检索结果-内蒙古大学图书馆

arXiv 2022年

作者： de Arruda Botelho Herr, Marius Graf, Michael Placzek, Peter König, Florian Bötte, Felix Stickel, Tyra Hieber, David Zimmermann, Lukas Slupina, Michael Mohr, Christopher Biergans, Stephanie Akgün, Mete Pfeifer, Nico Kohlbacher, Oliver Institute for Translational Bioinformatics University Hospital Tübingen Tübingen Germany Institute for Bioinformatics and Medical Informatics University of Tübingen Tübingen Germany Methods in Medical Informatics Department of Computer Science University of Tübingen Germany Applied Bioinformatics Department of Computer Science University of Tübingen Germany Medical Data Integration Center University Hospital Tübingen Tübingen Germany Medical Data Privacy and Privacy-Preserving ML on Healthcare Data Department of Computer Science University of Tübingen Germany

The need for data privacy and security – enforced through increasingly strict data protection regulations – renders the use of healthcare data for machine learning difficult. In particular, the transfer of data between different hospitals is often not permissible and thus cross-site pooling of data not an option. The Personal Health Train (PHT) paradigm proposed within the GO-FAIR initiative implements an’algorithm to the data’ paradigm that ensures that distributed data can be accessed for analysis without transferring any sensitive data. We present PHT-meDIC, a productively deployed open-source implementation of the PHT concept. Containerization allows us to easily deploy even complex data analysis pipelines (e.g, genomics, image analysis) across multiple sites in a secure and scalable manner. We discuss the underlying technological concepts, security models, and governance processes. The implementation has been successfully applied to distributed analyses of large-scale data, including applications of deep neural networks to medical image data. © 2022, CC BY.

关键词： Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Profit Maximization in a Gas Field Model 14

Profit Maximization in a Gas Field Model

引用

14th International Conference Management of Large-Scale System Development, MLSD 2021

作者： Skiba, Alexander Skiba, Nadezhda Federal Research Center 'Computer Science and Control' Russian Academy of Sciences Department of Mathematical Methods of Regional Programming Moscow Russia Kuban State Technological University Institute of Oil Gas and Energy Ministry of Science and Higher Education Department of Oil and Gas Business Named after Prof Vartumyan G. T. Krasnodar Russia

ISBN: (纸本)9781665412308

We consider a dynamic continuous gas production at a deposit. We set and solve the optimization control problem for maximum profit, taking into account the discount factor. The problem posed relates to some optimal control problems with a mixed constraint with a fixed time and an unbounded right endpoint. We use the principle of Pontryagin maximum in the Arrow form. © 2021 IEEE.

关键词： Deposits

来源：评论

学校读者我要写书评

暂无评论

Towards robust results in Multi-Criteria Decision Analysis: ranking reversal free methods case study 26

Towards robust results in Multi-Criteria Decision Analysis: ...

引用

26th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2022

作者： Wieckowski, Jakub Król, Robert Watróbski, Jaroslaw Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence Methods and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology Szczecin ul. Zolnierska 49 Szczecin71-210 Poland Doctoral School of University of Szczecin ul. Mickiewicza 16 Szczecin70-383 Poland Institute of Management University of Szczecin ul. Cukrowa 8 Szczecin71-004 Poland

The practical capabilities of decision support systems are beneficial in many complex problems. They aim to equip the decision-maker with knowledge about the preferred choices from the set under consideration. Often, there are minor differences between the alternatives analyzed, making it necessary to determine whether changes in the parameters characterizing them can influence their final position. For this purpose, a sensitivity analysis of the solutions can be used to examine the resistance of the results to changes. In this paper, we address the problem of performing the sensitivity analysis using MCDA methods. Most studies focus on testing the sensitivity of rankings of popular methods. However, their main disadvantage is their susceptibility to the phenomenon of ranking reversal. It may distort the results obtained in a sensitivity analysis. Therefore, it is worth using methods resistant to the ranking reversal phenomenon for this purpose. The SPOTIS and COMET methods were used in a theoretical multi-criteria problem, where the calculated results were then subjected to sensitivity analysis. The study showed that the SPOTIS method tends to be more robust to the computed results. © 2022 The Authors. Published by Elsevier B.V.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Accuracy of the TOPSIS Method with Different Input Data 26

Accuracy of the TOPSIS Method with Different Input Data

引用

26th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2022

作者： Król, Robert Wieckowski, Jakub Watróbski, Jaroslaw Doctoral School of University of Szczecin ul. Mickiewicza 16 Szczecin70-383 Poland Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence Methods and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology Szczecin ul. Zolnierska 49 Szczecin71-210 Poland Institute of Management University of Szczecin ul. Cukrowa 8 Szczecin71-004 Poland

Using fuzzy logic in multi-criteria problems allows real-world problems to be modeled with greater accuracy. In addition, it is possible to solve problems in which all data are incomplete. The difficulty may be the choice of an appropriate technique leading to a ranking calculation. methods fully integrated with fuzzy logic can be used. It is also possible to convert fuzzy data to crisp values and then apply traditional MCDA methods. In this paper, the performance of the TOPSIS method in a crisp and fuzzy environment was analyzed. The approaches of operating fully on uncertain data when calculating preference values were compared with converting data to crisp values using selected membership functions. The research has shown that significant differences and discrepancies in how the alternatives are classified are noticeable in the rankings. © 2022 The Authors. Published by Elsevier B.V.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

An extension method of sub-health intelligent prediction and transformation

引用

Procedia computer science 2022年 214卷 1554-1560页

作者： Junwen Sun Xingsen Li Zhengxiang Zhu Junlin Zeng Institute of Extenics and Innovation Methods Guangdong University of Technology Guangzhou 510006 China School of electromechanical engineering Guangdong University of Technology Guangzhou 510006China Consumer Finance Center Bank of NanJing NanJing 210002 China School of Computer Science and Technology Guangdong University of Technology Guangzhou 510006China

With the development of people's growing emphasis on health and the improving personal intelligent devices, wearable intelligent health monitoring devices have been popularized, and the data detected by them have great application potential in the prediction and improvement of sub-health. The current situation of wearable intelligent health monitoring devices is summarized, and the data of existing products and the data processing methods are listed. In order to study the relationship between physiological health data and sub-health, a construction method of decision tree and transformation tree based on extension theory is proposed, which enables it to intelligently acquire the rule knowledge of state transformation from the perspective of dynamic, and evaluate and analyze it through the superiority evaluation.

关键词： Sub-health Intelligence Health monitoring Extenics Decision Tree Transformation tree

来源：评论

学校读者我要写书评

暂无评论

Spectralhomogeneitycross frequencies can be a quality metric for the large-scale resting EEGpreprocessing

arXiv

引用

arXiv 2023年

作者： Hu, Shiang Ruan, Jie Langer, Nicolas Bosch-Bayard, Jorge Lv, Zhao Yao, Dezhong Valdes-Sosa, Pedro Antonio Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University 111 Jiulong Road Hefei230601 China Methods of Plasticity Research Department of Psychology University of Zurich Zurich Switzerland The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology University of Electronic Science and Technology of China Chengdu China Cuban Center for Neurocience La Habana Cuba

The brain projectsrequire the collectionof massiveelectrophysiologicaldata,aiming to the longitudinal, sectional,or populational neuroscience *** metrics automatically label the data after centralizedpreprocessing. However, although thewaveforms-basedmetricsarepartially useful, theymay be unreliable by neglecting the spectral profiles. Here, we detected the phenomenon of parallel log spectra(PaLOS)that thescalp EEG power in the log scale were parallel to each otherfrom 10% of 2549 HBNEEG. This phenomenon was reproduced in 8% of 412 PMDT EEG from 4 databases. We designed the PaLOSindex (PaLOSi) to indicate this phenomenon by decomposing the cross-spectraatdifferent frequenciesinto the common principal component spaces. We found that the PaLOS biophysically implied a prominently dominant dipolein the source spacewhich wasimplausible for the resting EEG. And it may be practically resulted from *** with the 1966 normative EEG cross-spectra, theHBN and the PMDT EEG with PaLOS presented generally much higherelectrode pairwise coherences and highersimilarity of coherence-based network patterns, which went against the known frequency dependent characteristic of coherence networks. We suggestthe PaLOSi should lay in the range of0.4-0.7 for large resting EEG quality assurance. Copyright © 2023, The Authors. All rights reserved.

关键词： Quality assurance

来源：评论

学校读者我要写书评

暂无评论

Crystal structure prediction by joint equivariant diffusion 23

Crystal structure prediction by joint equivariant diffusion

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Rui Jiao Wenbing Huang Peijia Lin Jiaqi Han Pin Chen Yutong Lu Yang Liu Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University and Institute for AIR Tsinghua University Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China National Supercomputer Center in Guangzhou School of Computer Science and Engineering Sun Yat-sen University Stanford University

Crystal Structure Prediction (CSP) is crucial in various scientific disciplines. While CSP can be addressed by employing currently-prevailing generative models (e.g. diffusion models), this task encounters unique challenges owing to the symmetric geometry of crystal structures—the invariance of translation, rotation, and periodicity. To incorporate the above symmetries, this paper proposes DiffCSP, a novel diffusion model to learn the structure distribution from stable crystals. To be specific, DiffCSP jointly generates the lattice and atom coordinates for each crystal by employing a periodic-E(3)-equivariant denoising model, to better model the crystal geometry. Notably, different from related equivariant generative approaches, DiffCSP leverages fractional coordinates other than Cartesian coordinates to represent crystals, remarkably promoting the diffusion and the generation process of atom positions. Extensive experiments verify that our DiffCSP significantly outperforms existing CSP methods, with a much lower computation cost in contrast to DFT-based methods. Moreover, the superiority of DiffCSP is also observed when it is extended for ab initio crystal generation. Code is available at https://***/jiaor17/DiffCSP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a SPOC of computer Ethics for students of computer science degree 11

Development of a SPOC of Computer Ethics for students of Com...

引用

11th International Conference on Virtual Campus, JICV 2021

作者： García-Holgado, Alicia García-Peñalvo, Francisco J. Therón, Roberto Vázquez-Ingelmo, Andrea Gamazo, Adriana González-González, Carina S. Iranzo, Rosa María Gil Silveira, Ismar Frango Alier Forment, Marc IUCE University of Salamanca GRIAL Research Group Computer Science Department Salamanca Spain IUCE University of Salamanca GRIAL GRIAL Research Group Didactics Organization and Research Methods Department Salamanca Spain University Institute of Women's Studies Universidad de la Laguna Computer and Systems Engineering Department San Cristóbal de la Laguna Spain Universitat de Lleida Computer Science and Industrial Engineering Department Lleida Spain Universidade Presbiteriana Mackenzie Faculdade de Computação e Informática Sao Paulo Brazil BCN-SEER BarcelonaTech Department of Service and Information System Engineering Barcelona Spain

ISBN: (纸本)9781665437035

Technology brings different benefits to society and involves challenges and ethical dilemmas that must be considered during any technology development. In this sense, graduates must recognise the social, legal, ethical and cultural issues inherent to the discipline of computer science. However, there is a lack of integration of computer ethics in the computer science curriculum in Spanish universities. This work introduces a pilot experience to develop a Small Private Open Course (SPOC) to introduce computer ethics as an extracurricular activity in the Bachelor's Degree of computer Engineering at the University of Salamanca. © 2021 IEEE.

关键词： Engineering education

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: Deep learning model for home automation and energy reduction in a smart home environment platform

引用

Neural Computing and Applications 2024年第28期36卷 17747-17747页

作者： Popa, Dan Pop, Florin Serbanescu, Cristina Castiglione, Aniello Computer Science Department University Politehnica of Bucharest Bucharest Romania National Institute for Research and Development in Informatics (ICI) Bucharest Romania Department of Mathematical Methods and Models University Politehnica of Bucharest Bucharest Romania Department of Computer Science University of Salerno Fisciano Italy

来源：评论

学校读者我要写书评

暂无评论

When to update your model: constrained model-based reinforcement learning 22

When to update your model: constrained model-based reinforce...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Tianying Ji Yu Luo Fuchun Sun Mingxuan Jing Fengxiang He Wenbing Huang Department of Computer Science and Technology Tsinghua University Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences JD Explore Academy *** Inc Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

ISBN: (纸本)9781713871088

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These discoveries encourage us to formulate a constrained lower-bound optimization problem to permit the monotonicity of MBRL. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns. Motivated by these analyses, we design a simple but effective algorithm CMLO (Constrained Model-shift Lower-bound Optimization), by introducing an event-triggered mechanism that flexibly determines when to update the model. Experiments show that CMLO surpasses other state-of-the-art methods and produces a boost when various policy optimization methods are employed.

关键词：

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：