检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Liang, Lijun Ma, Xuancao Lan, Chengyi Lin, Haoran Peng, Yiran Li, Tianyu Wang, Jiadong Azamat, Jafar College of Automation Hangzhou Dianzi University Hangzhou310018 China Center of Advanced Optoelectronic Materials and Devices Key Laboratory of Novel Materials for Sensor of Zhejiang Province College of Materials and Environmental Engineering Hangzhou Dianzi University Hangzhou310018 China School of Data Science and Artificial Intelligence Wenzhou University of Technology Wenzhou325035 China Department of Chemistry Education Farhangian University P.O. Box 14665-889 Tehran Iran

The development of energy-efficient and low-cost desalination techniques is crucial. Among these techniques, reverse osmosis (RO) is considered one of the most promising solutions for addressing the global water crisis. It has been widely implemented for both large-scale and distributed water desalination. One such promising desalination membrane is MXene with nanopores, thanks to its unique properties. However, accurately predicting the performance of the desalination process or designing new materials is challenging due to the complexity of the process and the various tunable properties of the membranes and nanopores themselves. The combination of machine learning (ML) and global optimization algorithms offers a superior approach to material design from multiple perspectives. Our study demonstrates that Ti3C2O2 with a specific charge on the nanopore mouth is an excellent candidate, as determined by the particle swarm optimization algorithm. By analyzing water density and ion density along the nanopore, we gain a deep understanding of how pore charge and functionalized groups affect salt rejection and water permeation. The integration of ML and global optimization algorithms can facilitate the design of materials with outstanding desalination performance. © 2024, The Authors. All rights reserved.

关键词： Desalination

来源：评论

学校读者我要写书评

暂无评论

Graph neural network and expert-guided deep reinforcement learning for solving flexible job-shop scheduling problem

引用

Computers & Operations Research 2025年 183卷

作者： Wenqiang Zhang Xuan Bao Huili Geng Guohui Zhang Mitsuo Gen School of Artificial Intelligence and Big Data Henan University of Technology China College of Information Science and Engineering Henan University of Technology China School of Management Engineering Zhengzhou University of Aeronautics China Fuzzy Logic Systems Institute/Tokyo University of Science Japan

Flexible Job-shop Scheduling Problem (FJSP) is crucial for efficient and flexible automated production. Recent advancements in Reinforcement Learning (RL) have shown promise in solving sequential decision problems. However, most Deep Reinforcement Learning (DRL) algorithms rely on Priority Dispatching Rules (PDRs), which limits scheduling efficiency. This paper proposed a novel Graph Neural Network and Expert-Guided Deep Reinforcement Learning (GNN-EGDRL) framework that employs Graph Neural Network (GNN) to extract features from both machines and operations, thereby integrating operation selection and machine assignment into a unified composite decision-making process. Expert solutions generated by PDRs guide the initial stages of training, allowing agents to gradually transition to self-directed action selection, thus balancing exploration and exploitation. The expert guidance strategy emphasizes the relationships between operations and machines, enhancing the model’s sensitivity and providing granular guidance for feature extraction, leading to optimized solutions. Extensive experiments demonstrate that the proposed GNN-EGDRL method consistently outperforms traditional PDRs and other end-to-end DRL over all problem instances. Notably, this superiority has been validated in a wide range of scenarios, including larger-scale examples, underscoring the method’s scalability and robustness. Furthermore, the method exhibits strong performance in scenarios not encountered during training, highlighting its effectiveness and adaptability in diverse production environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IIoT Mobile Business data Placement Strategy Based on Bayesian Optimization Algorithm

IIoT Mobile Business Data Placement Strategy Based on Bayesi...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Zhijie Shen Bowen Liu Xiaolong Xu Lianyong Qi Fei Dai Wanchun Dou State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen China College of Computer Science and Technology China University of Petroleum (East China) Qingdao China School of Computer Science Nanjing University of Information Science and Technology Nanjing China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China

As a standardized and systematic management method, business process management plays an important role in the industrial Internet of Things (IIoT) scenario. With the rapid development of mobile Internet and the increasing amount of data generated by the Internet of Things devices, the traditional storage scheme can no longer meet the requirements of managing the IIoT mobile business data. The cloud-edge collaborative data storage scheme provides mass storage capability by the cloud data center, and meanwhile takes access delay into account by storing data in the edge servers near to user, making it an effective solution to manage mobile business data in the IIoT scenario. However, the storage capacity of edge servers is relatively limited. How to design a reasonable data placement strategy to maximize the speed of data reading and tasks execution in IIoT business process has become an urgent problem to be solved. In order to shorten the overall running time, reduce data transmission costs and enhance users experience, we propose a data placement strategy based on Bayesian optimization algorithm, which can reasonably allocate storage capacity in the edge side, and further determine which edge server the data should be placed on. The results of the experiment show that the strategy based on our proposed algorithm performs better in a variety of different scenarios than the ones that based on other kind of optimization algorithms which have been adopted in similar studies.

关键词： Cloud computing Systematics Memory User experience Bayes methods Servers Task analysis

来源：评论

学校读者我要写书评

暂无评论

OPP-Miner: Order-preserving sequential pattern mining

arXiv

引用

arXiv 2022年

作者： Wu, Youxi Hu, Qian Li, Yan Guo, Lei Zhu, Xingquan Wu, Xindong School of Artificial Intelligence Hebei University of Technology Tianjin300401 China Hebei Key Laboratory of Big Data Computing Tianjin300401 China School of Artificial Intelligence Hebei University of Technology Tianjin300401 China School of Economics and Management Hebei University of Technology Tianjin300401 China State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology Tianjin300401 China Department of Computer Electrical Engineering and Computer Science Florida Atlantic University FL33431 United States Mininglamp Academy of Sciences Mininglamp Technology Beijing100084 China Ministry of Education Hefei230009 China

A time series is a collection of measurements in chronological order. Discovering patterns from time series is useful in many domains, such as stock analysis, disease detection, and weather forecast. To discover patterns, existing methods often convert time series data into another form, such as nominal/symbolic format, to reduce dimensionality, which inevitably deviates the data values. Moreover, existing methods mainly neglect the order relationships between time series values. To tackle these issues, inspired by order-preserving matching, this paper proposes an Order-Preserving sequential Pattern (OPP) mining method, which represents patterns based on the order relationships of the time series data. An inherent advantage of such representation is that the trend of a time series can be represented by the relative order of the values underneath the time series data. To obtain frequent trends in time series, we propose the OPP-Miner algorithm to mine patterns with the same trend (sub-sequences with the same relative order). OPP-Miner employs the filtration and verification strategies to calculate the support and uses pattern fusion strategy to generate candidate patterns. To compress the result set, we also study finding the maximal OPPs. Experiments validate that OPP-Miner is not only efficient and scalable but can also discover similar sub-sequences in time series. In addition, case studies show that our algorithms have high utility in analyzing the COVID-19 epidemic by identifying critical trends and improve the clustering performance. The algorithms and data can be downloaded from https://***/wuc567/Pattern-Mining/tree/master/OPP-Miner. Copyright © 2022, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Tipping Prediction of a Class of Large-Scale Radial-Ring Neural Networks

SSRN

引用

SSRN 2024年

作者： Lu, Yunxiang Xiao, Min Wu, Xiaoqun Karimi, Hamid Reza Xie, Xiangpeng Cao, Jinde Zheng, Wei Xing College of Automation College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing210023 China College of Computer Science and Software Engineering Shen Zhen University Shen Zhen518060 China Department of Mechanical Engineering Politecnico di Milano Milan20156 Italy Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210023 China School of Mathematics Southeast University Nanjing210096 China School of Computer Data and Mathematical Sciences Western Sydney University SydneyNSW2751 Australia

Understanding the emergence of collective dynamics in large-scale neural networks remains a challenging endeavor. This paper aims to address this gap by utilizing dynamic systems theory, particularly emphasizing tipping mechanisms. First of all, we introduce a novel $(n+mn)$-scale radial-ring neural network and utilize the topological approach of Coates' flow graph to determine the characteristic equation of the linearized network. Secondly, by deriving stability conditions and predicting the tipping point using the algebraic approach based on the integral element idea, we identify significant factors such as synaptic transmission delay, self-feedback coefficient, and network topology. Finally, we validate the effectiveness of the methodology in predicting the tipping point through numerical simulations. The simulations provide a thorough portrayal of the dynamics exhibited by large-scale neural networks, while also integrating robustness tests. This research contributes to a deeper understanding of the mechanisms underlying collective dynamics in large-scale neural networks, offering valuable insights for both theoretical frameworks and practical applications. © 2024, The Authors. All rights reserved.

关键词： Flow graphs

来源：评论

学校读者我要写书评

暂无评论

Fast Learning-Based Split Type Prediction Algorithm for VVC

Fast Learning-Based Split Type Prediction Algorithm for VVC

引用

IEEE International Conference on Image Processing

作者： Dayong Wang Liulin Chen Xin Lu Frederic Dufaux Weisheng Li Ce Zhu Chongqing Key Laboratory on Big Data for Bio Intelligence Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing University of Posts and Telecommunications Faculty of Computing Engineering and Media (CEM) De Montfort University Université Paris-Saclay CNRS CentraleSupélec Laboratoire des Signaux et systèmes Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications University of Electronic Science and Technology of China

As the latest video coding standard, Versatile Video Coding (VVC) is highly efficient at the cost of very high coding complexity, which seriously hinders its widespread application. Therefore, it is very crucial to improve its coding speed. In this paper, we propose a learning-based fast split type (ST) prediction algorithm for VVC using a deep learning approach. We first construct a large-scale database containing sufficient STs with diverse video resolution and content. Next, since the ST distributions of coding units (CUs) of different sizes are significantly distinct, so we separately design neural networks for all different CU sizes. Then, we merge ambiguous STs into four merged classes (MCs) to train models to obtain probabilities of MCs and skip unlikely ones. Experimental results demonstrate that the proposed algorithm can reduce the encoding time of VVC by 67.53% with 1.89% increase in Bjøntegaard delta bit-rate (BDBR) on average.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nearest-Better Network for Fitness Landscape Analysis of Continuous Optimization Problems

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Diao, Yiya Li, Changhe Zeng, Sanyou Yang, Shengxiang Coello, Carlos A. Coello China University of Geosciences School of Automation Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China Anhui University of Sciences and Technology School of Artificial Intelligence Hefei China China University of Geosciences School of Mechanical Engineering and Electronic Information Wuhan China De Montfort University School of Computer Science and Informatics LeicesterLE1 9BH United Kingdom Department of Computer Science CINVESTAV-IPN 07360 Mexico Tecnologico de Monterrey Faculty of Excellence The School of Engineering and Sciences N.L. Monterrey Mexico

Fitness landscape analysis (FLA) is quite important in evolutionary computation. In this paper, we propose a novel FLA method, the nearest-better network (NBN), which uses the nearest-better relationship to simplify the original fitness landscape of continuous optimization problems. We introduce an efficient algorithm to calculate NBN for continuous problems. We also propose four numerical measurements and a 3D visualization method based on NBN. Experiments show that compared to the other main FLA methods, the four numerical measurements proposed here can effectively measure the four intended features: neutrality, ruggedness, modality, and basin of attraction, respectively, and common features of the fitness landscape can be maintained in 3D NBN visualization, regardless of the scale of the problem. NBN also provides a view of how algorithms search in high-dimensional problems with the help of the 3D NBN visualization. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Full-Duplex NOMA Assisted Satellite-Terrestrial Systems with Hardware Impairments and Imperfect CSI

Performance Analysis of Full-Duplex NOMA Assisted Satellite-...

引用

International Conference on Information, Communication and Networks (ICICN)

作者： Jinlong Zhao Mingming Huo Wanwei Tang Xinwei Yue School of Artificial Intelligence Gansu University of Political Science and Law Lanzhou China School of Electronic and Information Engineering Beihang university Beijing China Archives Center Lanzhou University of Technology Lanzhou China Key Lab of Intelligent Data Information Processing and Control of Hebei Province Tangshan University Tangshan China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9781665490832

In this paper, we investigate the satellite-terrestrial system employing non-orthogonal multiple access (NOMA) scheme, where a full-duplex (FD) decode-and-forward (DF) relaying assists the user in weak channel condition. The effects of hardware impairments, imperfect channel state information (CSI) and imperfect interference cancellation on system performance are considered. For this setting, we derive the closed-form expressions of the exact and asymptotic outage probabilities as well as delay-limited sum throughput for NOMA users. Numerical results are provided to demonstrate the correctness of theoretical analysis and the superiority of adopting FD NOMA scheme in the proposed system.

关键词： NOMA Interference cancellation Satellites System performance Full-duplex system Probability Throughput

来源：评论

学校读者我要写书评

暂无评论

Bilevel aggregator-Prosumers' optimization problem in real-time: A convex optimization approach

arXiv

引用

arXiv 2021年

作者： Shomalzadeh, Koorosh Scherpen, Jacquelien M. A. Camlibel, M. Kanat Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence Faculty of Science and Engineering University of Groningen Nijenborgh 9 Groningen9747 AG Netherlands Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen Nijenborgh 4 Groningen9747 AG Netherlands

This paper proposes a Real-Time Market (RTM) platform for an aggregator and its corresponding prosumers to participate in the electricity wholesale market. The proposed energy market platform is modeled as a bilevel optimization problem where the aggregator and the prosumers are considered as self-interest agents. The current state-of-the-art Mathematical Programming with Equilibrium Constraints (MPEC) and Mixed-Integer Programming (MIP) based approaches to solve bilevel optimization problems are not satisfactory for real-time applications. The computation time for such approaches grows exponentially as the number of prosumers and decision variables increase. This paper presents a convex optimization problem which can capture a subset of the set of global optima of the bilevel problem as its optimal solution. Copyright © 2021, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Knowledge Tracing Based on Bayesian Neural Network 4th

Deep Knowledge Tracing Based on Bayesian Neural Network

引用

4th International Conference on Intelligent, Interactive Systems and Applications, IISA2019

作者： Donghua, Li Yanming, Jia Jian, Zhou Wufeng, Wang Ning, Xu School of Computer Science and Technology Wuhan University of Technology Wuhan China Artificial Intelligence and Big Data Department Beijing Global Wisdom Inc Beijing China School of Information Engineering Wuhan University of Technology Wuhan China Zhongshan Institute of Advanced Engineering Technology of WUT Zhongshan China

ISBN: (纸本)9783030343866

Knowledge Tracing (KT) is the de-facto standard for inferring student knowledge from performance data, modeling students’ changing knowledge state during skill acquisition. The existing knowledge tracing models have problems such as incomplete features consideration, poor effect and easy over-fitting in the process of simulating students’ knowledge acquisition. In order to better model students’ learning and track the process of students’ knowledge acquisition, a Bayesian neural network Deep Knowledge Tracing (BDKT) is proposed. The model combines Bayesian neural network with Deep Knowledge Tracing (DKT), it can not only model feature-rich students’ behavior data, but also effectively prevent over-fitting, enhance the generalization ability of the model, and accelerate the convergence speed of the model. The above performances of the model are tested by the experiments on the data sets of KDD Cup and Assistments. © 2020, Springer Nature Switzerland AG.

关键词： Students

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：