检索结果-内蒙古大学图书馆

Early Prediction of the Winner in StarCraft Matches

学校读者我要写书评

暂无评论

Early Prediction of the Winner in StarCraft Matches

9th International Joint Conference on Computational Intelligence, IJCCI 2017

作者： Alvarez-Caballero, Antonio Merelo, J.J. Sanchez, Pablo Garcıa Fernandez-Ares, A. Department of Computer Architecture and Computer Technology University of Granada Spain Department of Computer Science University of Cadiz Spain

ISBN: (纸本)9789897582745

A fast and precise prediction of the outcome of a game is essential for the design of bots that play the game;it can be used either offline as a fast way to design bot strategies or online for conserving resources and conceding defeat or speed up victory, as well as evaluating the consequences of actions. The objective of this paper is predicting the winner of a StarCraft match as soon as possible. This study is done with supervised learning, because a lot of suitable data is available. The main problem of this approach is the big amount of generated data, so it has to be selected and organised properly and be treated with proper tools. A set of six learning algorithms is used, from simpler ones to more complex algorithms. Spark and MLlib are used due to their capabilities to deal with big amounts of data. With the learned models, time of matches are restricted, trying to get a time bound for predicting results. With this approach we get that it is not necessary to play a whole match to predict its winner with high accuracy: with 10 minutes we can predict the outcome with 90% of accuracy. © 2017 by SCITEPRESS–Science and technology Publications, Lda. All rights reserved.

关键词： Forecasting

Ranking-based deep cross-modal hashing

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Xuanwu Yu, Guoxian Domeniconi, Carlotta Wang, Jun Ren, Yazhou Guo, Maozu College of Computer and Information Sciences Southwest University Chongqing China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan China Department of Computer Science George Mason University Fairfax United States SMILE Lab School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China

Cross-modal hashing has been receiving increasing interests for its low storage cost and fast query speed in multi-modal data retrievals. However, most existing hashing methods are based on hand-crafted or raw level features of objects, which may not be optimally compatible with the coding process. Besides, these hashing methods are mainly designed to handle simple pairwise similarity. The complex multilevel ranking semantic structure of instances associated with multiple labels has not been well explored yet. In this paper, we propose a ranking-based deep cross-modal hashing approach (RDCMH). RDCMH firstly uses the feature and label information of data to derive a semi-supervised semantic ranking list. Next, to expand the semantic representation power of hand-crafted features, RDCMH integrates the semantic ranking information into deep cross-modal hashing and jointly optimizes the compatible parameters of deep feature representations and of hashing functions. Experiments on real multi-modal datasets show that RDCMH outperforms other competitive baselines and achieves the state-of-the-art performance in cross-modal retrieval applications. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

Embodied emission profiles of building types: guidance for emission reduction in the early phases of construction projects

学校读者我要写书评

暂无评论

IOP Conference Series: Earth and Environmental Science 2020年第1期410卷

作者： Eirik Resch Helge Brattebø Inger Andresen Department of Applied Mathematics and Computer Science Technical University of Denmark Kgs. Lyngby Denmark Department of Architecture and Technology Norwegian University of Science and Technology Trondheim Norway Industrial Ecology Programme Norwegian University of Science and Technology Trondheim Norway

The embodied emissions of the construction materials in buildings are a significant contributor to climate change but have only rarely been systematically studied by statistical methods. In the early phases of a building project, empirical results of statistical emission profiles of different building types can act as useful guiding information to inform decisions regarding reduced embodied emissions from construction materials. However, engineers and architects do not have such information at disposition. In this paper, the embodied emissions from the production and transport of initial and recurring building material use in 7 Norwegian case studies of low-emission buildings are made comparable and then studied statistically to find out how the impact varies with building types. The building types studied are timber residential, concrete office, concrete school, and concrete swimming hall. Statistics are produced for each building type and are broken down by the impact contribution from different building elements and material categories. This results in embodied emission profiles and material use profiles for these four building types, which, when based on a larger dataset, can be used by architects and engineers to make informed decisions when aiming for reduced embodied emissions in the early phases of a construction project. Additionally, these profiles can be used as benchmarks by which the final building can be compared when the building is constructed. The statistical results are preliminary and based on a limited dataset, which makes them applicable only as an indication for Norwegian low-emission buildings of these four building types. Future work includes expansion of the dataset on which the profiling is based, further development of the statistical method, and applying the methodology to additional building types.

关键词：

AGlobal benchmark of algorithms for segmentinglate gadolinium-enhanced cardiac magnetic resonance imaging

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xiong, Zhaohan Xia, Qing Hu, Zhiqiang Huang, Ning Bian, Cheng Zheng, Yefeng Vesal, Sulaiman Ravikumar, Nishant Maier, Andreas Yang, Xin Heng, Pheng-Ann Ni, Dong Li, Caizi Tong, Qianqian Si, Weixin Puybareau, Elodie Khoudli, Younes Géraud, Thierry Chen, Chen Bai, Wenjia Rueckert, Daniel Xu, Lingchao Zhuang, Xiahai Luo, Xinzhe Jia, Shuman Sermesant, Maxime Liu, Yashu Wang, Kuanquan Borra, Davide Masci, Alessandro Corsi, Cristiana De Vente, Coen Veta, Mitko Karim, Rashed Preetha, Chandrakanth Jayachandran Engelhardt, Sandy Qiao, Menyun Wang, Yuanyuan Tao, Qian Nuñez-Garcia, Marta Camara, Oscar Savioli, Nicolo Lamata, Pablo Zhao, Jichao Auckland Bioengineering Institute University of Auckland Auckland New Zealand State Key Lab of Virtual Reality Technology and Systems Beihang University Beijing China School of Electronics Engineering and Computer Science Peking University Beijing China SenseTime Inc Shenzhen China Tencent Jarvis Laboratory Shenzhen China Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Shenzhen China School of Computer Science Wuhan University Wuhan China Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Epita Research and Development Laboratory Paris France Department of Computing Imperial College London London United Kingdom School of Naval Architecture Shanghai Jiao Tong University Ocean & Civil Engineering Shanghai China School of Data Science Fudan University Shanghai China Epione Research Group Universite Cote d'Azur Inria Sophia Antipolis France Harbin Institute of Technology School of Computer Science and Technology Harbin China Department of Electric University of Bologna Electronic and Information Engineering Cesena Italy Department of Biomedical Engineering Eindhoven University of Technology Eindhoven Netherlands School of Biomedical Engineering and Imaging Sciences Kings College London London United Kingdom Faculty of Electrical Engineering and Information Technology University of Magdeburg Magdeburg Germany Heidelberg University Hospital Germany Biomedical Engineering Center Fudan University Shanghai China Department of Radiology Leiden University Medical Center Leiden Netherlands Department of Information and Communication Technologies Universitat Pompeu Fabra Barcelona Spain D

Segmentation of cardiac images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI)widely used for visualizing diseased cardiacstructures, is a crucial first step for clinical diagnosis and treatment. However, direct segmentation ofLGE-MRIsischallenging due to *** most clinical studies have relied on manual and labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning *** address this, we organized the "2018 Left Atrium Segmentation Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset, and associated labels of the left atriumsegmented by three medical experts,ultimately attractingthe participation of27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis,offeringan overall picture ofthe major design choices of convolutional neural networks(CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show the top methodachieved a dice score of 93.2%and a mean surface to a surface distance of 0.7mm, significantly outperforming prior state-of-the-art. Particularly, our analysisdemonstrated that double, sequentially usedCNNs, in which a first CNN is used for automatic region-of-interestlocalization and a subsequent CNN is used for refinedregional segmentation, achieved far superiorresults than traditional methods and pipelinescontaining *** findings from this study can potentially be extended to other imaging datasets and modalities, having an impact on the wider medical imaging *** large-scale benchmarking study makes a significant step towards much-improved segmentation methods for cardiac LGE-MRIs, and will serveas animportant benchmark for evaluating and comparing the future works in the field. Copyright © 2020, Th

关键词： Magnetic resonance imaging

Corrigendum to “Effect of anisotropic porous structure on mixed permanent magnetic-convection heat transfer under permanent twin magnets” [ICHMT, 158, November 2024, 107831]

学校读者我要写书评

暂无评论

International Communications in Heat and Mass Transfer 2024年 159卷

作者： Mohsen Izadi Ahmad Hajjar Mohamed Moussa El Idi Q.N.G. Lam Faris Alqurashi Mohamed H. Mohamed Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Engineering & Technology Duy Tan University Da Nang Viet Nam Mechanical Engineering Department Faculty of Engineering Lorestan University Khorramabad Iran Center for Environmental Intelligence and College of Engineering and Computer Science VinUniversity Hanoi Viet Nam LabECAM ECAM La Salle Université de Lyon 69005 Lyon France Department of Mechanical Engineering College of Engineering University of Bisha Bisha 61922 P.O. Box 551 Saudi Arabia Mechanical Power Engineering Department Faculty of Engineering EL-Mattaria Helwan University P·O Box:11718 Cairo Egypt Mechanical Engineering Dept. College of Engineering and Islamic Architecture Umm Al-Qura University P.O. 5555 Makkah Saudi Arabia

A Minimal-Model Approach to Analyze Neuronal Circuit Dynamics from multifocal ERG (mERG)

学校读者我要写书评

暂无评论

A Minimal-Model Approach to Analyze Neuronal Circuit Dynamic...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Pascal Schröder Pablo Martínez-Cañada André Amorim Paulo Fernandes Ana Amorim-de-Sousa José Manuel González-Méijome Department of Human Sciences University of Osnabrück Osnabrück Germany Department of Computer Architecture and Technology CITIC-UGR University of Granada Granada Spain Clinical & Experimental Optometry Research Lab-CEORLab Center of Physics (Optometry) University of Minho Braga Portugal

The multifocal electroretinogram (mERG) is a valuable non-invasive tool used by clinicians for studying both the local physiology of the normal human retina, as well as retinal function affected by disease. However, the neural basis of the major components of the mERG is not well understood. Computational modeling of neural circuits has lead to important insights into the structure and workings of nervous systems. A better understanding of the different neural factors that contribute to the retina function and progression of the pathology can help in developing an effective clinical intervention. In this paper, we propose a minimal computational model as an analysis tool for inferring the relationship between mERG data of the human retina and its underlying neural activity and interpreting the data in terms of the specific neural features that contribute to it. In this preliminary study, the rigor of this analysis technique was assessed by fitting the model with a genetic algorithm (GA) to collected mERG data from ten healthy patients.

关键词： Retina Photoreceptors Data models Computational modeling Sociology Statistics Tools

KnowSeq R/bioc package: Beyond the traditional RNA-seq pipeline. A breast cancer case study

学校读者我要写书评

暂无评论

Research Square

Research Square 2019年

作者： Castillo-Secilla, Daniel Galvez, Juan Manuel Ortuno, Francisco Manuel Herrera, Luis Javier Rojas, Ignacio Department of Computer Architecture and Technology University of Granada Periodista Rafael Gómez Montero 2 Granada18014 Spain Hospital Universitario Virgen del Rocío Avenida Manuel Siurot s/n Sevilla41013 Spain

Background: The number of gene expression analyses has grown exponentially over the last years. The main triggers of this increase are the reduction in the sequencing cost per sample and the technological advances, specially in the computing scope. Those analyses generally involve a number of steps. Firstly, a raw samples alignment and a quality analysis are needed. After that, a Differentially Expressed Genes (DEGs) extraction and a subsequent gene enrichment can be performed. The development of intelligent predictive tools results essential in bioinformatics given that there exists a real need of assistance for decision-making systems towards precision medicine. Therefore, KnowSeq incorporates novel steps of feature selection and classifier design in the traditional RNA-seq pipeline. No tool exists in the research community that achieves this complete RNA-seq analysis, encapsulating all those steps in one single tool. Results: In order to show the functionalities provided by the general pipeline designed for the KnowSeq package, an application to a real problem is presented. Concretely, an analysis of a breast cancer set of patients collected from the controlled repository GDC portal is performed, keeping paired samples between tumour and control. As results show, KnowSeq achieves extracting more relevant biological knowledge related with breast cancer from the RNA raw data acquisition. KnowSeq is available through Bioconductor. Conclusions: KnowSeq R/bioc package is born with the purpose of providing an integrative tool, containing the necessary steps to address complex RNA-seq analyses in a modular and flexible way. In this paper a breast study case is addressed with KnowSeq, obtaining outstanding results and demonstrating the validity of KnowSeq to carry out gene expression analyses. © 2019, CC BY.

关键词： RNA

Efficient parallel linear scaling method to get the response density matrix in all-electron real-space density-functional perturbation theory

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shang, Honghui Liang, Wanzhen Zhang, Yunquan Yang, Jinlong State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Physical Chemistry of Solid Surfaces Collaborative Innovation Center of Chemistry for Energy Materials Fujian Provincial KeyLaboratory of Theoretical and Computational Chemistry Department of Chemistry College of Chemistry and Chemical Engineering Xiamen University XiamenFujian361005 China Hefei National Laboratory for Physical Sciences at Microscale Department of Chemical Physics Synergetic Innovation Center of Quantum Information and Quantum Physics University of Science and Technology of China Hefei Anhui230026 China

The real-space density-functional perturbation theory (DFPT) for the computations of the response properties with respect to the atomic displacement and homogeneous electric field perturbation has been recently developed and implemented into the all-electron, numeric atom-centered orbitals electronic structure package FHI-aims. It is found that the bottleneck for large scale applications is the computation of the response density matrix, which scales as O(N3). Here for the response properties with respect to the homogeneous electric field, we present an efficient parallel linear scaling algorithm for the response density matrix calculation. Our scheme is based on the second-order trace-correcting purification and the parallel sparse matrix-matrix multiplication algorithms. The new scheme reduces the formal scaling from O(N3) to O(N), and shows good parallel scalability over tens of thousands of cores. As demonstrated by extensive validation, we achieve a rapid computation of accurate polarizabilities using DFPT. Finally, the computational efficiency of this scheme has been illustrated by making the scaling tests and scalability tests on massively parallel computer systems. Copyright © 2020, The Authors. All rights reserved.

关键词： Matrix algebra

Exploring vestibulo-ocular adaptation in a closed-loop neuro-robotic experiment using STDP. A simulation study

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Naveros, Francisco Garrido, Jesús A. Arleo, Angelo Ros, Eduardo Luque, Niceto R. Department of Computer Architecture and Technology University of Granada Granada18014 Spain Institut de la Vision Institut National de la Santé et de la Recherche Médicale U968 and Centre National de la Recherche Scientifique ParisUMR_7210 France UMR_S 968 Sorbonne Universités Université Pierre et Marie Curie Paris 06 Paris France

Studying and understanding the computational primitives of our neural system requires for a diverse and complementary set of techniques. In this work, we use the Neuro-robotic Platform (NRP) to evaluate the vestibulo ocular cerebellar adaptation (Vestibulo-ocular reflex, VOR) mediated by two STDP mechanisms located at the cerebellar molecular layer and the vestibular nuclei respectively. This simulation study adopts an experimental setup (rotatory VOR) widely used by neuroscientists to better understand the contribution of certain specific cerebellar properties (i.e. distributed STDP, neural properties, coding cerebellar topology, etc.) to r-VOR adaptation. The work proposes and describes an embodiment solution for which we endow a simulated humanoid robot (iCub) with a spiking cerebellar model by means of the NRP, and we face the humanoid to an r-VOR task. The results validate the adaptive capabilities of the spiking cerebellar model (with STDP) in a perception-action closed-loop (r-VOR) causing the simulated iCub robot to mimic a human behavior. Copyright © 2020, The Authors. All rights reserved.

关键词： Brain