation for Holographic MIMO Communications

arXiv

引用

arXiv 2024年

作者： Yue, Shaohua Zeng, Shuhao Liu, Liang Eldar, Yonina C. Di, Boya The State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing100871 China The Department of Electronic and Information Engineering The Hong Kong Polytechnic University Hong Kong The Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot7610001 Israel

Holographic MIMO communications, enabled by large-scale antenna arrays with quasi-continuous apertures, is a potential technology for spectrum efficiency improvement. However, the increased antenna aperture size extends the range of the Fresnel region, leading to a hybrid near-far field communication mode. The users and scatterers randomly lie in near-field and far-field zones, and thus, conventional far-field-only and near-field-only channel estimation methods may not work. To tackle this challenge, we demonstrate the existence of the power diffusion (PD) effect, which leads to a mismatch between the hybrid-field channel and existing channel estimation methods. Specifically, in far-field and near-field transform domains, the power gain of one channel path may diffuse to other positions, thus generating fake paths. This renders the conventional techniques unable to detect those real paths. We propose a PD-aware orthogonal matching pursuit algorithm to eliminate the influence of the PD effect by identifying the PD range, within which paths diffuse to other positions. PD-OMP fits a general case without prior knowledge of near-field and far-field path numbers and the user’s location. The computational complexity of PD-OMP and the Cramér-Rao Lower Bound for the sparse-signal-recovery-based channel estimation are also derived. Simulation results show that PD-OMP outperforms state-of-the-art hybrid-field channel estimation methods. © 2024, CC BY-NC-ND.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Efficient Training Approaches for Performance Anomaly Detection Models in Edge Computing Environments

arXiv

引用

arXiv 2024年

作者： Fernando, Duneesha Rodriguez, Maria A. Arroba, Patricia Ismail, Leila Buyya, Rajkumar Laboratory School of Computing and Information Systems The University of Melbourne Parkville Australia The CCS Center for Computational Simulation Universidad Politécnica de Madrid Madrid Spain Lab Department of Computer Science and Software Engineering United Arab Emirates University United Arab Emirates

Microservice architectures are increasingly used to modularize IoT applications and deploy them in distributed and heterogeneous edge computing environments. Over time, these microservice-based IoT applications are susceptible to performance anomalies caused by resource hogging (e.g., CPU or memory), resource contention, etc., which can negatively impact their Quality of Service and violate their Service Level Agreements. Existing research on performance anomaly detection for edge computing environments focuses on model training approaches that either achieve high accuracy at the expense of a time-consuming and resource-intensive training process or prioritize training efficiency at the cost of lower accuracy. To address this gap, while considering the resource constraints and the large number of devices in modern edge platforms, we propose two clustering-based model training approaches: (1) intra-cluster parameter transfer learning-based model training (ICPTL) and (2) cluster-level model training (CM). These approaches aim to find a trade-off between the training efficiency of anomaly detection models and their accuracy. We compared the models trained under ICPTL and CM to models trained for specific devices (most accurate, least efficient) and a single general model trained for all devices (least accurate, most efficient). Our findings show that ICPTL's model accuracy is comparable to that of the model per device approach while requiring only 40% of the training time. In addition, CM further improves training efficiency by requiring 23% less training time and reducing the number of trained models by approximately 66% compared to ICPTL, yet achieving a higher accuracy than a single general model. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning of First-Order Nonlinear Hyperbolic Conservation Law Solvers

SSRN

引用

SSRN 2023年

作者： Morand, Victor Müller, Nils Weightman, Ryan Keimer, Alexander Piccoli, Benedetto Bayen, Alexandre M. Ecole Polytechnique Palaiseau France Department of Electrical Engineering and Computer Science University of California BerkeleyCA United States Max Planck Institute for Software Systems Saarland Informatics Campus Germany Max Planck Institute for Intelligent Systems Germany Department of Mathematics Rutgers University NJ United States Department of Mathematics FAU Erlangen-Nürnberg Germany

In this contribution, we study the numerical approximation of scalar conservation laws by computational optimization of the numerical flux function in a first-order finite volume method. The cell-averaging inherent to finite volume schemes presents a challenge in the design of such numerical flux functions toward achieving high solution accuracy. Dense neural networks, as well as (piecewise) polynomials, serve as function classes for the numerical flux. Using a parametrization of such a function class, we optimize the numerical flux with respect to its solution accuracy on a set of Riemann problems for which we have closed-form solutions. By design, our resulting first-order finite volume schemes are *** show empirically that the proposed schemes can achieve higher accuracy than the Godunov and EnquistOsher method on a wide range of *** proposed method can be applied to the inverse problem, i.e., the data-driven synthesis of macroscopic physical laws for real-world flux phenomena. © 2023, The Authors. All rights reserved.

关键词： Finite volume method

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Sleep Control in 5G and Beyond Radio Access Networks: An Overview

Deep Reinforcement Learning for Sleep Control in 5G and Beyo...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Nessrine Trabelsi Rihab Maaloul Lamia Chaari Fourati Wael Jaafar Laboratory of Signals systeMs aRtificial intelligence and neTworkS – Digital Research Center of Sfax Sfax Tunisia Higher Institute of Computer Science of Mahdia (ISIMa) University of Monastir Tunisia Higher Institute of Computer Science and Multimedia in Sfax (ISIMS) University of Sfax Tunisia Department of Software and IT Engineering École de technologies supérieure (ÉTS) Montreal Canada

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

The advent of 5G and beyond networks is envisioned to support lower latency, higher data rates, and wider connectivity than previous cellular network generations. However, given the denser deployment of base stations (BSs) to accommodate such improvements, this results inevitably in a significant and unsustainable increase in the network’s energy consumption. Sleep Control (SC), which allows switching off some BS hardware components during light-traffic time, is considered a viable solution for greener and more energy-efficient Radio Access Networks (RAN). However, the optimization of SC is a highly challenging large-scale network combinatorial problem that depends on dynamic wireless channel conditions and varying traffic demands with stringent Quality-of-Service (QoS) requirements. Driven by the benefits and efficiency of Deep Reinforcement Learning (DRL), which has been successfully applied to multiple wireless network optimization problems, this paper investigates DRL approaches addressing sleep control in 5G and beyond RAN. To this end, we propose a taxonomy to classify the related literature. Then, we provide an overview of the different components of the Markov Decision Process (MDP) modeling the sequential decision-making of sleep control and the applied DRL algorithms. Finally, we highlight the main challenges in existing works and suggest novel strategies to address them.

关键词： 5G mobile communication Wireless networks Taxonomy Decision making Quality of service Switches Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

TRACKING THE TOPOLOGY OF NEURAL MANIFOLDS ACROSS POPULATIONS

arXiv

引用

arXiv 2025年

作者： Yoon, Iris H.R. Henselman-Petrusek, Gregory Yu, Yiyi Ghrist, Robert Smith, Spencer Lavere Giusti, Chad Department of Mathematics and Computer Science Wesleyan University 265 Church Street MiddletownCT06459 United States Pacific Northwest National Laboratory 902 Battelle Boulevard RichlandWA99352 United States Department of Electrical and Computer Engineering University of California Santa Barbara Santa BarbaraCA93106 United States Department of Mathematics and Electrical & Systems Engineering University of Pennsylvania PhiladelphiaPA19104 United States Department of Mathematics Oregon State University 2000 SW Campus Way CorvallisOR97331 United States

Neural manifolds summarize the intrinsic structure of the information encoded by a population of neurons. Advances in experimental techniques have made simultaneous recordings from multiple brain regions increasingly commonplace, raising the possibility of studying how these manifolds relate across populations. However, when the manifolds are nonlinear and possibly code for multiple unknown variables, it is challenging to extract robust and falsifiable information about their relationships. We introduce a framework, called the method of analogous cycles, for matching topological features of neural manifolds using only observed dissimilarity matrices within and between neural populations. We demonstrate via analysis of simulations and in vivo experimental data that this method can be used to correctly identify multiple shared circular coordinate systems across both stimuli and inferred neural manifolds. Conversely, the method rejects matching features that are not intrinsic to one of the systems. Further, as this method is deterministic and does not rely on dimensionality reduction or optimization methods, it is amenable to direct mathematical investigation and interpretation in terms of the underlying neural activity. We thus propose the method of analogous cycles as a suitable foundation for a theory of cross-population analysis via neural manifolds. © 2025, CC BY-NC-ND.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

TEVA: Training-Efficient and Verifiable Aggregation for Federated Learning for Consumer Electronics in Industry 5.0

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Xia, Yuanjun Liu, Yining Chen, Jingxue Liang, Yangfan Khan, Fazlullah Alturki, Ryan Wang, Xiaopei Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software School of Computer and Information Security Guilin541004 China Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou325027 China University of Technology School of Mathematical and Physical Sciences SydneyNSW2007 Australia Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems The Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province The Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing314001 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Zhejiang Ningbo315104 China Umm AI-Qura University Makkah Department of Software Engineering College of Computing Saudi Arabia Riverside Department of Computer Science and Engineering University of California CA92521 United States

Federated learning (FL) has been widely used for privacy-preserving model updates in Industry 5.0, facilitated by 6G networks. Despite FL's privacy-preserving advantages, it remains vulnerable to attacks where adversaries can infer private data from local models or manipulate the central server (CS) to deliver falsified global models. Current privacy-preserving approaches, primarily based on the FedAvg algorithm, fail to optimize training efficiency for non-independent and identically distributed (non-IID) data. This article proposes training-efficient and verifiable aggregation (TEVA) for FL to resolve these issues. This scheme combines threshold Paillier homomorphic encryption (TPHE), verifiable aggregation, and an optimized double momentum update mechanism (OdMum). TEVA not only leverages TPHE to protect the privacy of local models but also ensures the integrity of the global model through a verifiable aggregation mechanism. Additionally, TEVA integrates the OdMum algorithm to effectively address the challenges posed by non-IID data, promoting rapid model convergence and significantly enhancing overall training efficiency. Security analysis indicates that TEVA meets the requirements for privacy protection. Extensive experimental results demonstrate that TEVA can accelerate model convergence while incurring lower computational and communication overheads. © 1975-2011 IEEE.

关键词： Differential privacy

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：