检索结果-内蒙古大学图书馆

13th International Conference on Machine Learning and Applications (ICMLA)

作者： Buzdalov, Maxim ITMO Univ 49 Kronverkskiy Prosp St Petersburg 197101 Russia

ISBN: (纸本)9781479974153

There exist optimization problems with the target objective, which is to be optimized, and several extra objectives, which may or may not be helpful in the optimization process. This paper considers the case when it is possible to find an optimum of the target objective by optimizing either the target objective or a single extra objective. An algorithm is presented that uses a single instance of an underlying single-objective optimization algorithm to optimize different objectives at different iterations and restarts the optimization algorithm between optimizing different objectives. This algorithm has the expected running time of at most 4K min(O) T-O until an optimum of the target objective is found, where T-O is the expected running time of the underlying optimization algorithm to find an optimum of the target objective by optimizing the objective O. An impact of not using restarts between iterations is also discussed.

关键词： optimisation exponential restart strategy objective selection runtime analysis single-objective optimization algorithm switch-and-restart algorithm algorithm design and analysis Memory management Optimization Portfolios Runtime Switches Upper bound algorithm selection ea+rl online selection Runtime algorithm design and analysis Store management Restarting Optimization algorithms Upper bound Switches BRIEFCASE Optimum oxygen

来源：评论

学校读者我要写书评

暂无评论

selection and Tuning of a Fast and Simple Phase-Contrast Microscopy Image Segmentation algorithm for Measuring Myoblast Growth Kinetics in an Automated Manner

引用

MICROSCOPY AND MICROANALYSIS 2013年第4期19卷 855-866页

作者： Juneau, Pierre-Marc Garnier, Alain Duchesne, Carl Univ Laval Dept Chem Engn Quebec City PQ G1V 0A6 Canada

Acquiring and processing phase-contrast microscopy images in wide-field long-term live-cell imaging and high-throughput screening applications is still a challenge as the methodology and algorithms used must be fast, simple to use and tune, and as minimally intrusive as possible. In this paper, we developed a simple and fast algorithm to compute the cell-covered surface (degree of confluence) in phase-contrast microscopy images. This segmentation algorithm is based on a range filter of a specified size, aminimum range threshold, and aminimum object size threshold. These parameters were adjusted in order to maximize the F-measure function on a calibration set of 200 hand-segmented images, and its performance was compared with other algorithms proposed in the literature. A set of one million images from 37 myoblast cell cultures under different conditions were processed to obtain their cell-covered surface against time. The data were used to fit exponential and logistic models, and the analysis showed a linear relationship between the kinetic parameters and passage number and highlighted the effect of culture medium quality on cell growth kinetics. This algorithm could be used for real-time monitoring of cell cultures and for high-throughput screening experiments upon adequate tuning.

关键词： phase-contrast microscopy live-cell imaging segmentation cell-covered surface degree of confluence myoblasts growth kinetics passage number algorithm tuning algorithm selection

来源：评论

学校读者我要写书评

暂无评论

Recommendation of Web Service selection algorithm Based on Web Application Review

Recommendation of Web Service Selection Algorithm Based on W...

引用

IEEE-Region-10 Conference (IEEE TENCON)

作者： Takahashi, Ryuichi Nishida, Kazuma Fukazawa, Yoshiaki Ibaraki Univ Coll Engn Ibaraki Japan Waseda Univ Sch Fundamental Sci & Engn Tokyo Japan

ISBN: (纸本)9781538654576

As the number of web services has increased, the number of services with the same functions has steadily risen. Consequently, many QoS (Quality of Service)-based service selection algorithms have been proposed to determine which service should be selected among those with the same functions. The prediction accuracy of the QoS attribute depends on the selection algorithm. In addition, the appropriate selection algorithm depends on the type of domain. For example, a stock notification service, which relies on real-time transactions, should employ a selection algorithm with a highly accurate response time. However, an automated method to recommend the optimal service selection algorithm has yet to be established. In this paper, we propose a method to recommend selection algorithms.

关键词： service oriented computing algorithm selection review analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-objective selection of algorithm Portfolios: Experimental Validation

Multi-objective Selection of Algorithm Portfolios: Experimen...

引用

14th International Conference on Parallel Problem Solving from Nature (PPSN)

作者： Horn, Daniel Schork, Karin Wagner, Tobias Tech Univ Dortmund Computat Stat Vogelpothsweg 87 D-44227 Dortmund Germany Tech Univ Dortmund Inst Machining Technol ISF Baroper Str 303 D-44227 Dortmund Germany

ISBN: (纸本)9783319458236;9783319458229

The selection of algorithms to build portfolios represents a multi-objective problem. From a possibly large pool of algorithm candidates, a portfolio of limited size but good quality over a wide range of problems is desired. Possible applications can be found in the context of machine learning, where the accuracy and runtime of different learning techniques must be weighed. Each algorithm is represented by its Pareto front, which has been approximated in an a priori parameter tuning. Our approach for multi-objective selection of algorithm portfolios (MOSAP) is capable to trade-off the number of algorithm candidates and the respective quality of the portfolio. The quality of the portfolio is defined as the distance to the joint Pareto front of all algorithm candidates. By means of a decision tree, also the selection of the right algorithm is possible based on the characteristics of the problem. In this paper, we propose a validation framework to analyze the performance of our MOSAP approach. This framework is based on a parametrized generator of the algorithm candidate's Pareto front shapes. We discuss how to sample a landscape of multiple Pareto fronts with predefined intersections. The validation is performed by calculating discrete approximations for different landscapes and assessing the effect of the landscape parameters on the MOSAP approach.

关键词： Multi-objective optimization algorithm selection Performance assessment Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A tensor-based selection hyper-heuristic for cross-domain heuristic search

引用

INFORMATION SCIENCES 2015年 299卷 412-432页

作者： Asta, Shahriar Oezcan, Ender Univ Nottingham Sch Comp Sci ASAP Res Grp Nottingham NG8 1BB England

Hyper-heuristics have emerged as automated high level search methodologies that manage a set of low level heuristics for solving computationally hard problems. A generic selection hyper-heuristic combines heuristic selection and move acceptance methods under an iterative single point-based search framework. At each step, the solution in hand is modified after applying a selected heuristic and a decision is made whether the new solution is accepted or not. In this study, we represent the trail of a hyper-heuristic as a third order tensor. Factorization of such a tensor reveals the latent relationships between the low level heuristics and the hyper-heuristic itself. The proposed learning approach partitions the set of low level heuristics into two subsets where heuristics in each subset are associated with a separate move acceptance method. Then a multi-stage hyper-heuristic is formed and while solving a given problem instance, heuristics are allowed to operate only in conjunction with the associated acceptance method at each stage. To the best of our knowledge, this is the first time tensor analysis of the space of heuristics is used as a data science approach to improve the performance of a hyper-heuristic in the prescribed manner. The empirical results across six different problem domains from a benchmark indeed indicate the success of the proposed approach. (C) 2014 Elsevier Inc. All rights reserved.

关键词： Hyper-heuristic Data science Machine learning Move acceptance Tensor analysis algorithm selection

来源：评论

学校读者我要写书评

暂无评论

A Literature Survey and Empirical Study of Meta-Learning for Classifier selection

引用

IEEE ACCESS 2020年 8卷 10262-10281页

作者： Khan, Irfan Zhang, Xianchao Rehman, Mobashar Ali, Rahman Dalian Univ Technol Sch Software Dalian 116620 Peoples R China Univ Tunku Abdul Rahman Fac Informat & Commun Technol Dept Informat Syst Kampar 31900 Malaysia Univ Peshawar QACC Peshawar 25120 Pakistan

Classification is the key and most widely studied paradigm in machine learning community. The selection of appropriate classification algorithm for a particular problem is a challenging task, formally known as algorithm selection problem (ASP) in literature. It is increasingly becoming focus of research in machine learning community. Meta-learning has demonstrated substantial success in solving ASP, especially in the domain of classification. Considerable progress has been made in classification algorithm recommendation and researchers have proposed various methods in literature that tackles ASP in many different ways in meta-learning setup. Yet there is a lack of survey and comparative study that critically analyze, summarize and assess the performance of existing methods. To fill these gaps, in this paper we first present a literature survey of classification algorithm recommendation methods. The survey shed light on the motivational reasons for pursuing classifier selection through meta-learning and comprehensively discusses the different phases of classifier selection based on a generic framework that is formed as an outcome of reviewing prior works. Subsequently, we critically analyzed and summarized the existing studies from the literature in three important dimensions i.e., meta-features, meta-learner and meta-target. In the second part of this paper, we present extensive comparative evaluation of all the prominent methods for classifier selection based on 17 classification algorithms and 84 benchmark datasets. The comparative study quantitatively assesses the performance of classifier selection methods and highlight the limitations and strengths of meta-features, meta-learners and meta-target in classification algorithm recommendation system. Finally, we conclude this paper by identifying current challenges and suggesting future work directions. We expect that this work will provide baseline and a solid overview of state of the art works in this domain to ne

关键词： Meta-learning algorithm selection classification machine learning

来源：评论

学校读者我要写书评

暂无评论

Assisting in search heuristics selection through multidimensional supervised classification: A case study on software testing

引用

INFORMATION SCIENCES 2014年 258卷 122-139页

作者： Sagarna, Ramon Mendiburu, Alexander Inza, Inaki Lozano, Jose A. Univ Basque Country Intelligent Syst Grp San Sebastian 20018 Spain

A fundamental question in the field of approximation algorithms, for a given problem instance, is the selection of the best (or a suitable) algorithm with regard to some performance criteria. A practical strategy for facing this problem is the application of machine learning techniques. However, limited support has been given in the literature to the case of more than one performance criteria, which is the natural scenario for approximation algorithms. We propose multidimensional Bayesian network (mBN) classifiers as a relatively simple, yet well-principled, approach for helping to solve this problem. Precisely, we relax the algorithm selection decision problem into the elucidation of the nondominated subset of algorithms, which contains the best. This formulation can be used in different ways to elucidate the main problem, each of which can be tackled with an mBN classifier. Namely, we deal with two of them: the prediction of the whole nondominated set and whether an algorithm is nondominated or not. We illustrate the feasibility of the approach for real-life scenarios with a case study in the context of Search Based Software Test Data Generation (SBSTDG). A set of five SBSTDG generators is considered and the aim is to assist a hypothetical test engineer in elucidating good generators to fulfil the branch testing of a given programme. (C) 2013 Elsevier Inc. All rights reserved.

关键词： algorithm selection Multidimensional classification Dominance relation Search based software testing

来源：评论

学校读者我要写书评

暂无评论

Automatic selection of clustering algorithms using supervised graph embedding

引用

INFORMATION SCIENCES 2021年 577卷 824-851页

作者： Cohen-Shapira, Noy Rokach, Lior Ben Gurion Univ Negev Beer Sheva Israel

The widespread adoption of machine learning (ML) techniques and the extensive expertise required to apply them have led to increased interest in automated ML solutions that reduce the need for human intervention. One of the main challenges in applying ML to previously unseen problems is algorithm selection - the identification of high-performing algorithm(s) for a given dataset, task, and evaluation measure. This study addresses the algorithm selection challenge for data clustering, a fundamental task in data mining that is aimed at grouping similar objects. We present MARCO-GE, a novel meta-learning approach for the automated recommendation of clustering algorithms. MARCO-GE first transforms datasets into graphs and then utilizes a graph convolutional neural network technique to extract their latent representation. Using the embedding representations obtained, MARCO-GE trains a ranking meta-model capable of accurately recommending top-performing algorithms for a new dataset and clustering evaluation measure. An extensive evaluation on 210 datasets, 17 clustering algorithms, and 10 clustering measures demonstrates the effectiveness of our approach and its superiority in terms of predictive and generalization performance over state-of-the-art clustering meta-learning approaches. (c) 2021 Elsevier Inc. All rights reserved.

关键词： Meta-learning algorithm selection Clustering AutoML algorithm ranking

来源：评论

学校读者我要写书评

暂无评论

Multiparameter method for analysis and selection of motion estimation algorithms for video compression

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2008年第1期38卷 119-146页

作者： Kaminsky, Evgeny Hadar, Ofer Ben Gurion Univ Negev Dept Elect & Comp Engn IL-84105 Beer Sheva Israel Ben Gurion Univ Negev Commun Syst Engn Dept IL-84105 Beer Sheva Israel

This paper proposes a new multiparameter method for analysis and selection of motion estimation algorithms for video compression. We present motion estimation algorithms, results of computer simulations and illustrate the analysis with tables, PSNR and performance plots. Numerous algorithms and tests for analysis of algorithm performance for video compression have recently been suggested, which has resulted in a need for effective evaluation methods. A highly qualified expert is also needed to evaluate the test results. The more input parameters used the more complex and subjective the evaluation will be. Our multiparameter method for algorithm analysis and selection eliminates subjectivity and provides a qualitative and quantitative evaluation of the tested algorithms for any number of algorithms and parameters. We propose two new methods of evaluation: (1) a quality method-a graphic method using the Pareto approach, and (2) a quantity method which obtains an integrated parameter composed of numerous evaluation parameters. In addition, we evaluate various motion estimation algorithms accordingly to two different implementation strategies: (a) using a software video encoder that depends on available processing resources using a computational complexity-rate-distortion (C-R-D) evaluation framework and (b) using a power-limited video encoder implemented on mobile or handheld computing platform by using energy-rate-distortion (E-R-D) behavior.

关键词： fast motion estimation (ME) block matching algorithms (BMA) video analysis algorithm evaluation algorithm selection multiparameter analysis Pareto approach

来源：评论

学校读者我要写书评

暂无评论

Autoencoder-kNN meta-model based data characterization approach for an automated selection of AI algorithms

引用

JOURNAL OF BIG DATA 2023年第1期10卷 1-18页

作者： Garouani, Moncef Ahmad, Adeel Bouneffa, Mourad Hamlich, Mohamed Univ Littoral Cote dOpale LISIC Lab Informat Signal & Image Cote Opale UR 4491 F-62100 Calais E France Univ Hassan 2 CCPS Lab ENSAM Casablanca Morocco HESTIM Study & Res Ctr Engn & Management CERIM Casablanca Morocco

The recent evolution of machine learning (ML) algorithms and the high level of expertise required to use them have fuelled the demand for non-experts solutions. The selection of an appropriate algorithm and the configuration of its hyperparameters is among the most complicated tasks while applying ML to new problems. It necessitates well awareness and knowledge of ML algorithms. The algorithm selection problem (ASP) is defined as the process of identifying the algorithm (s) that can deliver top performance for a particular problem, task, and evaluation measure. In this context, meta-learning is one of the approaches to achieve this objective by using prior learning experiences to assist the learning process on unseen problems and tasks. As a data-driven approach, appropriate data characterization is of vital importance for the meta-learning. Nonetheless, the recent literature witness a variety of data characterization techniques including simple, statistical and information theory based measures. However, their quality still needs to be improved. In this paper, a new Autoencoder-kNN (AeKNN) based meta-model with built-in latent features extraction is proposed. The approach is aimed to extract new characterizations of the data, with lower dimensionality but more significant and meaningful features. AeKNN internally uses a deep autoencoder as a latent features extractor from a set of existing meta-features induced from the dataset. From this new features vectors the computed distances are more significant, thus providing a way to accurately recommending top-performing pipelines for previously unseen datasets. In an application on a large-scale hyperparameters optimization task for 400 real world datasets with varying schemas as a meta-learning task, we show that AeKNN offers considerable improvements of the classical kNN as well as traditional meta-models in terms of performance.

关键词： algorithm selection AutoML Meta-learning Meta-features Data representation kNN Autoencoder

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：