检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yang, Fuchao Cheng, Jianhong Liu, Hui Dong, Yongqiang Jia, Yuheng Hou, Junhui College of Software Engineering Southeast University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China Yam Pak Charitable Foundation School of Computing and Information Sciences Saint Francis University Hong Kong Department of Computer Science City University of Hong Kong Hong Kong China

In partial label learning (PLL), every sample is associated with a candidate label set comprising the ground-truth label and several noisy labels. The conventional PLL assumes the noisy labels are randomly generated (instance-independent), while in practical scenarios, the noisy labels are always instance-dependent and are highly related to the sample features, leading to the instance-dependent partial label learning (IDPLL) problem. Instance-dependent noisy label is a double-edged sword. On one side, it may promote model training as the noisy labels can depict the sample to some extent. On the other side, it brings high label ambiguity as the noisy labels are quite undistinguishable from the ground-truth label. To leverage the nuances of IDPLL effectively, for the first time we create class-wise embeddings for each sample, which allow us to explore the relationship of instance-dependent noisy labels, i.e., the class-wise embeddings in the candidate label set should have high similarity, while the class-wise embeddings between the candidate label set and the non-candidate label set should have high dissimilarity. Moreover, to reduce the high label ambiguity, we introduce the concept of class prototypes containing global feature information to disambiguate the candidate label set. Extensive experimental comparisons with twelve methods on six benchmark data sets, including four fine-grained data sets, demonstrate the effectiveness of the proposed method. The code implementation is publicly available at https://***/Yangfc-ML/CEL. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Constrained Intelligent Frequency Control in an AC Microgrid: An Online Reinforcement Learning Based PID Tuning Approach

Constrained Intelligent Frequency Control in an AC Microgrid...

引用

IEEE General Meeting Power& Energy Society

作者： K. Nosrati A. Tepljakov E. Petlenkov V. Skiparev J. Belikov Y. Levron Department of Computer Systems Tallinn University of Technology Tallinn Estonia Department of Software Science Tallinn University of Technology Tallinn Estonia Faculty of Electrical & Computer Engineering Technion—Israel Institute of Technology Haifa Israel

Variable output power in isolated microgrids (MGs) threatens frequency stability and may even degrade power quality. In response, intelligent control methods have been developed and applied to frequency deviation control systems with excellent results. Nevertheless, a potential problem is that the application of such advanced techniques with a large search space is not enough to deal with highly dynamic environment and real-time operations of MGs. In this light, the present study introduces a flexible artificial neural network (ANN)-based frequency deviation control solution in a constrained structure that operates as follows. First, the stable controller parameter space of the PID-based AC microgrid is derived by using the stability boundary locus method. Then, the controller parameters are tuned and updated online by searching for an optimal combination of the coefficients with consideration of output variations sensed by a constrained ANN in the derived reduced parameter space. To accomplish this step, a reinforcement learning technique is applied to train the ANN-based tuners. The performance of the proposed technique has been verified under a given scenario to demonstrate how the reduced parameter space should facilitate the optimization procedure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Temporally Consistent Referring Video Object Segmentation with Hybrid Memory

arXiv

引用

arXiv 2024年

作者： Miao, Bo Bennamoun, Mohammed Gao, Yongsheng Shah, Mubarak Mian, Ajmal The Department of Computer Science and Software Engineering The University of Western Australia Perth CrawleyWA6009 Australia The School of Engineering Griffith University BrisbaneQLD4111 Australia The Center for Research in Computer Vision University of Central Florida OrlandoFL32816 United States

Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS paradigm that explicitly models temporal instance consistency alongside the referring segmentation. Specifically, we introduce a novel hybrid memory that facilitates inter-frame collaboration for robust spatio-temporal matching and propagation. Features of frames with automatically generated high-quality reference masks are propagated to segment the remaining frames based on multi-granularity association to achieve temporally consistent R-VOS. Furthermore, we propose a new Mask Consistency Score (MCS) metric to evaluate the temporal consistency of video segmentation. Extensive experiments demonstrate that our approach enhances temporal consistency by a significant margin, leading to top-ranked performance on popular R-VOS benchmarks, i.e., Ref-YouTube-VOS (67.1%) and Ref-DAVIS17 (65.6%). The code is available at https://***/bo-miao/HTR. © 2024, CC BY.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Photon-Counting CT Denoising with Comprehensive Noise Propagation Model

Self-Supervised Photon-Counting CT Denoising with Comprehens...

引用

IEEE Symposium on Nuclear science (NSS/MIC)

作者： Q. Wu X. Lei M. Su W. Qin X. Yu G. Quan W. Cao W. Wang X. Ji X. Lai Y. Chen School of Computer Science and Engineering Southeast University Nanjing China School of Biomedical Engineering ShanghaiTech University Shanghai China College of Software Engineering Southeast University Nanjing China The CT RPA Department United Imaging Healthcare Shanghai China

ISBN: (数字)9798350388152

ISBN: (纸本)9798350388169

Photon counting computed tomography (PCCT) is an emerging spectral CT technology with significant potential for revolutionizing clinical CT applications. However, noise amplification during signal decomposition significantly limits the utility of basis material images. While data-driven supervised learning has been successful in reducing noise in conventional CT images, applying this method to PCCT is challenging due to the early phase of clinical studies and difficulty in gathering sufficient clinical data for training. To solve this issue, this paper proposes a projection-domain noise propagation model for noise suppression during material decomposition. Firstly, an analytical model is derived from the decomposition of dual-energy materials to describe in detail the propagation of noise from the detector domain to the projection domain. Such model can accurately describe the variance of each pixel in the basis material images. Secondly, we incorporate this statistical model into self-supervised learning network and define a joint optimization strategy via maximizing the constrained log-likelihood with Gaussian statistics. For self-supervised learning, we suggest to construct pseudo training pairs to learn denoising solely from noisy samples. Extensive analyses on real data demonstrate that the proposed method is promising for improving the virtual monochromatic imaging (VMI) quality of PCCT. Our method uses a small amount of experimental data and could be implemented in a real clinical setting.

关键词： Training Semiconductor device modeling Semiconductor detectors Computed tomography Noise Noise reduction Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Inner-approximate Reachability Computation via Zonotopic Boundary Analysis

arXiv

引用

arXiv 2024年

作者： Ren, Dejin Liang, Zhen Wu, Chenyu Ding, Jianqiang Wu, Taoran Xue, Bai Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China College of Computer Science and Technology National University of Defense Technology Changsha China Department of Electrical Engineering and Automation Aalto University Espoo Finland

Inner-approximate reachability analysis involves calculating subsets of reachable sets, known as inner-approximations. This analysis is crucial in the fields of dynamic systems analysis and control theory as it provides a reliable estimation of the set of states that a system can reach from given initial states at a specific time instant. In this paper, we study the inner-approximate reachability analysis problem based on the set-boundary reachability method for systems modelled by ordinary differential equations, in which the computed inner-approximations are represented with zonotopes. The set-boundary reachability method computes an inner-approximation by excluding states reached from the initial set’s boundary. The effectiveness of this method is highly dependent on the efficient extraction of the exact boundary of the initial set. To address this, we propose methods leveraging boundary and tiling matrices that can efficiently extract and refine the exact boundary of the initial set represented by zonotopes. Additionally, we enhance the exclusion strategy by contracting the outer-approximations in a flexible way, which allows for the computation of less conservative inner-approximations. To evaluate the proposed method, we compare it with state-of-the-art methods against a series of benchmarks. The numerical results demonstrate that our method is not only efficient but also accurate in computing inner-approximations. Copyright © 2024, The Authors. All rights reserved.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

The Performance Analysis of Distributed Denial of Service Attacks in Wireless Networks

The Performance Analysis of Distributed Denial of Service At...

引用

International Conference on Futuristic Technologies (INCOFT)

作者： Trapty Agrawal R Raghavendra K. Ranjith Singh Rajiv Gandhi N Dharmesh Dhabliya Jitendra Kumar Katariya Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Indi Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore Karnataka India Department of Computer Science Karpagam Academy of Higher Education Coimbatore Department of Civil Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Information Technology Vishwakarma Institute of Information Technology Pune Maharashtra India Department of Computer Science & Application Vivekananda Global University Jaipur India

Complete studies paper that examines the outcomes that malicious 0.33-celebration actors will have on Wi-Fi networks via dispensed denial of carrier (DDoS) attacks. This paper explores the available numerous assault models and the potential countermeasures that may be applied if you want to mitigate the damage due to such assaults. In addition, this paper focuses on the capability blessings related to deploying preventative measures to lessen the impact of such assaults. Moreover, the paper investigates existing attack trends. It affords an outline of the safety techniques to be had for limiting the harm caused by DDoS attacks in wireless networks. By comparing and analyzing the performance of diverse protection mechanisms, this paper offers an evidenceprimarily based evaluation of the effectiveness of DDoS attack safety answers. ultimately, this paper concludes with the aid of supplying recommended measures for strengthening and ensuring the safety of Wi-Fi networks against malicious actors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DPFedSAM-Meas: Comparison Of Differential Privacy Federated Learning In Medical Image Classification

DPFedSAM-Meas: Comparison Of Differential Privacy Federated ...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Shunrong Jiang Zhi Wang Zixuan He Yonggang Li Xiaofan Li Haotian Chi Xiaojiang Du School of Computer Science China University of Mining and Technology Xuzhou China Jiangsu Jingchuang Electric CO. LTD School of Automation and Software Engineering Shanxi University Taiyuan China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Machine learning is widely used in medical image classification tasks. However, medical images often exhibit uneven distribution and high sensitivity to noise. A feasible solution involves using federated learning (FL) with differential privacy (DP), a distributed training method that protects patient privacy. In this work, many studies have proposed improved solutions for localized differential-private federated learning (DP-FL) frameworks. However, these studies are isolated, which would be detrimental to privacy practitioners in designing and using the algorithms. To provide a comprehensive analysis of these algorithms, we propose DPFedSAM-Meas, as a framework for comprehensive utility analysis of DP-FL. In this framework, we employed the state-of-the-art federated learning framework FedSAM. Moreover, we categorize DP algorithms into Laplace DP and Gaussian DP by the underlying DP mechanisms, and into Gradient DP and Parameter DP by the DP position in FL train. DPFedSAM-Meas allows a comparative analysis of these four DP techniques, measuring their model utility, privacy leakage, and overhead when FL uses different network structures. Finally, we evaluate DPFedSAM-Meas on datasets of Pneumonia, Blood, and Path, aiming to investigate the performance of different DP techniques on mainstream deep learning algorithms, including Convolutional Neural Networks (CNN) and Vision Transformers (ViT).

关键词： Training Privacy Differential privacy Sensitivity Pneumonia Federated learning Transformers Convolutional neural networks Biomedical imaging Image classification

来源：评论

学校读者我要写书评

暂无评论

Classification of Plants Leave Using Image Processing and Neural Network 8th

Classification of Plants Leave Using Image Processing and Ne...

引用

8th International Workshop on Soft Computing applications, SOFA 2018

作者： Bagherinezhad, Hashem Kuchaki Rafsanjani, Marjan Balas, Valentina Emilia Koles, Ioan E. Department of Computer Science Faculty of Mathematics and Computer Shahid Bahonar University of Kerman Kerman Iran Department of Automatics and Applied Software Faculty of Engineering Aurel Vlaicu University of Arad Arad Romania

ISBN: (纸本)9783030521899

Plants are one of the most widely used resources for humans in different fields. Therefore, the distinction between the plant species is important and it is referred to as the plant detection system. Until now, this task has been done by the expert botanists which is an overwhelming and time consuming task. Moreover, there is a lack of the memory and the human fault, so the researchers endeavored to solve these disadvantages using the AI algorithms. For this goal, in this paper, a system is proposed that includes four phases: pre-processing, feature extraction, training, and test. In this method, we use the combination of the useful features of the leave shape, the leave texture, the leave color, and we provide a method for the classification of a number of the plant species. Finally, the feature vectors will be created and then, the classification is performed by using feed-forward back-propagation multi-layer perceptron artificial neural network algorithm. Then, the results of this method compare with other methods. The obtained results show the high accuracy of this method for a large number of the species in different conditions (such as pests, season changes and lighting). © 2021, Springer Nature Switzerland AG.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Model Aggregation in Heterogenous Aerial and Space Networks

arXiv

引用

arXiv 2023年

作者： Dong, Fan Abbasi, Ali Leung, Henry Wang, Xin Zhou, Jiayu Drew, Steve Department of Electrical and Software Engineering University of Calgary CalgaryAB Canada Department of Geomatics Engineering University of Calgary CalgaryAB Canada Department of Computer Science and Engineering Michigan State University East LansingMI United States

Federated learning offers a promising approach under the constraints of networking and data privacy constraints in aerial and space networks (ASNs), utilizing large-scale private edge data from drones, balloons, and satellites. Existing research has extensively studied the optimization of the learning process, computing efficiency, and communication overhead. An important yet often overlooked aspect is that participants contribute predictive knowledge with varying diversity of knowledge, affecting the quality of the learned federated models. In this paper, we propose a novel approach to address this issue by introducing a Weighted Averaging and Client Selection (WeiAvgCS) framework that emphasizes updates from high-diversity clients and diminishes the influence of those from low-diversity clients. Direct sharing of the data distribution may be prohibitive due to the additional private information that is sent from the clients. As such, we introduce an estimation for the diversity using a projectionbased method. Extensive experiments have been performed to show WeiAvgCS’s effectiveness. WeiAvgCS could converge 46% faster on FashionMNIST and 38% faster on CIFAR10 than its benchmarks on average in our experiments. © 2023, CC BY.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

A Robust Methodology for Fruit Quality Prediction and Estimation Using Intelligent Learning Based Image Processing Logic

A Robust Methodology for Fruit Quality Prediction and Estima...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Malathi K Vunnava Dinesh Babu M. Ramkumar M. Ayyadurai Vivek K Hamzeh J Aljawawdeh Department of CSE Saveetha School of Engineering Saveetha Institute of Science and Technology (SIMATS) Saveetha University Chennai Department of CSE RV Institute of Technology Guntur Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai Chennai Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur Department of software engineering Faculty of information technology Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Fruit quality prediction plays a vital role in agricultural and food industries, ensuring that only high-quality produce reaches the consumer. Traditional methods of assessing fruit quality rely on manual inspection, which is both time-consuming and prone to human error. This paper presents a robust methodology for fruit quality prediction and estimation, utilizing a hybrid deep learning model that integrates DenseN et for feature extraction with LightGBM for efficient classification. The proposed model is designed to automate the process of fruit quality assessment by analyzing key attributes such as color, texture, and shape from high-resolution fruit images. The Fruit360 dataset was used for training and testing, with images classified into categories such as fresh, ripe, overripe, and damaged. A comprehensive comparison with nine existing models, including SVM, Random Forest, and XGBoost, was conducted using performance metrics such as accuracy, precision, recall, and Fl-score. The proposed model achieved an accuracy of 96.78%, significantly outperforming all other models. Furthermore, the model's precision and recall reached 95.33% and 95.67%, respectively, demonstrating its reliability in distinguishing high-quality fruits from low-quality ones.

关键词： Training Support vector machines Accuracy Shape Computational modeling Estimation Predictive models Feature extraction Reliability Testing

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：