检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Power, Electronics and computer Applications, ICPECA 2022

作者： Wu, Wei Feng, Huibin Junejo, Naveed Ur Rehman Qiu, Yuquan Yan, Jiaquan College of Computer and Control Engineering Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China University of Lahore Department of Computer Engineering Lahore Pakistan

ISBN: (纸本)9781665442763

Automatic recognition of marine mammals plays a significant role in the protection of endangered marine species, generally utilizing their vocalizations. In this paper, we propose a novel visual feature extraction approach for whale and dolphin signals incorporating variational mode decomposition (VMD) and Hilbert transform (VMD-HT) to construct the high-resolution time-frequency signatures and using gray level co-occurrence matrix (GLCM) to extort image features. Firstly, the objected signals are decomposed by VMD algorithm into multiple intrinsic mode functions (IMFs), which can capture local frequency features precisely. Secondly, the time-frequency signature of the objected signal with high resolution is constructed by linear superposition operation of each IMF time-frequency image depicted through Hilbert transform (HT). Thirdly, the image features are extracted using GLCM. Eventually, support vector machine (SVM) is adopted to validate the classification performance of the proposed method. The experimental results verify that the resolution improvement of time-frequency image attains the correct recognition rate and the proposed method accuracy is higher than the compared method about 11.11% © 2022 IEEE.

关键词： Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Towards Label-Efficient Deep Learning for Myopic Maculopathy Classification 1

引用

Myopic Maculopathy Analysis Challenge, MMAC 2023, which was a part of the 26th International Conference on Medical Image Computing and computer Assisted Intervention, MICCAI 2023

作者： Hou, Junlin Xu, Jilan Xiao, Fan Zhang, Bo Xu, Yiqian Zhang, Yuejie Zou, Haidong Feng, Rui School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China Department of Ophthalmology Shanghai General Hospital School of Medicine Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783031548574

ISBN: (纸本)9783031548567

Myopic Maculopathy is the leading cause of legal blindness in patients with pathologic myopia. Automated myopic maculopathy diagnosis is of vital importance to early treatment and progression slowdown. However, the scarcity of labeled fundus images with myopic maculopathy makes it challenging to improve diagnostic performance via deep learning models. In this paper, we construct a label-efficient deep learning framework for myopic maculopathy classification. In specific, we exploit two categories of pre-training methods, i.e., vision-language pre-training and self-supervised visual representation learning, to alleviate the overfitting problem caused by the limited number of training images. Moreover, we adopt a semi-supervised learning technique, namely pseudo labeling, to leverage a large number of unlabeled fundus images from external datasets. We also investigate the impact of other key components in model training for better performance, including backbone architecture, input resolution, and loss function. Our method is evaluated in the MICCAI 2023 Myopic Maculopathy Analysis Challenge (MMAC). Among 17 participating teams, our ensembled model ranked 1st on the leaderboard with an average score of 0.8752. The code will be publicly available at https://***/FDU-VTS/MMAC. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Orientation-Independent Chinese Text Recognition in Scene Images

arXiv

引用

arXiv 2023年

作者： Yu, Haiyang Wang, Xiaocong Li, Bin Xue, Xiangyang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China

Scene text recognition (STR) has attracted much attention due to its broad applications. The previous works pay more attention to dealing with the recognition of Latin text images with complex backgrounds by introducing language models or other auxiliary networks. Different from Latin texts, many vertical Chinese texts exist in natural scenes, which brings difficulties to current state-ofthe-art STR methods. In this paper, we take the first attempt to extract orientation-independent visual features by disentangling content and orientation information of text images, thus recognizing both horizontal and vertical texts robustly in natural scenes. Specifically, we introduce a Character Image Reconstruction Network (CIRN) to recover corresponding printed character images with disentangled content and orientation information. We conduct experiments on a scene dataset for benchmarking Chinese text recognition, and the results demonstrate that the proposed method can indeed improve performance through disentangling content and orientation information. To further validate the effectiveness of our method, we additionally collect a Vertical Chinese Text Recognition (VCTR) dataset. The experimental results show that the proposed method achieves 45.63% improvement on VCTR when introducing CIRN to the baseline model. Copyright © 2023, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Self-Training with Contrastive Learning for Adversarial Domain Adaptation

Self-Training with Contrastive Learning for Adversarial Doma...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Shanshan Wang Minbin Hu Xingyi Zhang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China School of Computer Science and Technology Anhui University Hefei China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Unsupervised domain adaptation (UDA) aims to transfer the knowledge learned from the labeled source domain to the unlabeled target domain. Traditional methods often focus on minimizing the distribution gap between feature spaces of the two domains to achieve domain-invariant representations. However, this approach may not fully leverage the inherent class-specific information and could adversely affect decision boundaries in the target domain. In this paper, we introduce an adversarial contrastive self-training framework. The model integrates both intra-class and inter-class domain differences for better alignment between the source and target domains. Initially, we augment target domain samples using Fourier transformations, obtaining reliable samples and pseudo-labels through self-training. We then employ intra-domain contrastive learning on the reliable samples and pseudo-labels, alongside labeled source domain samples, to achieve intra-domain compactness. Finally, we utilize adversarial learning to achieve global alignment. This comprehensive approach ensures improved adaptation performance while also addressing the limitations of previous methods.

关键词： Adaptation models Neural networks Contrastive learning Adversarial machine learning Reliability

来源：评论

学校读者我要写书评

暂无评论

Weight Perturbation as Defense against Adversarial Word Substitutions

Weight Perturbation as Defense against Adversarial Word Subs...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Xu, Jianhan Li, Linyang Zhang, Jiping Zheng, Xiaoqing Chang, Kai-Wei Hsieh, Cho-Jui Huang, Xuanjing School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing China Department of Computer Science University of California Los Angeles United States

The existence and pervasiveness of textual adversarial examples have raised serious concerns to security-critical applications. Many methods have been developed to defend against adversarial attacks for neural natural language processing (NLP) models. Adversarial training is one of the most successful defense methods by adding some random or intentional perturbations to the original input texts and making the models robust to the perturbed examples. In this study, we explore the feasibility of improving the adversarial robustness of NLP models by performing perturbations in the parameter space rather than the input feature space. The weight perturbation helps to find a better solution (i.e., the values of weights) that minimizes the adversarial loss among other feasible solutions. We found that the weight perturbation can significantly improve the robustness of NLP models when it is combined with the perturbation in the input embedding space, yielding the highest accuracy on both clean and adversarial examples across different datasets. © 2022 Association for Computational Linguistics.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Wideband Bonding Wire Compensation Structure Design and Electric-thermal Coupling Analysis for Chip Package

Wideband Bonding Wire Compensation Structure Design and Elec...

引用

Asia-Pacific Conference on Microwave

作者： Pei Ge Hao-Ran Zhu Yu Fa Sun School of Electronic Science and Engineering Anhui University An Hui China Key Laboratory of Intelligent Computing and Signal Processing of Heifei Anhui University An Hui China

ISBN: (数字)9798350363548

ISBN: (纸本)9798350363555

In this paper, a novel wire-bonding and BGA package is applied to a highly integrated MMIC. The novel compensation component of the bonding wires is composed of a capacitive strip-line and an inductive via below the transmission line. In addition, A large amount of heat is generated by high-intensity chip, leading to a decrease in transmission performance. Multilayered system in package is designed to improve the heat dissipation capability of chip. Multi physics field simulation is introduced to verify the effectiveness of the design. The proposed multilayered system in package is made using LTCC process and loaded with low noise amplifier chip. The return loss of the is better than 10dB and the gain is greater than 10dB in the frequency range of DC-20GHz.

关键词： Low-noise amplifiers System-in-package Power transmission lines Wires Noise Routing Microwave amplifiers Bonding Physics Wideband

来源：评论

学校读者我要写书评

暂无评论

Accuracy Prediction of Negative Surveys 4

Accuracy Prediction of Negative Surveys

引用

4th International Conference on Data Intelligence and Security, ICDIS 2022

作者： Liu, Ran Yu, Fengzhen Guo, Mingqiang School of Computer Science China Geoscience University Hubei Key Laboratory of Intelligent Geo-Information Processing Wuhan China School of Computer Science China Geoscience University Wuhan China

ISBN: (数字)9781665459686

ISBN: (纸本)9781665459686

Inspired by the artificial immune system, the negative survey is a privacy protection technology for multiple choice questions, with the advantage of cost-effective and decentralization. The current performance evaluation for the reconstruction of the negative survey relies on the original positive survey. The reconstructed results are compared with the original ones. The original positive survey, however, is unidentified, and the collector only owns negative surveys in practice. In this paper, we propose to extend current performance evaluation to address real-world applications. Based on our new model, we investigate the relationship between error and the probability transform matrix in detail. We show that in many cases, the reconstructed positive survey is accurate or inaccurate depending on the negative survey and the probability transform matrix. The feasibility of this method is experimentally verified by simulation of a synthetic data set. © 2022 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

A Novel Transformed Nested Array with Enhanced DOFs Based on Sum-Difference Coarray

A Novel Transformed Nested Array with Enhanced DOFs Based on...

引用

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

作者： Wei Xin Yingsong Li Harbin Engineering University China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China

Sum-difference driven coarray (SDCA) was paid great attention in array-signal-processing (ASP). By considering SDCA, the degrees of freedom (DOFs) for sparse arrays can be further improved. Here, a new transformed nested-array (TNA) is constructed, which reduces the element redundancy via rearranging the density of sub-arrays of the constructed new TNA. Compared to former TNAs, the constructed TNA gets higher DOFs and maximization signals, numerical simulation are given for getting its superior behaviors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic Array Fault Detection Based on Manifold Learning and Neural Network 5

Photovoltaic Array Fault Detection Based on Manifold Learnin...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Wang, Kai Zhong, Yanru Luo, Xiaonan Guilin University of Electronic Science and Technology Guangxi Key Laboratory of Intelligent Processing of Computer Images and Graphic Guilin China Guilin University of Electronic Science and Technology Satellite Navigation Positioning and Location Services National and Local Joint Engineering Research Center Guilin China

ISBN: (纸本)9798350373820

This paper endeavors to devise an ingenious methodology rooted in artificial intelligence, which, in turn, can be effectively employed to identify sundry categories of faults that are closely associated with photovoltaic arrays. This novel approach amalgamates the manifold learning algorithm with a formidable multilayer perceptron neural network (MLP). Intriguingly, it substantiates that the initial reduction in data dimensionality is achieved through the remarkable Isomap algorithm. Consequently, this compressed data is seamlessly channeled into the MLP, thereby yielding remarkable outcomes concerning fault detection. To validate and scrutinize the aforementioned proposition, a quintessential circuit representing a photovoltaic array is initially simulated utilizing the venerable Matlab/Simulink tool. During this simulation, an extensive corpus of both normal and faulty data is meticulously generated. Subsequently, the manifold learning algorithm is artfully applied to drastically diminish the dimensionality of this extensive dataset The resultant compressed data is then deftly fed into the MLP, allowing it to discern the salient characteristics pertaining to the sundry fault types. Through incessant iterations of intensive training, these faults can be astutely detected and discerned with remarkable accuracy. The results conclusively demonstrate the efficacy of combining manifold-based learning and multilayer perceptron neural network in detecting faults in photovoltaic arrays. The proposed method achieves high precision and effectiveness, surpassing the traditional approach by 2.52%. © 2024 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

DD-Net: Dynamic Network Architecture for Optimized Curve Segmentation and Reduce Computational Redundancy 27th

DD-Net: Dynamic Network Architecture for Optimized Curve Seg...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Cao, Yunxiang Chen, Li Wang, Yubo Feng, Zhida Tian, Jing School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China Institute of Systems Science National University of Singapore Singapore Singapore

ISBN: (纸本)9783031783821

Curvilinear Structure segmentation has numerous applications in various fields, including providing a better understanding of defects such as cracks on roads or walls, thereby assessing the structural safety of buildings. Numerous curve segmentation methods based on Convolutional Neural Networks(CNN) have been developed in recent years. However, preserving feature integrity remains a challenge. To address this issue, this paper introduces a double dynamic network, called DD-Net, which consists of a dynamic structure for training and dynamic masking for inference. Firstly, to enhance the nonlinearity of the model, a paradigm to auto-adjust the CNN structure via a trainable module is formed for better fine-grained feature extraction. This dynamic structure (DS) paradigm enables a trade-off to extract or discard the feature data in the model training. Due to the data heterogeneity between the training and inference data, models may contain some useless nodes that are less effective during inference. The dynamic masking (DM) is proposed to omit the useless nodes based on the score difference between the train and inference feature statistics, thereby reducing redundant computations. To further improve the model’s performance on thin-curve segmentation and to preserve feature integrity, we introduce a non-curve suppression (NCS) module. This module focuses on background information while considering foreground prediction to address noisy conditions. The experimental results show that our DD-Net achieves promising results on three benchmark datasets and outperforms state-of-the-art curve segmentation models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

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：