检索结果-内蒙古大学图书馆

2nd International Symposium on Mathematical and Computational Oncology, ISMCO 2020

作者： Roblin, Elvire Cournede, Paul-Henry Michiels, Stefan Department of Biostatistics and Epidemiology Gustave Roussy University Paris-Saclay Villejuif France Oncostat U1018 Inserm University Paris-Saclay labeled Ligue Contre le Cancer Villejuif France MICS - Laboratory of Mathematics and Computer Science CentraleSupélec University of Paris-Saclay Gif-sur-Yvette France

ISBN: (纸本)9783030645106

Motivation: The objective of this work is to confront artificial neural network models with time-to-event data, using specific ways to handle censored observations such as pseudo-observations and tailored loss functions. Methods: Different neural network models were compared. Cox-CC (Kvamme et al., 2019) uses a loss function based on a case-control approximation. DeepHit (Lee et al., 2019) is a model that estimates the probability mass function and combines log-likelihood with a ranking loss. DNNSurv (Zhao et al., 2019) circumvents the problem of censoring by using pseudo-observations. We also proposed other ways of computing pseudo-observations. We investigated the prediction ability of these models using data simulated from an Accelerated Failure Time model (Friedman et al., 2001), with different censoring rates. We simulated 100 data sets of 4,000 samples and 20 variables each, with pairwise interactions and non-linear effects of random subsets of these variables. Models were compared using the concordance index and integrated Brier score. We applied the methods to the METABRIC breast cancer data set, including 1,960 patients, 6 clinical covariates and the expression of 863 genes. Results: In the simulation study, we obtained the highest c-indices and lower integrated Brier score with CoxTime for low censoring and pseudo-discrete with high censoring. On the METABRIC data, the neural networks obtained comparable 5-year and 10-year discrimination performances with slightly higher values for the models based on optimised pseudo-observations. Availability: https://***/eroblin/NN_Pseudobs © 2020, Springer Nature Switzerland AG.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Generic Tabu Search

引用

Journal of Software Engineering and Applications 2022年第7期15卷 262-273页

作者： Chadi Kallab Samir Haddad Imad El-Zakhem Jinane Sayah Mohamad Chakroun Nisrine Turkey Jinan Charafeddine Hani Hamdan Wafaa Shakir Department of Computer Science and Mathematics Faculty of Arts and Sciences University of Balamand Koura Lebanon Department of Telecom and Networks Issam Fares Faculty of Technology University of Balamand Koura Lebanon Faculty of Computer Science and Electrical Engineering Universit&#228 t Rostock Rostock Germany Faculty of Engineering Notre Dame University Jounieh Lebanon Université Paris-Saclay P&#244 le scientifique et technologique de Vélizy Laboratoire d’Ingénierie des Systèmes de Versailles (LISV EA4048) Vélizy France Université Paris-Saclay CentraleSupélec CNRS Laboratoire des Signaux et Systèmes (L2S UMR CNRS 8506) Gif-sur-Yvette France Department of Computer Systems Faculty of Engineering Al-Furat Al-Awsat Technical University Babil Iraq

The Multiple Sequence Alignment problem is considered to be an NP-Hard problem, requiring initially a specific encoding schema and design, as for any other of its siblings, to implement and run any of the main categories of heuristic. This paper intends to discuss our proposed generic implementation of the Tabu Search algorithm, a heuristic procedure proposed by Fred Glover to solve discrete combinatorial optimization problems. In this research, we try to coordinate and synchronize different designs/implementations discussed in many literatures, with some of the references mentioned in this paper. The basic idea is to avoid that the search for best solutions stops when a local optimum is found, by maintaining a list of non-acceptable or forbidden (taboo) solutions/costs, called Tabu list or Short-Term Memory (STM). In our algorithm, we attempt to add some executions tracing functionalities in order to help later analysis for initial parameters tuning. On the other hand, we propose to include the concept of a list called Long-Term Memory (LTM), so that some of the best solutions found so far can be saved, for search diversification.

关键词： Generic Heuristics Bio-Informatics NP-Hard Tabu Search STM LTM

来源：评论

学校读者我要写书评

暂无评论

Using asynchronous simulation approach for interactive simulation

Using asynchronous simulation approach for interactive simul...

引用

第十八届分布式计算及其应用国际学术研讨会

作者： Mengchen Wang Nicolas Férey Patrick Bourdot Frédéric Magoulès Mathematics in Interaction with Computer Science CentraleSupélec Université Paris-Saclay VENISE Team LIMSI-CNRS Université Paris-SudUniversité Paris-Saclay

This paper discusses about the advantage of using asynchronous simulation in the case of interactive simulation in which user can steer and control parameters during a simulation in *** models allow to compute each iteration faster to address the issues of performance needed in an highly interactive context,and our hypothesis is that get partial results faster is better than getting synchronized and final results to take a decision,in a interactive simulation context.

关键词： Asynchronous simulation approach interactive simulation Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Mathematical Model with Energy and Clustering Energy Based Routing Protocols as Remediation to the Directional Source Aware Routing Protocol in Wireless Sensor Networks

引用

Wireless Sensor Network 2022年第2期14卷 23-39页

作者： Samir Haddad Jinane Sayah Bachar El-Hassan Chadi Kallab Mohamad Chakroun Nisrine Turkey Jinan Charafeddine Hani Hamdan Faculty of Arts and Sciences Department of Computer Science and Mathematics University of Balamand Koura Lebanon Issam Fares Faculty of Technology Department of Telecom and Networks University of Balamand Koura Lebanon Faculty of Engineering Branch 1 Department of Electricity and Electronics Lebanese University Lebanon Faculty of Computer Science and Electrical Engineering The University of Rostock Rostock Germany Faculty of Engineering Notre Dame University Lebanon Université Paris-Saclay P&ocirc le scientifique et technologique de Vélizy Laboratoire d'Ingénierie des Systèmes de Versailles (LISV EA4048) Vélizy France Université Paris-Saclay CentraleSupélec CNRS Laboratoire des Signaux et Systèmes (L2S UMR CNRS 8506) Gif-sur-Yvette France

In this paper, a routing protocol for wireless sensor network, baptized energy based protocol (EBP) is proposed. Wireless sensor network presents many challenges and constraints, and one of the major constraints is the routing problem. Due to the limited energy of sensor nodes, routing in this type of network shall perform efficiently to maximize the network lifetime. One of the proposed algorithms is the directional source aware routing protocol (DSAP) which, after simulation, showed a lot of limitations and drawbacks. The modified directional source aware routing protocol (MDSAP) was proposed by the authors of this paper to address some of the DSAP’s limitations but remains limited to a fixed topology, fixed source and stationary nodes. So EBP is proposed and operated under different scenarios and showed, after its simulation using TinyOS, many advantages in terms of load balancing, free looping, minimizing packet error rate and maximizing network lifetime.

关键词： Cluster DSAP Energy MDSAP Routing Sensor Network Topology Energy Based Protocol

来源：评论

学校读者我要写书评

暂无评论

Interactive 3D fluid simulation:steering the simulation in progress using Lattice Boltzmann Method

Interactive 3D fluid simulation:steering the simulation in p...

引用

第十八届分布式计算及其应用国际学术研讨会

This paper describes a work in progress about software and hardware architecture to steer and control an ongoing fluid simulation in a context of a serious game *** propose to use the Lattice Boltzmann Method as the simulation approach considering that it can provide fully parallel algorithms to reach interactive time and because it's easier to change parameters while the simulation is in progress remaining physically relevant than more classical simulation *** describe which parameters we can modify and how we solve technical issues of interactive steering and we finally show an application of our interactive fluid simulation approach of water dam phenomena.

关键词： Lattice Boltzmann Methods Interactive Fluid Simulation Serious Game

来源：评论

学校读者我要写书评

暂无评论

Interactive 3D Fluid Simulation: Steering the Simulation in Progress Using Lattice Boltzmann Method

Interactive 3D Fluid Simulation: Steering the Simulation in ...

引用

International Symposium on Distributed Computing and Applications to Business, Engineering and science (DCABES)

作者： Mengchen Wang Nicolas Férey Patrick Bourdot Frédéric Magoulès Mathematics in Interaction with Computer Science CentraleSupélec Université Paris-Saclay Gif-sur-Y vette France VENISE Team Université Paris-Saclay Orsay France Universite Paris-Saclay Orsay France Universite Paris-Saclay Gif-sur-Yvette France

This paper describes a work in progress about software and hardware architecture to steer and control an ongoing fluid simulation in a context of a serious game application. We propose to use the Lattice Boltzmann Method as the simulation approach considering that it can provide fully parallel algorithms to reach interactive time and because it's easier to change parameters while the simulation is in progress remaining physically relevant than more classical simulation approaches. We describe which parameters we can modify and how we solve technical issues of interactive steering and we finally show an application of our interactive fluid simulation approach of water dam phenomena.

关键词： Three-dimensional displays Data visualization Computational modeling Solid modeling Data models Adaptation models Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Application of Artificial Intelligence for Automatic Vascular Segmentation: Development of a Hybrid Method Combining Expert System with Deep Learning

引用

European Journal of Vascular and Endovascular Surgery 2022年第2期63卷 e42-e43页

作者： Juliette Raffort Cédric Adam Lê Cong Duy Marion Carrier Fabien Lareyre Université Côte d’Azur CHU Inserm U1065 Nice France Clinical Chemistry Laboratory University Hospital of Nice Nice France Laboratory of Applied Mathematics and Computer Science (MICS) CentraleSupélec Université Paris-Saclay Gif-sur-Yvette France Department of Vascular Surgery Hospital of Antibes Juan-les-Pins Antibes France

来源：评论

学校读者我要写书评

暂无评论

POS0543 MACHINE LEARNING PREDICTS RESPONSE TO METHOTREXATE IN RHEUMATOID ARTHRITIS: RESULTS ON THE ESPOIR, t-REACH AND LEIDEN COHORTS

引用

Annals of the Rheumatic Diseases 2022年 81卷 535-535页

作者： V. Bouget J. Duquesne P.H. Cournède B. Fautrel F. Guillemin P. De Jong J. Heutz A. Van der Helm-van Mil M. Verstappen S. Bitoun X. Mariette Scienta Lab Research department Paris France Université Paris-Saclay CentraleSupélec Lab of mathematics and computer science (MICS) Gif-sur-Yvette France Sorbonne Université – Assistance Publique Hôpitaux de Paris Groupe Hospitalier Pitié Salpêtrière Service de Rhumatologie Paris France Université de Lorraine APEMAC Nancy France University Medical Center Department of Rheumatology Rotterdam Netherlands Leiden University Medical Center Department of Rheumatology Leiden Netherlands Université Paris Saclay Assistance Publique-Hôpitaux de Paris Hôpital Bicêtre Service de Rhumatologie Le Kremlin-Bicêtre France

Background Methotrexate (MTX) is the first line of treatment for rheumatoid arthritis (RA) patients. Unfortunately, 30% to 40% of RA patients do not respond to MTX, resulting in uncontrolled joint pain and potential joints destruction. At the same time, many efficient second-line treatments exist and can be given to the inadequate responder patients. Predicting patient response to MTX before prescribing the treatment is therefore a major goal and could enable physicians to directly prescribe second-line treatments if inadequate response to MTX is predicted. Objectives We aimed to build machine learning models based on simple clinical and biological data to predict patient response to MTX. Methods We used data from the ESPOIR early arthritis (1) and Leiden cohorts (2) to train the models, and the tREACH cohort to validate the results. We included patients that fulfilled the EULAR/ACR 2010 criteria and that were treated with MTX in monotherapy as their first treatment for RA. The models take as inputs patient's characteristics at treatment initiation and predict the therapeutic response, defined as the EULAR response 3 to 12 months after treatment initiation. We evaluated four missing data imputation methods (median, mean, MICE, KNN); we used the backward feature selection algorithm to select the most relevant variables; and compared the performances of four models (Linear Regression, Random Forest, XGBoost, and Catboost) on the training set by cross-validated them using the Area Under the ROC Curve (AUCROC). The best model was then evaluated on the validation dataset. Results We included 435 patients from the ESPOIR cohort, 243 patients from the Leiden cohort and 143 patients from the t-REACH cohort. Results of the model are displayed in Table 1 . The variables automatically selected to perform prediction were Sex, DAS28, White blood cells, AST, ALT and lymphocytes. Our model performs well on unseen data, this result comes from the fact that we included two different

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Fuzzy Relations and Properties for Explainable Artificial Intelligence

Learning Fuzzy Relations and Properties for Explainable Arti...

引用

IEEE International Conference on Fuzzy Systems

作者： Regis Pierrard Jean-Philippe Poli Celine Hudelot Data Analysis and System Intelligence Laboratory CEA LIST Gif-sur-Yvette cedex France Mathematics Interacting with Computer Science CentraleSupélec Paris-Saclay University Gif-sur-Yvette France

The goal of explainable artificial intelligence is to solve problems in a way that humans can understand how it does it. However, few approaches have been proposed so far and some of them lay more emphasis on interpretability than on explainability. In this paper, we propose an approach that is based on learning fuzzy relations and fuzzy properties. We extract frequent relations from a dataset to generate an explained decision. Our approach can deal with different problems, such as classification or annotation. A model was built to perform explained classification on a toy dataset that we generated. It managed to correctly classify examples while providing convincing explanations. A few areas for improvement have been spotted, such as the need to filter relations and properties before or while learning them in order to avoid useless computations.

关键词： Fuzzy logic Task analysis Decision trees Training Knowledge representation Partitioning algorithms Neural networks

来源：评论

学校读者我要写书评

暂无评论

L’intelligence artificielle prédit la non-réponse aux anti-TNF dans la polyarthrite rhumatoïde : résultats sur les cohortes ESPOIR et ABIRA

引用

Revue du Rhumatisme 2021年 88卷 A110-A110页

作者： J. Duquesne V. Bouget C. Paul-Henry B. Fautrel F. Guillemin H. Signe M. Pallardy P. Bröet S. Bitoun X. Mariette Scienta lab research department Scienta Lab Paris Lab of mathematics and computer science (mics) CentraleSupélec - université Paris-Saclay Gif-sur-Yvette Service de rhumatologie hôpital Pitié-Salpêtrière Paris École de santé publique faculté de médecine Vandoeuvre-lès-Nancy Inserm u1018 cesp hôpital Paul-Brousse AP–HP Villejuif Umr996 faculté de pharmacie Châtenay-Malabry Rhumatologie CHU Bicêtre Le Kremlin-Bicêtre

Introduction On dispose aujourd’hui de 14 traitements ciblés biologiques ou synthétiques différents dans la polyarthrite rhumatoïde (PR) et il n’existe que très peu de critères obj...

Introduction On dispose aujourd’hui de 14 traitements ciblés biologiques ou synthétiques différents dans la polyarthrite rhumatoïde (PR) et il n’existe que très peu de critères objectifs permettant de choisir celui qui serait le plus efficace pour un patient donné. L’objectif de cette étude est d’évaluer si l’intelligence artificielle (IA), exploitant des donnes clinicobiologiques, peut aider à prédire la réponse aux anti-TNF chez des patients PR résistants au méthotrexate (MTX). Patients et méthodes Nous utilisons les données de la cohorte d’arthrite récente ESPOIR (*** NCT03666091 ) et de l’étude ABIRA qui suit prospectivement des PR sous un première ligne d’anti-TNF. Pour être inclus, les patients doivent vérifier les critères ACR/EULAR 2010 et avoir eu au moins une ligne d’anti-TNF. La réponse thérapeutique est définie par le critère de réponse EULAR à 12 mois (±6 mois). ESPOIR a servi de cohorte d’entraînement et ABIRA de cohorte de validation. Trois modèles sont évalués via un processus de validation croisée d’un contre tous : régression logistique, Random Forest et XGBoost. Les modèles prennent en entrée les variables-patient avant l’initiation du traitement et prédisent la réponse thérapeutique. Leurs performances sont comparées via l’aire sous la courbe ROC (AUC) et le modèle obtenant les meilleures performances est sélectionné. Cette méthode est mise en œuvre sur les anti-TNF globalement, ensuite, les patients traités par étanercept (ETN) d’une part et anticorps monoclonaux anti-TNF (AM) d’autre part sont séparés et la méthode est de nouveau mise en œuvre. Résultats Nous avons inclus 203 patients d’ESPOIR et 128 d’ABIRA. Pour tous les traitements, le modèle sélectionné est Random Forest , les résultats obtenus sont présentés dans le Tableau 1 , avec l’intervalle de confiance à 95 % associé. Discussion La baisse des AUC entre ESPOIR et ABIRA est modérée donc les algorithmes se généralisent correctement d’une base à l’autre. Nous obtenons des

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：