检索结果-内蒙古大学图书馆

11th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2024

作者： Inokuchi, Yuto Gonzalez, Pedro Henrique Aritsugi, Masayoshi Mendonca, Israel Kumamoto University Graduate School of Science and Technology Kumamoto Japan Federal University of Rio de Janeiro System Engineering and Computer Science Program Rio de Janeiro Brazil Kumamoto University Faculty of Advanced Science and Technology Kumamoto Japan

ISBN: (纸本)9798350367300

In this paper, we aim to reduce the number of nodes from Graph Neural Networks (GNNs), thereby simplifying models and reducing computational costs. GNNs are highly effective for various tasks, such as prediction, classification, and clustering, due to their ability to learn node and edge attributes and relationships, and they have been utilized for intelligent transportation systems recently by converting sensor networks into graph structures. Deep spatio-temporal neural networks, including Spatio-Temporal Graph Convolutional Networks (STGCNs), capture spatial and temporal dependencies, making them suitable for traffic speed forecasting, traffic demand prediction, and travel time estimation. Despite their success, GNNs face challenges in industrial applications due to significant memory usage and time consumption. In this paper, we propose a new approach to node reduction that outperforms existing methods in computational efficiency. Our experiments on two real-world traffic datasets demonstrate that using the heuristic and edge information to reduce nodes can cut computation time of optimization up to 95% and, by eliminating noise, can even enhance prediction accuracy. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Hyperparameter Optimization Using Deep Q-Network and BRKGA 13

Efficient Hyperparameter Optimization Using Deep Q-Network a...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Kobayashi, Kosei Aritsugi, Masayoshi González, Pedro Henrique Mendonça, Israel Graduate School of Science and Technology Kumamoto University Kumamoto Japan Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan System Engineering and Computer Science Program Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (纸本)9798350308365

Hyperparameter optimization (HPO) is paragon to maximize performance when designing machine learning models. Among different HPO methods, Genetic Algorithm (GA) based optimization is considered effective because it allows a wide and diverse range of solutions to be explored. However, GA's exploratory nature makes this type of algorithm to evaluate many solutions that do not improve the overall performance. This is specially costly when the objective function to be evaluated is time-consuming, like in the HPO field. In this paper, we propose an efficient hybrid algorithm that is able to reduce computational cost by combining deep reinforcement learning with the Biased Random Key Genetic Algorithm (BRKGA), a variant of genetic algorithms. Our reinforcement learning agent has a decision-making role during the population's fitness calculation, in which it filters out chromosomes that would not improve the overall fitness of the population. The agent uses small amounts of pre-trained data to identify trends in potentially good solutions, and carry out its decision process. We conduct experiments on eight different datasets to assess the effectiveness of the proposed method, and the results show that the proposed method can significantly reduce the computation time of hyperparameter search using BRKGA (up to 44% reduction in computational time) without compromising the quality of the solution (no statistically difference in results). © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Coordinated Planning Model with Demand Uncertainty

引用

OPSEARCH 2017年第2期40卷 63-80页

作者： Nagendra N. Nagarur Wipanan Iaprasert Anulark Techanitisawad Systems Science and Industrial Engineering Department Binghamton University Binghamton USA Industrial System Engineering Program Asian Institute of Technology Pathumthani Thailand

This paper develops a coordinated planning model for production and order planning for single-manufacturer and single-retailers, and single-manufacturer and two-retailers. The application is for products with short lifecycles, such as fashion goods. The demand is assumed to be random with a normal distribution, and is linearly correlated in the case of two retailers. The coordinated policy is compared with a ‘returns’ policy model where the manufacturer buys back all the unsold items at a pre-specified price. Order quantities and profits for manufacturer and retailer are derived for base model, returns policy model, and for coordinated planning model, all cast as a newsvendor problem. Results show that the expected total profits are higher for coordinated model than for other models. A compensation or profit sharing scheme is then suggested based on returns policy and it is shown that the coordinated model with such sharing yields a ‘win-win’ situation for both suppliers and retailers. Numerical results are presented to illustrate the profit patterns under various conditions. The model shows that coordination of such planning in supply chains has considerable economic benefits.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Responsiveness Improvement of Idling Speed Control for Automotive Using SMC

引用

Journal of Software engineering and Applications 2009年第5期2卷 309-315页

作者： Yang ZHANG Nobuo KURIHARA Hiroyuki YAMAGUCHI Doctor of Science Program in Mechanical Systems Hachinohe Institute of Technology Graduate School of Engineering Hachinohe Institute of Technology Department of System and Information Hachinohe Institute of Technology

To improve the responsiveness of engine speed control to disturbances, robust controls were investigated by simulation. The intake air control system of a gasoline engine is a typical nonlinear system, and the disturbances and parameter perturbations are generally regarded as being the unstable factors with regard to engine control. In this paper, a Mean-Value Engine Model (MVEM) with disturbances and parameter perturbations is investigated using Sliding Mode Control (SMC), which is a form of variable structure control, with a view to address instability in the idle speed control process. The simulation results confirmed that, compared with a conventional PI (Proportional-Integral) controller, the stability of the idle speed for an engine that is being subjected to disturbances, parameter variations and background noise is greatly improved by the application of SMC.

关键词： Gasoline Engine Intake Air Control Sliding Mode Control Simulation

来源：评论

学校读者我要写书评

暂无评论

Online measurement of polymer melt viscosity in injection molding 75

Online measurement of polymer melt viscosity in injection mo...

引用

75th Annual Technical Conference and Exhibition of the Society of Plastics Engineers, SPE ANTEC Anaheim 2017

作者： Huang, Ming-Shyan Nian, Shih-Chih Chen, Jian-Yu Yang, Kai-Jye Tseng, Jian-Chou Dept. of Mechanical and Automation Engineering National Kaohsiung First University of Science and Technology Taiwan Dept. of Power Mechanical Engineering National Taitung College Taiwan Bachelor Program in Precision System Design Feng Chia University Taiwan

ISBN: (纸本)9780692883099

Melt viscosity, determined by the shear rate, barrel temperatures, and pressure during plasticization, greatly affects the flow ability of polymer melts as well as the quality of injection-molded parts. In particular, the consistency of molding qualities is highly relevant to the plasticizing quality at each cycle (i.e., injection molding requiring a high yield rate highly relies on the stability of polymer melts). However, numerous factors affect the plasticizing quality, including the geometry of injection screws, processed polymer materials, processing parameters of plasticization such as the feeding rate, screw rotational speed, barrel temperatures, back pressure, and screw backward speed. The conventional approach of plasticization in injection molding machines uses a single reciprocating screw for conveying, melting, and metering polymer melts. The plasticizing quality is roughly adjusted by indirectly controlling barrel temperatures;thus, the melt viscosity varies. An in-suit approach of assuring melt quality is to measure the melt viscosity variation online, which is a more suitable indicator of the plasticizing quality than temperature. This study thus monitored the melt viscosity variations in polymer melts by using in-mold pressure sensors. Furthermore, the effects of the injection velocity and mold temperature on the melt viscosity variations were examined.

关键词： Polymer melts

来源：评论

学校读者我要写书评

暂无评论

An optimization-based approach to software development process tailoring

An optimization-based approach to software development proce...

引用

2nd International Symposium on Search Based Software engineering, SSBSE 2010

作者： Magdaleno, Andréa Magalhães COPPE/PESC System Engineering and Computer Science Program UFRJ Rio de Janeiro Brazil NP2Tec Research and Practice Group in Information Technology UNIRIO Rio de Janeiro Brazil

ISBN: (纸本)9780769541952

A major activity performed by the manager before starting a software project is tailoring its development process. Such activity requires information about the context under which the project will be executed, including organizational, project, and team characteristics. In addition, it also requires pondering many factors and evaluating all existing constraints. In this scenario, we claim that a balance between collaboration and discipline can be the drivers to tailor software development processes in order to meet project and organization needs. With the purpose of facilitating this balancing, it is possible to automate some of the steps to solve the problem, reducing the effort required to execute this task and improving the obtained process. Therefore, this work presents an optimization-based approach where the balancing in process tailoring is defined, modeled and briefly analyzed. This approach uses collaboration and discipline as utility functions to select the most appropriate process for a software development project, considering its current context. © 2010 IEEE.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

An Executable system Architecture Approach to Discrete Events system Modeling Using SysML in Conjunction with Colored Petri Net

An Executable System Architecture Approach to Discrete Event...

引用

2nd Annual IEEE Internatioal systems Conference

作者： Renzhong Wang Cihan H. Dagli System Engineering Graduate Program Missouri University of Science and Technology Rolla MO USA

This paper proposes an executable system architecting paradigm for discrete event system modeling and analysis through integration of a set of architecting tools, executable modeling tools, analytical tools, and visualization tools. The essential step is translating SysML-based specifications into Colored Petri Nets (CPNs) which enables rigorous static and dynamic system analysis as well as formal verification of the behavior and functionality of the SysML-based design. A set of tools have been studied and integrated that enable a structured architecture design process. Some basic principles of executable system architecture for discrete event system modeling that guide the process of executable architecture specification and analysis are discussed. This paradigm is aimed at general system design. Its feasibility was demonstrated with a C4-type network centric system as an example. The simulation results was used to check the overall integrity and internal consistency of the architecture models, refine the architecture design, and, finally, verify the behavior and functionality of the system being modeled.

关键词： Discrete-event system SysML CPN Modeling Executable Architecture

来源：评论

学校读者我要写书评

暂无评论

One-step flow synthesis of size-controlled polymer nanogels in a fluorocarbon microfluidic chip

引用

RSC Advances 2024年第16期14卷 11258-11265页

作者： Montalbo, Reynaldo Carlos K. Wu, Meng-Jie Tu, Hsiung-Lin Institute of Chemistry Academia Sinica Taipei11529 Taiwan Nanoscience and Technology Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan Department of Engineering and System Science National Tsing-Hua University Hsinchu300044 Taiwan Department of Chemistry National Cheng-Kung University Tainan70101 Taiwan Genome and Systems Biology Degree Program Academia Sinica and National Taiwan University Taiwan

Synthetic polymer nanoparticles (NPs) with biomimetic properties are ideally suited for different biomedical applications such as drug delivery and direct therapy. However, bulk synthetic approaches can suffer from poor reproducibility and scalability when precise size control or multi-step procedures are required. Herein, we report an integrated microfluidic chip for the synthesis of polymer NPs. The chip could sequentially perform homopolymer synthesis and subsequent crosslinking into NPs without intermediate purification. This was made possible by fabrication of the chip with a fluorinated elastomer and incorporation of two microfluidic mixers. The first was a long channel with passive mixing features for the aqueous RAFT synthesis of stimuli-responsive polymers in ambient conditions. The polymers were then directly fed into a hydrodynamic flow focusing (HFF) junction that rapidly mixed them with a crosslinker solution to produce NPs. Compared to microfluidic systems made of PDMS or glass, our chip had better compatibility and facile fabrication. The polymers were synthesized with high monomer conversion and the NP size was found to be influenced by the flow rate ratio between the crosslinker solution and polymer solution. This allowed for the size to be predictably controlled by careful adjustment of the fluid flow rates. The size of the NPs and their stimuli-responses were studied using DLS and SEM imaging. This microfluidic chip design can potentially streamline and provide some automation for the bottom-up synthesis of polymer NPs while offering on-demand size control. © 2024 The Royal Society of Chemistry.

关键词： Microfluidic chips

来源：评论

学校读者我要写书评

暂无评论

How Fast Can a Robotic Drummer Beat Using Dielectric Elastomer Actuators?

引用

IEEE Robotics and Automation Letters 2024年第3期9卷 2638-2645页

作者： Wakle, Sudhir Lin, Tse-Han Huang, Shu Basu, Sumit Lau, Gih-Keong National Yang Ming Chiao Tung University International College of Semiconductor Technology Hsinchu30010 Taiwan Indian Institute of Technology Kanpur Mechanical Engineering Department Kanpur208016 India National Yang Ming Chiao Tung University Department of Graduate Degree Program of Robotics Hsinchu30010 Taiwan Industrial Technology Research Institute Mechanical and Mechatronics System Research Labs Zhudong 31057 Taiwan National Yang Ming Chiao Tung University Department of Mechanical Engineering International College of Semiconductor Technology Hsinchu30010 Taiwan

Fast drumming presents a speed challenge to many robotic arms. To simultaneously meet the needs for speed, stroke, and force, we proposed and tested a new double-saddle dielectric elastomer actuator (DEA) as the artificial biceps for driving a lightweight robotic drummer. This work finds that fast force induction is instrumental to the fast drumming by a DEA-driven drumstick. While a pure-shear series of DEA under a large pre-stretch and lateral reinforcement can generate a large isotonic stroke, it is not fast in isometric force induction. Instead, this work found a double-saddle DEA, which is a degenerated two-segment pure-shear DEA with a middle laterally buckled beam, managed to induce a faster isometric force at a 0.5 s down time constant when its ultimate actuation tapered due to substantial strain stiffening effect. As such, this double-saddle DEA-driven drummer suffered less from the dynamic stroke decrement than the 8-segment DEA did. A 4.4 g DEA managed to swing freely a 7.8 g drumstick up to nearly 60° at 6 kV and a maximum tip speed of up to 0.45 m/s. The drumming frequency upon 5.5 kV activation was up to 2-2.5 Hz. In comparison, an 8-segment pure-shear DEA-driven drummer failed to reach the drum when pulsed at 2 Hz. Interestingly, a slower stroke excited multiple drumbeats due to secondary bounces. To achieve a faster drumming to match a human drummer, it is foreseen that a harder dielectric elastomer material will help drive a faster soft robot. © 2016 IEEE.

关键词： Dielectric materials

来源：评论

学校读者我要写书评

暂无评论

Decision Support system in Determining the Achievement of Widyaiswara Value Using WASPAS and TOPSIS Algorithm 1

Decision Support System in Determining the Achievement of Wi...

引用

1st International Conference on technology Innovation and Its Applications, ICTIIA 2022

作者： Pratama, Yudhistira Adhitya Iswara, Bagus Ajie Nababan, Adli Abdillah Information System Studies Program Pelita Harapan University Medan Campus Faculty Of Computer Science Medan Indonesia Master's Study Program Informatics Engineering Universitas Sumatera Utara Faculty Of Computer Science And Information Technology Medan Indonesia Digital Business Study Program Stmik Pelita Nusantara Medan Indonesia

ISBN: (数字)9781665488266

ISBN: (纸本)9781665488266

Widyaiswara is required to show the best performance to fulfill his duties and obligations. Therefore, it is very important to measure the performance of the Widyaiswara, so that it can be used as evaluation material by the BPSDM PROVSU. However, the assessment process that occurs is still not precise and time-consuming. Therefore, to minimize this, a decision support system is needed that can minimize time errors and data processing in decision-making so that the assessment runs well and accurately. This system was built by applying the WASPAS method and the TOPSIS method. Based on the results of tests carried out five times, the results of the WASPAS method processing time resulted in an average processing time of 0.00029791 ms and an average memory usage value of 2.836.44 kb, while the results of the TOPSIS method processing time test resulted in an average processing time - an average of 0.000296428 ms and an average memory usage value of 2.862.34 kb. © 2022 IEEE.

关键词： Decision support systems

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：