检索结果-内蒙古大学图书馆

Fast Bootstrapping Nonparametric Maximum Likelihood for Latent Mixture Models

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 870-874页

作者： Wang, Shijie Shin, Minsuk Bai, Ray Univ South Carolina Dept Stat Columbia SC 29208 USA Gauss Labs Palo Alto CA 94301 USA

Estimating the mixing density of a latent mixture model is an important task in signal processing. Nonparametric maximum likelihood estimation is one popular approach to this problem. If the latent variable distribution is assumed to be continuous, then bootstrapping can be used to approximate it. However, traditional bootstrapping requires repeated evaluations on resampled data and is not scalable. In this letter, we construct a generative process to rapidly produce nonparametric maximum likelihood bootstrap estimates. Our method requires only a single evaluation of a novel two-stage optimization algorithm. Simulations and real data analyses demonstrate that our procedure accurately estimates the mixing density with little computational cost even when there are a hundred thousand observations.

关键词： Bootstrap/resampling deep neural network generative process mixing density estimation nonparametric maximum likelihood estimation two-stage algorithm

来源：评论

学校读者我要写书评

暂无评论

two-stage Coordination Scheme for Multiple EV Charging Stations Connected to an Exclusive DC Feeder Considering Grid-Tie Converter Limitation

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2024年第4期10卷 8213-8223页

作者： Saber, Hossein Ranjbar, Hossein Hajipour, Ehsan Shahidehpour, Mohammad Sharif Univ Technol Ctr Excellence Power Syst Control & Management Elect Engn Dept Tehran *** Iran Univ Adelaide Sch Elect & Mech Engn Adelaide SA 5005 Australia IIT Robert W Galvin Ctr Elect Innovat Chicago IL 60616 USA King Abdulaziz Univ Jeddah 21589 Saudi Arabia

The rapid proliferation of electric vehicles (EVs), if not properly integrated, has the potential to impact the secure and economic operation of distribution systems. To tackle this challenge, the system operators and planners have two primary options: 1) expanding system capacity and 2) implementing charging management programs. In this article, we consider an exclusive dc feeder for supplying multiple EV charging stations, connected to the main grid via the grid-tie converter. In addition, a two-stage coordination algorithm is proposed in which the EV charging stations' daily quotas from the grid-tie converter capacity and their day-ahead scheduling plans are determined in the first stage. In this regard, the EV charging stations determine their profit curves, and then the local market operator (LMO) collects these curves and calculates the quotas by maximizing the total profit respecting the capacity constraint. Considering the calculated quotas, the EV charging stations determine and submit their day-ahead scheduling plans to the LMO. In the second stage, each EV charging station manages its real-time operation under the uncertainties of EV parking activities. To this end, the model predictive control (MPC) method is used to effectively handle model uncertainties. Furthermore, to encourage EV owners' participation in the charging control program, the EV charging station's profit is fairly distributed among EVs based on their provided flexibility. Finally, the simulation study is provided to illustrate the effectiveness and applicability of the proposed model from the perspective of system operation and EV owners.

关键词： Electric vehicle charging Uncertainty Batteries Distribution networks Costs State of charge Privacy EV charging management grid-tie converter limitation model predictive control (MPC) profit-sharing mechanism two-stage algorithm

来源：评论

学校读者我要写书评

暂无评论

Power transformer protection using chirplet transform

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2016年第10期10卷 2520-2530页

作者： Murugan, Senthil Kumar Simon, Sishaj Pulikottil Nayak, Panugothu Srinivasa Rao Sundareswaran, Kinattingal Padhy, Narayana Prasad Natl Inst Technol Dept Elect & Elect Engn Tiruchirappalli Tamil Nadu India Indian Inst Technol Dept Elect & Elect Engn Roorkee Uttar Pradesh India

This study presents a novel differential protection algorithm (DPA) for power transformer using chirplet transform (ChT). The proposed method combines the features of biased restraint characteristic (BRC) of the conventional differential relay and out-turn of ChT in a two-stage algorithm. In the first stage, the BRC plane is divided into three zones: namely, high-set (HS), non-trip and vulnerable zones. The tripping decisions are carried out in the first two zones based on differential and biased current. However, if the operating condition of the power transformer falls in the vulnerable zone, then there is an ambiguity in discriminating internal fault, inrush current and current transformer saturation cases. Therefore, in the second stage, ChT is applied to differential current signal to obtain an energy distribution on the time-frequency plane with respect to time, frequency and chirp rate. Then, using the mean and standard deviation of the normalised energy, power transformer operating conditions are classified. Also, most of the DPAs available in the literature are system dependent. However, the proposed novel DPA can be effectively used for any system. The proposed scheme is validated for two power transformer systems using PSCAD to simulate various operating conditions and MATLAB to implement the algorithm.

关键词： power transformer protection transforms current transformers power transformer protection chirplet transform differential protection algorithm biased restraint characteristic differential relay two-stage algorithm tripping decisions power transformer systems PSCAD MATLAB codes

来源：评论

学校读者我要写书评

暂无评论

A stochastic analysis of robust estimation algorithms in H_∞ with rational basis functions

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL 2002年第1期12卷 71-86页

作者： Akçay, H Anadolu Univ Dept Elect & Elect Engn TR-26470 Eskiesehir Turkey

In this paper, a two-stage nonlinear identification algorithm parameterized in terms of rational basis functions with fixed basis poles is studied when disturbances are subject to mild stochastic assumptions. The two-stage algorithm is the archetype for robust estimation algorithms in H-infinity and its first stage is linear-in-data. Conditions for the consistency of both the stages are derived. It is shown that the two-stage algorithm enjoys a better stochastic as well as deterministic performance than those of the linear algorithms. Copyright (C) 2001 John Wiley Sons, Ltd.

关键词： robust identification two-stage algorithm rational basis functions stochastic noise frequency response data

来源：评论

学校读者我要写书评

暂无评论

Performance Optimized Expectation Conditional Maximization algorithms for Nonhomogeneous Poisson Process Software Reliability Models

引用

IEEE TRANSACTIONS ON RELIABILITY 2017年第3期66卷 722-734页

作者： Nagaraju, Vidhyashree Fiondella, Lance Zeephongsekul, Panlop Jayasinghe, Chathuri L. Wandji, Thierry Univ Massachusetts Dept Elect & Comp Engn Dartmouth MA 02747 USA RMIT Univ Sch Math & Geospatial Sci Melbourne Vic 3000 Australia Univ Sri Jayewardenepura Fac Appl Sci Dept Stat Nugegoda 10250 Sri Lanka Naval Air Syst Command Patuxent River MD 20670 USA

Nonhomogeneous Poisson process (NHPP) and software reliability growth models (SRGM) are a popular approach to estimate useful metrics such as the number of faults remaining, failure rate, and reliability, which is defined as the probability of failure free operation in a specified environment for a specified period of time. We propose performance-optimized expectation conditional maximization (ECM) algorithms for NHPP SRGM. In contrast to the expectation maximization (EM) algorithm, the ECM algorithm reduces the maximum-likelihood estimation process to multiple simpler conditional maximization (CM)-steps. The advantage of these CM-steps is that they only need to consider one variable at a time, enabling implicit solutions to update rules when a closed form equation is not available for a model parameter. We compare the performance of our ECM algorithms to previous EM and ECM algorithms on many datasets from the research literature. Our results indicate that our ECM algorithms achieve two orders of magnitude speed up over the EM and ECM algorithms of [1] when their experimental methodology is considered and three orders of magnitude when knowledge of the maximum-likelihood estimation is removed, whereas our approach is as much as 60 times faster than the EM algorithms of [2]. We subsequently propose a two-stage algorithm to further accelerate performance.

关键词： Expectation conditional maximization (ECM) algorithm nonhomogeneous Poisson process (NHPP) software reliability software reliability growth model two-stage algorithm

来源：评论

学校读者我要写书评

暂无评论

The integration of resource allocation and time buffering for bi-objective robust project scheduling

引用

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH 2020年第13期58卷 3839-3854页

作者： Liang, Yangyang Cui, Nanfang Hu, Xuejun Demeulemeester, Erik Hubei Univ Econ Res Ctr Hubei Logist Dev Wuhan Hubei Peoples R China Huazhong Univ Sci & Technol Sch Management Wuhan Hubei Peoples R China Hunan Univ Business Sch Changsha Hunan Peoples R China Katholieke Univ Leuven Fac Econ & Business Dept Decis Sci & Informat Management Res Ctr Operat Management Leuven Belgium

In the recent decades, the recognition that uncertainty lies at the heart of modern project management has induced considerable research efforts on robust project scheduling for dealing with uncertainty in a scheduling environment. The literature generally provides two main strategies for the development of a robust predictive project schedule, namely robust resource allocation and time buffering. Yet, the previous studies seem to have neglected the potential benefits of an integration between the two. Besides, few efforts have been made to protect simultaneously the project due date and the activity start times against disruptions during execution, which is desperately demanded in practice. In this paper, we aim at constructing a proactive schedule that is not only short in time but also less vulnerable to disruptions. Firstly, a bi-objective optimisation model with a proper normalisation of the two components is proposed in the presence of activity duration variability. Then a two-stage heuristic algorithm is developed which deals with a robust resource allocation problem in the first stage and optimally determines the position and the size of time buffers using a simulated annealing algorithm in the second stage. Finally, an extensive computational experiment on the PSPLIB network instances demonstrates the superiority of the combination between resource allocation and time buffering as well as the effectiveness of the proposed two-stage algorithm for generating proactive project schedules with composite robustness.

关键词： robust project scheduling bi-objective optimisation robust resource allocation time buffering two-stage algorithm

来源：评论

学校读者我要写书评

暂无评论

Carbon dioxide source selection and supply planning for fracking operations in shale gas and oil wells

引用

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING 2018年 55卷 74-88页

作者： Li, Xin Ventura, Jose A. Ayala, Luis F. Penn State Univ Harold & Inge Marcus Dept Ind & Mfg Engn University Pk PA 16802 USA Penn State Univ John & Willie Leone Family Dept Energy & Mineral University Pk PA 16802 USA

As a promising alternative approach for shale gas and oil withdrawal, fracking using CO2 instead of water has been proved to be not only technically feasible but also environmentally friendly. This paper aims at evaluating CO2 fracking from an economic perspective by considering the collection, supply, transportation, and storage of CO2. More specifically, a CO2 source selection and supply planning problem is defined and discussed from three aspects: CO2 collection and storage at sources, CO2 transportation, and CO2 storage and usage at well pads. Cost models for the three aspects are built, based on which, a mixed-integer nonlinear programming model is developed to determine the optimal set of sources, the corresponding supply and transportation plan, and the investment in associated facilities and equipment. A two-stage algorithm is proposed, which decomposes the original model into a large set of simple sub-problems and a mixed-integer linear problem. A case study for three emerging well pads in North Dakota is presented to illustrate the implementation of the mathematical model and algorithm, and a sensitivity analysis is conducted to analyze the influences of four key parameters over the cost of using CO2.

关键词： CO2 fracking Source selection Supply planning Mathematical model two-stage algorithm Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

MATCHING 3-D LINE SEGMENTS WITH APPLICATIONS TO MULTIPLE-OBJECT MOTION ESTIMATION

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1990年第10期12卷 1002-1008页

作者： CHEN, HH HUANG, TS UNIV ILLINOIS COORDINATED SCI LABURBANAIL 61801

A two-stage algorithm for matching line segments using three-dimensional data is presented. In the first stage, a tree-search based on the orientation of the line segments is applied to establish potential matches. the sign ambiguity of line segments is fixed by a simple congruency constraint. In the second stage, a Hough clustering technique based on the position of line segments is applied to verify potential matches. Any paired line segments of a match that cannot be brought to overlap by the translation determined by the clustering are removed from the match. Unlike previous methods, this algorithm combats noise more effectively, and ensures the global consistency of a match. While the original motivation for the algorithm is multiple-object motion estimation from stereo image sequences, the algorithm can also be applied to other domains, such as object recognition and object model construction from multiple views.","doi":"10.1109/34.58872","publicationTitle":"IEEE Transactions on Pattern Analysis and Machine Intelligence","startPage":"1002","endPage":"1008","rightsLink":"http://***/AppDispatchServlet?publisherName=ieee&publication=0162-8828&title=Matching+3-D+line+segments+with+applications+to+multiple-object+motion+estimation&isbn=&publicationDate=Oct.+1990&author=H.H.+Chen&ContentID=10.1109/34.58872&orderBeanReset=true&startPage=1002&endPage=1008&volumeNum=12&issueNum=10","displayPublicationTitle":"IEEE Transactions on Pattern Analysis and Machine Intelligence","pdfPath":"/iel1/34/2141/***","keywords":[{"type":"IEEE Keywords","kwd":["Motion estimation","Stereo vision","Image sequences","Motion analysis","Clustering algorithms","Testing","Image recognition","Image motion analysis","Object recognition","Computer vision"]},{"type":"INSPEC: Controlled Indexing","kwd":["trees (mathematics)","pattern recognition","search problems"]},{"type":"INSPEC: Non-Controlled Indexing","kwd":["object model construction","pattern recognition","3-D line s

关键词： Motion estimation Stereo vision Image sequences Motion analysis Clustering algorithms Testing Image recognition Image motion analysis Object recognition Computer vision INSPEC: Controlled Indexing trees (mathematics) pattern recognition search problems INSPEC: Non-Controlled Indexing object model construction pattern recognition 3-D line segments multiple-object motion estimation two-stage algorithm matching tree-search sign ambiguity congruency constraint Hough clustering technique global consistency stereo image sequences object recognition

来源：评论

学校读者我要写书评

暂无评论

A two-stage optimization approach for subscription bus services network design: the China case

引用

PUBLIC TRANSPORT 2019年第3期11卷 589-616页

作者： Huang, Wencheng Shuai, Bin Antwi, Eric Southwest Jiaotong Univ Sch Transportat & Logist Chengdu 611756 Sichuan Peoples R China Southwest Jiaotong Univ Natl United Engn Lab Integrated & Intelligent Tra Chengdu 611756 Sichuan Peoples R China Southwest Jiaotong Univ Natl Engn Lab Integrated Transportat Big Data App Chengdu 611756 Sichuan Peoples R China

Subscription bus services (SBS) is a convenient and low-carbon rapid transport mode for passengers' daily commute. The network design becomes a vital problem because it closely relates to both operators' profit and passengers' daily convenient traveling. In this paper, a two-stage model is formulated to optimize the subscription bus services network design (SBSND). During the first stage we minimize the total service distance and the number of vehicles as a single target objective function;vehicle capacity utilization rate, service time, ratio of service distance and linear distance between origin and destination are limited by means of constraints. During the second stage we share the same objective function and similar constraints used during the first stage, but the parameter settings of the constraints are different. Correspondingly, a two-stage algorithm is also designed to solve the SBSND problem. Firstly, we obtain the possible service lines, match the passengers and bus capacity. Next, we use Dijkstra to obtain the shortest SBS operation lines. Finally, we form the SBS network. The three phases are the main processes about the algorithm during both stages. The comparison between existing SBS in Chengdu city and the optimized SBS shows the high efficiency of the optimization model and algorithm formulated in this paper: the operation line length increases from 250.6 to 300.9 km;only 40 passengers have no SBS after optimization;the average operation time is reduced from 56.8 to 50.2 min.

关键词： Subscription bus service Network design optimization two-stage optimization model two-stage algorithm

来源：评论

学校读者我要写书评

暂无评论

two-stage Method of Construction of Regularizing algorithms for Nonlinear Ill-Posed Problems

引用

PROCEEDINGS OF THE STEKLOV INSTITUTE OF MATHEMATICS 2018年第1-Sup期301卷 S173-S190页

作者： Vasini, V. V. Skurydina, A. F. Russian Acad Sci Krasovskii Inst Math & Mech Ural Branch Ekaterinburg 620990 Russia Ural Fed Univ Ekaterinburg 620000 Russia

For an equation with a nonlinear differentiable operator acting in a Hilbert space, we study a two-stage method of construction of a regularizing algorithm. First, we use the Lavrentiev regularization scheme. Then we apply to the regularized equation either Newton's method or nonlinear analogs of alpha-processes: the minimum error method, the minimum residual method, and the steepest descent method. For these processes, we establish the linear convergence rate and the Fej,r property of iterations. two cases are considered: when the operator of the problem is monotone and when the operator is finite-dimensional and its derivative has nonnegative spectrum. For the two-stage method with a monotone operator, we give an error bound, which has optimal order on the class of sourcewise representable solutions. In the second case, the error of the method is estimated by means of the residual. The proposed methods and their modified analogs are implemented numerically for three-dimensional inverse problems of gravimetry and magnetometry. The results of the numerical experiment are discussed.

关键词： Lavrentiev regularization scheme Newton's method nonlinear alpha-processes two-stage algorithm inverse gravimetry and magnetometry problems

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：