发布求助
文献互助 智能选刊 最新文献

2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)最新文献

筛选
英文 中文
Few-shot Classification based on CBAM and prototype network 基于CBAM和原型网络的少弹分类
2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967771
Shuo Xin, Hanjie Liu
{"title":"Few-shot Classification based on CBAM and prototype network","authors":"Shuo Xin, Hanjie Liu","doi":"10.1109/DOCS55193.2022.9967771","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967771","url":null,"abstract":"In recent years, with the continuous progress and development of deep learning, computer vision problems have been solved to a large extent, but the problem of few-shot has also appeared. Deep learning requires a lot of training data, so there is still a lack of learning from few samples. This paper focuses on the image classification problem in the few-shot problem as the research object. Firstly, based on the residual network ResNet18, and adding the convolution attention mechanism on this basis, the feature extraction network Res-CBAMnet is constructed. Secondly, the prototype network is used as the classifier to study the influence of different metric methods on the classification results. Experimental results show that the improved network achieves 99.72% and 67.42% accuracy on the few-shot image classification benchmark datasets Omniglot and mini-imagenet respectively.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124244137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
IDPSO for Influence Maximization under Independent Cascade Model 独立级联模型下影响最大化的IDPSO
2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967757
Bohan Wang, Lianbo Ma, Qiang He
{"title":"IDPSO for Influence Maximization under Independent Cascade Model","authors":"Bohan Wang, Lianbo Ma, Qiang He","doi":"10.1109/DOCS55193.2022.9967757","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967757","url":null,"abstract":"Influence maximization aims to find the most influential set of nodes from the network, through which specific information can achieve the widest dissemination in the network. The traditional influence maximization algorithm based on a greedy framework is challenging to apply to large networks due to the excessive computational overhead, and the heuristic algorithm is less than satisfactory in performance. In order to solve the imbalance between the running time and implementation of the influence maximization algorithm, we propose a local influence evaluation function to calculate the influence spread of the seed set in the network, reducing the time consumption. Then, we design an influence maximization algorithm based on improved discrete particle swarm optimization for the independent cascade model. Experiments on real social network datasets demonstrate that the proposed algorithm has superior running time and performance.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"5 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116858419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Cooperative Flow Simulator for Distributed Computing Based on Full-Dimensional Definable Network 基于全维可定义网络的分布式计算协同流模拟器
2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967710
Yuan Liang, Geyang Xiao, Shaofeng Yao, Hongsheng Wang, Xiaoyu Yi, Yonggang Tu
{"title":"A Cooperative Flow Simulator for Distributed Computing Based on Full-Dimensional Definable Network","authors":"Yuan Liang, Geyang Xiao, Shaofeng Yao, Hongsheng Wang, Xiaoyu Yi, Yonggang Tu","doi":"10.1109/DOCS55193.2022.9967710","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967710","url":null,"abstract":"To improve the efficiency of cluster computing, the research of cooperative flow scheduling algorithms provides another idea for further optimization. Cluster computing frameworks such as Spark and Map-Reduce carry running cluster computing tasks and have distinct stage division and dependency characteristics. With limited network resources, the overall completion time of the job can be reduced by minimizing the wait time of the computing phase due to the bottleneck of transmission capacity. The introduction of an artificial intelligence algorithm can provide a solution to this NP-hard problem. The simulator designed in this paper can realize the overall process of cooperative traffic generation, scheduling policy configuration, and scheduling effect feedback closed-loop through packet sender, packet receiver, scheduler, and programmable switch components according to the dependency between cluster computing stages.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117061596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Data-driven robust distributed MPC for collision avoidance formation navigation of constrained nonholonomic multi-robot systems 约束非完整多机器人系统避碰编队导航的数据驱动鲁棒分布MPC
2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967769
Junjie Fu, G. Wen
{"title":"Data-driven robust distributed MPC for collision avoidance formation navigation of constrained nonholonomic multi-robot systems","authors":"Junjie Fu, G. Wen","doi":"10.1109/DOCS55193.2022.9967769","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967769","url":null,"abstract":"In this work, we consider the robust collision avoidance formation navigation problem for multiple constrained nonholonomic robots with uncertain dynamics. Distributed model predictive control (MPC) based method is proposed in view of its ability to handle the input and state constraints of the robots explicitly. A synchronous non-iterative distributed algorithm is employed which reduces the communication requirement of the system. Furthermore, to enable the state trajectory prediction under uncertain robot dynamics, a data-driven online learning method is proposed to generate an accurate model of the nonholonomic robots adaptively. Based on the proposed control strategy, it is shown that robust collision avoidance formation navigation is successfully achieved while the input and state constraints of the robots are satisfied. Simulation examples are given to demonstrate the performance of the data-driven learning method and the distributed MPC based formation navigation controller.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124938031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Economic Dispatch of Smart Grid with Unknown Cost Functions and Switching Network Topology 具有未知成本函数和交换网络拓扑的智能电网经济调度
2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967783
G. Wen, Xinghuo Yu, Pengcheng Dai, Wenwu Yu
{"title":"Economic Dispatch of Smart Grid with Unknown Cost Functions and Switching Network Topology","authors":"G. Wen, Xinghuo Yu, Pengcheng Dai, Wenwu Yu","doi":"10.1109/DOCS55193.2022.9967783","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967783","url":null,"abstract":"The capability of economic dispatch (ED) algorithms to address the power dispatch problem with unknown cost functions and switching network topology is an important feature for practical applications of power dispatch algorithms in smart grid. Inspired by distributed fast consensus technique and reinforcement learning (RL) approach, this research presents a kind of ED strategy consisting of a fixed-time consensus tracking (FCT) algorithm and a distributed RL-based power dispatch algorithm to address the economic dispatch problem (EDP) with unknown cost functions and switching network topology. Different with existing results on EDP of smart grid where the feasible power outputs are calculated from centralized algorithm, a distributed FCT algorithm is utilised to balance the power demand and output for each dispatch duration, where the achievement of such a consensus leads to feasible power outputs and secures the system performance against switching interaction topology. Then, a distributed RL-based power dispatch algorithm is developed to train a policy for solving EDP with unknown cost functions through the technique of distributed training with distributed execution (DTDE). Finally, case studies are presented to demonstrate the effectiveness of the proposed ED algorithms.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"41 23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128491903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimal H∞ Control of Nonlinear Systems via Static and Dynamic Triggering Critic Learning 基于静态和动态触发批评学习的非线性系统最优H∞控制
2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967722
Zhiquan Zhang, Zhinan Peng, Bo Zhao, Rui Huang, Jiangping Hu, Hong Cheng
{"title":"Optimal H∞ Control of Nonlinear Systems via Static and Dynamic Triggering Critic Learning","authors":"Zhiquan Zhang, Zhinan Peng, Bo Zhao, Rui Huang, Jiangping Hu, Hong Cheng","doi":"10.1109/DOCS55193.2022.9967722","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967722","url":null,"abstract":"In this paper, a novel dynamic triggering based critic learning algorithm is proposed to solve the optimal H∞ control problem of a continuous-time nonlinear system. First, the H∞ control problem is formulated as a two-player zero-sum differential game. Then, an adaptive critic learning algorithm is adopted to acquire the approximate solution of the optimal control law under the worst-case external disturbance. Meanwhile, to improve the computational efficiency for the critic learning control method, an event-triggering mechanism is introduced to compute the approximate optimal control law. Then two kinds of triggering conditions, namely, static triggering scheme and dynamic triggering scheme, are designed for determining the event instants in the training process of the learning algorithm. In addition, the stability of the closed-loop system with the proposed triggering learning control method and the convergence of critic weight training procedure are both proved through Lyapunov theories. Finally, a simulation is carried out to demonstrate the effectiveness and performance of the proposed triggering based critic learning methods.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123845181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Research on Improved CLIQUE Partial Order Algorithm Weight 改进的CLIQUE偏序权重算法研究
2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967717
Lizhu Yue, Ying Hu
{"title":"Research on Improved CLIQUE Partial Order Algorithm Weight","authors":"Lizhu Yue, Ying Hu","doi":"10.1109/DOCS55193.2022.9967717","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967717","url":null,"abstract":"Aiming at the problem that the existing CLIQUE clustering algorithm does not consider the feature weight, which leads to the low accuracy, a weighted improvement method combined with POset idea is proposed. First, obtain the weight order of features. The original data are then weighted in partial order. Finally, the traditional CLIQUE algorithm is used to cluster the weighted data. This method can effectively integrate the weight information into the algorithm when only the feature weight order is obtained. The experimental results show that the clustering accuracy has been significantly improved, which fully reflects the role of feature weight. At the same time, the idea of POset can effectively integrate expert information. The representation of nearest neighbor elements in Hasse graph can enhance the robustness of clustering results. This is an effective method to improve CLIQUE clustering algorithm.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121270036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimizing Dosing Regimens of Tacrolimus in Lung Transplant Recipients 肺移植受者他克莫司给药方案的优化
2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967486
Boyang Xie, Chenyu Huang, Fangqing Gu
{"title":"Optimizing Dosing Regimens of Tacrolimus in Lung Transplant Recipients","authors":"Boyang Xie, Chenyu Huang, Fangqing Gu","doi":"10.1109/DOCS55193.2022.9967486","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967486","url":null,"abstract":"Tacrolimus, an immunosuppressant, is widely used to prevent rejection after transplantation. It has highly variable pharmacokinetics and a narrow therapeutic window. Therefore, there is a recognized need for Tacrolimus-personalized therapy. In solid organ transplantation, few lung transplants result in a lack of Tacrolimus data. To date, there has been little reliable reference to the elimination half-life of Tacrolimus in lung transplant recipients. In this paper, we construct a model based on an ordinary differential equation and a one-compartment model. It is scary to test the blood concentration of each patient in clinical trials. We present a piecewise nonlinear regression on the data of different patients to obtain the parameters of the ordinary differential equation. This study provides an approach to estimate the elimination half-life and therapeutic dose.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130462355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Co-evolutionary dynamics with alterable updating rules in the prisoner’s dilemma game 囚徒困境博弈中具有可变更新规则的协同进化动力学
2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967773
Xuesong Liu, Sinan Feng, Tieshan Li
{"title":"Co-evolutionary dynamics with alterable updating rules in the prisoner’s dilemma game","authors":"Xuesong Liu, Sinan Feng, Tieshan Li","doi":"10.1109/DOCS55193.2022.9967773","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967773","url":null,"abstract":"The emergence of cooperation has attracted lots of attention in various areas, ranging from sociology to robotics. Evolutionary game theory provides a suitable way to study the evolution of cooperative agents in selfish populations. In this work, we focus on the co-evolution of strategies and updating mechanisms in the prisoner’s dilemma game. Three mechanisms are available in these heterogeneous systems, where the agent updates its strategy with the classic Moran updating, or the imitation updating, or the aspiration-driven updating. Notably, the innovative feature of the aspiration-driven rule allows the agents to choose other rules even the whole population adopts the aspiration rule at a certain time. Results indicate that the unify of imitation rules can be always achieved in the final populations. Moreover, the speed of rule’s unification is always greater than the speed of strategy’s fixation. Remarkably, the decrease of the initial number of Moran agents makes the fixation of defection slow down, which is conducive to cooperation.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133054016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Adaptive Tracking Control for Hypersonic Flight Vehicle Using ADHDP 基于ADHDP的高超声速飞行器自适应跟踪控制
2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS) Pub Date : 2022-10-28 DOI: 10.1109/DOCS55193.2022.9967480
Liang Shuai, Wang Daqian, Xu Bin
{"title":"Adaptive Tracking Control for Hypersonic Flight Vehicle Using ADHDP","authors":"Liang Shuai, Wang Daqian, Xu Bin","doi":"10.1109/DOCS55193.2022.9967480","DOIUrl":"https://doi.org/10.1109/DOCS55193.2022.9967480","url":null,"abstract":"This paper investigates the tracking control problem for the uncertain system of hypersonic flight vehicle (HFV). An adaptive control scheme consisting of an adaptive baseline controller and an auxiliary optimization controller is proposed. The adaptive baseline controller is directly constructed by introducing a high-gain observer and only one neural network, which leads a much simpler design process than the backstepping scheme and does not require precise dynamics of HFv. Besides, action-dependent heuristic dynamic progranuning technology is applied to establish the auxiliary optimization controller, and the difference between the output and its reference signal can be further observed and minished by the auxiliary optimization controller. The stability is proved by Lyapunov theory and the superiority of the proposed strategy is verified by numerical simulation.","PeriodicalId":348545,"journal":{"name":"2022 4th International Conference on Data-driven Optimization of Complex Systems (DOCS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117330567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信