检索结果-内蒙古大学图书馆

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Meng, Xinhong Hu, Meng Ye, Hailiang Li, Ming Cao, Feilong School of Electronics and Communication Engineering Quanzhou University of Information Engineering Quanzhou362000 China College of Sciences China Jiliang University Hangzhou310018 China Zhejiang Normal University Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Jinhua321004 China

ISBN: (纸本)9798350303780

This paper presents a global-and-local convolutional neural network architecture (GLCNN) for point cloud classification tasks. Its core lies in the construction of a manifold learning module and a global-and-local convolution structure (GLConv). The former projects the point cloud into the two-dimensional planes in different views to learn sufficient low-dimensional information. Then the global feature learning is obtained by constructing attention mechanisms from Transformer and local feature learning is captured by convolution and pooling operators, thereby forming the GLConv by fusing these two features to further explore the long-distance dependency of point clouds. Experiments show that GLCNN has excellent performance on two public datasets. Particularly, the overall accuracy and class average accuracy of the ModelNet40 dataset reached 93.3% and 90.8%, respectively. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Phase Engineering of Nanomaterials: Metal Nanomaterials

引用

Chemical Research in Chinese Universities 2025年 1-44页

作者： Chen, Ye Liu, Jiawei Yun, Qinbai Cheng, Hongfei Cui, Xiaoya Fan, Zhanxi Fu, Lei Gao, Chuanbo Ge, Jingjie Ge, Yiyao Guo, Shaojun Han, Sumei Hong, Xun Huang, Bolong Huang, Hongwen Huang, Xiaoqing Liao, Xiaozhou Ling, Chongyi Liu, Dong Lu, Yang Lu, Qipeng Niu, Wenxin Saleem, Faisal Shao, Minhua Shao, Qi Shi, Zhenyu Song, Li Sun, Shouheng Tilley, Richard D. Wang, Deli Wang, An-Liang Wang, Jinlan Xi, Pinxian Xia, Younan Xiong, Yujie Yang, Nailiang Yin, Pengfei Yu, Yifu Zhang, Zhicheng Zhou, Meng Zhu, Ye Zhang, Hua Department of Chemistry The Chinese University of Hong Kong Shatin New Territories 999077 Hong Kong Hong Kong Branch of National Precious Metals Material Engineering Research Center (NPMM) City University of Hong Kong 999077 Hong Kong Department of Chemical and Biological Engineering & Energy Institute The Hong Kong University of Science and Technology 999077 Hong Kong Shanghai Key Laboratory for R & D and Application of Metallic Functional Materials Institute of New Energy for Vehicles School of Materials Science and Engineering Tongji University Shanghai 201804 China Engineering Research Center of Ministry of Education for Geological Carbon Storage and Low Carbon Utilization of Resources School of Materials Science and Technology China University of Geosciences Beijing 100083 China Hebei Key Laboratory of Resource Low-carbon Utilization and New Materials China University of Geosciences Beijing 100083 China Department of Chemistry City University of Hong Kong 999077 Hong Kong Hong Kong Institute for Clean Energy City University of Hong Kong Kowloon 999077 Hong Kong City University of Hong Kong Shenzhen Research Institute Shenzhen 518057 China College of Chemistry and Molecular Sciences Wuhan University Wuhan 430072 China The Institute for Advanced Studies Wuhan University Wuhan 430072 China Sate Key Laboratory of Multiphase Flow in Power Engineering Frontier Institute of Science and Technology Xi’an Jiaotong University Xi’an 710049 China Department of Applied Biology and Chemical Technology The Hong Kong Polytechnic University Hung Hom Kowloon 999077 Hong Kong State Key Laboratory for Advanced Metals and Materials University of Science and Technology Beijing Beijing 100083 China School of Materials Science and Engineering Peking University Beijing 100871 China School of Materials Science and Engineering University of Science and Technology Beijing Beijing 100083 China Center of Advanced Nanocatalysis (CAN) Department of Applied Chemistry Univers

Phase is a fundamental structural parameter that distinguishes the atomic arrangement in materials. The recent advancement in phase engineering of nanomaterials (PEN) has witnessed the discovery and intriguing physicochemical properties of a number of unconventional phases in metal nanomaterials, enabling their promising applications in catalysis, optics, and so on. With the aid of advanced characterization techniques and theoretical calculations, phase engineering of metal nanomaterials has made significant progress in terms of precisely controlled synthesis, phase transformation, and phase-dependent property studies. This review summarizes the recent progress of PEN with a focus on metal nanomaterials. First, we introduce various synthetic strategies to prepare unconventional-phase metal nanomaterials, including monometallic and multimetallic nanomaterials. Second, we discuss methods to realize phase transformation of metallic nanomaterials. Then, we demonstrate various phase-dependent properties and applications of metal nanomaterials. Last, current challenges and exciting opportunities in the phase engineering of metal nanomaterials are discussed. © Jilin University, The Editorial Department of Chemical Research in Chinese Universities and Springer-Verlag GmbH 2025.

关键词： Metal nanomaterial Nanocatalysis Phase engineering of nanomaterial Phase-dependent property Unconventional-phase nanomaterial

来源：评论

学校读者我要写书评

暂无评论

Investigation of Using Large-Scale Swarm Optimizers to Optimize Sub-Problems in Cooperative Co-Evolution

Investigation of Using Large-Scale Swarm Optimizers to Optim...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Lu, Ming-Yuan Yang, Qiang Liu, Dong Ma, Yuan-Yuan Li, Tao Zhang, Jun College of Computer and Information Engineering Henan Normal University Xinxiang China Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province Xinxiang China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China Zhejiang Normal University Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Jinhua China Hanyang University Department of Electrical and Electronic Engineering Ansan Korea Republic of

ISBN: (纸本)9798350337020

Cooperative co-evolutionary algorithms (CCEAs) have witnessed giant success in solving large-scale optimization problems (LSOPs). However, most existing CCEAs use low-dimensional EAs to optimize the decomposed sub-problems. Such utilization of low-dimensional EAs may limit the effectiveness of CCEAs because some of the decomposed sub-problems may still be high-dimensional. Since there exist many non-decomposition based large-scale EAs, it is interesting to investigate the optimization effectiveness of CCEAs by using these non-decomposition based large-scale EAs to solve the decomposed sub-problems. To this end, this paper incorporates two state-of-the-art large-scale swarm optimizers into CCEAs with five state-of-the-art decomposition strategies to solve LSOPs. Experiments conducted on the CEC'2010 and CEC'2013 LSOP benchmark sets have shown that the two large-scale swarm optimizers help CCEAs with the five decomposition strategies achieve much better performance than the most widely used low-dimensional EA. © 2023 IEEE.

关键词： Cooperative Co-evolution Evolutionary Algorithms High-Dimensional Optimization Large-Scale Optimization Problems Large-Scale Swarm Optimizers

来源：评论

学校读者我要写书评

暂无评论

Stochastic Dominant Cognitive Experience Guided Particle Swarm Optimization

Stochastic Dominant Cognitive Experience Guided Particle Swa...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Pan, Han-Yang Yang, Qiang Li, Ming Zhang, En Ma, Yuan-Yuan Li, Tao Liu, Dong Zhang, Jun College of Computer and Information Engineering Henan Normal University Xinxiang China Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province Xinxiang China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China Zhejiang Normal University Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Jinhua China Hanyang University Department of Electrical and Electronic Engineering Ansan Korea Republic of

ISBN: (纸本)9798350337020

This paper proposes a stochastic dominant cognitive experience-guided learning framework for particle swarm optimization (SDCEGPSO) to enhance its search ability in complex environment. Specifically, different from classical PSOs, SDCEGPSO randomly selects dominant cognitive experiences to guide the learning of particles. To this end, the cognitive experiences of all particles, namely their personal best positions, are sorted from the best to the worst. Then, each particle randomly chooses a personal best position better than its own to learn. For the cognitive experience selection, this paper designs three selection methods, namely the random selection, the roulette wheel selection, and the tournament selection. With this learning framework, particles have diverse guiding exemplars to learn from and thus high search diversity is expectedly maintained. Experiments conducted on the 50-D and 100-D CEC2014 problem suite have verified the effectiveness of SDCEGPSO. Compared with the classical global PSO (GPSO) and local PSO (LPSO), SDCEGPSO with the three selection schemes achieve significantly better performance. Besides, among the three selection schemes, the binary tournament selection is the most effective one to help SDCEGPSO solve optimization problems. © 2023 IEEE.

关键词： Evolutionary Algorithms Global Optimization Particle Swarm Optimization Stochastic Dominant Cognitive Experience Guided Learning

来源：评论

学校读者我要写书评

暂无评论

Long-range Brain Graph Transformer 38

Long-range Brain Graph Transformer

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yu, Shuo Jin, Shan Li, Ming Sarwar, Tabinda Xia, Feng School of Computer Science and Technology Dalian University of Technology China Ministry of Education China School of Software Dalian University of Technology China Zhejiang Institute of Optoelectronics China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University China School of Computing Technologies RMIT University Australia

Understanding communication and information processing among brain regions of interest (ROIs) is highly dependent on long-range connectivity, which plays a crucial role in facilitating diverse functional neural integration across the entire brain. However, previous studies generally focused on the short-range dependencies within brain networks while neglecting the long-range dependencies, limiting an integrated understanding of brain-wide communication. To address this limitation, we propose Adaptive Long-range aware TransformER (ALTER), a brain graph transformer to capture long-range dependencies between brain ROIs utilizing biased random walk. Specifically, we present a novel long-range aware strategy to explicitly capture long-range dependencies between brain ROIs. By guiding the walker towards the next hop with higher correlation value, our strategy simulates the real-world brain-wide communication. Furthermore, by employing the transformer framework, ALERT adaptively integrates both short- and long-range dependencies between brain ROIs, enabling an integrated understanding of multilevel communication across the entire brain. Extensive experiments on ABIDE and ADNI datasets demonstrate that ALTER consistently outperforms generalized state-of-the-art graph learning methods (including SAN, Graphormer, GraphTrans, and LRGNN) and other graph learning based brain network analysis methods (including FBNETGEN, BrainNetGNN, BrainGNN, and BrainNETTF) in neurological disease diagnosis. Cases of long-range dependencies are also presented to further illustrate the effectiveness of ALTER. The implementation is available at https://***/yushuowiki/ALTER. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SmokerViT: A Transformer-Based Method for Smoker Recognition

引用

Computers, Materials & Continua 2023年第10期77卷 403-424页

作者： Ali Khan Somaiya Khan Bilal Hassan Rizwan Khan Zhonglong Zheng College of Mathematics and Computer Science Zhejiang Normal UniversityJinhua321004China School of Electronics Engineering Beijing University of Posts and TelecommunicationsBeijing100876China Department of Electrical Engineering and Computer Science Khalifa University of Science and TechnologyAbu Dhabi127788United Arab Emirates Key Laboratory of Intelligent Education of Zhejiang Province Zhejiang Normal UniversityJinhua321004China

Smoking has an economic and environmental impact on society due to the toxic substances it *** Neural Networks(CNNs)need help describing low-level features and can miss important ***,accurate smoker detection is vital with minimum false *** answer the issue,the researchers of this paper have turned to a self-attention mechanism inspired by the ViT,which has displayed state-of-the-art performance in the classification *** effectively enforce the smoking prohibition in non-smoking locations,this work presents a Vision Transformer-inspired model called SmokerViT for detecting ***,this research utilizes a locally curated dataset of 1120 images evenly distributed among the two classes(Smoking and NotSmoking).Further,this research performs augmentations on the smoker detection dataset to have many images with various representations to overcome the dataset size *** convolutional operations used in most existing works,the proposed SmokerViT model employs a self-attention mechanism in the Transformer block,making it suitable for the smoker classification ***,this work integrates the multi-layer perceptron head block in the SmokerViT model,which contains dense layers with rectified linear activation and linear kernel regularizer with L2 for the recognition *** work presents an exhaustive analysis to prove the efficiency of the proposed SmokerViT *** performance of the proposed SmokerViT performance is evaluated and compared with the existing methods,where it achieves an overall classification accuracy of 97.77%,with 98.21%recall and 97.35%precision,outperforming the state-of-the-art deep learning models,including convolutional neural networks(CNNs)and other vision transformer-based models.

关键词： Smoker recognition SmokerViT deep learning transformer for vision

来源：评论

学校读者我要写书评

暂无评论

Perfecting and extending the near-infrared imaging window

引用

Light(Science & applications) 2021年第10期10卷 1949-1966页

作者： Zhe Feng Tao Tang Tianxiang Wu Xiaoming Yu Yuhuang Zhang Meng Wang Junyan Zheng Yanyun Ying Siyi Chen Jing Zhou Xiaoxiao Fan Dan Zhang Shengliang Li Mingxi Zhang Jun Qian State Key Laboratory of Modern Optical Instrumentations Centre for Optical and Electromagnetic ResearchCollege of Optical Science and EngineeringInternational Research Center for Advanced PhotonicsZhejiang University310058 HangzhouChina Intelligent Optics&Photonics Research Center Jiaxing Institute of Zhejiang University314000 JiaxingZhejiang ProvinceChina State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of Technology430070 WuhanChina Key Laboratory of Reproductive Genetics(Ministry of Education) Department of Reproductive EndocrinologyWomen’s HospitalZhejiang University School of Medicine310006 HangzhouChina College of Pharmaceutical Sciences Soochow University215123 SuzhouChina

In vivo fluorescence imaging in the second near-infrared window(NIR-II)has been considered as a promising technique for visualizing ***,the definition of the NIR-II region and the mechanism accounting for the excellent performance still need to be ***,we simulate the photon propagation in the NIR region(to 2340 nm),confirm the positive contribution of moderate light absorption by water in intravital imaging and perfect the NIR-II window as 900–1880 nm,where 1400–1500 and 1700–1880 nm are defined as NIR-IIx and NIR-IIc regions,***,2080–2340 nm is newly proposed as the third near-infrared(NIR-III)window,which is believed to provide the best imaging *** wide-field fluorescence microscopy in the brain is performed around the NIRIIx region,with excellent optical sectioning strength and the largest imaging depth of intravital NIR-II fluorescence microscopy to *** also propose 1400 nm long-pass detection in off-peak NIR-II imaging whose performance exceeds that of NIR-IIb imaging,using bright fluorophores with short emission wavelength.

关键词： perfect Perfect fir

来源：评论

学校读者我要写书评

暂无评论

Tunable structures and single-ion magnet property in two cobalt(II) coordination compounds constructed by mixed bipyridyl- tetracarboxylic ligands

引用

Journal of Molecular Structure 2025年 1340卷

作者： Wei, Xiao-Qin Zhang, Hui Zhang, Quan-Lin Li, Bo-Qiong He, Zhi Yu, Xing-Yi Shen, Fu-Xing Shao, Dong Department of Materials Science and Engineering Shanxi Province New Multi-functional Glass Technology Innovation Center Jinzhong University Jinzhong030619 China Hubei Key Laboratory of Processing and Application of Catalytic Materials Hubei Provincial Engineering Research Center of High Purity Raw Material Processing Technology of Electronic Materials College of Chemistry and Chemical Engineering Huanggang Normal University Huanggang438000 China Institute of Zhejiang University-Quzhou Quzhou324000 China Key Laboratory of Biomass Chemical Engineering of Ministry of Education College of Chemical and Biological Engineering Zhejiang University Hangzhou310058 China

Two cobalt(II) coordination compounds, [Co(dmbpy)2(H2btca)(H2O)]·H2O (1, dmbpy = 5,5′-Dimethyl-2,2′-bipyridine, H4btca = 1,2,4,5-benzenetetracarboxylic acid) and {[Co(dmbpy)(btca)1/2(H2O)2]}n (2), were structurally and magnetically reported. Single-crystal X-ray diffraction unambiguously establishes that compound 1 adopts a mononuclear structure, contrasting with the one-dimensional coordination polymer architecture of 2. The latter displays a rare ribbon-like topology characterized by octahedrally coordinated Co²⁺ centers. Magnetic susceptibility analyses reveal that both Co²⁺ ions reside in distorted octahedral geometries, though with distinct deviations. Detailed magnetic studies quantify significant easy-plane anisotropy in both complexes, with axial zero-field splitting parameters D = + 61.3 cm⁻¹ for 1 and D = + 72.6 cm⁻¹ for 2. Field-dependent ac susceptibility measurements confirm the emergence of slow magnetic relaxation in both systems under a 1000 Oe dc field, with disparate temperature-frequency correlations indicating distinct relaxation pathways. These observations collectively demonstrate single-ion magnet (SIM) behavior in both cobalt(II) complexes. The structural dichotomy between mononuclear 1 and polymeric 2 directly correlates with their divergent relaxation dynamics, highlighting the critical role of dimensionality in modulating SIM performance. This work not only provides two new cobalt(II) complexes showing SIM property but also demonstrates a bipyridyl-tetracarboxylic strategy for constructing a structurally adaptable SIM platform. © 2025 Elsevier B.V.

关键词： Magnetic susceptibility

来源：评论

学校读者我要写书评

暂无评论

Metal surface Feature Fusion for Defect Recognition

Metal surface Feature Fusion for Defect Recognition

引用

Robotics, Automation and intelligent Control (ICRAIC), International Conference on

作者： Wenkai Lyu Chengzhuan Yang School of Computer Science and Technology Zhejiang Normal University Zhejiang China Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Zhejiang China

Metal sheets have been widely used in various industrial production and production life aspects. However, the surface of metal plates is prone to multiple defects, which affect the electromagnetic characteristics and coating effect of metal plates. Currently, mainstream inspection uses YOLO, PaddleClas, and other methods to detect flat metal surfaces. These algorithms are all very potent in their classification capabilities, but as generalized defect handling algorithms, they cannot be specific to each type of defect in a real problem. In this paper, we propose a multi-information fusion method for defect recognition. We consider both low-level texture features and high-level convolutional features of metal surfaces for defect recognition. We use a convolutional neural network as the main body and add extracted and processed prompts during training. Finally, we test the proposed method extensively on Camshaft and Kaggle metal surface defects datasets, and the experimental results demonstrate that our method achieves a state-of-the-art recognition performance that surpasses previous defect recognition methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large Language Model Aided Multi-objective Evolutionary Algorithm: a Low-cost Adaptive Approach

arXiv

引用

arXiv 2024年

作者： Liu, Wanyi Chen, Long Tang, Zhenzhou Wenzhou Key Laboratory for Intelligent Networking Wenzhou University Wenzhou325035 China Key Laboratory of Intelligent Education Technology Application of Zhejiang Province Zhejiang Normal University Jinhua321000 China

Multi-objective optimization is a common problem in practical applications, and multi-objective evolutionary algorithm (MOEA) is considered as one of the effective methods to solve these problems. However, their randomness sometimes prevents algorithms from rapidly converging to global optimization, and the design of their genetic operators often requires complicated manual tuning. To overcome this challenge, this study proposes a new framework that combines a large language model (LLM) with traditional evolutionary algorithms to enhance the algorithm’s search capability and generalization *** our framework, we employ adaptive and hybrid mechanisms to integrate the LLM with the MOEA, thereby accelerating algorithmic convergence. Specifically, we leverage an auxiliary evaluation function and automated prompt construction within the adaptive mechanism to flexibly adjust the utilization of the LLM, generating high-quality solutions that are further refined and optimized through genetic ***, the hybrid mechanism aims to minimize interaction costs with the LLM as much as possible. By adopting this approach, we maximize the benefits of the LLM’s language understanding and generation capabilities, providing the MOEA with more intelligent and efficient search strategies. We conducted experiments on multiple multiobjective optimization benchmark problems, and the results demonstrate that LLM-assisted evolutionary search significantly accelerates population convergence, allowing it to stand out in competition with state-of-the-art evolutionary algorithms. These experimental findings reveal the potential advantages of utilizing pre-trained LLMs in the design of MOEAs. This framework combines LLM with MOEA, offering a promising new approach to solving multi-objective optimization problems. We believe that as LLM continue to evolve and improve, they will play an increasingly significant role in multi-objective optimization and other complex decision

关键词：

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：