检索结果-内蒙古大学图书馆

作者： Bu, Zhiqi University of Pennsylvania

学位级别：Ph.D., Doctor of Philosophy

The era of machine learning features large datasets that have high dimension of features. This leads to the emergence of various algorithms to learn efficiently from such high-dimensional datasets, as well as the need to analyze these algorithms from both the prediction and the statistical inference viewpoint. To be more specific, an ideal model is expected to predict accurately on the unseen new data, and to provide valid inference so as to harness the uncertainty in the model. Unfortunately, the high dimension of features poses a great challenge on the analysis of many prevalent models, rendering them either inapplicable or difficult to study. This thesis leverages the approximate message passing (AMP) algorithm, the optimization theory, and the Sorted L-One Penalized Estimation (SLOPE) to study several important problems of the sparse models. The first chapter introduces various l penalties including but not limited to the SLOPE, a relatively new convex optimization procedure via the sorted l1 penalty, in the general machine learning models. We then focus on the linear models and demonstrate some basic properties of SLOPE, especially its advantages over the Lasso. Next, we cover the AMP algorithm in terms of convergence behavior and asymptotic statistical characterization. The second chapter extends the AMP algorithms from Lasso to SLOPE and provides an asymptotically tight characterization of the SLOPE solution. Note that SLOPE is a relatively new convex optimization procedure for high-dimensional linear regression via the sorted l1 penalty: the larger the rank of the fitted coefficient, the larger the penalty. This non-separable penalty renders many existing techniques invalid or inconclusive in analyzing the SLOPE solution. We develop an asymptotically exact characterization of the SLOPE solution under Gaussian random designs through solving the SLOPE problem using approximate message passing (AMP). This algorithmic approach allows us to approximate the SLOPE

关键词： High-dimensional statistics Linear models Machine learning optimization algorithm Sparse models Statistical inference

来源：评论

学校读者我要写书评

暂无评论

Combustion system optimization for the integration of e-fuels (Oxymethylene Ether) in compression ignition engines

引用

FUEL 2021年 305卷

作者： Novella, Ricardo Bracho, Gabriela Gomez-Soriano, Josep Fernandes, Cassio S. Lucchini, Tommaso Univ Politecn Valencia CMT Motores Term Valencia Spain Politecn Milan Milan Italy

In this study, a numerical methodology for the optimization of the combustion chamber in compression ignited engines using OME as fuel is presented. The objective is to obtain a dedicated combustion system for an engine that is fueled with this alternative fuel improving the efficiency and reducing the emissions of NOx. This article proposes the integration between the optimization algorithm and CFD codes to evaluate the behavior of an engine fuelled with the low sooting fuel OME. Based on a diesel model validated against experimental data, a further model for OME fuel was implemented for evaluating the performance of the engine. The particle swarm algorithm (PSO) was modified based on the Novelty Search concepts and used as optimization algorithm. Several tools are coupled in order to create each CFD case where all the tools and optimization algorithm are coupled in a routine that automates the entire process. The result is an optimized combustion system that provides an increase of the efficiency (about 2.2%) and a NOx reduction (35.7%) in comparison with the baseline engine with conventional fuel. In addition, a neuronal network was trained with all the results of all simulations performed during the optimization process, studying the influence of each parameter on the emissions and efficiency. From this analysis it was concluded that the EGR rate and injection pressure affects the NOx emissions with a range of variability of 63% and 38% respectively.

关键词： Internal combustion engines CFD codes optimization algorithm Alternative fuel OME

来源：评论

学校读者我要写书评

暂无评论

Novel surface optimization for trajectory reconstruction in industrial robot tasks

引用

INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 2021年第6期18卷

作者： Angel Funes-Lora, Miguel Vega-Alvarado, Eduardo Rivera-Blas, Raul Barbara Calva-Yanez, Maria Sepulveda-Cervantes, Gabriel Univ Michigan Ann Arbor MI 48109 USA Inst Politecn Nacl Ciudad De Mexico Mexico

This study presents a novel algorithm implementation that optimizes manually recorded toolpaths with the use of a 3D-workpiece model to reduce manual error induced. The novel algorithm has three steps: workpiece declaration, manual toolpath declaration, and toolpath optimization using steepest descent algorithm. Steepest descent finds the surface route wherein the manually recorded toolpaths traverse over a 3D-workpiece surface. The optimized toolpaths were simulated and tested with an industrial robot showing minimal error compared to the desired optimized toolpaths. The results obtained from the presented implementation on three different trajectories demonstrate that the proposed methodology can reduce the manual error induced using as a reference the CAD-workpiece surface.

关键词： Free-form surface industrial robot optimization algorithm point cloud data

来源：评论

学校读者我要写书评

暂无评论

Statistical Learning for Solid Propellant Performance

Statistical Learning for Solid Propellant Performance

引用

AIAA Propulsion and Energy Forum / IEEE Electric Aircraft Technologies Symposium (EATS)

作者： Hartfield, Roy Carpenter, Mark Cervantes, Noel Auburn Univ Aerosp Engn 211 Davis Hall Auburn AL 36830 USA Auburn Univ Math & Stat Auburn AL 36830 USA

ISBN: (数字)9781624106118

ISBN: (纸本)9781624106118

This paper describes a methodology to rapidly model the performance of solid rocket motors and classify motors according to their geometries using statistical learning approaches. Star grain configurations are considered in this analysis. A variety of statistical learning approaches including neural networks have been applied to the problem of mapping pressure time curves for solid rocket motors and, using convolutional neural networks, backwardly map pressure time curves to the motor geometries which produced the pressure time profiles. This classification application is useful in reverse engineering applications and in identifying a range of possible options for achieving a given design goal. This paper contains a description of the physical model, the statistical learning methods required to robustly replicate the physics model, and the convolutional neural network approach used for the classification, along with results for both functions.

关键词： Solid Propellants Convolutional Neural Network Solid Rocket Motor Numerical Analysis Scatter Plot Computational Fluid Dynamics Monte Carlo Simulation Aerospace Engineering Open Source Software optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Frequency control of PV-connected micro grid system using fuzzy logic controller

Frequency control of PV-connected micro grid system using fu...

引用

International Conference on Advances in Materials Research (ICAMR)

作者： Rajesh, T. Gunapriya, B. Sabarimuthu, M. Karthikkumar, S. Raja, R. Karthik, M. Malla Reddy Engn Coll Dept Elect & Elect Engn Secunderabad India New Horizon Coll Engn Dept Elect & Elect Engn Bangalore Karnataka India Kongu Engn Coll Dept Elect & Elect Engn Perundurai 638060 Erode India Jai Shriram Engn Coll Dept Elect & Elect Engn Tirupur 638660 India Muthayammal Engn Coll Dept Elect & Elect Engn Namakkal Rasipuram 637408 India Sri Ramakrishna Engn Coll Dept Elect & Elect Engn Coimbatore 641022 Tamil Nadu India

Frequency is a variable parameter in a power system, and it denotes the balance among the generation and the requirement. The operator of the system has to maintain the frequency within certain acceptable limits. The tediousness of integrating Distributed Generators (DGs), like solar photovoltaic (PV) system or wind turbines is the intermittency in power system that balances the power and regulates the frequency and voltage. If a number of electric motors are connected along with PV, the frequency of rotor speed will be varied. Hence, this paper intends to propose a Fuzzy Logic Controller (FLC) for controlling the frequency of rotor speed to enhance the power system performance. Hence, the major objective of the proposed model is to provide control over the output signal by reducing the error between the reference signal and control signal. The performance evaluation of the proposed model is done and proved over other controllers with respect to switching time, and the performance metrics, namely settling time, rise time, and percentage overshoot. (c) 2021 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the International Conference on Advances in Materials Research-2019.

关键词： Wind turbines Distributed generators Solar photovoltaic system Frequency optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

An efficient optimizer for optimal overcurrent relay coordination in power distribution system

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年 199卷

作者： Acharya, Debasis Das, Dushmanta Kumar Natl Inst Technol Nagaland Dept Elect & Elect Engn Chumukedima 797103 India

In this paper, a student-learning strategy based efficient optimizer has been developed to solve optimal over current relay coordination problem in the power system. The power system is a massive, interrelated network with inherent nonlinearity. The conventional analytical methods to solve an overcurrent relay coordination issue is difficult for such systems. Therefore, the metaheuristic optimization technique can be a good choice for relay coordination problem in the power network. Class topper optimization (CTO) is a stochastic technique inspired by the student learning behavior to improve his/her performance to be the best in his/her class which is successfully applied for different optimization problems. Like the other metaheuristic algorithm, CTO faces the problem of local optima with premature convergence to deal with complex problems. In this paper, a sigmoid acceleration coefficient based chaotic search class topper optimization (SCCTO) is proposed to develop an efficient optimizer and applied to solve optimal relay coordination problem. The logistic map based chaotic search is used at initialization stage of SCCTO algorithm. In the update stage of the proposed algorithm, a slowly varying sigmoid function is used along with normal varying function. It will keep diversity in local solution to explore the optimum global solution in the search space. To validate the effectiveness of the proposed algorithm to solve an optimization problem, the optimal overcurrent relay coordination in the distribution network is tested. The optimal setting of time dial of the relay (over current) with total operating time minimization is the aim of such optimization problem considering relay coordination time gap as constraints. Three types of power distribution networks are examined optimal relay coordination problems. The simulation result shows the efficiency of the developed optimizer in relay coordination with an improvement of 26 to 35% in total relay operating time than e

关键词： optimization algorithm Time dial setting (TDS) Plug setting (PS) Coordination time interval (CTI)

来源：评论

学校读者我要写书评

暂无评论

Distributed Quadrotor UAV Tracking using a Team of Unmanned Ground Vehicles

Distributed Quadrotor UAV Tracking using a Team of Unmanned ...

引用

AIAA Science and Technology Forum and Exposition (AIAA SciTech Forum)

作者： Omotuyi, Oyindamola Pokhrel, Sameer Sharma, Rajnikant Univ Cincinnati Dept Mech & Mat Engn Cincinnati OH 45221 USA Univ Cincinnati Dept Aerosp Engn & Engn Mech Cincinnati OH USA Univ Cincinnati Aerosp Engn Cincinnati OH USA

ISBN: (数字)9781624106095

ISBN: (纸本)9781624106095

In this paper, we present an algorithm to optimally track a non-cooperative quadrotor using a team of Unmanned Ground Vehicles (UGVs) which are equipped with GPS as well as radar capable of sensing range, azimuth angle and elevation angle measurements. First, a distributed information filter algorithm is developed for each UGV to locally estimate the position and velocity of the quadrotor using its information and information from neighboring UGVs. We then fuse the information from various UGVs using a Consensus Filter such that their estimate of the state of the quadrotor converges. However, the accuracy of the estimation by the consensus filter depends upon the relative position of the sensors. Hence, it is necessary to design a control policy that leads to optimum configuration of UGVs in order to maximize the utility of measurement. A Model Predictive Controller(MPC) is developed to optimally control the UGVs to improve the state estimation. By defining a proper cost function and optimization algorithm in MPC, we are able to control the path of UGVs to increase the accuracy of estimating the position and velocity of a non-cooperative quadrotor.

关键词： Quadcopter Unmanned Ground Vehicle Unmanned Aerial Vehicle Model Predictive Control Track algorithm optimization algorithm Robots Optimal Control Path Planning Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

GRAPH SIGNAL DENOISING USING NESTED-STRUCTURED DEEP algorithm UNROLLING

GRAPH SIGNAL DENOISING USING NESTED-STRUCTURED DEEP ALGORITH...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Nagahama, Masatoshi Yamada, Koki Tanaka, Yuichi Chan, Stanley H. Eldar, Yonina C. Tokyo Univ Agr & Technol Tokyo Japan Purdue Univ W Lafayette IN 47907 USA Weizmann Inst Sci Rehovot Israel

ISBN: (纸本)9781728176055

In this paper, we propose a deep algorithm unrolling (DAU) based on a variant of the alternating direction method of multiplier (ADMM) called Plug-and-Play ADMM(PnP-ADMM) for denoising of signals on graphs. DAU is a trainable deep architecture realized by unrolling iterations of an existing optimization algorithm which contains trainable parameters at each layer. We also propose a nested-structured DAU: Its submodules in the unrolled iterations are also designed by DAU. Several experiments for graph signal denoising are performed on synthetic signals on a community graph and U.S. temperature data to validate the proposed approach. Our proposed method outperforms alternative optimization- and deep learning-based approaches.

关键词： Graph signal processing optimization algorithm deep learning signal denoising deep algorithm unrolling

来源：评论

学校读者我要写书评

暂无评论

A novel minimum generalized cross entropy-based multilevel segmentation technique for the brain MRI/dermoscopic images

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2022年第PT A期151卷 106214-106214页

作者： Jena, Bibekananda Naik, Manoj Kumar Panda, Rutuparna Abraham, Ajith Anil Neerukonda Inst Technol & Sci Dept Elect & Commun Engn Visakhapatnam 531162 Andhra Pradesh India Siksha O Anusandhan Fac Engn & Technol Bhubaneswar 751030 Orissa India Veer Surendra Sai Univ Technol Dept Elect & Telecommun Engn Burla 768018 Orissa India Sci Network Innovat & Res Excellence Machine Intelligence Res Labs Auburn WA 98071 USA

Background: One of the challenging and the primary stages of medical image examination is the identification of the source of any disease, which may be the aberrant damage or change in tissue or organ caused by infections, injury, and a variety of other factors. Any such condition related to skin or brain sometimes advances in cancer and becomes a life-threatening disease. So, an efficient automatic image segmentation approach is required at the initial stage of medical image ***: To make a segmentation process efficient and reliable, it is essential to use an appropriate objective function and an efficient optimization algorithm to produce optimal ***: The above problem is resolved in this paper by introducing a new minimum generalized cross entropy (MGCE) as an objective function, with the inclusion of the degree of divergence. Another key contribution is the development of a new optimizer called opposition African vulture optimization algorithm (OAVOA). The proposed optimizer boosted the exploration, skill by inheriting the opposition-based *** results: The experimental work in this study starts with a performance evaluation of the optimizer over a set of standards (23 numbers) and IEEE CEC14 (8 numbers) Benchmark functions. The comparative analysis of test results shows that the OAVOA outperforms different state-of-the-art optimizers. The suggested OAVOA-MGCE based multilevel thresholding approach is carried out on two different types of medical images - Brain MRI Images (AANLIB dataset), and dermoscopic images (ISIC 2016 dataset) and found superior than other entropybased thresholding methods.

关键词： Biomedical engineering Machine learning Multilevel thresholding Generalized cross -entropy optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Stability analysis of anti-dip bedding rock slopes using a limit equilibrium model combined with bi-directional evolutionary structural optimization (BESO) method

引用

COMPUTERS AND GEOTECHNICS 2021年 134卷

作者： Liu, Tingting Ding, Luyang Meng, Fei Li, Xinping Zheng, Yun Wuhan Univ Technol Key Lab Roadway Bridge & Struct Engn Wuhan 430070 Hubei Peoples R China Chinese Acad Sci Inst Rock & Soil Mech State Key Lab Geomech & Geotech Engn Wuhan 430071 Hubei Peoples R China

Anti-dip bedding rock slope (ABRS) is a very common type of rock slopes in nature and engineering construction. However, the stability assessment of ABRSs is still a hard problem for geotechnical engineers due to the difficulty in finding the critical failure surface. In this work, a new method called LEM-BESO was proposed to tackle this problem based on limit equilibrium theory and bi-directional evolutionary structural optimization method. Two model tests reported in previous studies were employed to verify the correctness of the LEM-BESO method. Moreover, a comparative study of the LEM-BESO method and the genetic algorithm was also conducted. The highly consistent results demonstrate that using the LEM-BESO method can accurately predict the failure surface of the slope. Then, the LEM-BESO method was extended to study the influence of two key parameters (i.e. friction angle of the joints and tensile strength of the rock layers) on the failure mechanism of anti-dip bedding rock slopes. The results show that these two parameters have a significant influence on the stability of the slope. However, the failure surface is insensitive to the tensile strength of the rock layers. The LEM-BESO method provides an effective means for the stability evaluation and engineering design of ABRSs.

关键词： Anti-dip bedding rock slope (ABRS) Toppling failure Failure surface optimization algorithm Bi-directional evolutionary structural optimization (BESO)

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：