检索结果-内蒙古大学图书馆

Q-learning Based Meta-Heuristics for Scheduling Bi-Objective Surgery Problems with Setup Time

Complex system Modeling and Simulation 2024年第4期4卷 321-338页

作者： Ruixue Zhang Hui Yu Adam Slowik Kaizhou Gao School of Computer Science Liaocheng UniversityLiaocheng 252000China Macao Institute of System Engineering Macao University of Science and TechnologyMacao 999078China the Department of Electronics and Computer Science Koszalin University of TechnologyKoszalin 75-453Poland

Since the increasing demand for surgeries in hospitals,the surgery scheduling problems have attracted extensive *** study focuses on solving a surgery scheduling problem with setup *** a mathematical model is created to minimize the maximum completion time(makespan)of all surgeres and patient waiting time,*** time by the fatigue effect is included in the surgery time,which is caused by doctors’long working ***,four mate-heuristics are optimized to address the relevant *** novel strategies are designed to improve the quality of the initial *** improve the convergence of the algorithms,seven local search operators are proposed based on the characteristics of the surgery scheduling ***,Q-learning is used to dynamically choose the optimal local search operator for the current state in each ***,by comparing the experimental results of 30 instances,the *** based local search strategy's effectiveness is *** all the compared algorithms,the improved artificial bee colony(ABC)with Q-leaming based local search has the best competiiveness.

关键词： surgery scheduling meta-heuristics Q-earning makespan

来源：评论

学校读者我要写书评

暂无评论

Comparison of Transformer Based and Traditional Models on Sentiment Analysis on Social Media Datasets

Comparison of Transformer Based and Traditional Models on Se...

引用

International Conference of computer and Informatics engineering (IC2IE)

作者： Arif Ridho Lubis Yulia Fatmi Deden Witarsyah Department of Computer Engineering and Informatics Politeknik Negeri Medan Medan Indonesia School of Industrial and System Engineering Telkom University Bandung Indonesia

In the field of computers and natural language processing, there is an interesting sub-field, namely sentiment analysis. Currently, the use of social media Twitter to actively communicate between individuals contains various review data, opinion data, and emotional data from discussions of topics between users on social media. So that the data generated by Twitter social media can identify patterns in the data for the field of sentiment analysis. In the sentiment analysis sub-sector, there are approaches, namely transformer-based models and traditional models, the traditional model includes the naïve Bayes algorithm, support vector machine, and regression have weaknesses in overcoming data complexity in Indonesian language tweets on Twitter social media while the transformer model includes the BERT (Bidirectional Encoder Representations from Transformers) algorithm is often applied because it has advantages in overcoming the complexity of Indonesian sentences in tweets obtained from social media and in the process this model goes through a training stage with large amounts of data then is adjusted in the concept of sentiment analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiple Sclerosis Detection with Reinforcement Learning and Differential Evolution

Multiple Sclerosis Detection with Reinforcement Learning and...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yang, Jing Yang, Jin Wu, Chenwei Jiang, Gaozhe Lv, Yaning Liu, Bingyan Xu, Feng Department of Computer System and Technology Universiti Malaya Kuala Lumpur Malaysia Mallinckrodt Institute of Radiology Washington University School of Medicine St. Louis United States Evident Battery Inc. Massachusetts United States Institute of Operations Research and Analytics National University of Singapore Singapore School of Mathematics and Statistics Xi'an University of Electronic Science and Technology Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China School of Engineering and Design Technical University of Munich Munich Germany

ISBN: (纸本)9798350368741

Multiple Sclerosis (MS) disrupts nerve communication, potentially leading to permanent damage. Convolutional Neural Networks (CNNs) are commonly recommended to accelerate magnetic resonance imaging (MRI) analysis for MS. Traditional CNN-based methods often face challenges with feature selection, imbalanced classification, and hyperparameter optimization, which can reduce their effectiveness. To address these challenges, this paper introduces a reinforcement learning (RL) strategy for tackling feature selection and class imbalance, complemented by an advanced Differential Evolution (DE) algorithm for hyperparameter tuning. The RL algorithm dynamically adapts, enhancing feature selection and class balance, and consistently outperforms traditional static methods by continually optimizing its response to the complex patterns in MS detection. Furthermore, the DE is enhanced with a novel mutation mechanism that utilizes k-means clustering to identify significant clusters. Tested on the SNAC-MS and ISBI datasets, our model demonstrates robust accuracy with average F-measures of 92.873% and 93.783%, respectively, highlighting its effectiveness and adaptability in diagnosing MS. © 2025 IEEE.

关键词： feature selection hyperparameter optimization imbalanced classification Multiple sclerosis reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Bat Algorithm: A Review on Theory, Modifications and Applications

Bat Algorithm: A Review on Theory, Modifications and Applica...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Hakam Singh Deden Witarsyah Alok Misra Raj Gaurang Tiwari Department of Computer Science and Engineering School of Engineering and Technology Chitkara University Baddi Himachal Paradesh India Information System Departement School of Industrial and System Engineering Telkom University Bandung Indonesia School of Computer Application Lovely Professional University Phagwara Punjab India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

Due to its many applications in a variety of domains, including clustering, cloud computing, and power systems, metaheuristic algorithms have attracted a lot of interest from the scholarly community. By using their self-explorative and adaptive processes, these algorithms provide certain benefits over conventional methods. One well-known metaheuristic approach is effective in resolving optimization problems with constraints and without constraints. This technique was inspired by nature, notably the echolocation ability of bat species. The Bat Algorithm (BA) makes use of a powerful search mechanism to provide the best results when compared to other algorithms of the same class. The theoretical underpinnings of the BA are explored in depth in this research, along with several changes and advancements that have improved its functionality. These enhancements include adjustments to search tactics as well as other developments. The report also thoroughly examines how the BA may be used across a variety of fields, demonstrating its competence and adaptability. The BA has been effectively used in several real-world applications, from cloud computing to clustering, and each one is carefully investigated. The study also offers a thoughtful examination of the BA's possible advancements and future possibilities. It also entails investigating novel modifications and tactics that might improve its effectiveness in handling challenging optimization issues. This study seeks to direct practitioners and academics toward more effective and efficient metaheuristic algorithms, thereby stimulating improvements in optimization approaches. It does this by summarising the present state of the BA and imagining its future development.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Active Deduction Heuristic Algorithm of Standard Contradiction Separation Rule Based on Reinforcement Learning

Active Deduction Heuristic Algorithm of Standard Contradicti...

引用

International Conference on Intelligent system and Knowledge engineering, ISKE

作者： Jian Zhong Peiyao Liu Shuwei Chen National-Local Joint Engineering Laboratory of System Credibility Automatic Verification School of Computer and Software Engineering Xihua University Chengdu China

Machine learning has been a prominent research focus in recent years, and integrating machine learning methods into automated theorem provers has become a current trend in theorem proving research. Standard contradiction separation rule is a newly proposed multi-clause, dynamic, and synergized deductive inference rule. The key aspect of standard contradiction separation rule is how to plan deduction paths. In order to better plan the deduction path, this paper explores the dynamic learning within the process of contradiction separation deduction and introduces a novel active deductive heuristic algorithm based on reinforcement learning. Experimental results demonstrate that this new algorithm enhances the reasoning capability of the theorem prover Prover9.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integration of SDN and Digital Twin for the Intelligent Detection of DoC Attacks in WRSNs

arXiv

引用

arXiv 2025年

作者： Qaisar, Muhammad Umar Farooq Yuan, Weijie Han, Guangjie Ahmed, Adeel Liu, Chang Piran, Md. Jalil School of Computer Science Northwestern Polytechnical University China School of System Design and Intelligent Manufacturing Southern University of Science and Technology China Department of Internet of Things Engineering Hohai University China School of Computer Science and Technology University of Science and Technology of China China School of Information Engineering Guangdong University of Technology Guangzhou China Department of Computer Science and Engineering Sejong University Seoul05006 Korea Republic of

Wireless rechargeable sensor networks (WRSNs), supported by recent advancements in wireless power transfer (WPT) technology, hold significant potential for extending network lifetime. However, traditional approaches often prioritize scheduling algorithms and network optimization, overlooking the security risks associated with the charging process, which exposes the network to potential attacks. This paper addresses this gap by integrating Software-Defined Networking (SDN) and Digital Twin technologies for the intelligent detection of Denial of Charging (DoC) attacks in WRSNs. First, it leverages the flexibility and intelligent control of SDN, in combination with Digital Twin, to enhance real-time detection and mitigation of DoC attacks. Second, it employs four key metrics to detect such attacks including charging request patterns, energy consumption, behavioral and reputation scores, and charging behavior and efficiency. The numerical results demonstrate the superior performance of the proposed protocol in terms of energy usage efficiency, survival rate, detection rate, and travel distance. © 2025, CC BY.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

VulPin: Finer-Grained Slicing for Pinpointing Vulnerability in Binary Programs: Precision in Vulnerability Detection: Advanced Slicing Techniques for Binary Program Analysis 7

VulPin: Finer-Grained Slicing for Pinpointing Vulnerability ...

引用

7th International Conference on computer Science and Artificial Intelligence, CSAI 2023

作者： Chukkol, Abdulrahman Hamman Adama Luo, Senlin Yunusa, Haruna Yusuf, Abdulganiyu Abdu Mohammed, Abulfatahi School of Information and Electronics Beijing Institute of Technology Beijing China Information System and Security and Countermeasures Experimental Center Beijing Institute of Technology Beijing China School of Automation Science and Electrical Engineering Beihang University Beijing China School of Computer Science Beijing Institute of Technology Beijing China School of Management and Information Technology Modibbo Adama University Yola Nigeria

ISBN: (纸本)9798400708688

Identifying vulnerabilities in binary code with precision is a critical area of study in the field of software security. Most existing techniques fail to pinpoint the vulnerability's exact location, due to the extensive labelled data requirement and lack of targeted approach to improve on the problematic code. In this paper, we introduce VulPin, a system specifically designed to pinpoint vulnerabilities in binary code. This framework uses a hierarchical attention network that analyze program slices along with a vulnerability position matrix. Experimental outcomes indicate that our framework not only outperforms existing approaches but also pinpoints vulnerabilities more rapidly with a high Accuracy and a very low rate of false positives. © 2023 ACM.

关键词： Binary codes

来源：评论

学校读者我要写书评

暂无评论

A new symbol timing and carrier frequency offset estimation algorithm for OTFS for B5G 2

A new symbol timing and carrier frequency offset estimation ...

引用

2nd IEEE International Conference on Emerging Research in Computational Science, ICERCS 2024

作者： Thangavel, Gunasekaran Rajan, Sheeba Subbulekshmi, S. Anthonisamy, Arun Ganapathi, Rohini Velankanni, Gowri University of Technology and Applied Sciences Department of Electronics and Communication Engineering Muscat Oman SRM Institute of Science and Technology School of Computing Tiruchirapalli India Prathyusha Engineering College Department of Electronics and Communication Engineering Chennai India Panimalar Engineering College Department of Computer Science and Business System Chennai India St. Joseph's Institute of Technology Department of Electronics and Communication Engineering Chennai India K. Ramakrishnan College of Technology Department of Electronics and Communication Engineering Trichy India

ISBN: (纸本)9798331534950

In B5G networks, accurate symbol timing estimate and estimation of the carrier frequency offset are both absolutely necessary. Particularly in highly mobile and interference-ridden settings, these factors are of paramount importance for sustaining high-throughput, dependable wireless communication. Estimating symbol timing and carrier frequency offset in OTFS can be difficult due to factors including the time-varying nature of Doppler shifts and interference from surrounding cells as well as the non-stationary nature of wireless channels. In such changing settings, traditional algorithms often fail to produce reliable estimations. To account for frequency changes caused by things like Doppler effects and drift, this research uses Machine Learning-Based Carrier Frequency Prediction Analysis (ML-CFPA) to implement a dynamic carrier frequency offset estimation and correction system. To preserve signal coherence and lower interference in B5G settings, carrier frequency offset adjustment is essential. Communication solutions with high performance are required for these applications to ensure they can function normally despite the complexity and changeability of their contexts. The outcomes demonstrate the higher performance of the algorithm in contrast to conventional approaches, highlighting its applicability to B5G networks. Its potential as a crucial enabling technology for the B5G future has been solidified by these simulations, which verify its capacity to maintain reliable communication under a variety of real-world conditions. © 2024 IEEE.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

NARX Neural Network Modeling of Batch Distillation Process

NARX Neural Network Modeling of Batch Distillation Process

引用

11th IEEE International Conference on system engineering and Technology, ICSET 2021

作者： Putri, Adi Novitarini MacHbub, Carmadi Hidayat, Egi Muhammad Idris School of Electrical Engineering and Informatics Institut Teknologi Control Computer System Research Group Bandung Indonesia

ISBN: (纸本)9781665437660

The batch distillation model is highly nonlinear due to the influence of mass and composition of the initial material to be separated. It is also caused by the thermodynamics of the system which is not ideal. Therefore, analytical batch distillation modeling does not fulfill superposition theory, or is nonlinear. Thus, any well-established linear control schemes can not be applied here. Meanwhile, modeling a system using the Nonlinear Autoregressive with eXogenous inputs (NARX) is quite widely used today because of its ability to represent non-linear system dynamics. This paper propose a system identification using NARX Neural Network (NARX-NN) to modeling batch distillation process. In order to prove the superiority of NARX-NN's accuracy in the system identification process, a comparison with linear ARMA models is done. In this study, ARMA approximation was carried out in two ways. The first way is to use a neural network, while the second method is through approximation to the discrete transfer function. The validation results show that the NARX-NN achieves significantly better fit compared to the linear models. NARX-NN and ARMA-NN were compared and their MSE ratio for delay input and output 1 and 3, respectively have the smallest value, i.e 1.71e-04 © 2021 IEEE.

关键词： Thermodynamics Analytical models system dynamics Conferences Neural networks Transfer functions systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

Optimal-Condition-Based Maintenance of Cold Standby system with Multiple Operating Units and Multiple Standby Units 14

Optimal-Condition-Based Maintenance of Cold Standby System w...

引用

14th International Conference on Reliability, Maintainability and Safety, ICRMS 2023

作者： Li, Yuxin Zhang, Yongfei Luo, Yuangeng He, Yugang Zhang, Xiaohong Wang, Jinhe School of Economics & Management Taiyuan University of Science & Technology Taiyuan Taiyuan China Division of Industrial and System Engineering Taiyuan University of Science & Technology 030024 China College of Computer Science and Technology Taiyuan University of Science & Technology Taiyuan030024 China

ISBN: (纸本)9798350329988

To ensure continuity and security in production processes, a redundancy structure involving multiple units for use and multiple units for standby (MUMS) is typically used. This paper proposes an offline state maintenance decision model for periodic switching and block replacement within the MUMS cold standby system. The concept of maintenance degree is introduced, and a model is established to represent the relationship among the maintenance effect, cost, and time, under the influence of the maintenance degree. By analyzing the alternate state transition characteristics of operating and standby units in the operation process, a steady probability model of the system state is obtained. Subsequently, a model for average rate costs in a limited scope is constructed to determine the optimal system switching period, preventive maintenance threshold, and maintenance degree. The model is validated using a hot roll system. The results show that the proposed framework can effectively reduce the cost rate and ensure system reliability. © 2023 IEEE.

关键词： Condition based maintenance

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：