Genetic and Nelder–Mead algorithms hybridized for a more accurate global optimization of continuous multiminima functions

Chelouah, Rachid; Siarry, Patrick

doi:10.1016/s0377-2217(02)00401-0

Cited by 267 publications

(161 citation statements)

References 13 publications

Supporting

Mentioning

155

Contrasting

Unclassified

Order By: Relevance

“…Under the absence of intuition about the initial point, the authors in [10] suggest to use a combination of a basic Genetic Algorithm (GA), to find some initial points, and later improve them using NM. In our case we design a classical GA where each genome is an instance of the parameters to be optimized, and each generation contains 100 genomes.…”

Section: Unige-hands: Hand-detection Datasetmentioning

confidence: 99%

A Dynamic Approach and a New Dataset for Hand-detection in First Person Vision

Betancourt

Morerio

Barakova

et al. 2015

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

Abstract. Hand detection and segmentation methods stand as two of the most most prominent objectives in First Person Vision. Their popularity is mainly explained by the importance of a reliable detection and location of the hands to develop human-machine interfaces for emergent wearable cameras. Current developments have been focused on hand segmentation problems, implicitly assuming that hands are always in the field of view of the user. Existing methods are commonly presented with new datasets. However, given their implicit assumption, none of them ensure a proper composition of frames with and without hands, as the hand-detection problem requires. This paper presents a new dataset for hand-detection, carefully designed to guarantee a good balance between positive and negative frames, as well as challenging conditions such as illumination changes, hand occlusions and realistic locations. Additionally, this paper extends a state-of-the-art method using a dynamic filter to improve its detection rate. The improved performance is proposed as a baseline to be used with the dataset.

show abstract

Section: Unige-hands: Hand-detection Datasetmentioning

confidence: 99%

A Dynamic Approach and a New Dataset for Hand-detection in First Person Vision

Betancourt

Morerio

Barakova

et al. 2015

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

show abstract

“…Thereafter, the search domain is reduced, an initial simplex is built inside this area and a local search based on Nelder and Mead Simplex is started. This continuous hybrid algorithm, called CHA, perform very well, reaching good results [8]. The exploitation moves are started using the simplex method around the best individual found in the exploration cycle.…”

Section: Related Workmentioning

confidence: 99%

Hybrid Evolutionary Algorithms and Clustering Search

Oliveira¹,

Lorena²

2007

Studies in Computational Intelligence

View full text Add to dashboard Cite

Summary. A challenge in hybrid evolutionary algorithms is to employ efficient strategies to cover all the search space, applying local search only in actually promising search areas. The inspiration in nature has been pursued to design flexible, coherent and efficient computational models. In this chapter, the Clustering Search (*CS) is proposed as a generic way of combining search metaheuristics with clustering to detect promising search areas before applying local search procedures. The clustering process aims to gather similar information about the search space into groups, maintaining a representative solution associated to this information. Two applications are examined for combinatorial and continuous optimization problems, presenting how to develop hybrid evolutionary algorithms based on *CS.

show abstract

“…In the second experiment, ECS is compared against other approach found in literature that works with the same idea of detecting promising search areas: the Continuous Hybrid Algorithm (CHA), briefly described in the introduction. The CHA results were taken from [5], where the authors worked with several n dimensional test functions. The most challenging of them are used for comparison in this work.…”

Section: Computational Experimentsmentioning

confidence: 99%

“…In the ECS experiments, the SR reflects the percentage of trials that have reached at least a gap of 0.001. The SR obtained in CHA experiments is not a classical one, according the authors, because it considers the actual landscape of the function at hand [5].…”

Section: Computational Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Promising Areas by Evolutionary Clustering Search

Oliveira

Lorena

2004

Advances in Artificial Intelligence – SBIA 2004

View full text Add to dashboard Cite

Abstract. A challenge in hybrid evolutionary algorithms is to define efficient strategies to cover all search space, applying local search only in actually promising search areas. This paper proposes a way of detecting promising search areas based on clustering. In this approach, an iterative clustering works simultaneously to an evolutionary algorithm accounting the activity (selections or updatings) in search areas and identifying which of them deserves a special interest. The search strategy becomes more aggressive in such detected areas by applying local search. A first application to unconstrained numerical optimization is developed, showing the competitiveness of the method.

show abstract

Genetic and Nelder–Mead algorithms hybridized for a more accurate global optimization of continuous multiminima functions

Cited by 267 publications

References 13 publications

A Dynamic Approach and a New Dataset for Hand-detection in First Person Vision

A Dynamic Approach and a New Dataset for Hand-detection in First Person Vision

Hybrid Evolutionary Algorithms and Clustering Search

Detecting Promising Areas by Evolutionary Clustering Search

Contact Info

Product

Resources

About