Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence最新文献_第8页

Survey on measures of image similarity applied in image inpainting base on deep learning 基于深度学习的图像绘制中图像相似性度量方法研究

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2022-12-23 DOI: 10.1145/3579654.3579737

Libo He, Z. Qiang, Yunyun Wu, Meijiao Wang

引用次数: 0

Ammunition Scheduling of Shipboard Aircraft According to Improved Ant Colony Algorithm 基于改进蚁群算法的舰载机弹药调度

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2022-12-23 DOI: 10.1145/3579654.3579754

Quan Yuan, Liting Wang, Xiao-Na Zheng, Ling Ma

引用次数: 0

FedDDB: Clustered Federated Learning based on Data Distribution Difference FedDDB:基于数据分布差异的聚类联邦学习

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2022-12-23 DOI: 10.1145/3579654.3579732

Chengyu You, Zihao Lu, Junli Wang, Chungang Yan

{"title":"FedDDB: Clustered Federated Learning based on Data Distribution Difference","authors":"Chengyu You, Zihao Lu, Junli Wang, Chungang Yan","doi":"10.1145/3579654.3579732","DOIUrl":"https://doi.org/10.1145/3579654.3579732","url":null,"abstract":"Clustered federated learning is a federated learning method based on multi-task learning. It groups similar clients into the same clusters and shares model parameters to solve the problem that the joint model is trapped in local optima on Non-IID data. Most of the existing clustered federated learning methods are based on the difference of model parameters for clients clustering. During the client model training process, the model parameters are biased and the clustering result is affected due to insufficient samples and missing eigenvalues in the dataset. In this paper, we develop a clustered federated learning method based on data distribution difference (FedDDB) in the dataset level. The method in this paper focuses on the distribution of label probability and eigenvalues, analyzes the difference of data distribution difference between clients and measures the distance between datasets which is used for client clustering. Every cluster will be trained independently and in parallel on the cluster center model. At the beginning of each round of training, the client clustering process needs to be repeated. We conduct relevant experiments and demonstrate the effectiveness of our method.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133600809","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

Idea Generation using Transformer Decoder Models 使用变压器解码器模型产生想法

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2022-12-23 DOI: 10.1145/3579654.3579706

Musammet Rafia Karim, Siam Shibly Antar, Mohammad Ashrafuzzaman Khan

引用次数: 1

Simulation and Analysis on the performance of Electric Explosive Device in electromagnetic environment of Naval Ships 舰船电磁环境下电爆炸装置性能仿真与分析

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2022-12-23 DOI: 10.1145/3579654.3579692

Fuqiang Li, Jingru Huang, Xiaomei Zheng

引用次数: 0

A Two-stage Framework for Online Unmanned Aerial Vehicles Search Planning 无人机在线搜索规划的两阶段框架

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2022-12-23 DOI: 10.1145/3579731.3579806

Hongbin Huang, Haopeng Duan, Lihua Liu, Kaiming Xiao

{"title":"A Two-stage Framework for Online Unmanned Aerial Vehicles Search Planning","authors":"Hongbin Huang, Haopeng Duan, Lihua Liu, Kaiming Xiao","doi":"10.1145/3579731.3579806","DOIUrl":"https://doi.org/10.1145/3579731.3579806","url":null,"abstract":"Unmanned Aerial Vehicles (UAV), also known as drones, have been widely used in regional data collection and information search, but there are also many practical challenges. In real-world operations of UAV search, the payoff and cost at each search point are unknown for the planner in advance which poses a great challenge to decision making. To this end, we first propose the problem of online decision making in UAV search planning where the drone has limited energy supply as a constraints and has to make an irrevocable decision to search this area or route to the next in an online manner. Then the online UAV search planning problem is decoupled into a traveling salesman problem (TSP) and an online resource planning problem such that it can be solved in a two-stage procedure. Specifically, the routing of search is obtained by solving TSP based on ant colony optimization, and the online decision is made through an online linear programming which is proven to be near-optimal. The effectiveness of the proposed two-stage approach is validated in wide-applied dataset, and experimental results show the superior performance of online search decision making.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116551861","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

An improved NSGA-Ⅱ for multi-objective job shop scheduling problems with overtime work consideration 考虑加班的多目标车间调度问题的改进NSGA-Ⅱ

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2022-12-23 DOI: 10.1145/3579654.3579698

Shuangyuan Shi, Hegen Xiong, Hanpeng Wang

{"title":"An improved NSGA-Ⅱ for multi-objective job shop scheduling problems with overtime work consideration","authors":"Shuangyuan Shi, Hegen Xiong, Hanpeng Wang","doi":"10.1145/3579654.3579698","DOIUrl":"https://doi.org/10.1145/3579654.3579698","url":null,"abstract":"In make-to-order (MTO) manufacturing systems, the workshop capacity is limited due to the production time horizon constraint of the order contract. If the total work load exceeds the shop capacity, a delay incurs, followed by a penalty, costs increasing and loss of customer loyalty. Overtime work is the most common resource to expand shop capacity. However, overtime work is often not used reasonably in the real manufacturing environment. In order to use overtime work optimally, a multi-objective job shop scheduling problem with overtime work consideration (MOJSSP/O) is studied in this paper. An improved NSGA-Ⅱ (INSGA-Ⅱ) algorithm with a two-stage decoding scheme, an adaptive mechanism and a local search procedure is designed to address the problem. The problem-specific two-stage decoding scheme equips the algorithm with the ability to further explore the solution space. The adaptive mechanism can extend the search space and accelerate the convergence speed. Furthermore, the local search procedure is applied to enhance the local exploitation capacity. The objective function of this study is to minimize total tardiness and overtime costs. The proposed algorithm is evaluated on 14 modified benchmarks, and compared with three state-of-the-art multi-objective algorithms. Computational results show that the proposed INSGA-Ⅱ outperforms the other three comparison algorithms on all test instances for balancing the costs of tardiness and overtime.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126736731","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 kiwifruit grading detection system based on depth limit learning machine 基于深度极限学习机的猕猴桃分级检测系统研究

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2022-12-23 DOI: 10.1145/3579654.3579758

Liang Wang

引用次数: 0

Customer Churn Combination Prediction Model Based on Convolutional Neural Network and Gradient Boosting Decision Tree 基于卷积神经网络和梯度提升决策树的客户流失组合预测模型

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2022-12-23 DOI: 10.1145/3579654.3579666

Shiyang Li, Guo-en Xia, Xianquan Zhang

引用次数: 0

Conditional Generative Adversarial Network Based Workload Generation for Cloud Cluster 基于条件生成对抗网络的云集群工作负载生成

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2022-12-23 DOI: 10.1145/3579654.3579723

Jun Xu, Junwei Liu, Jun Yao, Ao Ma, Lei Xu, Xinghua Zhao

{"title":"Conditional Generative Adversarial Network Based Workload Generation for Cloud Cluster","authors":"Jun Xu, Junwei Liu, Jun Yao, Ao Ma, Lei Xu, Xinghua Zhao","doi":"10.1145/3579654.3579723","DOIUrl":"https://doi.org/10.1145/3579654.3579723","url":null,"abstract":"Improving cluster utilization by scheduling and decision-making is a long-standing research problem for cloud vendors. The workload models can improve decision-making by providing a provision of the future workload for the public cloud scheduler. However, capturing the correlations in real traces was proven to be hard in former research. In this paper, we introduce a conditional generative adversarial network (CGAN) based model, which can provide a long-time provision for the cloud cluster. In the proposed approach, the workload model is generated by three-stage training with conditional GAN, which is not limited by the assumption of Poisson distribution. Besides, the conditional representation is redesigned based on Time2Vec, which makes the inter-job correlations among virtual machines (VMs) can be modeled accurately. According to our validation, the job arrival model accuracy is raised from 52.7% to 80.3% compared with the Poisson regression method, which indicated that the proposed CGAN-based model is a more universal and accurate generative model for large-scale cloud clusters.","PeriodicalId":146783,"journal":{"name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130619866","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