9,090 Hits in 7.8 sec

Rolling System Design Using Evolutionary Sequential Process Optimization

A. Tiwari, V. Oduguwa, R. Roy
2008 IEEE Transactions on Evolutionary Computation  
The design of a rolling system is a multistage process optimization problem involving sequential relationship between consecutive stages.  ...  This paper describes the optimization of a real-life rolling system design using a genetic algorithm (GA)-based approach capable of dealing with the sequential nature of this problem.  ...  Since the design of a rolling system is characterized by its multistaged sequential nature, this paper proposes an optimization approach for handling this challenge using GAs. IV.  ... 
doi:10.1109/tevc.2007.896688 fatcat:g5cpn3efdnet7khja2qoyl7bmi

LSH banding for large-scale retrieval with memory and recall constraints

Michele Covell, Shumeet Baluja
2009 2009 IEEE International Conference on Acoustics, Speech and Signal Processing  
Locality Sensitive Hashing (LSH) is widely used for efficient retrieval of candidate matches in very large audio, video, and image systems.  ...  However, extremely large reference databases necessitate a guaranteed limit on the memory used by the table lookup itself, no matter how the entries crowd different parts of the signature space, a guarantee  ...  We propose to use LSH, with off-line optimization of the hash subspaces, in order to minimize the worst-case expected crowding.  ... 
doi:10.1109/icassp.2009.4959971 dblp:conf/icassp/CovellB09 fatcat:sl4ein5oufhc7icu7dyw52wbyu

A non-dominated sorting hybrid algorithm for multi-objective optimization of engineering problems

Hossein Ghiasi, Damiano Pasini, Larry Lessard
2011 Engineering optimization (Print)  
To demonstrate this fact, NSHA is applied to the design of a carbon fibre bicycle stem simultaneously optimized for strength, weight and processing time.  ...  Among numerous multi-objective optimization algorithms, the Elitist non-dominated sorting genetic algorithm (NSGA-II) is one of the most popular methods due to its simplicity, effectiveness and minimum  ...  To increase the efficiency of the local search, only a randomly selected subset of three to five design variables are used for the local optimization and other variables are kept constant at their current  ... 
doi:10.1080/03052151003739598 fatcat:qv6k6rqozredpjh2iz4jxjwqxi

An Artificial Fish Swarm Filter-Based Method for Constrained Global Optimization [chapter]

Ana Maria A. C. Rocha, M. Fernanda P. Costa, Edite M. G. P. Fernandes
2012 Lecture Notes in Computer Science  
An artificial fish swarm algorithm based on a filter methodology for trial solutions acceptance is analyzed for general constrained global optimization problems.  ...  The preliminary numerical experiments with a wellknown benchmark set of engineering design problems show the effectiveness of the proposed method.  ...  Backtracking Line Search The step size α ∈ (0, 1] is determined by a backtracking line search technique.  ... 
doi:10.1007/978-3-642-31137-6_5 fatcat:w46n3llsevf3pb64bx23d27ur4

Genetic Algorithm with adaptive elitist-population strategies for multimodal function optimization

Yong Liang, Kwong-Sak Leung
2011 Applied Soft Computing  
This technique allows unimodal function optimization methods to be extended to efficiently explore multiple optima of multimodal problems.  ...  AEGA has been shown to be very efficient and effective in finding multiple solutions of complicated benchmark and real-world multimodal optimization problems.  ...  The authors would like to thank the anonymous reviewers for their constructive comments and suggestions which have significantly improved this paper.  ... 
doi:10.1016/j.asoc.2010.06.017 fatcat:fhxvgnupejdp5gtwfadjbdohvm

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning [article]

Liang Liu, Hao Lu, Hongwei Zou, Haipeng Xiong, Zhiguo Cao, Chunhua Shen
2020 arXiv   pre-print
We formulate counting as a sequential decision problem and present a novel crowd counting model solvable by deep reinforcement learning.  ...  By virtually placing a crowd image on one side of a scale, LibraNet (agent) sequentially learns to place appropriate weights on the other side to match the crowd count.  ...  A possible explanation is that, because of the huge searching space, the agent cannot search for actions smoothly.  ... 
arXiv:2007.08260v1 fatcat:w2f2co6kfbh65mta7vd2sfe5uq

Supplier Selection and Production Planning by Using Guided Genetic Algorithm and Dynamic Nondominated Sorting Genetic Algorithm II Approaches

H. S. Wang, C. H. Tu, K. H. Chen
2015 Mathematical Problems in Engineering  
SC management activities, such as delivery time, quality, and defect rate, are characterized by uncertainty.  ...  to achieve maximum efficiency and the competitiveness of firms to improve.  ...  Experimental Design. This study used the Guided-D-NSGA-II algorithm to determine the optimal efficiency of production.  ... 
doi:10.1155/2015/260205 fatcat:cwmql6lfjvaujbpnl6i4op5avu

Visual Search Without Selective Attention: A Cognitive Architecture Account

David E. Kieras
2018 Topics in Cognitive Science  
Including a simple mechanism for crowding in the model also allows it to account for significant effects on error rate (ER).  ...  In addition, there are little-explored effects of visual crowding, which is typically confounded with set size in visual search experiments.  ...  The author thanks David Meyer, Gregory Wakefield, and Anthony Hornof for useful discussions and comments.  ... 
doi:10.1111/tops.12406 fatcat:qnhuvdkuqbbtnctrsehn7fbu4m

Dynamically Pruned A* for re-planning in navigation meshes

Wouter van Toll, Roland Geraerts
2015 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
In this paper, we present Dynamically Pruned A* (DPA*), an extension of A* for re-planning optimal paths in dynamic navigation meshes.  ...  Our algorithm is memory-friendly and robust against structural changes in the graph, which makes it suitable for crowds in dynamic navigation meshes.  ...  algorithms are efficient in other applications, but they are not designed for large crowds or structural changes in the search space.  ... 
doi:10.1109/iros.2015.7353649 dblp:conf/iros/TollG15 fatcat:6x7fcpf2p5fmdpkgakwhpcfvuq

Niching in Evolutionary Multi-agent Systems

Daniel Krzywicki
2013 Computer Science  
Finally, preliminary experimental results show the efficiency and the simultaneous discovery of multiple optima by this modified EMAS.  ...  Niching is a group of techniques used in evolutionary algorithms, useful in several types of problems, including multimodal or nonstationary optimization.  ...  The research presented here was partially supported by the grant "Biologically inspired mechanisms in planning and management of dynamic environments" funded by the Polish National Science Centre, No.  ... 
doi:10.7494/csci.2013.14.1.77 fatcat:x423xpxervdwdc4ums63kme2bi

Knowledge Incorporation in Evolutionary Computation [Book Review]

Qingfu Zhang
2006 IEEE Computational Intelligence Magazine  
I believe that the work along the line of fitness approximation should be very helpful for bridging between evolutionary computation and traditional optimization methods.  ...  The approach combines learning-oriented and search-oriented methods for preference articulation by which the design trade-off strategy can be adapted and refined when more preference information is learned  ... 
doi:10.1109/mci.2006.329699 fatcat:op7hlvz2mzgozmdrhwmxbuzrj4

Multiple Instance Reinforcement Learning for Efficient Weakly-Supervised Detection in Images [article]

Stefan Mathe, Cristian Sminchisescu
2014 arXiv   pre-print
Our sequential method is weakly supervised and general (it does not require eye movements), finds optimal search strategies for any given detection confidence function and achieves performance similar  ...  Second, inspired from the saccade-and-fixate operating principle of the human visual system, we use reinforcement learning techniques to train efficient search models for detection.  ...  Additionally, we develop novel sequential models, in order to achieve optimal, efficient search strategies for detection based on reinforcement learning.  ... 
arXiv:1412.0100v1 fatcat:wnrqr4bi3zannh4ntpqpsqoa5a

Usability and Accessibility of eBay by Screen Reader [chapter]

Maria Claudia Buzzi, Marina Buzzi, Barbara Leporini, Fahim Akhter
2009 Lecture Notes in Computer Science  
Usually these sites have complex layouts crowded with active elements, and thus are difficult to navigate via screen reader.  ...  Interactive environments should be properly designed and delivered to everyone, including the blind, who usually use screen readers to interact with their computers.  ...  Information should be provided through both visual and auditory channels, the design should be optimized for reading via screen reader, the interface must be easy to use via keyboard, and no additional  ... 
doi:10.1007/978-3-642-10308-7_37 fatcat:qpdzoijoxve3fdm5hkmwlqxkem

Evolving the stimulus to fit the brain: A genetic algorithm reveals the brain's feature priorities in visual search

E. Van der Burg, J. Cass, J. Theeuwes, D. Alais
2015 Journal of Vision  
How does the brain find objects in cluttered visual environments? For decades researchers have employed the classic visual search paradigm to answer this question using factorial designs.  ...  Displays evolved quickly over generations towards a stable, efficiently searched array. Color properties evolved first, followed by orientation.  ...  Acknowledgments This work was supported by Australian Research Council Grant DE130101663 (EVdB) and DP120101474 (DA and JC).  ... 
doi:10.1167/15.2.8 pmid:25761347 fatcat:wktuqt6gj5gxbdxbtznb62bw2e

Your own face is no more precious than others': Evidence from the simultaneous–sequential paradigm

Suk Won Han, Woo Hyun Jung
2015 Psychonomic Bulletin & Review  
A similar pattern of results was found when participants searched for someone else's face, although there was a decline in the overall performance.  ...  Importantly, either all of the search stimuli were presented simultaneously or two different subsets of the stimuli were presented sequentially.  ...  This processing efficiency for self-face search was explained by the robust representation of familiar faces.  ... 
doi:10.3758/s13423-015-0880-x pmid:26082284 fatcat:ktnlmltsl5grbaajwow3ru7qna
« Previous Showing results 1 — 15 out of 9,090 results