检索结果-内蒙古大学图书馆

Robust interactive image segmentation using structure-aware labeling

EXPERT SYSTEMS WITH APPLICATIONS 2017年 79卷 90-100页

作者： Oh, Changjae Ham, Bumsub Sohn, Kwanghoon Yonsei Univ Sch Elect & Elect Engn Seoul 03722 South Korea

Interactive image segmentation has remained an active research topic in image processing and graphics, since the user intention can be incorporated to enhance the performance. It can be employed to mobile devices which now allow user interaction as an input, enabling various applications. Most interactive segmentation methods assume that the initial labels are correctly and carefully assigned to some parts of regions to segment. Inaccurate labels, such as foreground labels in background regions for example, lead to incorrect segments, even by a small number of inaccurate labels, which is not appropriate for practical usage such as mobile application. In this paper, we present an interactive segmentation method that is robust to inaccurate initial labels (scribbles). To address this problem, we propose a structure-aware labeling method using occurrence and co-occurrence probability (OCP) of color values for each initial, label in a unified framework. Occurrence probability captures a global distribution of all color values within each label, while co-occurrence one encodes a local distribution of color values around the label. We show that nonlocal regularization together with the OCP enables robust image segmentation to, inaccurately assigned labels and alleviates a small-cut problem. We analyze theoretic relations of our approach to other segmentation methods. Intensive experiments with synthetic and manual labels show that our approach outperforms the state of the art. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Interactive image segmentation Co-occurrence probability graph-based optimization

来源：评论

学校读者我要写书评

暂无评论

graph-based Airway Tree Reconstruction From Chest CT Scans: Evaluation of Different Features on Five Cohorts

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2015年第5期34卷 1063-1076页

作者： Bauer, Christian Eberlein, Michael Beichel, Reinhard R. Univ Iowa Dept Elect & Comp Engn Iowa City IA 52242 USA Univ Iowa Carver Coll Med Dept Internal Med Iowa City IA 52242 USA Univ Iowa Iowa Inst Biomed Imaging Iowa City IA 52242 USA

We present a graph-based framework for airway tree reconstruction from computerized tomography (CT) scans and evaluate the performance of different feature categories and their combinations on five lung cohorts. The approach consists of two main processing steps. First, potential airway branch and connection candidates are identified and represented by a graph structure with weighted nodes and edges, respectively. Second, an optimization algorithm is utilized for generating an airway detection result by selecting a subset of airway branches and connections based on graph weights derived from image features. The performance of the algorithm with different feature categories and their combinations was assessed on a set of 50 lung CT scans from five different cohorts, including normal and diseased lungs. Results show trade-offs between feature categories/combinations in terms of correctly (true positive) and incorrectly (false positive) identified airways. Also, the performance of features in dependence of lung cohort was analyzed. Across all cohorts, a good trade-off with high true positive rate (TPR) and low false positive rate (FPR) was achieved by a combination of gray-value, local shape, and structural features. This combination enabled extracting 91.80% of reference airways (TPR) in combination with a low FPR of 1.00%. In addition, this variant was evaluated on the public EXACT' 09 test set, and a comparison with other airway detection approaches is provided. One of the main advantages of the presented method is that it is robust against local disturbances/artifacts or other ambiguities that are frequently occurring in lung CT scans.

关键词： Airway detection graph-based optimization X-ray computed tomography

来源：评论

学校读者我要写书评

暂无评论

Evolutionary algorithm with a regression model for multiobjective minimization of systemic risk in financial systems

引用

SOFT COMPUTING 2024年第5期28卷 3921-3939页

作者： Michalak, Krzysztof Wroclaw Univ Econ & Business Dept Informat Technol Wroclaw Poland

This paper addresses a problem of systemic risk minimization in which the optimization algorithm has to simultaneously minimize the number of companies affected by a wave of bankruptcies simulated on a graph as well as the level of reserves the companies keep to avoid going bankrupt. A MOEA/D-NN algorithm (where NN stands for a neural network) is proposed, which optimizes parameters of a machine learning model (a neural network) used in turn to determine the level of reserves the companies keep, based on several attributes describing each node in the graph. In the experiments, the proposed MOEA/D-NN algorithm was found to outperform comparison methods: evolutionary algorithms optimizing the level of reserves for all companies and a method based on the training of neural networks on a dataset previously collected by an evolutionary algorithm solving "training" instances of the optimization problem. The neural networks optimized by MOEA/D-NN were also tested on problem instances based on REDS graphs generated using varying values of R, E, and S parameters and were found to be applicable to these instances for certain ranges of parameters. The R parameter controlling the possibility of generating long-distance connections was found to have a bigger impact on the performance of the optimized neural networks than the other two parameters.

关键词： graph-based optimization Neural networks Systemic risk mitigation Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Simheuristics for the Multiobjective Nondeterministic Firefighter Problem in a Time-Constrained Setting 19th

Simheuristics for the Multiobjective Nondeterministic Firefi...

引用

19th European Conference on the Applications of Evolutionary Computation (EvoApplications)

作者： Michalak, Krzysztof Knowles, Joshua D. Wroclaw Univ Econ Inst Business Informat Dept Informat Technol Wroclaw Poland Univ Birmingham Sch Comp Sci Birmingham W Midlands England

ISBN: (纸本)9783319311531

The firefighter problem (FFP) is a combinatorial problem requiring the allocation of 'firefighters' to nodes in a graph in order to protect the nodes from fire (or other threat) spreading along the edges. In the original formulation the problem is deterministic: fire spreads from burning nodes to adjacent, unprotected nodes with certainty. In this paper a nondeterministic version of the FFP is introduced where fire spreads to unprotected nodes with a probability P-sp (lower than 1) per time step. To account for the stochastic nature of the problem the simheuristic approach is used in which a metaheuristic algorithm uses simulation to evaluate candidate solutions. Also, it is assumed that the optimization has to be performed in a limited amount of time available for computations in each time step. In this paper online and offline optimization using a multipopulation evolutionary algorithm is performed and the results are compared to various heuristics that determine how to place firefighters. Given the time-constrained nature of the problem we also investigate for how long to simulate the spread of fire when evaluating solutions produced by an evolutionary algorithm. Results generally indicate that the evolutionary algorithm proposed is effective for P-sp >= 0.7, whereas for lower probabilities the heuristics are competitive suggesting that more work on hybrids is warranted.

关键词： graph-based optimization Nondeterministic firefighter problem Simheuristics

来源：评论

学校读者我要写书评

暂无评论

Solving the Parameterless Firefighter Problem using Multiobjective Evolutionary Algorithms 19

Solving the Parameterless Firefighter Problem using Multiobj...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Michalak, Krzysztof Wroclaw Univ Econ Inst Business Informat Dept Informat Technol Wroclaw Poland

ISBN: (纸本)9781450367486

The Firefighter Problem (FFP) is a graph-based optimization problem that is an abstraction of real-life problems such as epidemics control, economic crises prevention, etc. In the FFP spreading of fire is simulated on a graph in discrete time steps. In the original formulation of the problem a fixed number of graph nodes N-f can be defended in each time step. In this paper the problem is reformulated, and three different solution representations are studied. In one of the representations (N+P), the N-f parameter is a decision variable and in the other two (P using permutations and T using integer vectors) it is determined when the solution is decoded. Because higher N-f values mean more resources used for defense it is desirable to minimize this value, but on the other hand we want to minimize the number of graph nodes consumed by fire. Therefore the Parameterless FFP is tackled using two well-known multiobjective evolutionary algorithms: the MOEA/D and the NSGA-II as a multiobjective optimization problem with two and three objectives. The results presented in the paper show that for the Parameterless FFP the best solution representation is N+P.

关键词： graph-based optimization Solution representation Combinatorial optimization MOEA/D NSGA-II

来源：评论

学校读者我要写书评

暂无评论

MULTI-LABEL ENERGY MINIMIZATION FOR OBJECT CLASS SEGMENTATION

MULTI-LABEL ENERGY MINIMIZATION FOR OBJECT CLASS SEGMENTATIO...

引用

20th European Signal Processing Conference (EUSIPCO)

作者： Couprie, Camille NYU Dept Comp Sci Courant Inst New York NY 10003 USA

ISBN: (纸本)9781467310680

The task of associating a semantic class to the objects present in an image is challenging because this problem involves the joint segmentation and recognition of the objects. In this work, we use a recent approach embedding several optimization algorithms into a common framework named Power watershed to perform this task. We show how the fast watershed algorithm can be used to minimize an energy function for which the minimizer corresponds to the desired object class segmentation. Higher order potentials are then added to improve label consistency. We also demonstrate that the random walker algorithm can be successfully applied to semantic class segmentation problems. Comparisons with the graph Cuts algorithm show that the proposed approaches yield better segmentation results, obtained up to twelve times faster on a very challenging indoor scenes dataset.

关键词： Image processing Object class segmentation graph-based optimization graph cuts Random walker Watershed

来源：评论

学校读者我要写书评

暂无评论

Decision Forests with Spatio-Temporal Features for graph-based Tumor Segmentation in 4D Lung CT

Decision Forests with Spatio-Temporal Features for Graph-Bas...

引用

4th International Workshop on Machine Learning in Medical Imaging (MLMI) in Conjunction with the 16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

作者： Mirzaei, Hamidreza Tang, Lisa Werner, Rene Hamarneh, Ghassan Simon Fraser Univ Computat Vis Lab Burnaby BC V5A 1S6 Canada

ISBN: (纸本)9783319022673;9783319022666

We propose an automatic lung tumor segmentation in dynamic CT images that incorporates the novel use of tumor tissue deformations. In contrast to elastography imaging techniques for measuring tumor tissue properties, which require mechanical compression and thereby interrupt normal breathing, we completely avoid the use of any external physical forces. Instead, we calculate the tissue deformations during normal respiration using deformable registration. We investigate machine learning methods in order to discover the spatio-temporal dynamics that would help distinguish tumor from normal tissue deformation patterns and integrate this information into the segmentation process. Our method adapts an ensemble of decision trees combined with a 3D graph-based optimization that takes into account spatio-temporal consistency. The experimental results on patients with large tumors achieved an average F-measure accuracy of 0.79.

关键词： Lung tumor image segmentation registration CT images imbalance data machine learning graph-based optimization

来源：评论

学校读者我要写书评

暂无评论

Estimation of Distribution Algorithms for the Firefighter Problem 1

引用

17th European Conference on Evolutionary Computation in Combinatorial optimization (EvoCOP)

作者： Michalak, Krzysztof Wroclaw Univ Econ Inst Business Informat Dept Informat Technol Wroclaw Poland

ISBN: (数字)9783319554532

ISBN: (纸本)9783319554532;9783319554525

The firefighter problem is a graph-based optimization problem in which the goal is to effectively prevent the spread of a threat in a graph using a limited supply of resources. Recently, metaheuristic approaches to this problem have been proposed, including ant colony optimization and evolutionary algorithms. In this paper Estimation of Distribution Algorithms (EDAs) are used to solve the FFP. A new EDA is proposed in this paper, based on a model that represents the relationship between the state of the graph and positions that become defended during the simulation of the fire spreading. Another method that is tested in this paper, named EH-PBIL, uses an edge histogram matrix model with the learning mechanism used in the Population-based Incremental Learning (PBIL) algorithm with some modifications introduced in order to make it work better with the FFP. Apart from these two EDAs the paper presents results obtained using two versions of the Mallows model, which is a probabilistic model often used for permutation-based problems. For comparison, results obtained on the same test instances using an Ant Colony optimization (ACO) algorithm, an Evolutionary Algorithm (EA) and a Variable Neighbourhood Search (VNS) are presented. The state-position model proposed in this paper works best for graphs with 1000 vertices and more, outperforming the comparison methods. For smaller graphs (with less than 1000 vertices) the VNS works best.

关键词： Estimation of distribution algorithms graph-based optimization Firefighter problem

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Neural Networks for Livestock Disease Prevention

Evolutionary Neural Networks for Livestock Disease Preventio...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Michalak, Krzysztof Giacobini, Mario Wroclaw Univ Econ & Business Dept Informat Technol Wroclaw Poland Univ Torino Dept Vet Sci Grugliasco TO Italy

ISBN: (纸本)9798400701207

In this article, multiobjective optimization of neural models is studied, aimed at making decisions about vaccine distribution in a scenario of a disease spreading among farms, pastures and other locations. The epidemic is simulated using a real-life dataset of animal movements between such premises in Italy in years 2017-2020. Three neural models are studied: multilayer perceptrons (MLP), classical recurrent neural networks (RNN) and Long Short-Term Memory (LSTM) networks with the weights of the networks optimized using the MOEA/D algorithm. In the experiments, MOEA/D with the binary-vector representation optimizing the assignment of vaccinations to the premises was used as a comparison method. In order to assess the generalization capacity of the tested methods, the optimization was performed on data from the years 2017-2019 and the results (optimized neural models, and optimized vaccination assignments, respectively) were used for the year 2020. The two neural models which worked best were the MLP and the LSTM which outperformed both the RNN and MOEA/D optimizing the assignment of vaccinations. The advantage of the MLP and the LSTM is particularly well-visible when the number of vaccinated nodes is low, which may be important in practical applications.

关键词： epidemics control zoonotic diseases multiobjective optimization graph-based optimization

来源：评论

学校读者我要写书评

暂无评论

Simulation-based Crossover for the Firefighter Problem 17

Simulation-Based Crossover for the Firefighter Problem

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Michalak, Krzysztof Wroclaw Univ Econ Inst Business Informat Dept Informat Technol Komandorska 118-120 PL-53345 Wroclaw Poland

ISBN: (纸本)9781450349208

The Firefighter Problem (FFP) is a combinatorial optimization problem in which the goal is to find the best way of protecting nodes in a graph from spreading fire or other threat given limited resources. Because of high computational complexity the FFP is often solved using metaheuristic methods such as evolutionary algorithms (EAs). The problem that arises is that many crossover operators used in EAs were developed with problems such as the TSP or the flowshop problem in mind and are therefore not optimized towards the FFP. In this paper a new crossover operator SimX is proposed that determines how to combine information from parent specimens using a simulation of fire spreading and some problem-specific heuristics. The proposed crossover operator was compared to a set of ten permutation-based crossover operators in experiments performed using a multipopulation algorithm with operator autoadaptation. In the experiments it was observed that the proposed simulation-based crossover operator produced good offspring more often than the other operators.

关键词： graph-based optimization Multi-objective evolutionary optimization Firefighter problem Operator autoadaptation

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：