检索结果-内蒙古大学图书馆

2nd International Workshop on Modelling to Program, M2P 2020

作者： Skvortsov, Nikolay A. Institute of Informatics Problems of Federal Research Center "Computer Science and Control" of Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9783030726959

The paper is dedicated to reusing domain models from one research problem being solved in the domain community to another. The accustomed approach to research including immediate integration of existing data resources and services for problem-solving is not efficient. Domain modeling can be applied to solve this issue. It allows reusing results of previous research in a domain community which include data resources, method implementations, and results of their integration. An approach to domain specification reuse is demonstrated in examples of solving astronomical problems. The experience in domain specification reuse shows the fast saturation of specifications during solving different problems in a domain within a community. © 2021, Springer Nature Switzerland AG.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

Computing Dataflow Architectures: History and Implementation Perspectives

Computing Dataflow Architectures: History and Implementation...

引用

2021 International Conference Engineering Technologies and computer science, EnT 2021

作者： Zakharov, Victor Stepchenkov, Yury Khilko, Dmitry Diachenko, Yury Federal Research Center 'Computer Science and Control' of the Russian Academy of Sciences Institute of Informatics Problems Moscow Russia

ISBN: (纸本)9781665426749

The article analyzes computational architectures with data flow controlling computations. In particular, it analyzes the reasons that prevented the formation of this promising class of architectures. The paper considered the features of algorithms in digital signal processing and the requirements from the digital signal processors. A more accurate accounting of these features allows for proposing an approach for introducing the dataflow paradigm into the DSP area. The paper considers the concept of a new multicore dataflow recurrent architecture developed at the Federal research Center 'computer science and control' of the Russian Academy of sciences. It is designed for the parallel computing implementation of real-time signal processing. This architecture is currently at the final stage of prototyping on FPGA. © 2021 IEEE.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

The principles of data reuse in research infrastructures

The principles of data reuse in research infrastructures

引用

2020 International Conference "Common Digital Space of Scientific Knowledge: Problems and Solutions", CDSSK 2020

作者： Skvortsov, Nikolay Institute of Informatics Problems of Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia

The principles known by FAIR abbreviation have been applied for different kinds of data management technologies to support data reuse. In particular, they are important for investigations and development in research infrastructures but applied in significantly different ways. These principles are recognized as prospective since, according to them, data in the context of reuse should be readable and actionable by both humans and machines. The review of solutions for data interoperability and reuse in research infrastructures is presented in the paper. It is shown that conceptual modeling based on formal domain specifications still has good potential for data reuse in research infrastructures. It allows to relate data, methods, and other resources semantically, classify and identify them in the domain, integrate and verify the correctness of data reuse. Infrastructures based on formal domain modeling can make heterogeneous data management and research significantly more effective and automated. © 2021 Copyright for this paper by its authors.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Design Validation of Recurrent Signal Processor FPGA prototype

Design Validation of Recurrent Signal Processor FPGA prototy...

引用

2021 IEEE East-West Design and Test Symposium, EWDTS 2021

作者： Stepchenkov, Yury Khilko, Dmitry Shikunov, Yury Orlov, Georgy Institute of Informatics Problems Federal Research Center 'Computer Science and Control' of the Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9781665445030

This paper describes the final stage of the FPGA prototype development of a recurrent signal processor. During the development of this prototype, a set of tools was created, based on which design verification was carried out. We describe the development process and the prototype validation methodology on a class of DSP tasks using a demo task of isolated word recognition. Taking the previously developed tools and methods for verifying software and hardware models, we have developed a specialized design validation tool. This solution made it possible to ensure the uniformity of the validation process for various types of architecture implementation and to establish the correctness of their operation. © 2021 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Unveiling drug-induced side effects through network-based analysis: an update

Unveiling drug-induced side effects through network-based an...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Alessio Funari Federica Conte Paola Paci Department of Translational and Precision Medicine Sapienza University of Rome Institute for Systems Analysis and Computer Science “Antonio Ruberti” National Research Council Rome Italy Institute for Systems Analysis and Computer Science “Antonio Ruberti” National Research Council Rome Italy Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

In this article, we propose an updated version of our previously developed model for predicting drug-side effect associations, applied to two case studies: long QT syndrome and asthma. The classifier accepts the name of a specific drug side effect as input and outputs a list of drugs potentially associated with this side effect. By simulating how drug effects propagate within the interactome using the Random Walk with Restart algorithm, the classifier identifies genes potentially associated with the onset of the side effect. Based on the rationale that the more a drug perturbs these genes, the more likely it is to cause the side effect, the model identifies drugs potentially linked to the onset of the side effect. Moreover, the model enables the categorization of drugs into chemical subclasses using the ClassyFire schema, facilitating the analysis of complex side effects, such as asthma, through more specific mechanisms. The results show that the model identifies both drugs known to be associated with certain side effects, as well as drugs not officially reported by the FDA, demonstrating its generalizability and practical relevance. This method is also adaptable for analyzing other side effects.

关键词： Drugs Analytical models Adaptation models Predictive models Classification algorithms Bioinformatics Chemicals Asthma

来源：评论

学校读者我要写书评

暂无评论

State Derivative Normalization for Continuous-Time Deep Neural Networks

引用

IFAC-PapersOnLine 2024年第15期58卷 253-258页

作者： Jonas Weigand Gerben I. Beintema Jonas Ulmen Daniel Görges Roland Tóth Maarten Schoukens Martin Ruskowski Chair of Machine Tools and Control Systems RPTU Kaiserslautern and the German Research Center for Artificial Intelligence Kaiserslautern Germany Control Systems (CS) Group at the Department of Electrical Engineering Eindhoven University of Technology Netherlands. R. Tóth is also affiliated to the Systems and Control Laboratory at the Institute for Computer Science and Control Budapest Hungary Institute for Electromobility RPTU Kaiserslautern Germany

The importance of proper data normalization for deep neural networks is well known. However, in continuous-time state-space model estimation, it has been observed that improper normalization of either the hidden state or hidden state derivative of the model estimate, or even of the time interval can lead to numerical and optimization challenges with deep learning based methods. This results in a reduced model quality. In this contribution, we show that these three normalization tasks are inherently coupled. Due to the existence of this coupling, we propose a solution to all three normalization challenges by introducing a normalization constant at the state derivative level. We show that the appropriate choice of the normalization constant is related to the dynamics of the to-be-identified system and we derive multiple methods of obtaining an effective normalization constant. We compare and discuss all the normalization strategies on a benchmark problem based on experimental data from a cascaded tanks system and compare our results with other methods of the identification literature.

关键词： System Identification Continuous-Time Neural Ordinary Differential Equations Nonlinear State-Space

来源：评论

学校读者我要写书评

暂无评论

Industrial Scenario of Renewable Energy-Based Electromobility 3rd

Industrial Scenario of Renewable Energy-Based Electromobilit...

引用

3rd International Conference on Energy Systems, Drives and Automations, ESDA 2020

作者： Szymanski, Jerzy Zurek-Mortka, Marta Faculty of Transport Electrical Engineering and Computer Science Kazimierz Pulaski University of Technology and Humanities Radom Poland Department of Control Systems Lukasiewicz Research Network Institute for Sustainable Technology Radom Poland

ISBN: (纸本)9789811672736

The article presents the concept of a hybrid network topology in the enterprises with the use of a solar power plant and energy storage as well as a drive frequency converter for charging of transportation battery of wheels vehicles and powering of electric caterpillar mining machines. Two important functionalities of the drive frequency converter as a unidirectional EV battery charger and for powering electric motors are presented. The obtained results of the simulation and experimental tests of the presented model confirm the possibility of controlling the DC current value of connected to drive frequency converter of the diode rectifier unit charging the EV battery. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Model-based Policy Optimization using Symbolic World Model

Model-based Policy Optimization using Symbolic World Model

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Andrey Gorodetskiy Konstantin Mironov Aleksandr Panov Center of Cognitive Modeling Moscow Institute of Physics and Technology Dolgoprudny Russia Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia Artificial Intelligence Research Institute Moscow Russia

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

The application of learning-based control methods in robotics presents significant challenges. One is that model-free reinforcement learning algorithms use observation data with low sample efficiency. To address this challenge, a prevalent approach is model-based reinforcement learning, which involves employing an environment dynamics model. We suggest approximating transition dynamics with symbolic expressions, which are generated via symbolic regression. Approximation of a mechanical system with a symbolic model has fewer parameters than approximation with neural networks, which can potentially lead to higher accuracy and quality of extrapolation. We use a symbolic dynamics model to generate trajectories in model-based policy optimization to improve the sample efficiency of the learning algorithm. We evaluate our approach across various tasks within simulated environments. Our method demonstrates superior sample efficiency in these tasks compared to model-free and model-based baseline methods.

关键词： Heuristic algorithms Robot kinematics Neural networks Reinforcement learning Predictive models Transformers Approximation algorithms Inference algorithms Trajectory Optimization

来源：评论

学校读者我要写书评

暂无评论

Al-Biruni Earth Radius(BER)Metaheuristic Search Optimization Algorithm

引用

computer Systems science & Engineering 2023年第5期45卷 1917-1934页

作者： El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Seyedali Mirjalili Nima Khodadad Mona A.Al duailij Amel Ali Alhussan Doaa Sami Khafaga Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Centre for Artificial Intelligence Research and Optimization Torrens University AustraliaFortitude ValleyQLD 4006Australia Yonsei Frontier Lab Yonsei UniversitySeoul03722Korea Department of Civil and Environmental Engineering Florida International UniversityMiamiUSA Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

Metaheuristic optimization algorithms present an effective method for solving several optimization problems from various types of applications and *** metaheuristics and evolutionary optimization algorithms have been emerged recently in the literature and gained widespread attention,such as particle swarm optimization(PSO),whale optimization algorithm(WOA),grey wolf optimization algorithm(GWO),genetic algorithm(GA),and gravitational search algorithm(GSA).According to the literature,no one metaheuristic optimization algorithm can handle all present optimization *** novel optimization methodologies are still *** Al-Biruni earth radius(BER)search optimization algorithm is proposed in this *** proposed algorithm was motivated by the behavior of swarm members in achieving their global *** search space around local solutions to be explored is determined by Al-Biruni earth radius calculation method.A comparative analysis with existing state-of-the-art optimization algorithms corroborated the findings of BER’s validation and testing against seven mathematical optimization *** results show that BER can both explore and avoid local *** has also been tested on an engineering design optimization *** results reveal that,in terms of performance and capability,BER outperforms the performance of state-of-the-art metaheuristic optimization algorithms.

关键词： Metaheuristics evolutionary optimization exploration exploitation mutation Al-biruni earth radius

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning based Real-Time Application for Engagement Detection 9

A Machine Learning based Real-Time Application for Engagemen...

引用

9th Scholar's Yearly Symposium of Technology, Engineering and Mathematics, SYSTEM 2023

作者： Iacobelli, Emanuele Russo, Samuele Napoli, Christian Department of Computer Control and Management Engineering Sapienza University of Rome Roma00185 Italy Department of Psychology Sapienza University of Rome Roma00185 Italy Institute for Systems Analysis and Computer Science Italian National Research Council Roma00185 Italy Department of Computational Intelligence Czestochowa University of Technology Czestochowa42-201 Poland

The study of human engagement has significantly grown in recent years, particularly accelerated by the interaction with a growing number of smart computing machines [1, 2, 3]. Engagement estimation has significant importance across various domains of study, including advertising, marketing, human-computer interaction, and healthcare [4, 5, 6]. In this paper, we propose a real-time application that leverages a single RGB camera to capture user behavior. Our approach implements a novel method for estimating human engagement in real-world scenarios by extracting valuable information from the combination of facial expressions and gaze direction analysis. To acquire this data, we employed fast and accurate machine learning algorithms from the external library dlib, along with custom versions of Residual Neural Networks implemented from scratch. For training our models, we used a modified version of the DAiSEE dataset, a multi-label user affective states classification dataset that collects frontal videos of 112 different people recorded in real-world scenarios. In the absence of a baseline for comparing the results obtained by our application, we conducted experiments to assess its robustness in estimating engagement levels, leading to very encouraging results. © 2023 Copyright for this paper by its authors.

关键词： Eye tracking

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：