检索结果-内蒙古大学图书馆

Application of Maehly Approximation to em scattering from a Three-dimensional Rough Surface over a Frequency Band 5

学校读者我要写书评

暂无评论

Application of Maehly Approximation to em scattering from a ...

5th IEEE International Conference on Computational Electromagnetics, ICCEM 2019

作者： Wang, An Qi Zhang, Xue Huang, Zhi Xiang Anhui University School of Electronics and Information Engineering Key Laboratory of Intelligent Computing Signal Processing Hefei China

ISBN: (纸本)9781538671115

In this paper, the Maehly approximation, which is based on Chebyshev series, is proposed to fast simulate the EM scattering from a three-dimensional (3D) rough surface over a frequency band. Comparing with the exact results obtained by the method of moments (MoM), results of the Maehly approximation have achieved an excellent agreement both in co-polarization and cross-polarization. Moreover, the Maehly approximation is superior to the MoM in terms of the CPU time required. © 2019 IEEE.

关键词： Method of moments

Data gravitation-based three-way sampling method for imbalanced data classification

学校读者我要写书评

暂无评论

Information Sciences 2025年 718卷

作者： Yuanting Yan Weiqing Wang Yingao Ma Yang Tian Peng Zhou Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei Anhui Province 230601 PR China School of Computer Science and Technology Anhui University Hefei Anhui Province 230601 PR China

Data resampling is widely used for addressing the class imbalance problem, with numerous methods developed over recent decades. Among these, the K-nearest neighbor (KNN) technique is widely adopted for leveraging local neighborhood information in rebalancing imbalanced data. However, KNN struggles to accurately characterize local data distribution, as samples with identical KNNs may also exhibit divergent local structures, which may further hamper imbalanced learning performance. We propose a hybrid sampling method called data gravitation-based three-way sampling (DGS) to improve classification performance on imbalanced data. DGS introduces the concept of data gravitation into KNN to evaluate the local importance of samples, and combines it with three-way decision theory to selectively oversample minority-class samples and remove risky majority-class samples. DGS introduces a cost-sensitive sampling mechanism and adaptive threshold estimation using a Gaussian-based model, reducing reliance on manually tuned parameters. Extensive experiments on 38 datasets and seven classifiers demonstrate the superiority of DGS over 18 resampling methods across three evaluation metrics. Our code is available at https://***/ytyancp/DGS .

关键词： Class imbalance Data gravitation Hybrid sampling Three-way decision

Long-Tailed Multi-label Classification with Noisy label of Thoracic Diseases from Chest X-Ray

学校读者我要写书评

暂无评论

Long-Tailed Multi-Label Classification with Noisy Label of T...

IEEE International Symposium on Biomedical Imaging

作者： Haoran Lai Qingsong Yao Zhiyang He Xiaodong Tao S. Kevin Zhou School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Hefei P.R. China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou P.R. China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China Medical Business Department iFlytek Co. Ltd Hefei China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Chest X-rays (CXR) often reveal rare diseases, demanding precise diagnosis. However, current computer-aided diagnosis (CAD) methods focus on common diseases, leading to inadequate detection of rare conditions due to the absence of comprehensive datasets. To overcome this, we present a novel benchmark for long-tailed multi-label classification in CXRs, encapsulating both common and rare thoracic diseases. Our approach includes developing the "LTML-MIMIC-CXR" dataset, an augmentation of MIMIC-CXR with 26 additional rare diseases. We propose a baseline method for this classification challenge, integrating adaptive negative regularization to address negative logits' over-suppression in tail classes, and a large loss reconsideration strategy for correcting noisy labels from automated annotations. Our evaluation on LTML- MIMIC-CXR demonstrates significant advancements in rare disease detection. This work establishes a foundation for robust CAD methods, achieving a balance in identifying a spectrum of thoracic diseases in CXRs. Access to our code and dataset is provided at: https://***/laihaoran/LTML-MIMIC-CXR.

关键词： Design automation Annotations MIMICs Pipelines Tail Computer aided diagnosis Noise measurement

A Recommender System for Metaheuristic Algorithms for Continuous Optimization Based on Deep Recurrent Neural Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Artificial Intelligence

IEEE Transactions on Artificial Intelligence 2020年第1期1卷 5-18页

作者： Tian, Ye Peng, Shichen Zhang, Xingyi Rodemann, Tobias Tan, Kay Chen Jin, Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei 230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei 230601 China Honda Research Institute Europe Offenbach 63073 Germany Department of Computer Science City University of Hong Kong Kowloon Tong Hong Kong Hong Kong Department of Computer Science University of Surrey Guildford GU2 7XH United Kingdom Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang 110819 China

As revealed by the no free lunch theorem, no single algorithm can outperform any others on all classes of optimization problems. To tackle this issue, methods for recommending an existing algorithm for solving given problems have been proposed. However, existing recommendation methods for continuous optimization suffer from low practicability and transferability, mainly due to the difficulty in extracting features that can effectively describe the problem structure and lack of data for training a recommendation model. This work proposes a generic recommender system to address the above two challenges. First, a novel method is proposed to represent an analytic objective function of a continuous optimization problem as a tree, which is directly used as the features of the problem. For black-box optimization problems whose objective function is unknown, a symbolic regressor is adopted to estimate the tree structure. Second, a large number of benchmark problems are randomly created based on the proposed tree representation, providing an abundant amount of training data with various levels of difficulty. By employing a deep recurrent neural network, a recommendation model is trained to recommend a most suitable metaheuristic algorithm for white- or black-box optimization, making a significant step forward towards fully automated algorithm recommendation for continuous optimization. Experimental results on 100 000 benchmark problems show that the proposed recommendation model achieves considerably better performance than existing ones, and exhibits high transferability to real-world problems. Impact Statement—Real-world optimization problems, such as aerodynamic design of turbine engines and automated trading, have been successfully solved by metaheuristics. However, practitioners are confronted with the challenge of how to choose an appropriate metaheuristic algorithm to solve a particular instance of these problems. This paper proposes a recommender system that can auto

关键词： Algorithm recommendation continuous optimization problem decision tree deep recurrent neural network metaheuristics symbolic regression

Quantifying robustness to adversarial word substitutions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Yuting Huang, Pei Ma, Fei Fei Cao, Juan Zhang, Meishan Zhang, Jian Li, Jintao Key Lab Of Intelligent Information Processing Institute Of Computing Technology Chinese Academy Of Sciences Beijing100190 China University Of Chinese Academy Of Sciences Beijing100049 China Beijing100190 China Laboratory Of Parallel Software And Computational Science ISCAS Beijing100190 China China

Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. Before they are widely adopted, the fundamental issues of robustness need to be addressed. Along this line, we propose a formal framework to evaluate word-level robustness. First, to study safe regions for a model, we introduce robustness radius which is the boundary where the model can resist any perturbation. As calculating the maximum robustness radius is computationally hard, we estimate its upper and lower bound. We repurpose attack methods as ways of seeking upper bound and design a pseudo-dynamic programming algorithm for a tighter upper bound. Then verification method is utilized for a lower bound. Further, for evaluating the robustness of regions outside a safe radius, we reexamine robustness from another view: quantification. A robustness metric with a rigorous statistical guarantee is introduced to measure the quantification of adversarial examples, which indicates the model's susceptibility to perturbations outside the safe radius. The metric helps us figure out why state-of-the-art models like BERT can be easily fooled by a few word substitutions, but generalize well in the presence of real-world noises. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamic programming

Principled design of translation, scale, and rotation invariant variation operators for metaheuristics

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Tian, Ye Zhang, Xingyi He, Cheng Tan, Kay Chen Jin, Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China Guangdong Provincial Key Laboratory of Braininspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Computer Science University of Surrey Guildford SurreyGU2 7XH United Kingdom

In the past three decades, a large number of metaheuristics have been proposed and shown high performance in solving complex optimization problems. While most variation operators in existing metaheuristics are empirically designed, this paper aims to design new operators automatically, which are expected to be search space independent and thus exhibit robust performance on different problems. For this purpose, this work first investigates the influence of translation invariance, scale invariance, and rotation invariance on the search behavior and performance of some representative operators. Then, we deduce the generic form of translation, scale, and rotation invariant operators. Afterwards, a principled approach is proposed for the automated design of operators, which searches for highperformance operators based on the deduced generic form. The experimental results demonstrate that the operators generated by the proposed approach outperform state-of-theart ones on a variety of problems with complex landscapes and up to 1000 decision variables. © 2021, CC BY.

关键词： Heuristic algorithms

Towards Transferable Adversarial Attacks on Vision Transformers

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wei, Zhipeng Chen, Jingjing Goldblum, Micah Wu, Zuxuan Goldstein, Tom Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Department of Computer Science University of Maryland United States

Vision transformers (ViTs) have demonstrated impressive performance on a series of computer vision tasks, yet they still suffer from adversarial examples. In this paper, we posit that adversarial attacks on transformers should be specially tailored for their architecture, jointly considering both patches and self-attention, in order to achieve high transferability. More specifically, we introduce a dual attack framework, which contains a Pay No Attention (PNA) attack and a PatchOut attack, to improve the transferability of adversarial samples across different ViTs. We show that skipping the gradients of attention during backpropagation can generate adversarial examples with high transferability. In addition, adversarial perturbations generated by optimizing randomly sampled subsets of patches at each iteration achieve higher attack success rates than attacks using all patches. We evaluate the transferability of attacks on state-of-the-art ViTs, CNNs and robustly trained CNNs. The results of these experiments demonstrate that the proposed dual attack can greatly boost transferability between ViTs and from ViTs to CNNs. In addition, the proposed method can easily be combined with existing transfer methods to boost performance. Code is available at https://***/zhipeng-wei/PNA-PatchOut. © 2021, CC BY.

关键词： Iterative methods

Complete b-symbol weight distribution of some irreducible cyclic codes

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhu, Hongwei Shi, Minjia Özbudak, Ferruh Key Laboratory of Intelligent Computing Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Anhui Hefei230601 China Department of Mathematics Institute of Applied Mathematics Middle East Technical University Ankara Turkey

Recently, b-symbol codes are proposed to protect against b-symbol errors in b-symbol read channels. It is an interesting subject of study to consider the complete b-symbol weight distribution of cyclic codes since b-symbol metric is a generalization for Hamming metric. The complete b-symbol Hamming weight distribution of irreducible codes is known in only a few cases. In this paper, we give a complete b-symbol Hamming weight distribution of a class of irreducible codes with two nonzero b-symbol Hamming weights. © 2021, CC0.

关键词：

Gradually Vanishing Gap in Prototypical Network for Unsupervised Domain Adaptation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Shanshan Zhou, Hao Yang, Xun He, Zhenwei Wang, Mengzhu Zhang, Xingyi Wang, Meng The Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information Technology Anhui University Hefei230601 China The Department of Electronic Engineering and Information Science School of Information Science and Technology University of Science and Technology of China Hefei230026 China The College of Computer Science and Engineering Chongqing University of Technology Chongqing400054 China The School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China The School of Artificial Intelligence Hebei University of Technology Tianjin China The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education The School of Computer Science and Technology Anhui University Hefei230601 China

Unsupervised domain adaptation (UDA) is a critical problem for transfer learning, which aims to transfer the semantic information from labeled source domain to unlabeled target domain. Recent advancements in UDA models have demonstrated significant generalization capabilities on the target domain. However, the generalization boundary of UDA models remains unclear. When the domain discrepancy is too large, the model can not preserve the distribution structure, leading to distribution collapse during the alignment. To address this challenge, we propose an efficient UDA framework named Gradually Vanishing Gap in Prototypical Network (GVG-PN), which achieves transfer learning from both global and local perspectives. From the global alignment standpoint, our model generates a domain-biased intermediate domain that helps preserve the distribution structures. By entangling cross-domain features, our model progressively reduces the risk of distribution collapse. However, only relying on global alignment is insufficient to preserve the distribution structure. To further enhance the inner relationships of features, we introduce the local perspective. We utilize the graph convolutional network (GCN) as an intuitive method to explore the internal relationships between features, ensuring the preservation of manifold structures and generating domain-biased prototypes. Additionally, we consider the discriminability of the inner relationships between features. We propose a pro-contrastive loss to enhance the discriminability at the prototype level by separating hard negative pairs. By incorporating both GCN and the pro-contrastive loss, our model fully explores fine-grained semantic relationships. Experiments on several UDA benchmarks validated that the proposed GVG-PN can clearly outperform the SOTA models. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment