检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2253-2263页

作者： Deng, Guizhou Fu, Huiqiao Wang, Xinpeng Liu, Canghai Tang, Kaiqiang Chen, Chunlin Southwest University of Science and Technology Mechanical Engineering School of Manufacturing Science and Engineering Mianyang621000 China Nanjing University School of Management and Engineering Nanjing210093 China Nanjing University Department of Control and Systems Engineering School of Management and Engineering Nanjing210093 China

Rapid adaptation to the environment is the long-term task of reinforcement learning. However, reinforcement learning faces great challenges in dynamic environments, especially with continuous state-action spaces. In this article, we propose a systematic incremental reinforcement learning method via performance evaluation and policy perturbation (IRL-PEPP) to improve the adaptability of reinforcement learning algorithms in dynamic environments with continuous state-action spaces, which mainly includes three parts, i.e., performance evaluation, policy perturbation, and importance weighting. First, in performance evaluation, we apply the learned optimal policy to sample a few episodes in the original environment and use these samples to evaluate the policy applicability in the new environment. Then, in policy perturbation, the policy is perturbed according to the policy applicability to balance the tradeoff between exploration and exploitation in the new environment. Finally, importance weighting is applied to weight the information to speed up the adjustment process of the policy. Experimental results demonstrate the feasibility and efficiency of the proposed IRL-PEPP method for continuous control tasks in comparison with the existing state-of-the-art methods. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimal MBU Positioning under Fault Scenario for Distribution Networks with high PV Penetration 14

Optimal MBU Positioning under Fault Scenario for Distributio...

引用

14th Mediterranean Conference on Power Generation Transmission, Distribution and Energy Conversion, MEDPOWER 2024

作者： Caruana, Cedric Bhattacharya, Somesh Raute, Reiko Micallef, Alexander Scerri, Kenneth Department of Electrical Engineering Faculty of Engineering University of Malta Msida Malta Department of Systems and Control Faculty of Engineering University of Malta Malta

ISBN: (纸本)9781837242689

Faults on distribution networks due to abnormal weather events can lead to disruption and can cause high socio-economic losses. In line with the rising frequency of such events, the paper proposes an algorithm for the optimal deployment of mobile battery units to restore sections of the network. The considered battery units are rated at 1MVA to keep them realistic for the mobile application. The placement algorithm is formulated as a mixed integer mathematical optimisation problem. Sectionalising/tie switches are assumed on each branch of the network in order to increase the restoration configuration flexibility. Photovoltaic systems, distributed along the network, are allowed to contribute to the restored network sections. A number of critical loads are defined and these are prioritised in the restoration process. The objective function also considers the reduction of the overall renewable energy curtailment. The performance of the algorithm is tested on the IEEE 33 bus network with four tie lines. Scenarios with increasing levels of PV power are considered and the effect of incorporating the PV power is studied. © The Institution of engineering & Technology 2024.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

A zeroth-order algorithm for distributed optimization with stochastic stripe observations

引用

Science China(Information Sciences) 2023年第9期66卷 297-298页

作者： Yinghui WANG Xianlin ZENG Wenxiao ZHAO Yiguang HONG School of Automation and Electrical Engineering University of Science and Technology Beijing Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Department of Control Science and Engineering Tongji University

Recent years have seen a rising interest in distributed optimization problems because of their widespread applications in power grids, multi-robot control, and regression *** the last few decades, many distributed algorithms have been developed for tackling distributed optimization problems. In these algorithms, agents over the network only have access to their own local functions and exchange information with their neighbors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

a-Synuclein: A fusion chaperone significantly boosting the enzymaticperformance of PET hydrolase

引用

Chinese Journal of chemical engineering 2023年第12期64卷 18-25页

作者： Renwen Tian Yan Sun Department of Biochemical Engineering School of Chemical Engineering and Technology and Key Laboratory of Systems Bioengineering and Frontiers Science Center for Synthetic Biology(Ministry of Education)Tianjin UniversityTianjin 300350China

Extensive use of polyethylene terephthalate (PET) has brought about global environmental problems. Arecently reported PET hydrolase (PETase) discovered from Ideonella sakaiensis showed high potentialfor degrading PET at moderate temperatures, but its activity and stability need further improvementfor practical applications. Herein, we proposed to use a-synuclein (aS) as a fusion chaperone and createdsix PETase-aS fusion enzymes with linkers of different types and lengths. All the fusion enzymes exhibited improved enzymatic performance, presenting 1.5 to 2.6-fold higher activity towards bis-2(hydroxyethyl) terephthalate than PETase, as well as significantly increased stabilities. Fluorescencespectroscopy indicated that the chaperone fusion tightened the overall conformation and resulted inthe opening of the substrate binding pocket, which led to the improved thermal stability and catalyticactivity of the fusion enzymes. Remarkably, one of the fusion proteins, PETase-[(GS)(EK)]10-aS, showed3.2 to 5.1 times higher PET degradation capability than PETase. The significantly boosted PET degradationperformance was not only attributed to the enhanced enzymatic activity and stability, but also possiblydue to the binding affinity of the fused aS domain for PET. These findings demonstrated that aS was aneffective fusion chaperone for significantly enhancing the enzymatic performance of PETase.

关键词： PET hydrolase a-Synuclein Fusion enzyme Stability Pollution Degradation

来源：评论

学校读者我要写书评

暂无评论

Facile purification and immobilization of organophosphorus hydrolase on protein-inorganic hybrid phosphate nanosheets

引用

Chinese Journal of chemical engineering 2023年第4期56卷 119-125页

作者： Zhenfu Wang Jie Gao Qinghong Shi Xiaoyan Dong Yan Sun Department of Biochemical Engineering School of Chemical Engineering and Technology and Key Laboratory of Systems Bioengineering and Frontiers Science Center for Synthetic Biology(Ministry of Education)Tianjin UniversityTianjin 300350China

Oriented immobilization of enzymes helps to maintain their native structure and proper orientation for high-performance engineering to meet extensive biocatalysis ***,the supporting materials used for orientated immobilization are usually costly or complicated in preparation,affecting their practical *** this work,a facile purification and immobilization method was proposed for enzyme immobilization based on organic-inorganic hybrid calcium phosphate nanocrystal(Ca Ps)induced by Cu^(2+) modified bovine serum albumin(BSA-Cu).Then,the as-prepared hybrid calcium phosphate nanosheet,BSA-Cu@Ca Ps,was utilized for one-pot purification and immobilization of His-tagged organophosphorus hydrolase(OPH)by metal-affinity binding to the incorporated ***-Cu@Ca PsOPH exhibited enhanced p H stability and thermal stability compared to the free ***,BSA-Cu@Ca Ps-OPH could retain more than 75%and 56%of initial activity after reuse 5 and 10 times,*** results demonstrated that this facile strategy was promising for the effective biodegradation of organophosphorus pesticides with the immobilized enzyme.

关键词： Calcium phosphate nanocrystal(CaPs) Biomimetic mineralization Organophosphorus hydrolase(OPH) Oriented immobilization Hydrolysis Methyl parathion

来源：评论

学校读者我要写书评

暂无评论

Multiple effects of polydopamine nanoparticles on Cu^(2+)-mediated Alzheimer's β-amyloid aggregation

引用

Chinese Journal of chemical engineering 2023年第2期54卷 144-152页

作者： Xueqing Chen Weiqun Gao Yan Sun Xiaoyan Dong Department of Biochemical Engineering School of Chemical Engineering and Technology and Key Laboratory of Systems Bioengineering and Frontiers Science Center for Synthetic Biology(Ministry of Education)Tianjin UniversityTianjin 300350China

Deposition of β-amyloid protein(Aβ) is the main hallmark of Alzheimer's disease(AD), and it has been well recognized that Cu^(2+)-mediated Aβ aggregation plays a crucial role in AD pathological ***^(2+)binding to Aβ can promote the production of reactive oxygen species(ROS) through Fenton-like reactions and produce more toxic Aβ-Cu^(2+)species under Cu^(2+)stimulation. Thus, the development of nanomaterials that can inhibit Cu^(2+)-mediated Aβ aggregation and degrade Aβ-Cu^(2+)complexes is considered an effective strategy for the prevention and treatment of AD. In this study, polydopamine nanoparticles(PDA NPs) were prepared and the results reveal that PDA NPs potently inhibit Cu^(2+)-mediated Aβaggregation and effectively reduce the formation of Aβ-Cu^(2+)complexes. In vitro experiments show that PDA NPs efficiently eliminate ROS generation catalyzed by Cu^(2+)or Aβ-Cu^(2+)complexes, thus rescuing cultured cells by reducing intracellular ROS levels. More importantly, PDA NPs can depolymerize Aβ-Cu^(2+)complexes, and the degradation of Aβ-Cu^(2+)complexes is promoted by near-infrared light irradiation due to their high photothermal conversion ability. In vivo studies reveal that PDA NPs significantly reduce the deposition of Aβ plaques in the presence of Cu^(2+)and extend the lifespan of AD nematodes from 11 to 14 d. Thus, the PDA NPs developed herein are multifunctional against Cu^(2+)-mediated Aβ aggregation for the potential prevention and treatment of AD.

关键词： Protein Aggregation Nanoparticles Photothermal therapy Reactive oxygen species Cu^(2+)chelator

来源：评论

学校读者我要写书评

暂无评论

Considering solid shear stress in MP-PIC simulation of a CFB riser

引用

Particuology 2024年第6期89卷 79-87页

作者： Tagir Kadyrov Fei Li Atta Ullah Nature-inspired Engineering Center University of TyumenTyumen 625003Russia Laboratory of Theory and Optimization of Chemical and Technological Processes University of TyumenTyumen625003Russia State Key Laboratory of Multi-phase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China Department of Chemical Engineering Pakistan Institute of Engineering&Applied SciencesIslamabad 45650Pakistan

To enable successful multi-phase particle-in-cell(MP-PIC)simulations of circulating fluidized beds(CFBs),both the interphase drag force and interparticle collisions need to be carefully *** collisions are usually represented by the solid stress consisting of the normal and shear components,in which the normal stress was found to have a leading role in the numerical stability of MP-PIC simulations,whereas the impact of the shear stress has seldom been *** this work,the effects of the solid shear stress are investigated by using two-dimensional simulations of the moderately dense laboratory-scale CFB riser with in-house MP-PIC code implemented on MFIX open-source *** including only normal solid stress and those considering both normal and shear solid stresses are *** results of solids flux,axial and radial solids profiles are compared with available experimental *** results show that the solid shear stress plays a minor role on the accuracy of simulation,and the increase of PPP(number particles per parcel)leads to a lower accuracy of simulation.

关键词： Simulation Fluidization Multiphase particle-in-cell(MP-PIC) Solid shear stress

来源：评论

学校读者我要写书评

暂无评论

A deep learning LSTM-based approach for AMD classification using OCT images

引用

Neural Computing and Applications 2024年第31期36卷 19531-19547页

作者： Hamid, Laila Elnokrashy, Amgad Abdelhay, Ehab H. Abdelsalam, Mohamed M. Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Mansoura Ophthalmic Center Faculty of Medicine Mansoura University Mansoura Egypt Electronics and Communications Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Faculty of Engineering Mansoura National University Mansoura Egypt

Age-related macular degeneration (AMD) is an age-related, persistent, painless eye disease that impairs central vision. The central area (macula) of the retina, located at the back of the eye, sustains damage that is the cause of loss of vision. The early detection of AMD can increase the probability of treatment and prevent vision loss. The AMD can be classified into dry and wet AMD based on the absence of neovascularization. This study introduces a new methodology for the classification of AMD using optical coherence tomography (OCT) retinal images. The proposed methodology is based on three stages. The first stage is the data preparation stage for resizing and normalizing the used images. The second stage is the image processing stage for enhancing the image quality as contrast and resolution these enhancements have been checked by the weighted peak signal-to-noise ratio (WPSNR) methodology. The third stage is the deep feature extraction and classification stage, which consists of two sub-models. The first model is MobileNet V1 which has been used as a deep feature extractor. The second model is LSTM (long short-term memory), fed with deep features to classify the AMD stages. A multi-classification with six separate trials has been employed with the proposed methodology, and compared with other models like DenseNet201 and InceptionV3. The proposed model has been tested on a sample of benchmark data with 4005 grayscale images labeled into three classes. The proposed methodology has achieved an accuracy of 98.85%, a sensitivity of 99.09%, and a specificity of 99.1%. To ensure the effectiveness of the proposed methodology, a comparative analysis has been established with previous approaches in the related field, and the results demonstrated the superiority of the proposed system in AMD multi-classification. © The Author(s) 2024.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization and Scaling Design for Solving Sylvester Equations

引用

Journal of systems Science & Complexity 2024年第6期37卷 2487-2510页

作者： CHENG Songsong YU Xin ZENG Xianlin LIANG Shu HONG Yiguang Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui UniversityHefei 230601China Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of TechnologyBeijing 100081China Department of Control Science and Engineering Tongji UniversityShanghai 201804China Shanghai Research Institute for Intelligent Autonomous Systems Tongji UniversityShanghai 201210China

This paper develops distributed algorithms for solving Sylvester *** authors transform solving Sylvester equations into a distributed optimization problem,unifying all eight standard distributed matrix *** the authors propose a distributed algorithm to find the least squares solution and achieve an explicit linear convergence *** results are obtained by carefully choosing the step-size of the algorithm,which requires particular information of data and Laplacian *** avoid these centralized quantities,the authors further develop a distributed scaling technique by using local information *** a result,the proposed distributed algorithm along with the distributed scaling design yields a universal method for solving Sylvester equations over a multi-agent network with the constant step-size freely chosen from configurable ***,the authors provide three examples to illustrate the effectiveness of the proposed algorithms.

关键词： Distributed optimization least squares solution linear convergence rate step-size interval Sylvester equation

来源：评论

学校读者我要写书评

暂无评论

Data Information integrated Neural Network (DINN) algorithm for modelling and interpretation performance analysis for energy systems

引用

Energy and AI 2024年第2期16卷 306-315页

作者： Waqar Muhammad Ashraf Vivek Dua The Sargent Centre for Process Systems Engineering Department of Chemical EngineeringUniversity College LondonTorrington PlaceLondon WC1E 7JEUK

Developing a well-predictive machine learning model that also offers improved interpretability is a key challenge to widen the application of artificial intelligence in various application domains. In this work, we present a Data Information integrated Neural Network (DINN) algorithm that incorporates the correlation information present in the dataset for the model development. The predictive performance of DINN is also compared with a standard artificial neural network (ANN) model. The DINN algorithm is applied on two case studies of energy systems namely energy efficiency cooling (ENC) & energy efficiency heating (ENH) of the buildings, and power generation from a 365 MW capacity industrial gas turbine. For ENC, DINN presents lower mean RMSE for testing datasets (RMSE_test = 1.23 %) in comparison with the ANN model (RMSE_test = 1.41 %). Similarly, DINN models have presented better predictive performance to model the output variables of the two case studies. The input perturbation analysis following the Gaussian distribution for noise generation reveals the order of significance of the variables, as made by DINN, can be better explained by the domain knowledge of the power generation operation of the gas turbine. This research work demonstrates the potential advantage to integrate the information present in the data for the well-predictive model development complemented with improved interpretation performance thereby opening avenues for industry-wide inclusion and other potential applications of machine learning.

关键词： Explainable AI Model interpretation Scientific machine learning Artificial neural network Loss function

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：