检索结果-南通市图书馆

Adaptive Multi-Step Evaluation Design With Stability Guarantee for Discrete-Time Optimal Learning Control

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1797-1809页

作者： Ding Wang Jiangyu Wang Mingming Zhao Peng Xin Junfei Qiao IEEE faculty of Information Technology the Beijing Key Laboratory of Computational Intelligence and Intelligent Systemthe Beijing Laboratory of Smart Environmental Protectionand the Beijing Institute of Artificial IntelligenceBeijing University of TechnologyBeijing 100124China

This paper is concerned with a novel integrated multi-step heuristic dynamic programming(MsHDP)algorithm for solving optimal control *** is shown that,initialized by the zero cost function,MsHDP can converge to the optimal solution of the Hamilton-Jacobi-Bellman(HJB)***,the stability of the system is analyzed using control policies generated by ***,a general stability criterion is designed to determine the admissibility of the current control *** is,the criterion is applicable not only to traditional value iteration and policy iteration but also to ***,based on the convergence and the stability criterion,the integrated MsHDP algorithm using immature control policies is developed to accelerate learning efficiency ***,actor-critic is utilized to implement the integrated MsHDP scheme,where neural networks are used to evaluate and improve the iterative policy as the parameter ***,two simulation examples are given to demonstrate that the learning effectiveness of the integrated MsHDP scheme surpasses those of other fixed or integrated methods.

关键词： Adaptive critic artificial neural networks Hamilton-Jacobi-Bellman(HJB)equation multi-step heuristic dynamic programming multi-step reinforcement learning optimal control

Impact of informatics on QIPC

在线全文

学校读者我要写书评

暂无评论

南京邮电大学学报（自然科学版） 2011年第2期31卷 40-48页

作者： Jozef Gruska faculty of informatics Masaryk University Botanická 68a

Quantum information processing and communication(QIPC) is an area of science that has two main goals: On one side,it tries to explore(still not well known) potential of quantum phenomena for(efficient and reliable) information processing and(efficient,reliable and secure) *** the other side,it tries to use quantum information storing,processing and transmitting paradigms,principles,laws,limitations,concepts,models and tools to get deeper insights into the phenomena of quantum world and to find efficient ways to describe and handle/simulate various complex physical *** order to do that QIPC has to use concepts,models,theories,methods and tools of both physics and *** main role of physics at that is to discover primitive physical phenomena that can be used to design and maintain complex and reliable information storing,processing and transmitting *** main role of informatics is,one one side,to explore,from the information processing and communication point of view,limitations and potentials of the potential quantum information processing and communication technology,and to prepare information processing methods that could utilise potential of quantum information processing and communication *** the other side,the main role of informatics is to guide and support,by theoretical tools and outcomes,physics oriented research in *** paper is to describe and analyse a variety of ways and potential informatics contributes and should/could contribute to the development of QIPC--see also Gruska(1999,2006,2008).

关键词： informatics quantum complexity theory quantum cryptography quantum algorithm

A Quantum Algorithm for Evaluating the Hamming Distance

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第4期71卷 1065-1078页

作者： Mohammed Zidan Manal G.Eldin Mahmoud Y.Shams Mohamed Tolan Ayman Abd-Elhamed Mahmoud Abdel-Aty Department of Artificial intelligence Hurghada Faculty of Computers and Artificial IntelligenceSouth Valley UniversityEgypt faculty of Engineering King Salman International UniversitySouth SinaiEgypt Department of Mathematics and Computer Science Faculty of ScienceBeni-Suef UniversityBeni-SuefEgypt Department of Machine Learning and Information Retrieval Faculty of Artificial IntelligenceKafrelsheikh UniversityEgypt Mechanical Department Faculty of Technology and EducationSuez UniversitySuezEgypt faculty of Technological Industries King Salman International UniversitySouth SinaiEgypt faculty of Engineering at Mataria Helwan UniversityCairoEgypt Department of Mathematics Faculty of SciencesSohag University82524 SohagEgypt

We present a novel quantum algorithm to evaluate the hamming distance between two unknown oracles via measuring the degree of entanglement between two ancillary *** particular,we use the power of the entanglement degree based quantum computing model that preserves at most the locality of interactions within the quantum model *** model uses one of two techniques to retrieve the solution of a quantum computing problem at *** the first technique,the solution of the problem is obtained based on whether there is an entanglement between the two ancillary qubits or *** the second,the solution of the quantum computing problem is obtained as a function in the concurrence value,and the number of states that can be generated from the Boolean *** proposed algorithm receives two oracles,each oracle represents an unknown Boolean function,then it measures the hamming distance between these two *** hamming distance is evaluated based on the second *** is shown that the proposed algorithm provides exponential speedup compared with the classical counterpart for Boolean functions that have large numbers of Boolean *** proposed algorithm is explained via a case ***,employing recently developed experimental techniques,the proposed algorithm has been verified using IBM’s quantum computer simulator.

关键词： Quantum computing quantum algorithm quantum circuit

A PROCESS FOR SOLVING A FEW EXTREME EIGENPAIRS OF LARGE SPARSE POSITIVE DEFINITE GENERALIZED EIGENVALUE PROBLEM

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computational Mathematics 2000年第4期18卷 387-402页

作者： Chong-hua Yu O.Axelsson Department of Mathematics Fudan UniversityShanghai 200433China faculty of Mathematics and informatics University of Nijmegen6525 ED NijmegenThe Netherlands

In this paper, an algorithm for computing some of the largest (smallest) generalized eigenvalues with corresponding eigenvectors of a sparse symmetric positive definite matrix pencil is presented. The algorithm uses an iteration function and inverse power iteration process to get the largest one first, then executes m - 1 Lanczos-like steps to get initial approximations of the next m - 1 ones, without computing any Ritz pair, for which a procedure combining Rayleigh quotient iteration with shifted inverse power iteration is used to obtain more accurate eigenvalues and eigenvectors. This algorithm keep the advantages of preserving sparsity of the original matrices as in Lanczos method and RQI and converges with a higher rate than the method described in [12] and provides a simple technique to compute initial approximate pairs which are guaranteed to converge to the wanted m largest eigenpairs using RQL. In addition, it avoids some of the disadvantages of Lanczos and RQI, for solving extreme eigenproblems. When symmetric positive definite lira ear systems must be solved in the process, an algebraic multilevel iteration method (AMLI) is: applied. The algorithm is fully parallelizable. [ABSTRACT FROM AUTHOR]

关键词： eigenvalue sparse problem

EMU-Net: Automatic Brain Tumor Segmentation and Classification Using Efficient Modified U-Net

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第10期77卷 557-582页

作者： Mohammed Aly Abdullah Shawan Alotaibi Department of Artificial intelligence Faculty of Artificial IntelligenceEgyptian Russian UniversityBadr City11829Egypt Computer Science Department Shaqra UniversityShaqra City11961Saudi Arabia

Tumor segmentation is a valuable tool for gaining insights into tumors and improving treatment *** segmentation is crucial but *** learning methods have emerged as key players in automating brain tumor *** this paper,we propose an efficient modified U-Net architecture,called EMU-Net,which is applied to the BraTS 2020 *** approach is organized into two distinct phases:classification and *** this study,our proposed approach encompasses the utilization of the gray-level co-occurrence matrix(GLCM)as the feature extraction algorithm,convolutional neural networks(CNNs)as the classification algorithm,and the chi-square method for feature *** simulation results,the chi-square method for feature selection successfully identifies and selects four GLCM *** utilizing the modified U-Net architecture,we achieve precise segmentation of tumor images into three distinct regions:the whole tumor(WT),tumor core(TC),and enhanced tumor(ET).The proposed method consists of two important elements:an encoder component responsible for down-sampling and a decoder component responsible for *** components are based on a modified U-Net architecture and are connected by a bridge *** proposed CNN architecture achieves superior classification accuracy compared to existing methods,reaching up to 99.65%.Additionally,our suggested technique yields impressive Dice scores of 0.8927,0.9405,and 0.8487 for the tumor core,whole tumor,and enhanced tumor,***,the method presented demonstrates a higher level of trustworthiness and accuracy compared to existing *** promising accuracy of the EMU-Net study encourages further testing and evaluation in terms of extrapolation and generalization.

关键词： MR images GLCM SVM segmentation U-Net CNN

A three-stage approach for resilience-constrained scheduling of networked microgrids

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Modern Power Systems and Clean Energy 2019年第4期7卷 705-715页

作者： Saeed TEIMOURZADEH Osman Bulent TOR Mahmut Erkut CEBECI Adela BARA Simona Vasilica OPREA Engineering ProcurementResearch and Analysis(EPRA)Electric Energy Co.AnkaraTurkey Department of Economic informatics and Cybernetics Faculty of CyberneticsStatistics and Economic InformaticsBucharest University of Economic Studies(BUES)BucharestRomania

This paper deals with optimal scheduling of networked microgrids(NMGs)considering resilience *** proposed scheme attempts to mitigate the damaging impacts of electricity interruptions by effectively exploiting NMG capabilities.A three-stage framework is *** Stage 1,the optimal scheduling of NMGs is studied through determining the power transaction between the NMGs and upstream network,the output power of distributed energy resources(DERs),commitment status of conventional DERs as well as demand-side *** Stage 2,the decisions made at Stage 1 are realized considering uncertainties pertaining to renewable generation,market price,power consumption of loads,and unintentional islanding of NMGs from the upstream network and *** 3 deals with uncertainties of unintentional islanding of each MG from the rest of islanded NMGs and *** problem is formulated as a mixed-integer linear programming problem and its effectiveness is assured by simulation studies.

关键词： Networked microgrid(NMG) Distributed energy resource(DER) Power system resilience Point estimate method

Hybrid Feature Selection Method for Predicting Alzheimer’s Disease Using Gene Expression Data

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第3期74卷 5559-5572页

作者： Aliaa El-Gawady BenBella S.Tawfik Mohamed A.Makhlouf Department of Information Systems Faculty of Computers and InformaticsSuez Canal UniversityIsmailia41522Egypt faculty of Computer Science Nahda UniversityBeni SuefEgypt

Gene expression(GE)classification is a research trend as it has been used to diagnose and prognosis many *** machine learning(ML)in the prediction of many diseases based on GE data has been a flourishing research ***,some diseases,like Alzheimer’s disease(AD),have not received considerable attention,probably owing to data scarcity *** this work,we shed light on the prediction of AD from GE data accurately using *** approach consists of four phases:preprocessing,gene selection(GS),classification,and performance *** the preprocessing phase,gene columns are preprocessed *** the GS phase,a hybrid filtering method and embedded method are *** the classification phase,three ML models are implemented using the bare minimum of the chosen genes obtained from the previous *** final phase is to validate the performance of these classifiers using different *** crux of this article is to select the most informative genes from the hybrid method,and the best ML technique to predict AD using this minimal set of *** different datasets are used to achieve our *** predict AD with impressive values forMultiLayer Perceptron(MLP)classifier which has the best performance metrics in four datasets,and the Support Vector Machine(SVM)achieves the highest performance values in only one *** assessed the classifiers using sevenmetrics;and received impressive results,allowing for a credible performance *** metrics values we obtain in our study lie in the range[.97,.99]for the accuracy(Acc),[.97,.99]for F1-score,[.94,.98]for kappa index,[.97,.99]for area under curve(AUC),[.95,1]for precision,[.98,.99]for sensitivity(recall),and[.98,1]for *** these results,the proposed approach outperforms recent interesting *** these results,the proposed approach outperforms recent interesting results.

关键词： Gene expression gene selection machine learning classification Alzheimer’s disease

Optimization of Sentiment Analysis Using Teaching-Learning Based Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第11期69卷 1783-1799页

作者： Abdullah Muhammad Salwani Abdullah Nor Samsiah Sani Center for Artificial intelligence Technology Faculty of Information Science&TechnologyUniversiti KebangsaanKajang43000Malaysia

Feature selection and sentiment analysis are two common studies that are currently being conducted;consistent with the advancements in computing and growing the use of social *** dimensional or large feature sets is a key issue in sentiment analysis as it can decrease the accuracy of sentiment classification and make it difficult to obtain the optimal subset of the ***,most reviews from social media carry a lot of noise and irrelevant ***,this study proposes a new text-feature selection method that uses a combination of rough set theory(RST)and teaching-learning based optimization(TLBO),which is known as *** framework to develop the proposed RSTLBO includes numerous stages:(1)acquiring the standard datasets(user reviews of six major ***)which are used to validate search result feature selection methods,(2)preprocessing of the dataset using text processing *** involves applying text processing methods from natural language processing techniques,combined with linguistic processing techniques to produce high classification results,(3)employing the RSTLBO method,and(4)using the selected features from the previous process for sentiment classification using the Support Vector Machine(SVM)*** show an improvement in sentiment analysis when combining natural language processing with linguistic processing for text *** importantly,the proposed RSTLBO feature selection algorithm is able to produce an improved sentiment analysis.

关键词： Feature selection sentiment analysis rough set theory teachinglearning optimization algorithms text processing

A Novel Multi-Stage Bispectral Deep Learning Method for Protein Family Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第7期76卷 1173-1193页

作者： Amjed Al Fahoum Ala’a Zyout Hiam Alquran Isam Abu-Qasmieh Biomedical Systems and informatics Engineering Department Hijjawi Faculty for Engineering TechnologyYarmouk UniversityIrbid21163Jordan

Complex proteins are needed for many biological *** amino acid chains reveals their properties and *** support healthy tissue structure,physiology,and *** medicine and treatments require quantitative protein identification and *** technical advances and protein sequence data exploration,bioinformatics’“basic structure”problem—the automatic deduction of a protein’s properties from its amino acid sequence—remains *** function inference from amino acid sequences is the main biological data *** study analyzes whether raw sequencing can characterize biological facts.A massive corpus of protein sequences and the Globin-like superfamily’s related protein families generate a solid vector representation.A coding technique for each sequence in each family was devised using two representations to identify each amino acid precisely.A bispectral analysis converts encoded protein numerical sequences into images for better protein sequence and family *** and validation employed 70%of the dataset,while 30%was used for *** paper examined the performance of multistage deep learning models for differentiating between sixteen protein families after encoding and representing each encoded sequence by a higher spectral representation image(Bispectrum).Cascading minimized false positive and negative cases in all *** initial stage focused on two classes(six groups and ten groups).The subsequent stages focused on the few classes almost accurately separated in the first stage and decreased the overlapping cases between families that appeared in single-stage deep learning *** single-stage technique had 64.2%+/-22.8%accuracy,63.3%+/-17.1%precision,and a 63.2%+/19.4%*** two-stage technique yielded 92.2%+/-4.9%accuracy,92.7%+/-7.0%precision,and a 92.3%+/-5.0%*** work provides balanced,reliable,and precise forecasts for all families in all measures.

关键词： Globin-like superfamily numerical encoding bispectral analysis classification model deep convolutional neural network