J. Comput. Sci.最新文献

A new collective anomaly detection approach using pitch frequency and dissimilarity: Pitchy anomaly detection (PAD) 一种基于基音频率和不相似度的集体异常检测方法:基音异常检测(PAD)

J. Comput. Sci. Pub Date : 2023-09-01 DOI: 10.2139/ssrn.4349068

E. C. Erkus, Vilda Purutçuoglu Gazi

引用次数: 1

Distributed source scheme for Poisson equation using finite element method 用有限元法求解泊松方程的分布式源格式

J. Comput. Sci. Pub Date : 2023-07-01 DOI: 10.2139/ssrn.4397801

N. Goona, S. Parne

引用次数: 0

Neural network control design for solid composite materials 固体复合材料的神经网络控制设计

J. Comput. Sci. Pub Date : 2023-06-01 DOI: 10.2139/ssrn.4361699

S. Ossandón, Mauricio Barrientos

引用次数: 0

Inductive and transductive link prediction for criminal network analysis 犯罪网络分析的感应和传导环节预测

J. Comput. Sci. Pub Date : 2023-06-01 DOI: 10.2139/ssrn.4331130

Zahra Ahmadi, Hoang H. Nguyen, Zijian Zhang, Dmytro Bozhkov, D. Kudenko, Maria Jofre, F. Calderoni, Noa Cohen, Yosef Solewicz

引用次数: 0

Democracy by Design: Perspectives for Digitally Assisted, Participatory Upgrades of Society 设计中的民主:数字辅助、参与式社会升级的视角

J. Comput. Sci. Pub Date : 2023-05-01 DOI: 10.2139/ssrn.4266038

D. Helbing, Sachit Mahajan, Regula Hänggli Fricker, Andrea Musso, C. Hausladen, C. Carissimo, Dino Carpentras, Elisabeth Stockinger, Javier Argota Sánchez-Vaquerizo, Joshua Yang, M. Ballandies, Marcin Korecki, R. Dubey, Evangelos Pournaras

引用次数: 13

SRL-Assisted AFM: Generating Planar Unstructured Quadrilateral Meshes with Supervised and Reinforcement Learning-Assisted Advancing Front Method srl辅助AFM:基于监督和强化学习辅助推进前沿法生成平面非结构化四边形网格

J. Comput. Sci. Pub Date : 2023-04-30 DOI: 10.48550/arXiv.2305.00540

Huai-Shui Tong, Kuanren Qian, Eni Halilaj, Y. Zhang

{"title":"SRL-Assisted AFM: Generating Planar Unstructured Quadrilateral Meshes with Supervised and Reinforcement Learning-Assisted Advancing Front Method","authors":"Huai-Shui Tong, Kuanren Qian, Eni Halilaj, Y. Zhang","doi":"10.48550/arXiv.2305.00540","DOIUrl":"https://doi.org/10.48550/arXiv.2305.00540","url":null,"abstract":"High-quality mesh generation is the foundation of accurate finite element analysis. Due to the vast interior vertices search space and complex initial boundaries, mesh generation for complicated domains requires substantial manual processing and has long been considered the most challenging and time-consuming bottleneck of the entire modeling and analysis process. In this paper, we present a novel computational framework named ``SRL-assisted AFM\"for meshing planar geometries by combining the advancing front method with neural networks that select reference vertices and update the front boundary using ``policy networks.\"These deep neural networks are trained using a unique pipeline that combines supervised learning with reinforcement learning to iteratively improve mesh quality. First, we generate different initial boundaries by randomly sampling points in a square domain and connecting them sequentially. These boundaries are used for obtaining input meshes and extracting training datasets in the supervised learning module. We then iteratively improve the reinforcement learning model performance with reward functions designed for special requirements, such as improving the mesh quality and controlling the number and distribution of extraordinary points. Our proposed supervised learning neural networks achieve an accuracy higher than 98% on predicting commercial software. The final reinforcement learning neural networks automatically generate high-quality quadrilateral meshes for complex planar domains with sharp features and boundary layers.","PeriodicalId":14601,"journal":{"name":"J. Comput. Sci.","volume":"142 1","pages":"102109"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74327447","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 novel global clustering coefficient-dependent degree centrality (GCCDC) metric for large network analysis using real-world datasets 一种新的全局聚类系数相关度中心性(GCCDC)度量，用于使用真实世界数据集的大型网络分析

J. Comput. Sci. Pub Date : 2023-04-01 DOI: 10.2139/ssrn.4284451

Ubaida Fatima, Saman Hina, Muhammad Wasif

引用次数: 0

Numerical solution of extended black-oil model incorporating capillary effects based on a high-resolution central scheme 基于高分辨率中心格式的考虑毛细效应的扩展黑油模型的数值解

J. Comput. Sci. Pub Date : 2023-03-01 DOI: 10.2139/ssrn.4281400

H. Biglarian, M. Salimi

引用次数: 0

Dynamic Hunting Leadership optimization: Algorithm and applications 动态狩猎领导力优化:算法与应用

J. Comput. Sci. Pub Date : 2023-03-01 DOI: 10.2139/ssrn.4288827

B. Ahmadi, Juan S. Giraldo, Gerwin Hoogsteen

引用次数: 1

Customizable Adaptive Regularization Techniques for B-Spline Modeling b样条建模的可定制自适应正则化技术

J. Comput. Sci. Pub Date : 2023-01-03 DOI: 10.48550/arXiv.2301.01209

David Lenz, Raine Yeh, V. Mahadevan, I. Grindeanu, T. Peterka

{"title":"Customizable Adaptive Regularization Techniques for B-Spline Modeling","authors":"David Lenz, Raine Yeh, V. Mahadevan, I. Grindeanu, T. Peterka","doi":"10.48550/arXiv.2301.01209","DOIUrl":"https://doi.org/10.48550/arXiv.2301.01209","url":null,"abstract":"B-spline models are a powerful way to represent scientific data sets with a functional approximation. However, these models can suffer from spurious oscillations when the data to be approximated are not uniformly distributed. Model regularization (i.e., smoothing) has traditionally been used to minimize these oscillations; unfortunately, it is sometimes impossible to sufficiently remove unwanted artifacts without smoothing away key features of the data set. In this article, we present a method of model regularization that preserves significant features of a data set while minimizing artificial oscillations. Our method varies the strength of a smoothing parameter throughout the domain automatically, removing artifacts in poorly-constrained regions while leaving other regions unchanged. The proposed method selectively incorporates regularization terms based on first and second derivatives to maintain model accuracy while minimizing numerical artifacts. The behavior of our method is validated on a collection of two- and three-dimensional data sets produced by scientific simulations. In addition, a key tuning parameter is highlighted and the effects of this parameter are presented in detail. This paper is an extension of our previous conference paper at the 2022 International Conference on Computational Science (ICCS) [Lenz et al. 2022].","PeriodicalId":14601,"journal":{"name":"J. Comput. Sci.","volume":"25 3 1","pages":"102037"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79741039","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