检索结果-南通市图书馆

Gene locations may contribute to predicting gene regulatory relationships

维普期刊数据库评论

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 Zhejiang University-Science B(Biomedicine & Biotechnology) 2018年第1期19卷 25-37页

作者： Jun MENG Wen-yuan XU Xiao CHEN Tao LIN Xiao-yu DENG Department of System Science and Engineering School of Electrical Engineering Zhejiang University laboratory of machine learning and optimization école Polytechnique Fédérale de Lausanne (EPFL)

We propose that locations of genes on chromosomes can contribute to the prediction of gene regulatory relationships. We constructed a time-based gene regulatory network of zebrafish cardiogenesis on the basis of a spatio-temporal neighborhood method. Through the network, specific regulatory pathways and order of gene expression during zebrafish cardiogenesis were obtained. By comparing the order with locations of these genes on chromosomes, we discovered that there exists a reversal phenomenon between the order and order of gene locations. The discovery provides an inherent rule to instruct exploration of gene regulatory relationships. Specifically, the discovery can help to predict if regulatory relationships between genes exist and contribute to evaluating the correctness of discovered gene regulatory relationships.

关键词： Prediction Gene regulatory relationships Order of gene location Spatio-temporal neighborhood method Zebrafish cardiogenesis

An efficient quantum proactive incremental learning algorithm

在线全文

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2025年第1期Mechanics & Astronomy) .卷 49-57页

作者： Lingxiao Li Jing Li Yanqi Song Sujuan Qin Qiaoyan Wen Fei Gao State Key laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications School of Cyberspace Security Beijing University of Posts and Telecommunications

In scenarios where a large amount of data needs to be learned, incremental learning can make full use of old knowledge, significantly reduce the computational cost of the overall learning process, and maintain high performance. In this paper, taking the MaxCut problem as our example, we introduce the idea of incremental learning into quantum computing, and propose a Quantum Proactive Incremental learning algorithm(QPIL). Instead of a one-off training of quantum circuit, QPIL contains a multi-phase training on gradually-increased subgraphs of all vertices, proactively reducing large-scale problems to smaller ones to solve in steps, providing an efficient solution for MaxCut. Specifically, some vertices and corresponding edges are randomly selected for training to obtain optimized parameters of the quantum circuit at first. Then, in each incremental phase, the remaining vertices and corresponding edges are gradually added and the parameters obtained from the previous phase are reused in the parameter initialization of the current phase. We perform experiments on 120 different small-scale graphs, and it shows that QPIL performs superior to prevalent quantum and classical baselines in terms of approximation ratio(AR), time cost, anti-forgetting, and solving stability. In particular, QPIL's AR surpasses 20% of mainstream quantum baselines, and the time cost is less than 1/5 of them. The idea of QPIL is expected to inspire efficient and high-quality solutions in large-scale Max Cut and other combinatorial optimization problems.

关键词： variational quantum algorithm incremental learning multi-phase training MaxCut quantum computing

High-speed identification of suspended carbon nanotubes using Raman spectroscopy and deep learning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2022年第1期8卷 259-267页

作者： Jian Zhang Mickael L.Perrin Luis Barba Jan Overbeck Seoho Jung Brock Grassy Aryan Agal Rico Muff Rolf Brönnimann Miroslav Haluska Cosmin Roman Christofer Hierold Martin Jaggi Michel Calame laboratory for Transport at Nanoscale Interfaces EmpaSwiss Federal Laboratories for Materials Science and TechnologyCH-8600 DübendorfSwitzerland machine learning and optimization laboratory School of Computer and Communication SciencesEPFLCH-1015 LausanneSwitzerland Department of Physics and Swiss Nanoscience Institute University of BaselCH-4056 BaselSwitzerland Micro-and Nanosystems Department of Mechanical and Process EngineeringETH ZurichCH-8092 ZurichSwitzerland

The identification of nanomaterials with the properties required for energy-efficient electronic systems is usually a tedious human task.A workflow to rapidly localize and characterize nanomaterials at the various stages of their integration into large-scale fabrication processes is essential for quality control and,ultimately,their industrial *** this work,we develop a high-throughput approach to rapidly identify suspended carbon nanotubes(CNTs)by using high-speed Raman imaging and deep learning *** for Raman spectra with extremely low signal-to-noise ratios(SNRs)of 0.9,we achieve a classification accuracy that exceeds 90%,while it reaches 98%for an SNR of *** applying a threshold on the output of the softmax layer of an optimized convolutional neural network(CNN),we further increase the accuracy of the ***,we propose an optimized Raman scanning strategy to minimize the acquisition time while simultaneously identifying the position,amount,and metallicity of CNTs on each *** approach can readily be extended to other types of nanomaterials and has the potential to be integrated into a production line to monitor the quality and properties of nanomaterials during fabrication.

关键词： carbon suspended speed

Sampled Value Attack Detection for Busbar Differential Protection Based on a Negative Selection Immune System

维普期刊数据库评论

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 2023年第2期11卷 421-433页

作者： Jun Mo Hui Yang Guangxi Key laboratory of Power System optimization and Energy Technology Guangxi UniversityNanning 530004China

Considering a variety of sampled value(SV)attacks on busbar differential protection(BDP)which poses challenges to conventional learning algorithms,an algorithm to detect SV attacks based on the immune system of negative selection is developed in this *** healthy SV data of BDP are defined as self-data composed of spheres of the same size,whereas the SV attack data,i.e.,the nonself data,are preserved in the nonself space covered by spherical detectors of different *** avoid the confusion between busbar faults and SV attacks,a self-shape optimization algorithm is introduced,and the improved self-data are verified through a power-frequency fault-component-based differential protection criterion to avoid false *** on the difficulty of boundary coverage in traditional negative selection algorithms,a self-data-driven detector generation algorithm is proposed to enhance the detector coverage.A testbed of differential protection for a 110 kV double busbar system is then *** SV attacks of BDP such as amplitude and current phase tampering,fault replays,and the disconnection of the secondary circuits of current transformers are considered,and the delays of differential relay operation caused by detection algorithms are investigated.

关键词： Cyberattack busbar differential protection(BDP) negative selection self-data-driven detector sampled value attacks internal faults

Understanding adversarial attacks on observations in deep reinforcement learning

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第5期67卷 69-83页

作者： You QIAOBEN Chengyang YING Xinning ZHOU Hang SU Jun ZHU Bo ZHANG Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua-Bosch Joint Center for Machine Learning Institute for Artificial Intelligence Tsinghua University Peng Cheng laboratory

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease the cumulative expected reward of a victim by manipulating its observations. Despite the efficiency of previous optimization-based methods for generating adversarial noise in supervised learning, such methods might not achieve the lowest cumulative reward since they do not generally explore the environmental ***, a framework is provided to better understand the existing methods by reformulating the problem of adversarial attacks on reinforcement learning in the function space. The reformulation approach adopted herein generates an optimal adversary in the function space of targeted attacks, repelling them via a generic two-stage framework. In the first stage, a deceptive policy is trained by hacking the environment and discovering a set of trajectories routing to the lowest reward or the worst-case performance. Next, the adversary misleads the victim to imitate the deceptive policy by perturbing the observations. Compared to existing approaches, it is theoretically shown that our adversary is strong under an appropriate noise level. Extensive experiments demonstrate the superiority of the proposed method in terms of efficiency and effectiveness, achieving state-of-the-art performance in both Atari and MuJoCo environments.

关键词： deep learning reinforcement learning adversarial robustness adversarial attack

Multi-index Evaluation based Reinforcement learning Method for Cyclic optimization of Multiple Energy Utilization in Steel Industry

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Multi-index Evaluation based Reinforcement Learning Method f...

A mesh optimization method using machine learning technique and variational mesh adaptation

第三十九届中国控制会议

作者： Ze Wang Linqing Wang Zhongyang Han Jun Zhao Key laboratory of Intelligent Control and optimization for Industrial Equipment（Dalian University of Technology） Ministry of Education

Energy including coal, electricity, gas, etc., are directly related to the production process of steel industry. As such, a scientific and reasonable scheme for energy utilization is undoubtedly support the fulfillment of the production plan along with reduce energy consumption and environmental pollution. Aiming at optimizing the input amount of each energy resource in the Integrated Energy System（IES） of steel industry, a series of optimization models along with cyclic solution method based on Actor-Critic are proposed in this study, which can efficiently obtain the optimal energy utilization scheme considering both the global and local index. Firstly, the Energy Consumption per Ton Steel in the perspective of the whole IES and the emission of the byproduct gas regarding the energy subsystem are defined as the optimization objective respectively. Then, with the consideration of the practical constraints of the energy network, the mathematical programming models are accordingly established. Due to the existence of nonlinear constraints which brings about the difficulty for the conventional optimization method, a reinforcement learning based strategy is then designed to cyclically solve the optimization models for obtaining the final energy utilization scheme. Based on the practical data of steel industry, the experiment results demonstrate that compared with the commonly deployed methods, the proposed approach exhibits obvious superiority in controlling energy consumption as well as improving energy efficiency, which provides effective support for enterprises on energy saving.

关键词： Integrated Energy System(IES) Steel industry Cyclic Reinforcement learning Multi-index evaluation

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2022年第3期35卷 27-41页

作者： Tingfan WU Xuejun LIU Wei AN Zenghui HUANG Hongqiang LYU MIITKey laboratory of Pattern Analysis and machine Intelligence College of Computer Science and TechnologyNanjing University of Aeronautics and AstronauticsNanjing 211106China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 210023China College of Aerospace Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China

Computational mesh is an important ingredient that affects the accuracy and efficiency of CFD numerical *** light of the introduced large amount of computational costs for many adaptive mesh methods,moving mesh methods keep the number of nodes and topology of a mesh unchanged and do not increase CFD computational *** the state-of-the-art moving mesh method,the variational mesh adaptation approach has been introduced to CFD ***,quickly estimating the flow field on the updated meshes during the iterative algorithm is challenging.A mesh optimization method,which embeds a machine learning regression model into the variational mesh adaptation,is *** regression model captures the mapping between the initial mesh nodes and the flow field,so that the variational method could move mesh nodes iteratively by solving the mesh functional which is built from the estimated flow field on the updated mesh via the regression *** the optimization,the density of the nodes in the high gradient area increases while the density in the low gradient area *** examples are first used to verify the feasibility and effectiveness of the proposed *** then we use the steady subsonic and transonic flows over cylinder and NACA0012 airfoil on unstructured triangular meshes to test our *** show that the proposed method significantly improves the accuracy of the local flow features on the adaptive *** work indicates that the proposed mesh optimization approach is promising for improving the accuracy and efficiency of CFD computation.

关键词： CFD Flow field machine learning Moving mesh method Regression models Variational mesh adaptation

A novel hybrid estimation of distribution algorithm for solving hybrid flowshop scheduling problem with unrelated parallel machine

在线全文

学校读者我要写书评

暂无评论

Journal of Central South University 2017年第8期24卷 1779-1788页

作者：孙泽文顾幸生 Key laboratory of Advanced Control and optimization for Chemical Process Ministry of Education(East China University of Science and Technology)Shanghai 200237China

The hybrid flow shop scheduling problem with unrelated parallel machine is a typical NP-hard combinatorial optimization problem, and it exists widely in chemical, manufacturing and pharmaceutical industry. In this work, a novel mathematic model for the hybrid flow shop scheduling problem with unrelated parallel machine(HFSPUPM) was proposed. Additionally, an effective hybrid estimation of distribution algorithm was proposed to solve the HFSPUPM, taking advantage of the features in the mathematic model. In the optimization algorithm, a new individual representation method was adopted. The(EDA) structure was used for global search while the teaching learning based optimization(TLBO) strategy was used for local search. Based on the structure of the HFSPUPM, this work presents a series of discrete operations. Simulation results show the effectiveness of the proposed hybrid algorithm compared with other algorithms.

关键词： hybrid estimation of distribution algorithm teaching learning based optimization strategy hybrid flow shop unrelated parallel machine scheduling

Wind field reconstruction for the dispersion modeling of accidental chemical spills on complex geometry

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2019年第11期27卷 2712-2724页

作者： Bing Wang Feng Qian Weimin Zhong Key laboratory of Advanced Control and optimization for Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China

Chemical spills on complex geometry are difficult to model due to the uneven concentration distribution caused by air flow over ground obstacles. Computational fluid dynamics(CFD) is one of the powerful tools to estimate the building-resolving wind flow as well as pollutant dispersion. However, it takes too much time and requires enormous computational power in emergency situations. As a time demanding task, the estimation of the chemical spill consequence for emergency response requires abundant wind field information. In this paper, a comprehensive wind field reconstruction framework is proposed, providing the ability of parameter tuning for best reconstruction accuracy. The core of the framework is a data regression model built on principal component analysis(PCA) and extreme learning machine(ELM). To improve the accuracy, the wind field estimation from the regression model is further revised from local wind observations. The optimal placement of anemometers is provided based on the maximum projection on minimum eigenspace(MPME) algorithm. The fire dynamic simulator(FDS) generates high-resolution data of wind flow over complex geometries for the framework to be implemented. The reconstructed wind field is evaluated against simulation data and an overall reconstruction error of 9% is achieved. When used in real case,the error increases to around 12% since no convergence check is available. With parameter tuning abilities,the proposed framework provides an efficient way of reconstructing the wind flow in congested areas.

关键词： Wind field reconstruction CFD PCA Extreme learning machine Sensor placement