检索结果-内蒙古大学图书馆

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Oldenhof, Martijn Ács, Gergely Pejó, Balázs Schuffenhauer, Ansgar Holway, Nicholas Sturm, Noé dieckmann, Arne Fortmeier, Oliver Boniface, Eric Mayer, Clément Gohier, Arnaud Schmidtke, Peter Niwayama, ritsuya Kopecky, dieter Mervin, Lewis rathi, Prakash Chandra Friedrich, Lukas Formanek, András Antal, Peter rahaman, Jordon Zalewski, Adam Heyndrickx, Wouter Oluoch, Ezron Stößel, Manuel Vančo, Michal Endico, david Gelus, Fabien de Boisfossé, Thaïs darbier, Adrien Nicollet, Ashley Blottière, Matthieu Telenczuk, Maria Nguyen, Van Tien Martinez, Thibaud Boillet, Camille Moutet, Kelvin Picosson, Alexandre Gasser, Aurélien djafar, Inal Simon, Antoine Arany, Ádám Simm, Jaak Moreau, Yves Engkvist, Ola Ceulemans, Hugo Marini, Camille Galtier, Mathieu KU Leuven ESAT-STADIUS Kasteelpark Arenberg 10 Heverlee3001 Belgium BME-HIT CrySyS Lab Budapest Hungary BME-MIT Budapest Hungary Novartis Institutes for BioMedical Research Novartis Campus BaselCH-4002 Switzerland Bayer AG Leverkusen51373 Germany Substra Foundation - Labelia Labs Nantes France Discngine 79 Avenue Ledru Rollin Paris75012 France Institut de Recherches Servier 125 chemin de ronde Croissy-sur-Seine78290 France Boehringer Ingelheim RCV GmbH & Co KG Vienna Austria Molecular AI Discovery Sciences R&D AstraZeneca Cambridge United Kingdom R&D IT AstraZeneca Cambridge United Kingdom Molecular AI Discovery Sciences R&D AstraZeneca Gothenburg Sweden Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden Merck KGaA Global Research & Development Frankfurter Strasse 250 Darmstadt64293 Germany GmbH Staffelseestraße 2 Munich81477 Germany Pillar Biosciences Inc. 9 Strathmore Rd NatickMA01760 United States Janssen Pharmaceutica NV Turnhoutseweg 30 Beerse2340 Belgium Kubermatic Hamburg Germany Owkin Paris France

ISBN: (纸本)9781577358800

To apply federated learning to drug discovery we developed a novel platform in the context of European Innovative Medicines Initiative (IMI) project MELLOddY (grant n°831472), which was comprised of 10 pharmaceutical companies, academic research labs, large industrial companies and startups. The MELLOddY platform was the first industry-scale platform to enable the creation of a global federated model for drug discovery without sharing the confidential data sets of the individual partners. The federated model was trained on the platform by aggregating the gradients of all contributing partners in a cryptographic, secure way following each training iteration. The platform was deployed on an Amazon Web Services (AWS) multi-account architecture running Kubernetes clusters in private subnets. Organisationally, the roles of the different partners were codified as different rights and permissions on the platform and administrated in a decentralized way. The MELLOddY platform generated new scientific discoveries which are described in a companion paper. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Industrial research

来源：评论

学校读者我要写书评

暂无评论

Constructing a Blockchain-Based Loyalty Program Model for Secure and Transparent Customer rewards in retail Marketing

Constructing a Blockchain-Based Loyalty Program Model for Se...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Ch. Anudeep Kathari Santosh M Sandeep Kumar Jahnavi M Sabareesh r B Kiran Bala GITAM school of business GITAM University Visakhapatnam A.P. Department of MBA CMR Institute of Technology Bengaluru India RV Institute of Management Bengaluru India Skill Development & Employability Programs Fortuna Business Solutions(R&D) Coimbatore Tamil Nadu Department of Artificial Intelligence and Data Science K. Ramakrishnan college of Engineering Trichy TN

ISBN: (数字)9798350305463

ISBN: (纸本)9798350305470

As the retail industry continues to evolve in the digital era, businesses are exploring innovative solutions to enhance customer engagement and loyalty. This research proposes a novel approach to loyalty programs by leveraging blockchain technology to create a secure and transparent model for customer rewards. Traditional loyalty programs often face challenges related to security, transparency, and trust, leading to issues such as fraud and customer skepticism. The proposed model outlines the design and implementation of a blockchainbased loyalty program, ensuring a secure and immutable ledger for tracking customer transactions and rewards. Smart contracts, self-executing contracts with predefined rules, are utilized to automate and enforce the terms of the loyalty program, reducing the potential for disputes and enhancing transparency. The decentralized nature of the blockchain ensures that customer data is securely stored and accessible only to authorized parties, addressing privacy concerns prevalent in centralized loyalty systems. This research employs a mix of theoretical analysis and practical implementation to validate the feasibility and effectiveness of the blockchain-based loyalty program model. The proposed Ethereum Blockchain model stands out with a significantly higher throughput of 5300 transactions per day, accompanied by an exceptional transaction transparency score of 99.5 .

关键词： Industries data privacy Communication systems Smart contracts Throughput Blockchains Fraud

来源：评论

学校读者我要写书评

暂无评论

Optimization of Natural Language Processing Models for Multilingual Legal document Analysis

Optimization of Natural Language Processing Models for Multi...

引用

IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS)

作者： A. radhika Narinder Kumar Bhasin Sabareesh r Yallapragada ravi raju K.N.V. Satyanarayana I Infant raj Department of CSE SRK Institute of Technology Vijayawada lndia Amity University Zonal Head Indian Institute of Banking and Finance Delhi India Academic Training Skill Development & Employability Programs Fortuna Business Solutions(R&D) Coimbatore India Department Of Computer Science &Technology Madanapalle Institute of Technology & Science Madanapalle Andhra Pradesh India Department of ECE S.R.K.R. Engineering College China amiram bhimavaram A.P India Department of computer science & Engineering K.Ramakrishnan college of Engineering Trichy Tamil Nadu India

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361193

Multilingual legal document analysis poses unique challenges in the field of Natural Language Processing (NLP) due to the intricacies of legal language and the diverse linguistic landscape of legal texts across jurisdictions. This paper presents an optimization framework designed to enhance the performance of NLP models specifically tailored for multilingual legal document analysis. The proposed framework incorporates advanced techniques in pre-processing, feature engineering, and model architecture to address the complexities inherent in legal language. Leveraging multilingual embeddings and domain-specific knowledge, the model demonstrates improved accuracy in tasks such as named entity recognition, sentiment analysis, and document categorization across a range of languages. Additionally, the optimization framework emphasizes the importance of domain adaptation, acknowledging the nuances and variations in legal terminology across different legal systems. Through a combination of transfer learning and fine-tuning strategies, the model adapts to specific legal domains, ensuring robust performance in diverse legal contexts. Experimental results on a comprehensive dataset of multilingual legal documents validate the effectiveness of the proposed optimization framework. Comparative analyses with baseline models showcase significant improvements in precision, recall, and overall model performance. The findings underscore the potential of the optimized NLP model for applications in legal information retrieval, contract analysis, and legal knowledge management in a multilingual context. This research contributes to the growing body of knowledge in NLP and legal informatics, offering a valuable resource for researchers, practitioners, and developers working on multilingual legal document analysis. The optimized model presented in this paper has the potential to enhance the efficiency and accuracy of automated systems in handling legal texts across diverse linguistic enviro

关键词： Analytical models Adaptation models Text analysis Law Terminology Transfer learning Linguistics

来源：评论

学校读者我要写书评

暂无评论

Simulation-based trajectory tracking coordination of intelligent vehicle with explicit model prediction

引用

International Journal of Simulation and Process Modelling 2020年第6期15卷 546-561页

作者： Xu, Xingyuan Xie, Liyang Zhang, Yin Northeastern University Wenhua Rd. 3-11 Shenyang110819 China Brilliance Auto R&D Center Economical and Technology Development Zone No. 12 8th Rd. Shenyang110141 China

In this paper a novel approach to trajectory tracking problem of intelligent vehicle is presented. A model-based optimisation algorithm for steering systems with multiple physical constraints is designed. A simplified linear vehicle model is designed in order to improve its real-time ability. Moreover, an offline solving method based on explicit model predictive control (EMPC) is presented to improve the computation speed. The simulation results show the offline solving method has the same tracking performance compared with the online solving problem by YALMIP toolbox. The computation speed is significantly increased. © 2020 Inderscience Enterprises Ltd.

关键词： Automobile steering equipment

来源：评论

学校读者我要写书评

暂无评论

development and Performance Evaluation of New High Temperature resistant Bulk Expanded Polymer Material 8th

Development and Performance Evaluation of New High Temperatu...

引用

8th International Field Exploration and development Conference, IFEdC 2019

作者： Shao, Li-ming Fang, Ping-liang Wei, Fa-lin Li, Wei-tao dai, Ming-li Research Institute of Petroleum Exploration and Development PetroChina Beijing China CNPC Engineering Technology R&D Company Limited PetroChina Beijing100083 China

ISBN: (纸本)9789811524844

High temperature-resistant polymer (HTP) was synthesized by in-situ cross-linking of interpenetrating reaction using H-2 monomer containing amide bond and H-1 molecule containing hydroxyl as raw materials. Ir spectra result showed that there were characteristic functional groups of H-1 and H-2 cross bond at the same time, that was to say that H-1 cross-linking reaction and H-2 polymerization could simultaneously take place. The interpenetrating cross-linking structure, extension properties at room temperature and long-term heat resistance properties of the material were tested. The experiment results showed that in the whole range of observations, HTP material cross-links and interpenetrates uniformly. The SEM pictures confirmed the interpenetration structure of HTP material. After cross-linking and interpenetration, the scale of HTP structure became smaller than before. This material had tensile resistance, dispersion stability in water, volume expansion, and could reach the maximum swelling ratio of 1.69 within 1.5 h at room temperature. At 90 °C, 120 °C and 140 °C, after soaking 130 days in formation water, HTP volume reduction rate was 1.57%, 3.24% and 6.82%, respectively. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Heat resistance

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation for the Multi-media dynamic Changes in the Fracturing and development of Tight Oil reservoir 8th

Numerical Simulation for the Multi-media Dynamic Changes in ...

引用

8th International Field Exploration and development Conference, IFEdC 2019

作者： Fang, Ping-liang Shao, Li-ming Xu, Xian-guang Cheng, rong-chao Kang, Xiao-na CNPC Engineering Technology R&D Company Limited PetroChina Beijing100083 China Research Institute of Petroleum Exploration and Development PetroChina Beijing China

ISBN: (纸本)9789811524844

In order to identify the function of coupling of flow and deformation during fracturing and development in tight oil reservoir and study the effect on reservoir performances due to the multi-media dynamic changes. Based on the mechanics mechanism of multi-media deformation on tight sandstone reservoir, the coupling of multiphase flow and reservoir deformation during fracturing and production was stated. The dynamic model of reservoir parameters for different development stages and the multiphase seepage mathematical model were established. On this basis, an integration of fracturing and production software module was developed. According to the numerical simulation on staged fracturing of horizontal wells and production in a Xinjiang tight oil field, the changing rules of physical parameters in porous and fracture media were obtained. By using this technology, the deformation law of multi-media in different development stages, such as expansion and contraction, opening and closing, rupture and propagation could be revealed;meanwhile, the effect of coupling of flow and deformation interaction on reservoir performances was analyzed quantitatively. Therefore, numerical simulation for dynamic changes of the multi-media in the fracturing and production can be used to exploit tight oil reservoir highly efficiently. © 2020, Springer Nature Singapore Pte Ltd.

关键词： deformation

来源：评论

学校读者我要写书评

暂无评论

Characterization of wear modes in orthogonal milling of 15-5PH stainless steel 24

Characterization of wear modes in orthogonal milling of 15-5...

引用

24th International ESAFOrM Conference on Material Forming, ESAFOrM 2021

作者： david, Tom Methon, Grégory M'Saoubi, rachid Girinon, Mathieu rech, Joël Courbon, Cédric Univ Lyon ENISE ECL ENTPE CNRS LTDS UMR 5513 Saint-EtienneF-42023 France R&D Material and Technology Development Seco Tools AB FagerstaSE-73782 Sweden CETIM 52 avenue Félix-Louat Senlis60300 France

ISBN: (纸本)9782870193020

Tool wear remains of high interest for industry, as it influences process costs and part's surface integrity. Although experimental and analytical investigations have been the main ways to investigate wear, the growing development of computational power enables predicting tool wear based on chip formation simulations. If this has been quite successful in turning, developments in milling are still limited due to the specific nature of this machining operation characterized by an interrupted cutting process leading to mechanical and thermal cyclic loadings onto the cutting tool. Wear modes are often not well characterized and become even more difficult to model as far as hard to machine material such as martensitic stainless steels are concerned. The present work propose to investigate wear in orthogonal milling of a 15-5PH martensitic stainless steel. An experimental campaign is first performed to identify the wear modes when cutting this material with uncoated and coated carbide tools. Milling forces, tool wear and material transfer are especially studied. A multi-scale numerical procedure is then developed by combining an Arbitrary-Lagrangian-Eulerian (ALE) thermomechanical model to a pure thermal sub-model in order to predict the thermomechanical loadings withstood by the tool. The thermal sub-model is applied at the scale of the coating in order to extract the thermal gradients generated by the interrupted cutting. These loadings are finally compared to the reported wear modes to identify a correlation and improve their understanding. © ESAFOrM 2021 - 24th Inter. Conf. on Mat. Forming. All rights reserved.

关键词： Coatings

来源：评论

学校读者我要写书评

暂无评论

Multiple dynamic evaluation and information management of research talents

Multiple dynamic evaluation and information management of re...

引用

Education, Knowledge and Information Management (ICEKIM), International Conference on

作者： dongsheng Li Yaping ren Drilling Equipment and Technology R&D Center Xi 'an Research Institute Co. LTD. China Coal Technology & Engineering Group Xi'an China Technology Development Department Xi'an Research Institute Co. LTD. China Coal Technology & Engineering Group Xi'an China

ISBN: (纸本)9781665416672

In order to solve the problem of talent evaluation and information management in manufacturing enterprises, a diversified dynamic evaluation information management system for manufacturing research talents and teams is constructed. Through the clustering algorithm of scientific research results built into the IPd talent information management system, the scientific research talents in the product development process are classified into five categories: basic research, applied research, technology development, results transformation and science and technology management services. The system scores the diversity indicators of research individuals with hierarchical analysis, and the four dimensions of finance, customers, internal operation, and learning and growth with the balanced scorecard method. The system has the function of classifying the information of scientific research achievements of enterprise talents; the function of storing, managing and classifying the information of scientific research talents; and the function of retrieving the information of scientific research achievements and talents for the decision-making level. The research on the multiple dynamic evaluation and information management system of scientific research talents is useful for improving the evaluation mechanism of r&d talents and teams, scientific research achievements and talent information management in manufacturing enterprises.

关键词： Symbiosis technology management Heuristic algorithms Education Finance Product development Manufacturing

来源：评论

学校读者我要写书评

暂无评论

From requirements to prototyping: Application of human-system integration methodology to digital twin design 23

From requirements to prototyping: Application of human-syste...

引用

23rd International Conference on Engineering design, ICEd 2021

作者： Camara dit Pinto, Stélian Masson, dimitri Villeneuve, Eric Boy, Guy Urfels, Laetitia Université Paris-Saclay CentraleSupélec Laboratoire Génie Industriel Gif-sur-Yvette91190 France UNIV. BORDEAUX ESTIA INSTITUTE OF TECHNOLOGY BidartF-64210 France TOTAL SE R&D Program Gas and Sustainable development Pau64000 France

Industrial digital transformation is bringing a need for new tools and concepts. However, designing such complex tools and concept requires methods to be correctly implemented. These methods are studied as part of system engineering to satisfy various identified goals, and more specifically human-system integration, which is the topic of this paper. This article introduces the method used to define key elements of human perception of reality called reality anchors to design scenarios to be tested in a digital twin prototype. This method goes from regulation study to user cognitive function analysis on the specific case of digital twin designing in oil-and-gas industry. This method highlighted the differences between theoretical process and the followed process as well as tools and competencies used to identify reality anchors. This knowledge will then be used to implement a new process to be implemented with a digital twin and scenarios to test the prototype using realistic simulation. © ICEd *** right reserved.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

Effect of Sds on the Formation and Blockage Characteristics of Ch4 Hydrate in a Flow Loop

SSRN

引用

SSrN 2022年

作者： Zang, Chunyang Ma, Guiyang Huang, Shaochang Qin, Yue Ao, di Liu, Chaoguang Zhang, Yuda College of Petroleum Engineering Liaoning Petrochemical University Liaoning Fushun113001 China Research Institute of Petroleum Exploration & Development Beijing100083 China CNPC Engineering Technology R&D Company Limited Beijing102206 China

Anti-agglomeration is an ideal solution for the reduction of gas hydrate risks in deep-sea pipelines. Currently, the ineffectiveness of water-based systems limits their application. To ensure safe flow within a pipeline, a high-pressure flow loop with observation windows was designed, and SdS was used as an anti-agglomerant (AA). A series of CH 4 hydrate formation and slurry flow experiments was carried out under horizontal and inclined flow loops. The growth and blockage rules of hydrates in SdS solution and the effects of different factors on the hydrate induction period and blockage time were obtained. The experimental results show that SdS has a good anti-agglomeration effect in the water-based system. After the addition of SdS, the hydrate can only minimally deposit on the wall, allowing the hydrate slurry to flow stably for a long time and a higher volume fraction. Increasing the flow rate can prolong the hydrate slurry flow time. With the increase in the inclination angle of the loop, hydrate particles with larger particle sizes are more likely to appear, and the time until blockage is decreased. The flow rate in the loop decreases with increasing hydrate particle size. Understanding the flow process and blockage trend of hydrate slurry in a pipeline transportation system can, to an extent, provide a reference for the industrial application of CH 4 hydrate slurry flow. © 2022, The Authors. All rights reserved.

关键词： Agglomeration

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：