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

High-Performance Chip Design With Parallel Architecture for Magnetic Field Imaging system

引用

IEEE Transactions on Instrumentation and Measurement 2024年 73卷 1-13页

作者： Lin, Ming-Yi Hsieh, Sheng-Hsien Chen, Ching-Han Lin, Chun-Hung Yuan Ze University Department of Computer Science and Engineering Taoyuan320315 Taiwan National Pingtung University of Science and Technology Program of Artificial Intelligence and Mechatronics Pingtung912301 Taiwan National Central University Department of Computer Science and Information Engineering Taoyuan32001 Taiwan International Games System Company Ltd. New Taipei City248 Taiwan

To address the limitations of typical coil detection systems and enhance the performance of traditional magnetic field imaging (MFI) systems, we propose a MFI system that uses a 4×4 array of anisotropic magnetoresistance (AMR) sensors. The core controller of the proposed system was designed using a pipelined parallelization algorithm and implemented on a high-speed field-programmable gate array (FPGA) in a fully hardware-based architecture. The designed MFI system can achieve parallel acquisition of magnetic field components from the 16-channel AMR sensor array, parallel data processing, parallel data transmission, and parallel computations in a single cycle of only 4 ms. Compared with typical detection systems, the proposed solution not only exhibits superior performance but can also provide dynamic visual representations of sensed information. © 1963-2012 IEEE.

关键词： Parallel architectures

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

Performance Comparison Study of Cherry Tomato Ripeness Detection Using Multiple YOLO Models

引用

Journal of Institute of Control, Robotics and systems 2024年第11期30卷 1214-1220页

作者： Yang, Dayeon Son, Hyoung Il Ju, Chanyoung Department of Convergence Biosystems Engineering Chonnam National University Korea Republic of Interdisciplinary Program in IT-Bio Convergence System Chonnam National University Korea Republic of Research Center for Biological Cybernetics Chonnam National University Korea Republic of Purpose Built Mobility Group Korea Institute of Industrial Technology Korea Republic of

Millions of tons of cherry tomatoes are produced annually, with the harvesting process being crucial. This paper presents a deep learning-based approach to distinguish the ripeness of cherry tomatoes during the harvesting process. It specifically analyzes the performance of the YOLO (You Only Look Once)v5 and YOLOv8 models, which are designed to rapidly detect the ripeness of cherry tomatoes in real time. The proposed system is expected to resolve rural issues caused by population decline and enhance productivity in cherry tomato harvesting environments. Future research will aim to apply this technology to harvesting robots for the automatic recognition and harvesting of cherry tomatoes. © 2024, Institute of Control, Robotics and systems. All rights reserved.

关键词： Fruits

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

Bioprinting Methods for Fabricating In Vitro Tubular Blood Vessel Models

引用

Cyborg and Bionic systems 2023年第1期4卷 178-195页

作者： Seon-Jin Kim Min-Gyun Kim Jangho Kim Jessie SJeon Jinsoo Park Hee-Gyeong Yi Department of Rural and Biosystems Engineering College of Agriculture and Life SciencesChonnam National UniversityGwangjuRepublic of Korea Department of Convergence Biosystems Engineering College of Agriculture and Life SciencesChonnam National UniversityGwangjuRepublic of Korea Interdisciplinary Program in IT-Bio Convergence System Chonnam National UniversityGwangju 61186Republic of Korea Department of Mechanical Engineering Korea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea Department of Mechanical Engineering Chonnam National UniversityRepublic of Korea

Dysfunctional blood vessels are implicated in various diseases,including cardiovascular diseases,neurodegenerative diseases,and *** studies have attempted to prevent and treat vascular diseases and understand interactions between these diseases and blood vessels across different organs and *** studies were conducted using 2-dimensional(2D)in vitro and animal ***,these models have difficulties in mimicking the 3D microenvironment in human,simulating kinetics related to cell activities,and replicating human pathophysiology;in addition,3D models involve remarkably high ***,in vitro bioengineered models(BMs)have recently gained *** created through biofabrication based on tissue engineering and regenerative medicine are breakthrough models that can overcome limitations of 2D and animal *** can also simulate the natural microenvironment in a patient-and target-specific *** this review,we will introduce 3D bioprinting methods for fabricating bioengineered blood vessel models,which can serve as the basis for treating and preventing various vascular ***,we will describe possible advancements from tubular to vascular ***,we will discuss specific applications,limitations,and future perspectives of fabricated BMs.

关键词： Blood organs printing

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach with BRKGA and Data Mining for the Early/Tardy Scheduling Problem 13

A Hybrid Approach with BRKGA and Data Mining for the Early/T...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Mendonça, Israel Fatyanosa, Tirana Noor Aritsugi, Masayoshi Silva, Pedro Henrique González Kumamoto University Faculty of Advanced Science and Technology Kumamoto Japan Brawijaya University Faculty of Computer Science Malang Indonesia Federal University of Rio de Janeiro System Engineering and Computer Science Program Rio de Janeiro Brazil

ISBN: (纸本)9798350308365

This paper introduces a novel hybrid genetic algorithm combined with data mining to solve a version of the early/tardy scheduling problem in which no unforced idle time may be inserted in a sequence. The chromosome representation of the problem is based on random keys and we use the Biased Random-Key Genetic Algorithm (BRKGA) to establish an order in which jobs are scheduled. A data mining component gathers data from the evolutionary steps of BRKGA and suggests chromosomes based on past observations. In this way, we address a key challenge in BRKGA - the exploration of solutions near an individual gene - by leveraging data-driven insights to refine and enhance the search space. Comparative analysis reveals that our hybrid algorithm significantly benefits from the pattern recognition capabilities of data mining, leading to improved scheduled efficiency. The results of a series of computational experiments underscore the potential of this hybrid approach that, although requiring slightly longer computational times, is better than the previous baseline BRKGA algorithm in terms of solution quality. © 2024 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Electric Motor Torque Meter Using Microcontroller

Design and Development of Electric Motor Torque Meter Using ...

引用

Research, Invention, and Innovation Congress (RI2C)

作者： Peerawat Meesuk Natthaphong Nak-Udom Kittiphong Phimyotha Program of Electrical Engineering and Automation Control System Faculty of Engineering and Industrial Technology Bansomdejchaopraya Rajabhat University Bangkok Thailand Program of Electromechanic Manufacturing Engineering Faculty of Engineering and Industrial Technology Bansomdejchaopraya Rajabhat University Bangkok Thailand

ISBN: (数字)9798331506018

ISBN: (纸本)9798331506025

This article presents the development of electric motor torque meter using microcontroller together with dynamometer process and application of light process to find out revolutions per minute (RPM) which torque is a variable that affects the effectiveness of electrical machine. A torque meter is, therefore, a tool that has an important role to work with mechanical part. The torque meter and RPM was tested and found that there is an error of torque measure at 13.74 percent and found that the torque has higher errors when it exceeds 2 N-m and there is an error of RPM at 5.36 percent.

关键词： Technological innovation Torque Microcontrollers Measurement uncertainty Size measurement Pollution measurement Electrical resistance measurement Tachometers Standards Electric motors

来源：评论

学校读者我要写书评

暂无评论

Analysis of Regenerative Braking Energy Utilization in KfW i9000 Electric Trains on the Palur-Yogyakarta Operation 7

Analysis of Regenerative Braking Energy Utilization in KfW i...

引用

7th Astechnova International Energy Conference, ASTECHNOVA 2023

作者： Darmawan, Arief Budiarto, Rachmawan Irnawan, Roni Master Program System Engineering Faculty of Engineering Universitas Gadjah Mada Jl. Teknika utara no 3 Yogyakarta55281 Indonesia Department of Nuclear Engineering and Engineering Physics Faculty of Engineering Universitas Gadjah Mada Jl. Grafika 2 Yogyakarta55281 Indonesia Department of Electrical Engineering and Information Technology Faculty of Engineering Universitas Gadjah Mada Jl. Grafika 2 Yogyakarta55281 Indonesia

This study explores the potential assessment. of regenerative braking energy in the operation of Electric Multiple Units (EMU) on the Yogyakarta-Palur railway line, a 65.03 km. Prompted by a noticeable increase in passenger numbers in the Yogyakarta metropolitan buffer zone, the study calls for future energy management strategies, involving regenerative braking to reduce energy consumption. Utilizing a mathematical model implemented via MATLAB Simulink, the research encompasses complex train movement scenarios, considering variables such as acceleration values of 0.558 m/s2 and 1 m/s2, and deceleration values of -0.555 m/s2 and 0.36 m/s2. Speed limitations, travel patterns, and energy profiles are rigorously examined, along with incline influences, such as tangent angles of 0.0032 degrees and 0.0017 degrees. In segments like Purwosari-Solo Jebres, electrical energy consumption is quantified at 23.02 kWh, with regenerative braking energy at 1.42 kWh;in Maguwo-Brambanan, consumption is 15.28 kWh, with regenerative energy at 2.42 kWh. The peak power requirements and regenerative braking potentials were also determined, with values such as 619.9 kW and 225.7 kW, and 1785 kW and 198.2 kW respectively. The total electrical consumption for the routes from Palur to Yogyakarta and vice versa was found to be 325.52 kWh and 276.73 kWh, with energy recovery of 31.43 kWh and 26.6 kWh, and average energy recovery ratios of 9.66% and 9.61%. © Published under licence by IOP Publishing Ltd.

关键词： Railroads

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

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

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：