检索结果-内蒙古大学图书馆

28th International Conference on Knowledge Based and Intelligent information and engineering Systems, KES 2024

作者： Abdollahi, Mahdi Gao, Xiaoying Mei, Yi Ghosh, Shameek Li, Jinyan Narag, Michael School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand Founder & CTO Medius Health Sydney Australia Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China

The document classification (DC) task assigns predefined classes to unlabeled documents using trained models. In the medical field, DC is crucial for tasks like categorizing risk factors and classifying electronic health records. This paper addresses challenges in medical document analysis, such as the prevalence of abbreviations and acronyms. Existing classification performance in medical documents is suboptimal. The paper introduces novel feature engineering methods leveraging domain-specific knowledge to enhance classification performance. Results indicate that the Three-Stage approach surpasses related works, showcasing improved medical document classification performance. © 2024 The Authors.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

A Light Spot Centroid Determination Method for Accurate Digital Refractometer 23

A Light Spot Centroid Determination Method for Accurate Digi...

引用

23rd International Conference on control, Automation and Systems, ICCAS 2023

作者： Wang, Zhenxing Jia, Zhenyuan School of Computer and Information Engineering Shanghai Polytechnic University Shanghai201209 China School of Intelligent Manufacturing and Control Engineering Shanghai Polytechnic University Shanghai201209 China

ISBN: (纸本)9788993215274

In this paper, we propose the development of a highly stable and low-cost refractometer for measuring the sucrose concentration. Laboratory-grade refractometers are prohibitively costly and impractical for everyday applications, while currently accessible low-cost commercial alternatives suffer from insufficient stability and precision. To address this gap, our proposed refractometer replaces the costly CCD sensor and light source with a conventional LED and a cost-effective CMOS sensor. By analyzing the output waveform pattern, we achieve high precision with an accuracy of 0.1%, which is suitable for individual use. We repeat 100 measurements on various samples to determine the dependability and consistency of our refractometer, and the results demonstrate its accuracy. The algorithm operates on a 480 MHz ARM processor and acquires data within 20mS. Our instrument provides an affordable and reliable method for measuring sucrose concentration and demonstrates stability and accuracy compared to existing cost-effective options. © 2023 ICROS.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

Study of milk concentration detection based on the AC signal-modulated LED 2

Study of milk concentration detection based on the AC signal...

引用

2nd Conference on Biomedical Photonics and Cross-Fusion, BPC 2023

作者： Haonan, Xing Xiaoqi, Wei Lin, Gui Mingyu, Cao Xuhuix, Chen Cunliang, Cheng School of Intelligent Manufacturing and Control Engineering Shanghai Polytechnic University Shanghai201209 China School of Computer and Information Engineering Shanghai Polytechnic University Shanghai201209 China

ISBN: (数字)9781510667556

ISBN: (纸本)9781510667549

As milk consumption increases, rapid detection of milk concentration is becoming more and more crucial. In this research, we propose an LED-based milk concentration detection system, which is a new detection method that detects milk concentration by loading the LED with RF signals. The system includes an arbitrary waveform generator (AWG), LED, lampshade, silicon photo dioxide (PD), oscilloscope, and other components. After passing through different concentrations of milk solution, the light signal carrying a specific frequency is received by the PD, and after photoelectric conversion, the signal carrying a specific frequency in the light signal is converted out, and the concentration of the milk solution to be measured is obtained by reading the peak value measured by the oscilloscope. The experiments validated different brands of milk solutions with varying concentrations, demonstrating the feasibility of LED-based milk concentration detection, and the test analysis was performed for the same brand of milk solutions with varying concentrations, yielding a quadratic fit R2=0.9169, confirming that the system has good sensing performance for milk concentration and validating the method's feasibility. © 2023 SPIE.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

The Design and Implementation of a Secure Time Distribution System Based on Blockchain Oracle 1

The Design and Implementation of a Secure Time Distribution ...

引用

1st International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2024

作者： Hong, Jianlei Zhao, Jindong Zhang, Xuedong Sun, Yukai Qiu, Xuqiang School of Computer and Control Engineering Yantai University Yantai264005 China Yantai Yantai Chijiu Clock Co. Ltd. Yantai264005 China

ISBN: (纸本)9781643685779

With the proliferation of e-government, e-commerce, and other applications, the demand for secure and accurate time information services has become more and more urgent in various industries. The traditional time distribution service has some risks regarding the security of time information. To cope with this demand, a secure time distribution system based on blockchain oracle is designed and implemented to provide secure and trustworthy time distribution services for internet applications. In the system, the oracle mechanism is used to introduce external time source data into the blockchain to ensure that the time information is accurate and traceable, and the time saved in the blockchain is distributed to the clients through the time synchronization protocol. To address the time delay problem introduced by software operation, a software delay smoothing algorithm is designed to smooth and optimize fluctuating and uncontrollable software delays. The experimental results show that the software delay smoothing algorithm has a smoothing effect of 72.7% on software delays, and the systematic error caused by software delay in this system is 718.0 μs,and the accuracy of the timestamps distributed to clients reaches the microsecond level. Compared with traditional methods, the secure time distribution system based on blockchain oracles significantly improves the accuracy of blockchain timestamps, and utilizes the decentralized and tamper-proof characteristics of blockchain to add a "traceable" feature to each timestamp, which can provide trustworthy time services for financial transactions, e-government affairs, and other key areas. © 2025 The Authors.

关键词： Blockchain Oracle time distribution

来源：评论

学校读者我要写书评

暂无评论

Viewpoint Optimization using Genetic Algorithm for Flying Robot Inspection of Electricity Transmission Tower Equipment

引用

Chinese Journal of Electronics 2025年第2期23卷 426-431页

作者： Guotian Yang Ruifang Dong Hua Wu Chang'an Liu School of Control and Computer Engineering North China Electric Power University Beijing China

To fully exploit the limited flight-time of the flying robot, and ensure the successful visibility of target, viewpoint optimization is proposed in this paper for the inspection of electricity transmission tower equipment with an optimization function to determine the best viewpoints in a local viewpoint region. The local viewpoint regions are generated from the local objective regions which are determined by the geometrical structure of a priori 3D model for the electricity transmission tower equipment. The optimization function is structured based on three factors including visibility, viewing quality and observation distance. In addition, the fitness function of genetic algorithm is used to find the optimal viewpoint. The experimental results demonstrate the effectiveness and efficiency of the proposed viewpoint selection algorithm.

关键词： Solid modeling Three-dimensional displays Electricity Poles and towers Inspection Optimization Robots Drones Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Coordinated Power and Mechanical Loads Optimization Strategy of Wind Turbine Based on Model Predictive control

引用

Journal of control, Automation and Electrical Systems 2025年 1-12页

作者： Wei, Bo Hu, Hao Wang, Shuangao School of Control and Computer Engineering North China Electric Power University Beijing China

Modern wind turbine design is evolving toward large-scale, high-capacity configurations. Under complex operational conditions, these turbines are subjected to significant mechanical loads coupled with power fluctuations. The pitch control system, a critical component of wind turbines, plays a pivotal role in regulating power output and alleviating load fluctuations. Given the limitations of conventional pitch control in adapting to wide-ranging wind speed variations and the need to balance power regulation with load mitigation objectives, this study proposes a pitch control framework based on nonlinear model predictive control. Using the National Renewable Energy Laboratory 5MW turbine as the research object, a reduced-order dynamic model is developed through mechanistic analysis and applied to the pitch control system design. Leveraging the OpenFAST and MATLAB/Simulink co-simulation platform, numerical validation is performed under diverse wind conditions. The results demonstrate that the controller adapts dynamically to the turbine’s real-time operating conditions and dynamic scenarios. The multi-objective optimization framework enhances power regulation performance while effectively suppressing tower fore-aft oscillations, thereby reducing tower mechanical loads. Compared to traditional strategies, the proposed framework achieves simultaneous optimization of power output and mechanical load mitigation.

关键词： Wind turbine Pitch control Reduced-order model Model predictive control Optimization

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Placement of Tie-lines and Distributed Generations to Optimize Distribution System Post-outage Operations and Minimize Energy Losses

引用

CSEE Journal of Power and Energy Systems 2021年第2期7卷 318-328页

作者： Farzaneh Shojaei Mohammad Rastegar Morteza Dabbaghjamanesh Department of Power and Control Engineering School of Electrical and Computer EngineeringShiraz UniversityShirazIran Electrical and Computer Engineering Department The University of Texas at DallasUSA.

This study proposes a new method which aims to optimally install tie-lines and distributed generations *** is done to optimize the post-outage reconfiguration and minimize energy losses and energy not supplied of distribution *** number and location of tie-lines,as well as the number,size,and location of DGs,are pinpointed through teaching the learning-based optimization(TLBO)*** objective function in the current research is to minimize the costs pertaining to the investment,operation,energy losses,and energies not *** addition to the normal operational condition,fault operational condition is also ***,the optimal post-fault reconfigurations for fault occurrences in all lines are ***,the operational constraints such as the voltage and line current limits are taken into account in both normal and post-fault operational ***,the modified IEEE 33-bus and 69-bus distribution test systems are selected and tested to demonstrate the effectiveness of the simultaneous placement of DGs and tie-line technique proposed in this paper.

关键词： Distribution system reliability distributed generation energy loss post-outage reconfiguration tie-lines

来源：评论

学校读者我要写书评

暂无评论

Social Recommendation System Based on Multi-agent Deep Reinforcement Learning 8

Social Recommendation System Based on Multi-agent Deep Reinf...

引用

8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022

作者： Yinggang, Li Xiangrong, Tong Yantai University School of Computer and Control Engineering Yantai Shandong China

ISBN: (纸本)9781665477352

Currently, deep reinforcement learning is widely used to transform the recommendation process into a sequential task. Despite this, the recommendation system continues to be plagued by data sparsity and cold start issues as a result of high online costs and a sparse user-item rating matrix. To address the aforementioned issues, this article proposes a social multi-agent reinforcement learning framework (MATR). Two agents collaborate within the framework to enhance the performance of conventional solutions. Specifically, one agent is responsible for capturing the dynamic preferences of users based on their interaction with the system. The other agent leverages a ubiquitous social network to minimise cold starts and data sparsity for some users. In addition, we designed a module for learning state representations from social networks and user rating matrices. To optimise the use of social networks in the state representation module, in addition to first-order social neighbour features, we used trust inference to discover high-level social neighbour features, and we integrated Feature aggregation modelling state representation with graph convolutional neural networks and attention mechanisms. Our method has been shown to be effective and advantageous using actual data sets. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Trust Prediction Method Based on Heterogeneous Information Networks 8

A Trust Prediction Method Based on Heterogeneous Information...

引用

8th International Conference on Systems and Informatics, ICSAI 2022

作者： Xiao, Ruili Tong, Xiangrong Li, Yinggang Yantai University School of Computer and Control Engineering Yantai264005 China

ISBN: (纸本)9781665474481

It is essential to predict the level of trust among users before they interact to reduce the risk of interaction. Due to the sparsity of trust relationships, it is inefficient to simply use explicit trust relationships to predict the trust among users, and even the trust path may be lost. On the other hand, there are implicit trust relationships among users such as the joint items that several users all rated. Once the trust relationship is extracted, it will greatly expand the number of trusted users. To this end, a trust prediction method incorporating rating information is proposed to address this problem. It first constructs a heterogeneous information network consisting of social and rating information. Secondly, in the trust prediction period, if the user has no trusted users to choose from, the joint item is used as a bridge to find implicit trusted users from users who have jointly rated the item. Finally, the Dueling DQN algorithm is used to calculate the strength of the trust path, and the predicted trust value is derived by aggregating multiple trust paths based on an aggregation function. The experimental results on two datasets indicate the presented approach outperforms most existing trust prediction methods. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimal decarbonisation pathway for mining truck fleets

引用

Journal of Automation and Intelligence 2024年第3期3卷 129-143页

作者： Gang Yu Xianming Ye Yuxiang Ye Hongxu Huang Xiaohua Xia Department of Electrical Electronic and Computer EngineeringUniversity of PretoriaPretoria 0002South Africa School of Economics and Finance University of the WitwatersrandJohannesburg 2000South Africa School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China

The fossil fuel powered mining truck fleets can contribute up to 80%of total emissions in open pit *** study investigates the optimal decarbonisation pathway for mining truck ***,our proposed pathway incorporates power generation,negative carbon technologies,and carbon ***,financial,and environmental models of decarbonisation technologies are established,capturing regional variations and time dynamic characteristics such as cost trends and carbon capture *** dynamic natures of characteristics pose challenges for using the cost-effective analyses approach to find the optimal decarbonisation *** address this,we introduce a mixed-integer programming optimisation framework to find the decarbonisation pathway with minimum life cycle costs during the planning period.A case study for the optimal decarbonisation pathway of truck fleets in a South African coal mine is conducted to illustrate the applicability of the proposed *** indicate that the optimal decarbonisation pathway is significantly influenced by factors such as land cost,annual budget,and carbon trading *** proposed method provides invaluable guidance for transitioning towards a cleaner and more sustainable mining industry.

关键词： Coal mine Truck fleet Carbon emission Optimal decarbonisation pathway

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：