检索结果-内蒙古大学图书馆

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Wu, Guotong Shu, Tianye Nan, Yang Shang, Ke Ishibuchi, Hisao Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9781665430654

The hypervolume-based multi-objective evolutionary algorithms (HV-MOEAs) have proven to be highly effective in solving multi-objective optimization problems. However, the computation time of the hypervolume calculation increases significantly as the number of objectives increases. To address this issue, an R2-based hypervolume contribution approximation (R2-HVC) method was proposed. Nevertheless, the original R2-HVC generates a large number of vectors and computes the HVC only once. In this study, we propose an ensemble method based on the R2-HVC method. By using a small number of vectors for repetitive computation and majority voting, the ensemble method can reduce the probability of making incorrect choices. Experimental results show that the proposed method can improve the approximation accuracy while maintaining a similar computation time to the original R2-HVC method. © 2023 IEEE.

关键词： Ensemble Method Hypervolume Contribution Majority Voting Multi-objective Optimization

来源：评论

学校读者我要写书评

暂无评论

Variable-order fractional derivative rutting depth prediction of asphalt pavement based on the RIOHTrack full-scale track

引用

science China(Information sciences) 2023年第5期66卷 196-214页

作者： Yu WANG Jiaojiao YAN Wei HUANG Leszek RUTKOWSKI Jinde CAO School of Mathematics Southeast University Jiangsu Provincial Key Laboratory of Networked Collective Intelligence Southeast University Intelligent Transportation System Research Center Southeast University Systems Research Institute of the Polish Academy of Sciences Institute of Computer Science AGH University of Science and Technology Information Technology Institute University of Social Sciences Yonsei Frontier Lab Yonsei University

Rutting deformation is typical damage to asphalt pavement and can be quantitatively described as the time-varying mechanical deformation feature of the asphalt mixture during the creep process. First,a nonlinear viscoelastic creep model is established based on the Caputo variable-order fractional *** fractional order in this model is not fixed and is defined as a time-varying function. The time-dependent mechanical properties of asphalt mixtures are efectively reflected. Based on the modified Burgers model, the variable-order function is revised to a linear form. Second, the variable-order fractional Burgers rutting model is obtained by fitting the test data of the RIOHTrack full-scale track. The Levenberg-Marquardt optimization algorithm is used to analyze the test data and the corresponding parameters to obtain more accurate and applicable variable-order fractional rutting mechanics and empirical models for diferent asphalt pavement structures. Finally, according to the classification of the pavement structure, structures III and VI are taken as examples. The rutting prediction and comparison results of several representative pavement structures are obtained to verify that the proposed rutting prediction model can also accurately predict all road sections of RIOHTrack. The new model is also compared with the rutting model of the mechanistic-empirical pavement design guide, the fractional-order Burgers rutting model, and the modified Burgers rutting model. The fitting results are evaluated using the determination coefficient R2. The results show that the variable-order fractional Burgers rutting model proposed in this study exhibits a better fit and is more applicable to describe the rutting deformation of asphalt pavement.

关键词： RIOHTrack full-scale track Caputo fractional derivative variable-order fractional modified Burgers model rutting prediction

来源：评论

学校读者我要写书评

暂无评论

Electronic structure regulation of Fe-doped Ni2P nanocrystals towards durable electrocatalytic oxygen evolution

引用

Rare Metals 2024年第12期43卷 6405-6415页

作者： Ya Liu Xing Cao Jia-Jia Liu Mei-Sheng Han Gao-Wei Zhang Yu-Bin Zhao Huan-Hui Chen Liang Yu Jun-Rong Zeng Zhi-Kai Cheng Liu-Biao Zhong Li-Juan Song Ye-Jun Qiu Shenzhen Engineering Lab of Flexible Transparent Conductive Films School of Materials Science and EngineeringHarbin Institute of TechnologyShenzhen518055China School of Physics Harbin Institute of TechnologyHarbin150001China Department of Mechanical and Energy Engineering Southern University of Science and TechnologyShenzhen518055China School of Science Harbin Institute of TechnologyShenzhen 518055China Guangdong Provincial Key Laboratory of Semiconductor Optoelectronic Materials and Intelligent Photonic Systems Harbin Institute of TechnologyShenzhen518055China

The inherent electrocatalytic potential of transition metal phosphides(TMPs)for oxygen evolution is influenced by the reduced efficiency of electron transfer resulting from the interaction between electronegative phosphorus atoms and transition ***,we introduce Fe into Ni_(2)P nanocrystals by thermal injection synthesis method,and anchor them on nickel foam(NF)by facile spraying to prepare self-supporting oxygen evolution reaction(OER)***,the optimized electrode of Ni_(2)P-Fe-2/NF demonstrates low overpotentials of 212 mV with 10 mA·cm^(-2)and a 0.9%decay within300 h test of 50 mA·cm^(-2).Notably,when electrode size was expanded to 600 cm^(2)and applied to a larger electrolyzer,its 9 h decay rate at 6 A current was only 1.69%.Characterization results show that Fe doped NiOOH is generated during OER reaction as actual catalyst,Results from density functional theory(DFT)computations suggest that Fe doping shifts NiOOH d-band center to Fermi level,lowering critical *OOH intermediates formation energy barrier during the OER *** findings inform the large-scale industrial application of TMPs as robust electrocatalysts.

关键词： Electronic structure regulation Fe doping Colloidal nanocrystals Ni2P Oxygen evolution reaction

来源：评论

学校读者我要写书评

暂无评论

Normalization in R2-Based Hypervolume and Hypervolume Contribution Approximation

Normalization in R2-Based Hypervolume and Hypervolume Contri...

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Wu, Guotong Shu, Tianye Shang, Ke Ishibuchi, Hisao Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9781665430654

In this paper, we examine the effect of normalization in R2-based hypervolume and hypervolume contribution approximation. The fact is that the region with different scales on objective space brings approximation bias. The basic idea of normalization is to perform a coordinate transformation to make the shape of the approximated region more regular, and then transform it to obtain the final value according to the property of hypervolume and hypervolume contribution. The performance of normalization is evaluated on different datasets by comparing it with the original R2-based method. We use two different metrics to evaluate hypervolume and hypervolume contribution separately, and the results indicate that normalization does exactly improve the approximation accuracy and outperforms the original R2-based method. © 2023 IEEE.

关键词： Hypervolume Normalization ─Multi-objective Optimization

来源：评论

学校读者我要写书评

暂无评论

Rationally Leveraging Polymer Chain-Length Heterogeneity for Robust Structural Engineering

引用

CCS Chemistry 2024年第8期6卷 1965-1977页

作者： Zhanhui Gan Luyang Li Dongdong Zhou Zhuoqi Xu Zhuang Ma Jiawen He Weihua Li Xue-Hui Dong South China Advanced Institute for Soft Matter Science and Technology School of Emergent Soft MatterSouth China University of TechnologyGuangzhou 510640 State Key Laboratory of Molecular Engineering of Polymers Key Laboratory of Computational Physical SciencesDepartment of Macromolecular ScienceFudan UniversityShanghai 200433 College of Polymer Science and Engineering State Key Laboratory of Polymer Materials EngineeringSichuan UniversityChengdu 610065 Guangdong Provincial Key Laboratory of Functional and Intelligent Hybrid Materials and Devices South China University of TechnologyGuangzhou 510640

The inherent uncertainty of chain length in synthetic polymers casts doubt on the explicit understanding of fundamental *** study quantitatively assesses the critical role of chain-length distribution in the self-assembly process,aiming to identify the point at which discernible discrepancies begin to *** blending discrete diblock copolymers of varying sizes,chain-length nonuniformity can be precisely regulated while the average composition remains *** a minor heterogeneity leads to an expansion of lattice dimension,while a phase transition occurs as the difference exceeds a ***,a transition from the Frank–Kasperσphase to the body-centered cubic phase was triggered by enlarging the size difference of the corona block,while introducing heterogeneity in the core block stabilized the hexagonally close-packed spheres.A self-consistent field theory calculation reveals that the synergy between the long and short chains effectively releases packing frustration,leading to substantial changes in the free-energy landscape and stabilizing unconventional phases otherwise *** work calls particular attention to the importance of chain-length heterogeneity and provides a robust approach to finely tuning the phase behavior and physical properties of block copolymers without altering their chemical composition.

关键词： discrete polymer molecular weight distribution self-assembly hexagonally close-packed phase Frank-Kasper phases

来源：评论

学校读者我要写书评

暂无评论

Multi-objective evolutionary optimization for hardware-aware neural network pruning

引用

Fundamental Research 2024年第4期4卷 941-950页

作者： Wenjing Hong Guiying Li Shengcai Liu Peng Yang Ke Tang Guangdong Provincial Key Laboratory of Brain-Inspired Inteligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China Research Institute of Trustworthy Autonomous Systems Southern University of Science and TechnologyShenzhen 518055China Department of Statistics and Data Science Southern University of Science and TechnologyShenzhen 518055China

Neural network pruning is a popular approach to reducing the computational complexity of deep neural *** recent years,as growing evidence shows that conventional network pruning methods employ inappropriate proxy metrics,and as new types of hardware become increasingly available,hardware-aware network pruning that incorporates hardware characteristics in the loop of network pruning has gained growing attention,Both network accuracy and hardware efficiency(latency,memory consumption,etc.)are critical objectives to the success of network pruning,but the conflict between the multiple objectives makes it impossible to find a single optimal *** studies mostly convert the hardware-aware network pruning to optimization problems with a single *** this paper,we propose to solve the hardware-aware network pruning problem with Multi-Objective Evolutionary Algorithms(MOEAs).Specifically,we formulate the problem as a multi-objective optimization problem,and propose a novel memetic MOEA,namely HAMP,that combines an efficient portfoliobased selection and a surrogate-assisted local search,to solve *** studies demonstrate the potential of MOEAs in providing simultaneously a set of alternative solutions and the superiority of HAMP compared to the state-of-the-art hardware-aware network pruning method.

关键词： Multi-objective optimization Evolutionary algorithm Neural network pruning Hardware-awaremachine learning Hardware efficiency

来源：评论

学校读者我要写书评

暂无评论

Analysis of Partition Methods for Dominated Solution Removal from Large Solution Sets

Analysis of Partition Methods for Dominated Solution Removal...

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Shu, Tianye Nan, Yang Shang, Ke Ishibuchi, Hisao Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9781665430654

In evolutionary multi-objective optimization (EMO), one important issue is to efficiently remove dominated solutions from a large number of solutions examined by an EMO algorithm. An efficient approach to remove dominated solutions from a large solution set is to partition it into small subsets. Dominated solutions are removed from each subset independently. This partition method is fast but cannot guarantee to remove all dominated solutions. To further remove remaining dominated solutions, a simple idea is to iteratively perform this approach. In this paper, we first examine three partition methods (random, objective value-based and cosine similarity-based methods) and their iterative versions through computational experiments on artificial test problems (DTLZ and WFG) and real-world problems. Our results show that the choice of an appropriate partition method is problem dependent. This observation motivates us to use a hybrid approach where different partition methods are used in an iterative manner. The results show that all dominated solutions are removed by the hybrid approach in most cases. Then, we examine the effects of the following factors on the computation time and the removal performance: the number of objectives, the shape of the Pareto front, and the number of subsets in each partition method. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Conjoint Response in Post-stroke Patients Using the Attention-coupled Weighting Method

引用

Machine Intelligence Research 2025年第2期22卷 352-367页

作者： Jingyao Chen Chen Wang Ningcun Xu Zeng-Guang Hou Liang Peng Pu Zhang Faculty of Innovation Engineering CASIA-MUST Joint Laboratory of Intelligence Science and TechnologyMacao University of Science and TechnologyMacao 999078China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Analysis and Testing Beijing Academy of Science and TechnologyBeijing 100089China Department of Rehabilitation Evaluation China Rehabilitation Research CenterBeijing 100068China

Rehabilitation assessment plays a vital role in the recovery process of post-stroke ***,many studies have focused on the implementation of automated assessment ***,the impact of stroke on the synergistic pattern between different human joints is not well *** this study,we developed an attention-coupled weighting based quantitative analysis model to identify the pathological alteration in the conjoint response structure between stroke patients and healthy participants,thus providing more intrinsic suggestions for the post-stroke rehabilitation *** collaboration with the China Rehabilitation Research Center and the Macao University of science and technology,we recruited 15 post-stroke patients and 15 healthy participants to complete several actions selected from the Fugl-Meyer assessment(FMA)scale,which is a commonly used post-stroke rehabilitation assessment scale in clinical *** study proposed an attentional coupling weight(ACW)extraction *** filtering the weights in the attentional coupling network using a priori matrix,we can analyse the effect of stroke on the alteration of synergistic structures and the coordination patterns of the upper and lower ***,we used a commonly accepted synergy analysis method,the nonnegative matrix decomposition(NMF)method,for comparison and *** experimental results demonstrated the effectiveness of our method in quantifying the synergistic structure pattern alterations in post-stroke patients,which provides a new targeted option for the rehabilitation process.

关键词： intelligent assessment conjoint response attentional coupling network spatio-temporal weight extraction.

来源：评论

学校读者我要写书评

暂无评论

Simultaneous enhancement of sensitivity, resonant frequency, and overload capability of piezoresistive accelerometers by heavily-doped fillet structures on sensing beams

引用

IEEE Sensors Journal 2025年第11期25卷 19138-19146页

作者： Xia, Yong Wang, Tao Lv, Yang Han, Xiangguang Yu, Mingzhi Tan, Renjie Huang, Mimi Jia, Chen Zhao, Libo Sun, Lin Yang, Ping Lu, Dejiang Xi'an Jiaotong University School of Mechanical Engineering State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technologies Xi'an710049 China Ningbo CRRC Times Transducer Technology Co. LTD Department of Basic Research and Development Ningbo315021 China Research Institute for Intelligent Sensing Technology and System School of Instrument Science and Technology State Key Laboratory for Manufacturing Systems Engineering State Industry-Education Integration Center for Medical Innovations International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technologies Xi'an Jiaotong University Xi'an710049 China Shandong Laboratory of Advanced Materials and green Manufacturing at Yantai Yantai264000 China

High sensitivity, high natural frequency, and high overload capability are desired for accelerometers used in industrial applications, but simultaneously enhancing all is challenging. Here, via designing novel heavily-doped fillet structures, we prove the sensitivity, resonant frequency, and overload capability can be simultaneously enhanced. The enhancements are attributed to regulations of stress concentration and effective sensing regions by the heavily-doped fillets. The sensors with and without fillets are designed, fabricated, packaged, and tested. The results show a sensitivity of 0.31±0.02 mV/g@5V, a natural frequency of 37.87±2.09 kHz, and an overload of 10040.17±531.76 g for sensors with 10-μm fillets, which are superior to 0.27±0.01 mV/g@5V, 34.13±0.90 kHz, and 7368.55±843.92 g for those no-fillet counterparts. Additionally, the developed sensor further exhibited feasibility in air-bearing vibration monitoring. The proposed design is envisioned to give insights into the novel designs of high-performance stress-based sensors, including accelerometers, pressure sensors, and strain gauges. © 2001-2012 IEEE.

关键词： Strain gages

来源：评论

学校读者我要写书评

暂无评论

Challenges and future directions of secure federated learning:a survey

引用

Frontiers of computer science 2022年第5期16卷 173-180页

作者： Kaiyue ZHANG Xuan SONG Chenhan ZHANG Shui YU Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Faculty of Engineering and Information Technology University of Technology SydneySydney 2007Australia SUSTech-UTokyo Joint Research Center on Super Smart City Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China

Federated learning came into being with the increasing concern of privacy security,as people’s sensitive information is being exposed under the era of big *** is an algorithm that does not collect users’raw data,but aggregates model parameters from each client and therefore protects user’s ***,due to the inherent distributed nature of federated learning,it is more vulnerable under attacks since users may upload malicious data to break down the federated learning *** addition,some recent studies have shown that attackers can recover information merely from ***,there is still lots of room to improve the current federated learning *** this survey,we give a brief review of the state-of-the-art federated learning techniques and detailedly discuss the improvement of federated *** open issues and existing solutions in federated learning are *** also point out the future research directions of federated learning.

关键词： federated learning privacy protection security

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：