检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： Weichen Sun Fei Su School of Information and Communication Engineering Beijing University of Posts and Telecommunications

ISBN: (纸本)9781479983407

A novel objective function of deep neuron networks with companion losses of both convolutional layers and non-linear activation functions is proposed, aiming to obtain more discriminative features. Conventional deep neuron networks were generally trained by the end-to-end supervised learning framework, whose performance is restricted by the training problems, such as the gradient vanishing problem, leading to less discriminative features, especially in lower layers. Instead, we build a novel objective function with two kinds of companion losses. The advantages of this framework are as follows: Firstly, it facilities the optimization by solving the gradient vanishing problem. Secondly, both kinds of companion supervised information contribute to obtain more discriminative features. Finally, a good initialization for fine-tuning could be obtained with the aid of the companion supervised training. Experimental results demonstrate the proposed model yielding better performances on the image classification benchmark dataset.

关键词： Deep neuron networks Regularization Companion objective function Image classification Image classification Companions objective function Activating function Neural network Neurons Frameworks

来源：评论

学校读者我要写书评

暂无评论

Optimized Association Rules using objective function for Mammography Image Classification

Optimized Association Rules using Objective Function for Mam...

引用

International Conference on Communication and Signal Processing

作者： Poonam Sonar Dipti Jadhav Udhav Bhosle Department of Electronics and Telecommunication Engineering Rajiv Gandhi Institute of Technology Mumbai University of Mumbai Department of Computer Engineering Ramrao Adik Institute of Technology Navi Mumbai University of Mumbai Department of Electronics and Telecommunication Engineering Rajiv Gandhi Institute of Technology Mumbai. University of Mumbai

ISBN: (纸本)9781467385497

Image mining is more than just an extension of data mining to image domain. In recent years, the concept of utilizing association rules for classification has emerged. This approach proved often is more efficient and accurate than traditional techniques. This paper presents the concept of association rule mining and applied to the problem of mammogram image classifications. Association rules are obtained using Apriori algorithm. Authors propose graph theory based objective function to optimize association rules such that graph generated by the optimized rules is simple graph with simple walk. The proposed algorithm is tested on mammogram images for classification of images into benign and malignant classes. Through experimentation, it is estimated that, with and without optimization of association rules accuracy is 85% for malignant and 95% for benign class. The average accuracy is 90%. The propose technique reduces the time and space complexity associated with calculating optimized rule while maintaining the classification accuracy.

关键词： Association rule Confidence Support Image mining objective function

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Optimize the objective function Based on VC Dimension and Structural Risk Minimization

A Novel Approach to Optimize the Objective Function Based on...

引用

第三十届中国控制会议

作者： QIU Xintao,FU Dongmei,YANG Tao School of Automation,University of Science and Technology Beijing,Beijing 100083,P.R.China

So far,lots of algorithms and learning methods are taking the empirical risk for the optimization *** this paper,we propose a new way to optimize the objective function based on VC dimension and structural risk *** optimized function F is firstly defined by us,and some effective design forms of it will also be *** we fulfill a useful criterion—the balance minimum optimization *** principle considers not only the empirical risk,but also considers the VC dimension of learning *** the two factors can avoid the underfitting problem and overfitting *** results show that the method we proposed is effective to improve the property of algorithm efficiency,convergence and generalization of the learning ***,the proposed principle for optimization is a new criterion,which is not a practical method for a particular problem of ***,this method is suitable to be applied in many practical situations, which may bring a good generalization performance and efficiency in some learning problems.

关键词： VC Dimension objective function Structural Risk Minimization Balance Minimum Optimization Principle

来源：评论

学校读者我要写书评

暂无评论

Iterative learning control in feedback systems based on an objective function

引用

Asian Journal of Control 2000年第2期2卷 101-110页

作者： Choi, Chong-Ho Jang, Tae-Jeong School of Electrical Eng. ASRI ERC-ACI Seoul National University Kwanak-ku Seoul 151-742 San 56-1 Shinlim-dong South Korea Division of Electrical and Computer Eng. Kangwon National University Chunuchon 200-701 192-1 Hyoja2-dong Ngowon-do South Korea

An objective function is proposed and an iterative learning control algorithm is derived based on this. The objective function is a quadratic form consisting of the output error and the input. By adjusting the weights in the objective function, the control objective of good command following at smaller input energy can be realized. The weight on the input energy in the objective function is shown to be directly related to the forgetting factor for robust iterative learning control. The convergence of the control algorithm has been proven and its characteristics are shown in the simulation examples.

关键词： Iterative learning control Nonlinear systems objective function

来源：评论

学校读者我要写书评

暂无评论

Estimation of unsaturated soil parameters: Effect of data errors and choice of objective function

引用

ISH Journal of Hydraulic Engineering 2003年第1期9卷 46-60页

作者： Hari Prasad, K.S. Trivedi, M.K. Agrawal, K.K. Department of Civil Engg. IIT Roorkee India Madhav Institute of Technology and Science Gwalior India Infosys Technologies Bangalore India

Some of the important factors which need consideration for reliable estimation of unsaturated soil parameters through inverse procedures are (i) identifiability, (ii) errors in the data and (iii) proper choice of objective function. The present study addresses the effect of data errors and proper choice of objective function on parameter estimates obtained using inverse procedures. Even if a parametric model is identifiable, the accuracy of parameter estimates depends on the objective function used in the parameter estimation in the presence of noise in the data. A detailed statistical analysis is carried out to study the effect of three objective functions on the estimated parameters, when the data contain errors. The results indicate that these objective functions induce a bias in the estimated parameters and as such selecting a suitable objective function should also be given due importance in the parameter estimation. © 2003 Taylor & Francis Group, LLC.

关键词： Identifiability Inverse modelling Noisy data objective function Parameter estimation Richards equation Unsaturated zone

来源：评论

学校读者我要写书评

暂无评论

Grid Computing and Surrogate objective function Assisted Multi-objective Shape Optimal Design of PMLSM

Grid Computing and Surrogate Objective Function Assisted Mul...

引用

Biennial Institute of Electrical and Electronics Engineers Conference on Electomagnetic Field Computation

作者： Minho Song Heesung Yoon Hong-soon Choi Chang Seop Koh School of Electrical Engineering Chungbuk National University School of EECS Kyungbuk National University

ISBN: (纸本)9781424470594

A permanent magnet linear synchronous motor (PMLSM) is shape optimized in Pareto sense to get a minimum detent force and maximum thrust force per mass. In the optimization, a surrogate objective function is constructed with the help of grid computing technique by using Multi-quadric radial basis function to reduce the computing time related with finite element analysis.

关键词： thrust shape optimal design Finite element method linear synchronous motors objective function maximum thrust Grid computing detent

来源：评论

学校读者我要写书评

暂无评论

Pareto Front Analysis of the objective function in Model Predictive Control Based Power Management System of a Plug-in Hybrid Electric Vehicle

Pareto Front Analysis of the Objective Function in Model Pre...

引用

IEEE Transportation Electrification Conference and Expo

作者： Nicolas Sockeel Jian Shi Masood Shahverdi Michael Mazzola Mississippi State University Center for Advanced Vehicular System California State University Los Angeles Energy Production and Infrastructure Center

Model predictive control strategy (MPC) has been identified as an efficient path for reducing fuel consumption, greenhouse gasses (GHG) emission, or degradation of power-train components for electrified vehicles. MPC is an optimization-based control strategy that aims at finding the optimal control actions of a system by predicting its future behaviors. As the main contribution, this paper provides a Pareto-front analysis of the objective function taking into account the equivalent fuel consumption and the battery aging when the PHEV is in the charge sustaining (CS) mode. The results show that the MPC controller can decrease the battery capacity fade by 45% for only increasing the equivalent vehicle fuel consumption of 0.1% compared to an engine on-off thermostat control strategy.

关键词： Pareto Front Analysis objective function Model Predictive

来源：评论

学校读者我要写书评

暂无评论

A time-scale based objective function for EEG signal parameters optimization

A time-scale based objective function for EEG signal paramet...

引用

International Conference on Electrical Engineering

作者： Asma Bouchema Abdellah Kacha Antoine Nonclercq Francis Grenez Laboratory of Physics of Radiation and Applications Department of Automatic Jijel University Laboratories of Image Signal processing and Acoustics Universite Libre de Bruxelles

ISBN: (纸本)9781467366748

This paper concerns the optimization of EEG signal parameters for epileptic seizure detection. In a previous study, a macroscopic model has been used to model various waveforms of EEG signal and to optimize its parameters by means of a genetic algorithm (GA). In the GA-based method for EEG parameters estimation, an optimization procedure is used. The aim of the optimization procedure is to minimize an objective function. The minimized error function compares the desired waveform (real EEG signal) and the waveform of the signal provided by the model both in the time domain and frequency domain. In the present study, we propose a time-scale based representation for the objective function as an alternative to the time and frequency based objective function used in the early study. The proposed objective function takes into account the non-stationary nature of the EEG signal. The performance of the proposed wavelet-based objective function is compared to that of the spectral objective function.

关键词： Epileptic seizure detection objective function EEG parameters optimization Time-scale analysis

来源：评论

学校读者我要写书评

暂无评论

CAPACITY OF PHYSICAL AND NON-PHYSICAL CHARACTERISTICS IN PREDICTING objective function OF WOMEN WITH PATELLOFEMORAL PAIN

引用

Brazilian Journal of Physical Therapy 2024年 28卷 101005-101005页

作者： da Silva, Théo Muniz de Souza Borges Perez, Vitoria Ozores Waiteman, Marina Cabral Lopes, Helder dos Santos Briani, Ronaldo Valdir Azevedo, Fábio Mícolis de Sao Paulo State University (UNESP) School of Science and Technology Physical Therapy Department Presidente Prudente São Paulo Brazil

BackgroundPatellofemoral pain (PFP) is a chronic musculoskeletal disorder characterized by an insidious and diffuse pain around and/or behind the patella. People with PFP have decreased levels of physical activity and muscle strength of the knee extensors, as well as higher levels of pain, kinesiophobia, and body mass index (BMI). In addition, people with PFP experience decreased performance during objective function tests, such as the single leg hop test (SLHT). Although, theoretically, all the alterations above mentioned may be contributing to the decreased SLHT performance of individuals with PFP, no study has investigated this to date. objectivesTo determine the capacity of physical activity level, BMI, pain level, kinesiophobia and muscle strength of knee extensors in predicting SLHT performance of people with PFP. MethodsSixty-two women with PFP were included in this study. Demographic data, level of physical activity (Baecke questionnaire), kinesiophobia (Tampa Scale) and average pain in the previous month (Visual Analogue Scale – 0 to 100 mm) were obtained. The objective function was evaluated with the SLHT, in which participants were required to hop forward as far as possible and the distance in centimeters was obtained. The concentric strength of the knee extensors was obtained with an isokinetic dynamometer at 60°/s. A multiple linear regression was performed to determine the capacity of muscle strength, kinesiophobia, BMI, pain and the level of physical activity in predicting the objective function of women with PFP. ResultsNone of the independent variables (i.e., concentric knee extensor strength, Kinesiophobia, Pain, Physical activity level, BMI) were able to significantly predict the SLHT performance of women with PFP (F( 5.56)=0.328; p=0.884; R 2=0.028). ConclusionDespite the theoretical plausibility, the variables investigated in this study were not able to significantly predict the SLHT performance of women with PFP. It is possible that other varia

关键词： Patellofemoral pain objective function Performance

来源：评论

学校读者我要写书评

暂无评论

Optimization of batch cooling crystallization systems considering crystal growth,nucleation and *** I:Simulation

引用

Particuology 2025年第1期96卷 84-96页

作者： Qilei Xu Bin Lian Yan Long Baoming Shan Xuezhong Wang Fangkun Zhang College of Automation and Electronic Engineering Qingdao University of Science&TechnologyQingdao266061China School of Chemical and Process Engineering University of LeedsLeedsLS29JTUnited Kingdom Centre for Pharmaceutical and Crystallization Process Systems Engineering School of Chemical EngineeringBeijing Institute of Petrochemical TechnologyBeijing102617China

Optimal control of batch crystallization systems is still a focus and hot topic in the field of industrial crystallization, which seriously affects the consistency of batch product quality. In this paper, a new method with a new objective function and improved optimization algorithm was proposed for optimization of crystal size distribution (CSD) in case of fine crystals occurrence. The new objective function was developed with better margin metric and weighting technique to minimize fine crystal mass, meanwhile, a newly constructed sinusoidal weight function was introduced to improve the particle swarm optimization (PSO) algorithm. A precise control of CSD with suppressed numerical discrepancy caused by fine crystals removal was developed by combining seed recipe and temperature-swing. In addition, the effects of temperature curve segments on CSD during process optimization were systematically investigated to achieve optimal results. Two typical batch cooling crystallization systems were used to verify the effectiveness of the proposed method in controlling product CSD while minimizing fine crystal mass. Results demonstrated that the desired product CSD can be achieved with minor errors while the fine crystals could be shrunk to be negligible, i.e., the fine crystal mass and number can be reduced by over 90%. This work has an important guiding significance for the removal of fine crystals in industrial crystallization processes, especially when only operational optimization rather than equipment updating is considered.

关键词： Crystal size distribution Optimization objective function Fine crystals removal Batch crystallization

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：