A particular strength of many evolution strategies is their invariance against strictly monotonic and therefore rank-preserving transformations of the objective function. Their view onto a continuous fitness landscape is therefore completely determined by the shapes of the level sets. Most modern algorithms can cope well with diverse shapes as long as these are sufficiently smooth. In contrast, the sharp angles found in level sets of ridge functions can cause premature convergence to a non-optimal point. We propose a simple and generic family of transformation of the fitness function to avoid this effect. This allows general purpose evolution strategies to solve even extremely sharp ridge problems.
{"title":"Handling sharp ridges with local supremum transformations","authors":"T. Glasmachers","doi":"10.1145/2576768.2598215","DOIUrl":"https://doi.org/10.1145/2576768.2598215","url":null,"abstract":"A particular strength of many evolution strategies is their invariance against strictly monotonic and therefore rank-preserving transformations of the objective function. Their view onto a continuous fitness landscape is therefore completely determined by the shapes of the level sets. Most modern algorithms can cope well with diverse shapes as long as these are sufficiently smooth. In contrast, the sharp angles found in level sets of ridge functions can cause premature convergence to a non-optimal point. We propose a simple and generic family of transformation of the fitness function to avoid this effect. This allows general purpose evolution strategies to solve even extremely sharp ridge problems.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131047406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recent work on novelty and behavioral diversity in evolutionary computation has highlighted the potential disadvantage of driving search purely through objective means. This paper suggests that leveraging human insight during search can complement such novelty-driven approaches. In particular, a new approach called novelty-assisted interactive evolutionary computation (NA-IEC) combines human intuition with novelty search to facilitate the serendipitous discovery of agent behaviors in a deceptive maze. In this approach, the human user directs evolution by selecting what is interesting from the on-screen population of behaviors. However, unlike in typical IEC, the user can now request that the next generation be filled with novel descendants. The experimental results demonstrate that combining human insight with novelty search not only finds solutions significantly faster and at lower genomic complexities than fully-automated processes guided purely by fitness or novelty, but it also finds solutions faster than the traditional IEC approach. Such results add to the evidence that combining human users and automated processes creates a synergistic effect in the search for solutions.
{"title":"A novel human-computer collaboration: combining novelty search with interactive evolution","authors":"Brian G. Woolley, Kenneth O. Stanley","doi":"10.1145/2576768.2598353","DOIUrl":"https://doi.org/10.1145/2576768.2598353","url":null,"abstract":"Recent work on novelty and behavioral diversity in evolutionary computation has highlighted the potential disadvantage of driving search purely through objective means. This paper suggests that leveraging human insight during search can complement such novelty-driven approaches. In particular, a new approach called novelty-assisted interactive evolutionary computation (NA-IEC) combines human intuition with novelty search to facilitate the serendipitous discovery of agent behaviors in a deceptive maze. In this approach, the human user directs evolution by selecting what is interesting from the on-screen population of behaviors. However, unlike in typical IEC, the user can now request that the next generation be filled with novel descendants. The experimental results demonstrate that combining human insight with novelty search not only finds solutions significantly faster and at lower genomic complexities than fully-automated processes guided purely by fitness or novelty, but it also finds solutions faster than the traditional IEC approach. Such results add to the evidence that combining human users and automated processes creates a synergistic effect in the search for solutions.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128358733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recently, an easy-to-use fitness-level technique was introduced to prove upper bounds on the expected runtime of randomised search heuristics with non-elitist populations and unary variation operators. Following this work, we present a new and much more detailed analysis of the population dynamics, leading to a significantly improved fitness-level technique. In addition to improving the technique, the proof has been simplified. From the new fitness-level technique, the upper bound on the runtime in terms of generations can be improved from linear to logarithmic in the population size. Increasing the population size therefore has a smaller impact on the runtime than previously thought. To illustrate this improvement, we show that the current bounds on the runtime of EAs with non-elitist populations on many example functions can be significantly reduced. Furthermore, the new fitness-level technique makes the relationship between the selective pressure and the runtime of the algorithm explicit. Surprisingly, a very weak selective pressure is sufficient to optimise many functions in expected polynomial time. This observation has important consequences of which some are explored in a companion paper.
{"title":"Refined upper bounds on the expected runtime of non-elitist populations from fitness-levels","authors":"D. Dang, P. Lehre","doi":"10.1145/2576768.2598374","DOIUrl":"https://doi.org/10.1145/2576768.2598374","url":null,"abstract":"Recently, an easy-to-use fitness-level technique was introduced to prove upper bounds on the expected runtime of randomised search heuristics with non-elitist populations and unary variation operators. Following this work, we present a new and much more detailed analysis of the population dynamics, leading to a significantly improved fitness-level technique. In addition to improving the technique, the proof has been simplified. From the new fitness-level technique, the upper bound on the runtime in terms of generations can be improved from linear to logarithmic in the population size. Increasing the population size therefore has a smaller impact on the runtime than previously thought. To illustrate this improvement, we show that the current bounds on the runtime of EAs with non-elitist populations on many example functions can be significantly reduced. Furthermore, the new fitness-level technique makes the relationship between the selective pressure and the runtime of the algorithm explicit. Surprisingly, a very weak selective pressure is sufficient to optimise many functions in expected polynomial time. This observation has important consequences of which some are explored in a companion paper.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127224193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Inherent networks of potential energy surfaces proposed in physical chemistry inspired a compact network characterization of combinatorial fitness landscapes. In these so-called Local Optima Networks (LON), the nodes correspond to the local optima and the edges quantify a measure of adjacency - transition probability between them. Methods so far used an exhaustive search for extracting LON, limiting their applicability to small problem instances only. To increase scalability, in this paper a new data-driven methodology is proposed that approximates the LON from actual runs of search methods. The method enables the extraction and study of LON corresponding to the various types of instances from the Quadratic Assignment Problem Library (QAPLIB), whose search spaces are characterized in terms of local minima connectivity. Our analysis provides a novel view of the unified testbed of QAP combinatorial landscapes used in the literature, revealing qualitative inherent properties that can be used to classify instances and estimate search difficulty.
{"title":"Data-driven local optima network characterization of QAPLIB instances","authors":"David Iclanzan, F. Daolio, M. Tomassini","doi":"10.1145/2576768.2598275","DOIUrl":"https://doi.org/10.1145/2576768.2598275","url":null,"abstract":"Inherent networks of potential energy surfaces proposed in physical chemistry inspired a compact network characterization of combinatorial fitness landscapes. In these so-called Local Optima Networks (LON), the nodes correspond to the local optima and the edges quantify a measure of adjacency - transition probability between them. Methods so far used an exhaustive search for extracting LON, limiting their applicability to small problem instances only. To increase scalability, in this paper a new data-driven methodology is proposed that approximates the LON from actual runs of search methods. The method enables the extraction and study of LON corresponding to the various types of instances from the Quadratic Assignment Problem Library (QAPLIB), whose search spaces are characterized in terms of local minima connectivity. Our analysis provides a novel view of the unified testbed of QAP combinatorial landscapes used in the literature, revealing qualitative inherent properties that can be used to classify instances and estimate search difficulty.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126455123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Many-objective (four or more objectives) optimization problems pose a great challenge to the classical Pareto-dominance based multi-objective evolutionary algorithms (MOEAs), such as NSGA-II and SPEA2. This is mainly due to the fact that the selection pressure based on Pareto-dominance degrades severely with the number of objectives increasing. Very recently, a reference-point based NSGA-II, referred as NSGA-III, is suggested to deal with many-objective problems, where the maintenance of diversity among population members is aided by supplying and adaptively updating a number of well-spread reference points. However, NSGA-III still relies on Pareto-dominance to push the population towards Pareto front (PF), leaving room for the improvement of its convergence ability. In this paper, an improved NSGA-III procedure, called θ-NSGA-III, is proposed, aiming to better tradeoff the convergence and diversity in many-objective optimization. In θ-NSGA-III, the non-dominated sorting scheme based on the proposed θ-dominance is employed to rank solutions in the environmental selection phase, which ensures both convergence and diversity. Computational experiments have shown that θ-NSGA-III is significantly better than the original NSGA-III and MOEA/D on most instances no matter in convergence and overall performance.
{"title":"An improved NSGA-III procedure for evolutionary many-objective optimization","authors":"Yuan Yuan, Hua Xu, Bo D. Wang","doi":"10.1145/2576768.2598342","DOIUrl":"https://doi.org/10.1145/2576768.2598342","url":null,"abstract":"Many-objective (four or more objectives) optimization problems pose a great challenge to the classical Pareto-dominance based multi-objective evolutionary algorithms (MOEAs), such as NSGA-II and SPEA2. This is mainly due to the fact that the selection pressure based on Pareto-dominance degrades severely with the number of objectives increasing. Very recently, a reference-point based NSGA-II, referred as NSGA-III, is suggested to deal with many-objective problems, where the maintenance of diversity among population members is aided by supplying and adaptively updating a number of well-spread reference points. However, NSGA-III still relies on Pareto-dominance to push the population towards Pareto front (PF), leaving room for the improvement of its convergence ability. In this paper, an improved NSGA-III procedure, called θ-NSGA-III, is proposed, aiming to better tradeoff the convergence and diversity in many-objective optimization. In θ-NSGA-III, the non-dominated sorting scheme based on the proposed θ-dominance is employed to rank solutions in the environmental selection phase, which ensures both convergence and diversity. Computational experiments have shown that θ-NSGA-III is significantly better than the original NSGA-III and MOEA/D on most instances no matter in convergence and overall performance.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125251700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The (1+1) EA is a simple evolutionary algorithm that is known to be efficient on linear functions and on some combinatorial optimization problems. In this paper, we rigorously study its behavior on two easy combinatorial problems: finding the 2-coloring of a class of bipartite graphs, and constructing satisfying assignments for a class of satisfiable 2-CNF Boolean formulas. We prove that it is inefficient on both problems in the sense that the number of iterations the algorithm needs to minimize the cost functions is superpolynomial with high probability. Our motivation is to better understand the influence of problem instance structure on the runtime character of a simple evolutionary algorithm. We are interested in what kind of structural features give rise to so-called metastable states at which, with probability 1 - o(1), the (1+1) EA becomes trapped and subsequently has difficulty leaving. Finally, we show how to modify the (1+1) EA slightly in order to obtain a polynomial-time performance guarantee on both problems.
{"title":"Superpolynomial lower bounds for the (1+1) EA on some easy combinatorial problems","authors":"Andrew M. Sutton","doi":"10.1145/2576768.2598278","DOIUrl":"https://doi.org/10.1145/2576768.2598278","url":null,"abstract":"The (1+1) EA is a simple evolutionary algorithm that is known to be efficient on linear functions and on some combinatorial optimization problems. In this paper, we rigorously study its behavior on two easy combinatorial problems: finding the 2-coloring of a class of bipartite graphs, and constructing satisfying assignments for a class of satisfiable 2-CNF Boolean formulas. We prove that it is inefficient on both problems in the sense that the number of iterations the algorithm needs to minimize the cost functions is superpolynomial with high probability. Our motivation is to better understand the influence of problem instance structure on the runtime character of a simple evolutionary algorithm. We are interested in what kind of structural features give rise to so-called metastable states at which, with probability 1 - o(1), the (1+1) EA becomes trapped and subsequently has difficulty leaving. Finally, we show how to modify the (1+1) EA slightly in order to obtain a polynomial-time performance guarantee on both problems.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114648430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Martin Zaefferer, Beate Breiderhoff, B. Naujoks, Martina Friese, Jörg Stork, A. Fischbach, Oliver Flasch, T. Bartz-Beielstein
Cyclone separators are filtration devices frequently used in industry, e.g., to filter particles from flue gas. Optimizing the cyclone geometry is a demanding task. Accurate simulations of cyclone separators are based on time consuming computational fluid dynamics simulations. Thus, the need for exploiting cheap information from analytical, approximative models is evident. Here, we employ two multi-objective optimization algorithms on such cheap, approximative models to analyze their optimization performance on this problem. Under various limitations, we tune both algorithms with Sequential Parameter Optimization (SPO) to achieve best possible results in shortest time. The resulting optimal settings are validated with different seeds, as well as with a different approximative model for collection efficiency. Their optimal performance is compared against a model based approach, where multi-objective SPO is directly employed to optimize the Cyclone model, rather than tuning the optimization algorithms. It is shown that SPO finds improved parameter settings of the concerned algorithms and performs excellently when directly used as an optimizer.
{"title":"Tuning multi-objective optimization algorithms for cyclone dust separators","authors":"Martin Zaefferer, Beate Breiderhoff, B. Naujoks, Martina Friese, Jörg Stork, A. Fischbach, Oliver Flasch, T. Bartz-Beielstein","doi":"10.1145/2576768.2598260","DOIUrl":"https://doi.org/10.1145/2576768.2598260","url":null,"abstract":"Cyclone separators are filtration devices frequently used in industry, e.g., to filter particles from flue gas. Optimizing the cyclone geometry is a demanding task. Accurate simulations of cyclone separators are based on time consuming computational fluid dynamics simulations. Thus, the need for exploiting cheap information from analytical, approximative models is evident. Here, we employ two multi-objective optimization algorithms on such cheap, approximative models to analyze their optimization performance on this problem. Under various limitations, we tune both algorithms with Sequential Parameter Optimization (SPO) to achieve best possible results in shortest time. The resulting optimal settings are validated with different seeds, as well as with a different approximative model for collection efficiency. Their optimal performance is compared against a model based approach, where multi-objective SPO is directly employed to optimize the Cyclone model, rather than tuning the optimization algorithms. It is shown that SPO finds improved parameter settings of the concerned algorithms and performs excellently when directly used as an optimizer.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117252428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chuan-Bin Zhang, Yue-jiao Gong, Jingjing Li, Ying Lin
This paper proposes a path planner for autonomous underwater vehicles (AUVs) in 3-D underwater space. We simulate an underwater space with rugged seabed and suspending obstacles, which is close to real world. In the proposed representation scheme, the problem space is decomposed into parallel subspaces and each subspace is described by a grid method. The paths of AUVs are simplified as a set of successive points in the problem space. By jointing these waypoints, the entire path of the AUV is obtained. A cost function with penalty method takes into account the length, energy consumption, safety and curvature constraints of AUVs. It is applied to evaluate the quality of paths. Differential evolution (DE) algorithm is used as a black-box optimization tool to provide optimal solutions for the path planning. In addition, we adaptively adjust the parameters of DE according to population distribution and the blockage of parallel subspaces so as to improve its performance. Experiments are conducted on 6 different scenarios. The results validate that the proposed algorithm is effective for improving solution quality and avoiding premature convergence.
{"title":"Automatic path planning for autonomous underwater vehicles based on an adaptive differential evolution","authors":"Chuan-Bin Zhang, Yue-jiao Gong, Jingjing Li, Ying Lin","doi":"10.1145/2576768.2598267","DOIUrl":"https://doi.org/10.1145/2576768.2598267","url":null,"abstract":"This paper proposes a path planner for autonomous underwater vehicles (AUVs) in 3-D underwater space. We simulate an underwater space with rugged seabed and suspending obstacles, which is close to real world. In the proposed representation scheme, the problem space is decomposed into parallel subspaces and each subspace is described by a grid method. The paths of AUVs are simplified as a set of successive points in the problem space. By jointing these waypoints, the entire path of the AUV is obtained. A cost function with penalty method takes into account the length, energy consumption, safety and curvature constraints of AUVs. It is applied to evaluate the quality of paths. Differential evolution (DE) algorithm is used as a black-box optimization tool to provide optimal solutions for the path planning. In addition, we adaptively adjust the parameters of DE according to population distribution and the blockage of parallel subspaces so as to improve its performance. Experiments are conducted on 6 different scenarios. The results validate that the proposed algorithm is effective for improving solution quality and avoiding premature convergence.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123467823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Community detection is a key problem in social network analysis. We propose a two-phase algorithm for detecting community structure in social networks. First phase employs a local-search method to group together nodes that have a high chance of falling in a single community. The second phase is bi-partitioning strategy that optimizes network modularity and deploys a variant of quantum-inspired genetic algorithm. The proposed algorithm does not require any knowledge of the number of communities beforehand and works well for both directed and undirected networks. Experiments on synthetic and real-life networks show that the method is able to successfully reveal community structure with high modularity.
{"title":"Quantum inspired genetic algorithm for community structure detection in social networks","authors":"Shikha Gupta, S. Taneja, Naveen Kumar","doi":"10.1145/2576768.2598277","DOIUrl":"https://doi.org/10.1145/2576768.2598277","url":null,"abstract":"Community detection is a key problem in social network analysis. We propose a two-phase algorithm for detecting community structure in social networks. First phase employs a local-search method to group together nodes that have a high chance of falling in a single community. The second phase is bi-partitioning strategy that optimizes network modularity and deploys a variant of quantum-inspired genetic algorithm. The proposed algorithm does not require any knowledge of the number of communities beforehand and works well for both directed and undirected networks. Experiments on synthetic and real-life networks show that the method is able to successfully reveal community structure with high modularity.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122816476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Genetic Improvement (GI) is shown to optimise, in some cases by more than 35percent, a critical component of healthcare industry software across a diverse range of six nVidia graphics processing units (GPUs). GP and other search based software engineering techniques can automatically optimise the current rate limiting CUDA parallel function in the NiftyReg open source C++ project used to align or register high resolution nuclear magnetic resonance NMRI and other diagnostic NIfTI images. Future Neurosurgery techniques will require hardware acceleration, such as GPGPU, to enable real time comparison of three dimensional in theatre images with earlier patient images and reference data. With millimetre resolution brain scan measurements comprising more than ten million voxels the modified kernel can process in excess of 3 billion active voxels per second.
{"title":"Improving 3D medical image registration CUDA software with genetic programming","authors":"W. Langdon, M. Modat, J. Petke, M. Harman","doi":"10.1145/2576768.2598244","DOIUrl":"https://doi.org/10.1145/2576768.2598244","url":null,"abstract":"Genetic Improvement (GI) is shown to optimise, in some cases by more than 35percent, a critical component of healthcare industry software across a diverse range of six nVidia graphics processing units (GPUs). GP and other search based software engineering techniques can automatically optimise the current rate limiting CUDA parallel function in the NiftyReg open source C++ project used to align or register high resolution nuclear magnetic resonance NMRI and other diagnostic NIfTI images. Future Neurosurgery techniques will require hardware acceleration, such as GPGPU, to enable real time comparison of three dimensional in theatre images with earlier patient images and reference data. With millimetre resolution brain scan measurements comprising more than ten million voxels the modified kernel can process in excess of 3 billion active voxels per second.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123718052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：