检索结果-内蒙古大学图书馆

Frequency Information Matters for image Matting 1

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Luo, Rongsheng Wei, Rukai Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Wuhan National Laboratory For Optoelectronics Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9783031476341

ISBN: (纸本)9783031476334

image matting aims to estimate the opacity of foreground objects in order to accurately extract them from the background. Existing methods are only concerned with RGB features to obtain alpha mattes, limiting the perception of local tiny details. To address this issue, we introduce frequency information as an auxiliary clue to accurately distinguish foreground boundaries and propose the Frequency Matting Network (FMN). Specifically, we deploy a Frequency Boosting Module (FBM) in addition to the Discrete Cosine Transform (DCT) to extract frequency information from input images. The proposed FBM is a learnable component that empowers the model to adapt to complex scenarios. Furthermore, we design a Domain Aggregation Module (DAM) to effectively fuse frequency features with RGB features. With the assistance of frequency clues, our proposed FMN achieves significant improvements in matting accuracy and visual quality compared with state-of-the-art methods. Extensive experiments on Composition-1k and Distinctions-646 datasets demonstrate the superiority of introducing frequency information for image matting. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Multi-scale convolutional neural networks for brain disease diagnosis

Multi-scale convolutional neural networks for brain disease ...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Hu, Zhongyi Gao, Libin Tong, Yinsheng Lu, Xingjin Li, Rui Xiao, Lei Li, Zuoyong Wenzhou University College of Computer Science and Aritificial Intelligence Wenzhou325035 China Key Laboratory of Intelligent Image Processing and Analysis Wenzhou China Minjiang University College of Computer and Control Engineering Fuzhou China

ISBN: (纸本)9798350337488

The brain is the most sophisticated and complex organ in the human body. Nowadays, diagnosing complex and diverse brain diseases is a hot topic. Alzheimer's Disease (AD), Autism Spectrum Disorder (ASD), and others are common brain diseases. With the increased usage of Artificial Intelligence (AI) in medical image analysis, the endeavor to make AI comprehend brain images for assisting doctors in making objective diagnoses of brain diseases has gained considerable attention. Resting-state functional magnetic resonance imaging (rs-fMRI) is a widely used tool for diagnosing and analyzing brain ***, the Pearson correlation coefficient (PCC) method constructs a dynamic functional connectivity (dFC) network using a fixed window size. However, this method has limitations as it is challenging to extract potential high-level features from the dFC and determine local feature relevance. This paper presents a method for constructing dFC based on multi-scale sliding windows and proposes Multi-scale Convolutional Neural Networks (MsCNN) for learning and analyzing dFC at various scales. Finally, a deep fusion of features learned at different scales is employed for the diagnostic classification of brain *** to the rs-fMRI dataset from ADNI, the classification accuracy was 84.0% for eMCI/lMCI, 84.4% for lMCI/AD, and 58.4% for NC/eMCI/lMCI/AD. Applied to rs-fMRI data from ABIDE, the accuracy was 74.7% for ASD/NC. The proposed method exhibits robust classification performance and introduces a new approach to diagnosing other brain diseases. © 2023 IEEE.

关键词： Brain diseases Classification Diagnostic Multi-scale convolutional neural networks (MsCNN) Resting-state functional magnetic resonance imaging (rs-fMRI)

来源：评论

学校读者我要写书评

暂无评论

Cooperative online schedule of interconnected data center microgrids with shared energy storage

引用

ENERGY 2023年 285卷

作者： Xiao, Jiang-Wen Yang, Yan-Bing Cui, Shichang Wang, Yan-Wu Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Adv Electromagnet Technol Wuhan 430074 Peoples R China

The rapid increasing of data centers calls for an efficient method to reduce high operation costs and carbon emissions. This paper proposes a cooperative online schedule framework for local interconnected data centers considering shared energy storage. A time-average optimization problem is built to reduce the overall operation cost with essential operational constraints. Multiple randomness and the temporal coupling constraints of energy system levels make it challenging to solve the stochastic problem. Adapting the Lyapunov optimization theory with relaxation and perturbation technique, an online algorithm is proposed to find an acceptable solution to the problem to achieve both good service coordination and efficient energy coordination. The algorithm does not require prediction of random parameters, and has a fast convergence rate. Especially, the theoretical conditions for convergence and the distance between the acceptable and real optimal solution are derived in a closed form. Simulation studies show that the algorithm can effectively reduce operation cost of data centers, carbon emissions, and dependence on the main grid.

关键词： Data center Service coordination Energy coordination Energy storage sharing Online optimization

来源：评论

学校读者我要写书评

暂无评论

controllability of Multi-Agent Systems With Cartesian Product Networks

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2024年第2期71卷 838-850页

作者： Liu, Bo Hu, Mengjie Huang, Junjie Chen, Yin Su, Housheng Minzu Univ China Sch Informat Engn Minist Educ Key Lab Intelligent Anal & Secur Governance Ethn Beijing 100081 Peoples R China Inner Mongolia Univ Sch Math Sci Hohhot 010021 Peoples R China Univ Strathclyde Dept Elect & Elect Engn Glasgow G1 1XW Scotland Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Autonomous Intelligent Unmanned Syst Engn Res Ctr Image Proc & Intelligent Control Key LabEduc Min Wuhan 430074 Peoples R China

This paper investigates the controllability of Cartesian product networks consisting of smaller factor networks via Cartesian product of graphs, reveals the controllability relationship between the Cartesian product network and its factor networks, and presents a theoretic analysis framework for a Cartesian product network by the eigenvalue-eigenvector pairs of factor networks. A sufficient and necessary condition for the controllability of Cartesian product networks is established based on the PBH test conjoining with the properties of Kronecker products, which is an important theoretical analysis tool to analyze the controllability of product networks. This work will help us to understand the cooperative mechanisms of the system controllability, network topology and nodal dynamics, and provide a theory and technical guidance to build a more reasonable large-scale network model and design an effective control scheme for a real networked system.

关键词： controllability Network topology Topology Laplace equations Multi-agent systems Analytical models Eigenvalues and eigenfunctions multi-agent systems Cartesian product networks eigenvalue-eigenvector pair

来源：评论

学校读者我要写书评

暂无评论

Adaptive multiobjective evolutionary algorithm for large-scale transformer ratio error estimation

引用

MEMETIC COMPUTING 2022年第2期14卷 237-251页

作者： Huang, Changwu Li, Lianghao He, Cheng Cheng, Ran Yao, Xin Southern Univ Sci & Technol Dept Comp Sci & Engn Guangdong Prov Key Lab Brain Inspired Intelligent Shenzhen 518055 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Informat Proc & Intelligent Control Wuhan 430074 Peoples R China

As a typical large-scale multiobjective optimization problem extracted from real-world applications, the voltage transformer ratio error estimation (TREE) problem is challenging for existing evolutionary algorithms (EAs). Due to the large number of decision variables in the problems, existing algorithms cannot solve TREE problems efficiently. Besides, most EAs may fail to balance the convergence enhancement and diversity maintenance, leading to the trap in local optima even at the early stage of the evolution. This work proposes an adaptive large-scale multiobjective EA (LSMOEA) to handle the TREE problems with thousands of decision variables. Generally, multiple efficient offspring generation and environmental selection strategies selected from some representative LSMOEAs are included. Then an adaptive selection strategy is used to determine which offspring generation and environmental selection operators are used in each generation of the evolution. Thus, the search behavior of the proposed algorithm evolves along with the evolution process, the balance between convergence and diversity is maintained, and the proposed algorithm is expected to solve TREE problems effectively and efficiently. Experimental results show that the proposed algorithm achieves significant performance improvement due to the adaptive selection of different operators, providing an effective and efficient approach for large-scale optimization problems.

关键词： Large-scale optimization Multiobjective optimization Adaptive operator selection Voltage transformer ratio error estimation

来源：评论

学校读者我要写书评

暂无评论

Elevating the acceptable cost threshold for solid oxide cells: A case study on refinery decarbonization

引用

APPLIED ENERGY 2024年 373卷

作者： Chi, Yingtian Lin, Jin Li, Peiyang Yu, Zhipeng Mu, Shujun Li, Xi Song, Yonghua Tsinghua Univ Dept Elect Engn State Key Lab Power Syst Operat & Control Beijing 10084 Peoples R China Tsinghua Sichuan Energy Internet Res Inst Chengdu 610213 Peoples R China Natl Inst Clean & Low Carbon Energy Beijing 102211 Peoples R China Huazhong Univ Sci & Technol Educ Minist Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Univ Macau State Key Lab Internet Things Smart City Zhuhai 999078 Macao Peoples R China

Solid oxide cells (SOCs) have multiple advantages, including high efficiency and reversibility, but they are still characterized by low maturity and high investment costs. Their cost-effectiveness remains to be evaluated from an investment viewpoint for their ability to compete with mature and low-cost alkaline electrolysis (ALK). To this end, this study considers the application of SOC in the production of green hydrogen and electricity to decarbonize a refinery plant, a potential application scenario favoring the efficient SOC technology due to its requirement for stable operation and lack of inexpensive renewable electricity. A planning model is proposed to optimize the system configuration and minimize the system cost, based on which the acceptable cost threshold enabling SOC to compete with ALK is determined, defined as the unit investment cost of SOC at which substituting ALK with SOC will not increase the system cost. The results show that the high efficiency of SOC reduces the investment in renewable generation to fulfill the hydrogen demand, and its reversibility eliminates additional hydrogen-to-electricity and ammonia-to-electricity investments to realize long-duration energy storage. These factors enable SOC to compete with ALK at an investment cost of 11.6 CNY/W, three times the investment cost of ALK. Moreover, when SOC and ALK are combined, SOC can operate at a capacity factor above 75%, 1.5 times the capacity factor of ALK. This further boosts the threshold to 20.4 CNY/W, revealing that SOC and ALK, instead of competing, can work together to lower the system cost and drive commercialization of the emerging SOC technology.

关键词： Solid oxide cell Acceptable cost threshold Cost effectiveness Refinery decarbonization Long-duration energy storage Ammonia

来源：评论

学校读者我要写书评

暂无评论

An Aggregated Convolutional Transformer Based on Slices and Channels for Multivariate Time Series Classification

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2023年第3期7卷 768-779页

作者： Wu, Yupeng Lian, Cheng Zeng, Zhigang Xu, Bingrong Su, Yixin Wuhan Univ Technol Sch Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan Peoples R China

Convolutional neural network has achieved remarkable success, and has excellent local feature extraction ability. Similarly, Transformer has been developed markedly in recent years, achieving excellent representation capabilities in terms of global features, which has aroused heated discussions. In terms of multivariate time series classification, most previous networks had convolution and long and short-term memory structures. This paper innovatively proposes a combination of Transformer-encoder and convolutional structures, which we refer to as the Multivariate time series classification Convolutional Transformer Network (MCTNet). The different advantages of convolutional neural network and self-attention are used to capture potential deep information in multivariate time series more accurately. The Transformer is considered to be data-hungry, and combined with the induction bias of the convolutional neural network to solve this problem, early features are extracted through the convolutional layers, and the both squeeze and excitation convolution encoder (BC-Encoder) structure is proposed. Attentional prototype learning is also used to mitigate the limited label problem. Moreover, a new network design that focuses on slices and channels is proposed, moving beyond the concept that the use of Transformer will require many parameters. Experimental results from 26 datasets of the well-known multivariate time series archive UEA show that the performance of our model is better than that of most state-of-the-art models.

关键词： Time series analysis Transformers Convolution Feature extraction Deep learning Convolutional neural networks Prototypes Convolutional Neural Network Transformer Encoder Slices and Channels Multivariate Time Series Classification

来源：评论

学校读者我要写书评

暂无评论

Discrete-Time controllability of Cartesian Product Networks

引用

IEEE TRANSACTIONS ON SIGNAL AND INFORMATION processing OVER NETWORKS 2024年 10卷 868-880页

作者： Liu, Bo Hu, Mengjie Huang, Junjie Zhang, Qiang Chen, Yin Su, Housheng Minzu Univ China Sch Informat Engn Minist Educ Key Lab Intelligent Anal & Secur Gover Beijing 100081 Peoples R China Inner Mongolia Univ Sch Math Sci Hohhot 010021 Peoples R China Univ Strathclyde Dept Elect & Elect Engn Glasgow City G1 1XW Scotland Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Educ Mini Autonomous Intelligent Unmanned Syst Engn Res Ctr Wuhan Peoples R China

This work studies the discrete-time controllability of a composite network formed by factor networks via Cartesian products. Based on the Popov-Belevitch-Hautus test and properties of Cartesian products, we derive the algebra-theoretic necessary and sufficient conditions for the controllability of the Cartesian product network (CPN), which is devoted to carry out a comprehensive study of the intricate interplay between the node-system dynamics, network topology and the controllability of the CPN, especially the intrinsic connection between the CPN and its factors. This helps us enrich and perfect the theoretical framework of controllability of complex networks, and gives new insight into designing a valid control scheme for larger-scale composite networks.

关键词： controllability Complex networks Observability Network systems Laplace equations Information processing Topology System performance Stability analysis Power system dynamics Cartesian product networks composite networks

来源：评论

学校读者我要写书评

暂无评论

CRNet: A Fast Continual Learning Framework With Random Theory

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第9期45卷 10731-10744页

作者： Li, Depeng Zeng, Zhigang Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Inst Artificial Intelligence Wuhan 430074 Peoples R China Minist China Key Lab Image Proc & Intelligent Control Educ Wuhan 430074 Peoples R China

Artificial neural networks are prone to suffer from catastrophic forgetting. Networks trained on something new tend to rapidly forget what was learned previously, a common phenomenon within connectionist models. In this work, we propose an effective and efficient continual learning framework using random theory, together with Bayes' rule, to equip a single model with the ability to learn streaming data. The core idea of our framework is to preserve the performance of old tasks by guiding output weights to stay in a region of low error while encountering new tasks. In contrast to the existing continual learning approaches, our main contributions concern (1) closed-formed solutions with detailed theoretical analysis;(2) training continual learners by one-pass observation of samples;(3) remarkable advantages in terms of easy implementation, efficient parameters, fast convergence, and strong task-order robustness. Comprehensive experiments under popular image classification benchmarks, FashionMNIST, CIFAR-100, and imageNet, demonstrate that our methods predominately outperform the extensive state-of-the-art methods on training speed while maintaining superior accuracy and the number of parameters, in the class incremental learning scenario. Code is available at https://***/toil2sweet/CRNet.

关键词： Catastrophic forgetting continual learning incremental learning randomized learning technique random vector functional-link network

来源：评论

学校读者我要写书评

暂无评论

Improved genetic algorithm based on time windows decomposition for solving resource-constrained project scheduling problem

引用

AUTOMATION IN CONSTRUCTION 2022年第0期142卷

作者： Hua, Zhengming Liu, Zhenyuan Yang, Lijing Yang, Liu Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist Image Proc & Intelligent Control Key Lab Wuhan 430074 Peoples R China

The resource-constrained project scheduling problem (RCPSP) is one of the project scheduling problems which are widely used in construction and many industrial disciplines. The challenge of the problem is to design some appropriate search mechanism for finding solutions in feasible space. An improved genetic algorithm based on time window decomposition is proposed in this paper. Three derivation methods are applied to increase population diversity. The sampling count allocation strategy and the use of destructive lower bounds improve the search efficiency. The computational experiments on PSPLIB show that the proposed approach is more effective than that only using the decomposition mechanism and is competitive in solving two real-life cases. This research illustrates that continuously changing the search subspaces has potential advantages, which may be useful for studying RCPSP using other evolutionary algorithms in future. Some other better results may be obtained by using machine learning methods to flexibly determine the sampling times for each individual.

关键词： Project scheduling Resource constrained Decomposition-based approach Genetic algorithm Extended serial scheduling scheme

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：