检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Guo, Qingbei Wu, Xiao-Jun Kittler, Josef Feng, Zhiquan Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan250022 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Although group convolution operators are increasingly used in deep convolutional neural networks to improve the computational efficiency and to reduce the number of parameters, most existing methods construct their group convolution architectures by a predefined partitioning of the filters of each convolutional layer into multiple regular filter groups with an equal spatial group size and data-independence, which prevents a full exploitation of their potential. To tackle this issue, we propose a novel method of designing self-grouping convolutional neural networks, called SG-CNN, in which the filters of each convolutional layer group themselves based on the similarity of their importance vectors. Concretely, for each filter, we first evaluate the importance value of their input channels to identify the importance vectors, and then group these vectors by clustering. Using the resulting data-dependent centroids, we prune the less important connections, which implicitly minimizes the accuracy loss of the pruning, thus yielding a set of diverse group convolution filters. Subsequently, we develop two fine-tuning schemes, i.e. (1) both local and global fine-tuning and (2) global only fine-tuning, which experimentally deliver comparable results, to recover the recognition capacity of the pruned network. Comprehensive experiments carried out on the CIFAR-10/100 and ImageNet datasets demonstrate that our self-grouping convolution method adapts to various state-of-the-art CNN architectures, (Figure presented) Figure 1: Evolution of group convolutions. (a) Regular convolution. (b) Regular group convolution. (c) Permuting group convolution. (d) Learned group convolution. (d) Self-grouping convolution. Note that white channels represent the ignored input channels, and gray channels indicate the reused input channels. such as ResNet and DenseNet, and delivers superior performance in terms of compression ratio, speedup and recognition accuracy. We demonstrate the ability of SG-CNN

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Future of Electromagnetic Education

Future of Electromagnetic Education

引用

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Wei E.I. Sha Zhixiang Huang College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei China

We share personal views on future of electromagnetic (EM) education in this conference paper. Firstly, several approaches and examples regarding the enhancement of depth and breadth of existing EM courses are presented. Secondly, study and research in interdisciplinary fields correlated to electromagnetics are analyzed. Finally, the training strategies for commercial software use are discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Polar codes with memory

arXiv

引用

arXiv 2019年

作者： Zhou, Wenyue Liu, Qiang Shen, Yifei Zhou, Xiaofeng Zhang, Chuan Xu, Yaohua Li, Liping Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China National Mobile Communications Research Laboratory Southeast University Nanjing China

Polar codes with memory (PCM) are proposed in this paper: a pair of consecutive code blocks containing a controlled number of mutual information bits. The shared mutual information bits of the succeeded block can help the failed block to recover. The underlying polar codes can employ any decoding scheme such as the successive cancellation (SC) decoding (PCM-SC), the belief propagation (BP) decoding (PCM-BP), and the successive cancellation list (SCL) decoding (PCM-SCL). The analysis shows that the packet error rate (PER) of PCM decreases to the order of PER squared while maintaining the same complexity as the underlying polar codes. Simulation results indicate that for PCM-SC, the PER is comparable to (less than 0.3 dB) the stand-alone SCL decoding with two lists for the block length N = 256. The PER of PCM-SCL with L lists can match that of the stand-alone SCL decoding with 2L lists. Two hardware decoders for PCM are also implemented: the in-serial (IS) decoder and the low-latency interleaved (LLI) decoder. For N = 256, synthesis results show that in the worst case, the latency of the PCM LLI decoder is only 16.1% of the adaptive SCL decoder with L = 2, while the throughput is improved by 13 times compared to it. Copyright © 2019, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

New Framework for Code-Mapping-based Reversible Data Hiding in JPEG Images

arXiv

引用

arXiv 2020年

作者： Du, Yang Yin, Zhaoxia Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China Anhui Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China School of Communication & Electronic Engineering East China Normal University Shanghai200241 China

Code mapping (CM) is an efficient technique for reversible data hiding (RDH) in JPEG images, which embeds data by constructing a mapping relationship between the used and unused codes in the JPEG bitstream. This study presents a new framework for designing a CM-based RDH method. First, a new code mapping strategy is proposed to suppress file size expansion and improve applicability. Based on our proposed strategy, the mapped codes are redefined by creating a new Huffman table rather than selecting them from the unused codes in the original Huffman table. The critical issue of designing the CM-based RDH method, that is, constructing code mapping, is converted into a combinatorial optimization problem. This study proposes a novel CM-based RDH method that utilizes a genetic algorithm (GA). The experimental results demonstrate that the proposed method achieves a high embedding capacity with no signal distortion while suppressing file size expansion. Copyright © 2020, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Prediction of SOH and RUL for Lithium-ion Batteries Using Transferable Knowledge Sharing Network

引用

IEEE Transactions on Power Electronics 2025年

作者： Zhong, Kai Liu, Zhihao Tian, Jiaqiang Fan, Chao Li, Mince Wang, Yujie Liu, Xinghua Wang, Peng Anhui University Institutes of Physical Science and Information Technology Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education Hefei230601 China Anhui University School of Eelectrical Engineering and Automation Anhui230039 China Hefei Comprehensive National Science Center Institute of Energy Hefei230601 China University of Science and Technology of China Department of Automation Hefei230027 China Xi'an University of Technology School of Electrical Engineering Xi'an710048 China Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore

The state of health (SOH) and remaining useful life (RUL) prediction of lithium-ion batteries are critical for the safe operation and maintenance optimization of electrical systems. However, existing methods face challenges in generalization ability and prediction accuracy, including the limitations of single-task learning for joint SOH and RUL prediction, sensitivity to complex operating conditions, and the impact of cross-domain data distribution differences. To address these challenges, this paper proposes a dual-representation transferable knowledge sharing network (DRTKSN) to predict SOH and RUL for batteries. The proposed algorithm is based on the framework of multi task learning (MTL) and Transfer Learning. By extracting and fusing dual-representation data features, the framework effectively captures the latent patterns of battery aging characteristics. It employs parameter and network structure sharing mechanisms to enhance the adaptability and generalization of cross-domain features. The proposed model achieves information collaboration between SOH and RUL tasks through a shared network, effectively reducing computational costs and improving prediction accuracy. Experimental results demonstrate that the proposed framework exhibits excellent robustness and transferability in complex degradation scenarios, significantly outperforming baseline models. © 1986-2012 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Optimal puncturing of polar codes with a fixed information set

arXiv

引用

arXiv 2019年

作者： Li, Liping Song, Wei Niu, Kai Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China Key Laboratory of Universal Wireless Communication Ministry of Education Beijing University of Posts and Telecommunications Beijing100876 China

For a given polar code construction, the existing literature on puncturing for polar codes focuses in finding the optimal puncturing pattern, and then re-selecting the information set. This paper devotes itself to find the optimal puncturing pattern when the information set is fixed. Puncturing the coded bits corresponding to the worst quality bit channels, called the worst quality puncturing (WQP), is proposed, which is analyzed to minimize the bit channel quality loss at the punctured positions. Simulation results show that WQP outperforms the best existing puncturing schemes when the information set is fixed. Copyright © 2019, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Adapter RGBT Tracking

Multi-Adapter RGBT Tracking

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Cheng Long Li Andong Lu Ai Hua Zheng Zhengzheng Tu Jin Tang Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Key Laboratory of Industrial Image Processing and Analysis of Anhui Province Hefei China

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

The task of RGBT tracking aims to take the complementary advantages from visible spectrum and thermal infrared data to achieve robust visual tracking, and receives more and more attention in recent years. Existing works focus on modality-specific information integration by introducing modality weights to achieve adaptive fusion or learning robust feature representations of different modalities. Although these methods could effectively deploy the modality-specific properties, they ignore the potential values of modality-shared cues as well as instance-aware information, which are crucial for effective fusion of different modalities in RGBT tracking. In this paper, we propose a novel Multi-Adapter convolutional Network (MANet) to jointly perform modality-shared, modality-specific and instance-aware feature learning in an end-to-end trained deep framework for RGBT tracking. We design three kinds of adapters within our network. In a specific, the generality adapter is to extract shared object representations, the modality adapter aims at encoding modality-specific information to deploy their complementary advantages, and the instance adapter is to model the appearance properties and temporal variations of a certain object. Moreover, to reduce computational complexity for real-time demand of visual tracking, we design a parallel structure of generic adapter and modality adapter. Extensive experiments on two RGBT tracking benchmark datasets demonstrate the outstanding performance of the proposed tracker against other state-of-the-art RGB and RGBT tracking algorithms.

关键词： Adaptation models Robustness Target tracking Feature extraction Visualization Task analysis

来源：评论

学校读者我要写书评

暂无评论

A New Free-Standing Aqueous Zinc-Ion Capacitor Based on MnO2–CNTs Cathode and MXene Anode

引用

Nano-Micro Letters 2019年第4期11卷 227-238页

作者： Siliang Wang Qiang Wang Wei Zeng Min Wang Limin Ruan Yanan Ma Key Laboratory of Intelligent Computing and Signal Processing Ministry of EducationAnhui UniversityNo.3 Feixi RoadHefei 230039Anhui ProvincePeople’s Republic of China National Engineering Research Center for Agro-Ecological Big Data Analysis and Application School of Electronics and Information EngineeringAnhui UniversityNo.111 Jiulong RoadHefei 230601Anhui ProvincePeople’s Republic of China School of Sciences Hubei University of Automotive TechnologyNo.167 Checheng West RoadShiyan 442002Hubei ProvincePeople’s Republic of China

Restricted by their energy storage mechanism,current energy storage devices have certain drawbacks,such as low power density for batteries and low energy density for ***,the nearest ion capacitors,such as lithium-ion and sodium-ion capacitors containing battery-type and capacitor-type electrodes,may allow achieving both high energy and power *** the inspiration,a new zinc-ion capacitor(ZIC)has been designed and realized by assembling the free-standing manganese dioxide-carbon nanotubes(MnO2-CNTs)battery-type cathode and MXene(Ti3C2Tx)capacitortype anode in an aqueous *** ZIC can avoid the insecurity issues that frequently occurred in lithium-ion and sodium-ion capacitors in organic *** expected,the ZIC in an aqueous liquid electrolyte exhibits excellent electrochemical performance(based on the total weight of cathode and anode),such as a high specific capacitance of 115.1 F g?1(1 mV s?1),high energy density of 98.6 Wh kg?1(77.5 W kg?1),high power density of 2480.6 W kg?1(29.7 Wh kg?1),and high capacitance retention of^83.6%of its initial capacitance(15,000 cycles).Even in an aqueous gel electrolyte,the ZIC also exhibits excellent *** work provides an essential strategy for designing next-generation high-performance energy storage devices.

关键词： Energy storage Zinc-ion capacitor Battery-type and capacitor-type electrodes MXene Electrochemical performance

来源：评论

学校读者我要写书评

暂无评论

Automated Selection of Evolutionary Multi-objective Optimization Algorithms

Automated Selection of Evolutionary Multi-objective Optimiza...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Ye Tian Shichen Peng Tobias Rodemann Xingyi Zhang Yaochu Jin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Honda Research Institute Europe Offenbach/Main Germany Department of Computer Science University of Surrey Guildford Surrey United Kingdom

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

In the last two decades, many evolutionary algorithms have shown promising performance in solving a variety of multi-objective optimization problems (MOPs). Since there does not exist an evolutionary algorithm having the best performance on all the MOPs, it is unreasonable to use a single evolutionary algorithm to tackle all the MOPs. Since many real-world MOPs are computationally expensive, selecting the best evolutionary algorithm from multiple candidates via empirical comparisons is also impractical. To address the above issues, this paper proposes an automated algorithm selection method for choosing the most suitable evolutionary algorithm for a given MOP. The proposed method establishes a predictor based on the performance of a set of candidate evolutionary algorithms on multiple benchmark MOPs, where the inputs of the predictor are the explicit and implicit features of an MOP, and the output is the index of the evolutionary algorithm having the best performance on the MOP. Experimental results indicate that the evolutionary algorithm suggested by the proposed method is highly competitive among all the candidate evolutionary algorithms, demonstrating the practical value of the proposed method for engineers to select an evolutionary algorithm for their applications.

关键词： Evolutionary computation Benchmark testing Feature extraction Optimization Prediction algorithms Convergence Linear programming

来源：评论

学校读者我要写书评

暂无评论

First-principle calculation of Chern number in gyrotropic photonic crystals

arXiv

引用

arXiv 2020年

作者： Zhao, Ran Xie, Guo-Da Chen, Menglin L.N. Lan, Zhihao Huang, Zhixiang Sha, Wei E.I. Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230039 China Key Laboratory of Electromagnetic Environmental Sensing Department of Education of Anhui Province Hefei230039 China Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong Department of Electronic and Electrical Engineering University College London United Kingdom Key Laboratory of Micro-nano Electronic Devices and Smart Systems of Zhejiang Province College of Information Science Electronic Engineering Zhejiang University Hangzhou310027 China

As an important figure of merit for characterizing the quantized collective behaviors of the wavefunction, Chern number is the topological invariant of quantum Hall insulators. Chern number also identifies the topological properties of the photonic topological insulators (PTIs), thus it is of crucial importance in PTI design. In this paper, we develop a first principle computatioal method for the Chern number of 2D gyrotropic photonic crystals (PCs), starting from the Maxwell’s equations. Firstly, we solve the Hermitian generalized eigenvalue equation reformulated from the Maxwell’s equations by using the full-wave finite-difference frequency-domain (FDFD) method. Then the Chern number is obtained by calculating the integral of Berry curvature over the first Brillouin zone. Numerical examples of both transverse-electric (TE) and transverse-magnetic (TM) modes are demonstrated, where convergent Chern numbers can be obtained using rather coarse grids, thus validating the efficiency and accuracy of the proposed method. Copyright © 2020, The Authors. All rights reserved.

关键词： Photonic crystals

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：