2012 Brazilian Symposium on Neural Networks最新文献

筛选
英文 中文
Particle Swarm Optimization Applied to the Dynamic Allocation Problem 粒子群算法在动态分配问题中的应用
2012 Brazilian Symposium on Neural Networks Pub Date : 2012-10-20 DOI: 10.1109/SBRN.2012.35
J. L. Pierobom, M. Delgado, Celso A. A. Kaestner
{"title":"Particle Swarm Optimization Applied to the Dynamic Allocation Problem","authors":"J. L. Pierobom, M. Delgado, Celso A. A. Kaestner","doi":"10.1109/SBRN.2012.35","DOIUrl":"https://doi.org/10.1109/SBRN.2012.35","url":null,"abstract":"Particle Swarm Optimization (PSO) is based on the analysis of emergent behavior of bird flocks. Though it was originally designed for continuous optimization, PSO has provided good results in some recent works when applied to static and discrete optimization problems. In this paper, the particle encoding scheme is based on permutations and the PSO algorithm is adapted to solve a real-world application (cabs-customers allocation) of the dynamic task assignment problem. In the proposed approach, as the optimal solution may change during the optimization process, different strategies to detect and react to changes are tested. The results show that combinations of traditional techniques achieve good solutions in tested instances defined with different sizes and scales of changes.","PeriodicalId":303166,"journal":{"name":"2012 Brazilian Symposium on Neural Networks","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126810997","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}
引用次数: 6
I-MOPSO: A Suitable PSO Algorithm for Many-Objective Optimization I-MOPSO:一种适合多目标优化的粒子群优化算法
2012 Brazilian Symposium on Neural Networks Pub Date : 2012-10-20 DOI: 10.1109/SBRN.2012.20
André Britto, A. Pozo
{"title":"I-MOPSO: A Suitable PSO Algorithm for Many-Objective Optimization","authors":"André Britto, A. Pozo","doi":"10.1109/SBRN.2012.20","DOIUrl":"https://doi.org/10.1109/SBRN.2012.20","url":null,"abstract":"Multi-Objective Optimization Problems are problems with more than one objective function. In the literature, there are several Multi-Objective Evolutionary Algorithms (MOE As) that deals with MOPs, including Multi-Objective Particle Swarm Optimization (MOPSO). However, these algorithms scale poorly when the number of objective grows. Many-Objective Optimization researches methods to decrease the negative effect of applying MOE As into problems with more than three objective functions. Here, it is proposed a new PSO algorithm, called I-MOPSO, which explores specific aspects of MOPSO to deal with Many-Objective Problems. This algorithm takes advantage of an archiving method to introduce more convergence and from the strategy of the leader's selection to introduce diversity on the search. I-MOPSO is evaluated through an empirical analysis aiming to observe how it works in Many-Objective scenarios in terms of convergence and diversity to the Pareto front. The proposed algorithm is compared to other MOE As from the literature through the use of quality indicators and statistical tests.","PeriodicalId":303166,"journal":{"name":"2012 Brazilian Symposium on Neural Networks","volume":"2001 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127396741","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}
引用次数: 24
Self-Organizing Mapping of Robotic Environments Based on Neural Networks 基于神经网络的机器人环境自组织映射
2012 Brazilian Symposium on Neural Networks Pub Date : 2012-10-20 DOI: 10.1109/SBRN.2012.17
M. Figueiredo, S. Botelho, Paulo L. J. Drews-Jr, Celina Häffele Da Rocha
{"title":"Self-Organizing Mapping of Robotic Environments Based on Neural Networks","authors":"M. Figueiredo, S. Botelho, Paulo L. J. Drews-Jr, Celina Häffele Da Rocha","doi":"10.1109/SBRN.2012.17","DOIUrl":"https://doi.org/10.1109/SBRN.2012.17","url":null,"abstract":"An important aspect in robotics is mapping environments, it means know free space configuration of the robot and establish landmarks. It enables the robot to calculate its position in the environment. In this context, this paper proposes a method for mapping generic environments (structured or not) based on topological maps (SOM and Growing Cell Structures), which uses self-organizing networks. The results obtained on different dynamic and ambiguous environment demonstrate both generalization and compactness.","PeriodicalId":303166,"journal":{"name":"2012 Brazilian Symposium on Neural Networks","volume":"164 2-3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115878326","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}
引用次数: 5
Using Interacting Forces to Perform Semi-supervised Learning 利用相互作用的力量进行半监督学习
2012 Brazilian Symposium on Neural Networks Pub Date : 2012-10-20 DOI: 10.1109/SBRN.2012.24
T. Cupertino, Liang Zhao
{"title":"Using Interacting Forces to Perform Semi-supervised Learning","authors":"T. Cupertino, Liang Zhao","doi":"10.1109/SBRN.2012.24","DOIUrl":"https://doi.org/10.1109/SBRN.2012.24","url":null,"abstract":"Semi-Supervised Learning (SSL) is a learning paradigm in which the classification task is performed by taking into account just a few labeled instances. The unlabeled instances also participate in the process, but by providing additional information about the dataset. In this paper, a new semi-supervised technique based on interacting forces is proposed. Both labeled and unlabeled instances play different roles in the proposed mechanism: the labeled instances perform attraction forces over the unlabeled instances to accomplish label propagation. Inside a defined neighborhood, a label in able to propagates to an unlabeled instance. The technique mainly takes into account two important SSL assumptions: smoothness and cluster. Results obtained from simulations performed on artificial and real datasets exhibit the effectiveness of the proposed method.","PeriodicalId":303166,"journal":{"name":"2012 Brazilian Symposium on Neural Networks","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132426779","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}
引用次数: 5
An Object-Based Visual Selection Model with Bottom-Up and Top-Down Modulations 具有自底向上和自顶向下调制的基于对象的视觉选择模型
2012 Brazilian Symposium on Neural Networks Pub Date : 2012-10-20 DOI: 10.1109/SBRN.2012.48
A. X. Benicasa, M. G. Quiles, Liang Zhao, R. Romero
{"title":"An Object-Based Visual Selection Model with Bottom-Up and Top-Down Modulations","authors":"A. X. Benicasa, M. G. Quiles, Liang Zhao, R. Romero","doi":"10.1109/SBRN.2012.48","DOIUrl":"https://doi.org/10.1109/SBRN.2012.48","url":null,"abstract":"Research in qualitative models of visual attention has mainly focused on the bottom-up guidance of early visual features. Here we propose a new model which combine both bottom-up and top-down modulation into the visual selection model. The proposed model is composed of five main components: a Visual Feature Extraction module, a LEGION network for image segmentation to deal with objects, a Multi-Layer Perceptron (MLP) network for object recognition, a Kohonen's Self-Organizing Maps (SOM) combined with a network of integrate and fire neurons which creates our attribute-saliency map, and finally, and object selection module which highlights the most salient object in the scene. Experiments with synthetic and real images is conducted and the results demonstrate the effectiveness of the proposed approach.","PeriodicalId":303166,"journal":{"name":"2012 Brazilian Symposium on Neural Networks","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123055434","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}
引用次数: 6
A Study on Class Noise Detection and Elimination 类噪声检测与消除研究
2012 Brazilian Symposium on Neural Networks Pub Date : 2012-10-20 DOI: 10.1109/SBRN.2012.49
L. P. F. Garcia, Ana Carolina Lorena, A. Carvalho
{"title":"A Study on Class Noise Detection and Elimination","authors":"L. P. F. Garcia, Ana Carolina Lorena, A. Carvalho","doi":"10.1109/SBRN.2012.49","DOIUrl":"https://doi.org/10.1109/SBRN.2012.49","url":null,"abstract":"Real data may present a significant amount of noise, generated by inaccuracies in data collection, transmission and storage. The presence of noisy data in a training dataset used for the induction of a Machine Learning model may increase the training time and the complexity of the induced model, resulting in the deterioration of its predictive performance for new data. Noise may be found in the input and target attributes. In this study, we are concerned with noise in the class label of the target attribute. For such, we propose and experimentally investigate some simple class noise detection and elimination strategies for classification problems, introducing controlled noise levels in five UCI datasets originally free of inconsistencies. The results obtained in the experiments performed show the potential of the proposed approaches.","PeriodicalId":303166,"journal":{"name":"2012 Brazilian Symposium on Neural Networks","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133624277","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}
引用次数: 27
Self-Controlling Dominance Particle Swarm Optimization 自控制优势粒子群优化
2012 Brazilian Symposium on Neural Networks Pub Date : 2012-10-20 DOI: 10.1109/SBRN.2012.28
Olacir Rodrigues Castro Junior, André Britto, A. Pozo
{"title":"Self-Controlling Dominance Particle Swarm Optimization","authors":"Olacir Rodrigues Castro Junior, André Britto, A. Pozo","doi":"10.1109/SBRN.2012.28","DOIUrl":"https://doi.org/10.1109/SBRN.2012.28","url":null,"abstract":"A well-known problem faced by Pareto Based Multi Objective Optimization Algorithms, including Multi-Objective Particle Swarm Optimization (MOPSO) algorithms is the deterioration of its search ability when the number of objectives scales up. In the literature some techniques were proposed to overcome these limitations, between them the modification of the domination relation. This work aims to propose a new MOPSO algorithm called SCDAS-SMPSO which uses the Self-Controlling Dominance Area of Solutions (S-CDAS) technique to modify the domination relation and increase the selection pressure needed in many-objective optimization. The new MOPSO is compared through experiments with other two MOPSOs in terms of convergence and diversity in many-objective scenarios. The results were analyzed through different quality indicators and statistical tests.","PeriodicalId":303166,"journal":{"name":"2012 Brazilian Symposium on Neural Networks","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124311356","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}
引用次数: 1
Firing Activity Induced by Nonidentical Signal Phases in Two Coupled Excitable Neurons 两个耦合可兴奋神经元不同信号相诱导的放电活动
2012 Brazilian Symposium on Neural Networks Pub Date : 2012-10-20 DOI: 10.1109/SBRN.2012.18
X. Liang, Liang Zhao
{"title":"Firing Activity Induced by Nonidentical Signal Phases in Two Coupled Excitable Neurons","authors":"X. Liang, Liang Zhao","doi":"10.1109/SBRN.2012.18","DOIUrl":"https://doi.org/10.1109/SBRN.2012.18","url":null,"abstract":"In this paper, we study the firing activity of two coupled excitable neurons with sub threshold periodic signalsfootnote{A sub threshold signal means that the signal is too weak to make the neuron firing.}. Particularly, we find that the two coupled excitable neurons can generate spikes to the sub threshold signals with no identical signal phases, indicating that the nonidentical signal phases play an active role for enhancing neuronal response to weak signals. Moreover, we find that regular spikes can be generated by neurons if the level of nonidentical signal phases is at an intermediate value and thus resulting in a resonance-like phenomenon. Furthermore, under the influence of nonidentical signal phases, the regularity of the firing activity also exhibits a resonance-like dependency on the value of coupling coefficient. Finally, we give a explanation to analyze the mechanism of these two types of resonance behavior. We believe that the phenomena found in this paper will be useful for designing neural information processing systems.","PeriodicalId":303166,"journal":{"name":"2012 Brazilian Symposium on Neural Networks","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130126723","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}
引用次数: 2
Effect of the PSO Topologies on the Performance of the PSO-ELM PSO拓扑结构对PSO- elm性能的影响
2012 Brazilian Symposium on Neural Networks Pub Date : 2012-10-20 DOI: 10.1109/SBRN.2012.26
Elliackin M. N. Figueiredo, Teresa B Ludermir
{"title":"Effect of the PSO Topologies on the Performance of the PSO-ELM","authors":"Elliackin M. N. Figueiredo, Teresa B Ludermir","doi":"10.1109/SBRN.2012.26","DOIUrl":"https://doi.org/10.1109/SBRN.2012.26","url":null,"abstract":"In recent years, the Extreme Learning Machine (ELM) has been hybridized with the Particle Swarm Optimization (PSO). This hybridization is named PSO-ELM. In most of these hybridizations, the PSO uses the global topology. However, other topologies were designed to improve the performance of the PSO. The performance of PSO depends on its topology, and there is not a best topology for all problems. Thus, in this paper, we investigate the effect of the PSO topology on performance of the PSO-ELM. In our study, we investigate five topologies: Global, Local, Von Neumann, Wheel and Four Clusters. The results showed that the Global topology can be more promising than all other topologies.","PeriodicalId":303166,"journal":{"name":"2012 Brazilian Symposium on Neural Networks","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116683534","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}
引用次数: 21
SCAS-IS: Knowledge Extraction and Reuse in Multiprocessor Task Scheduling Based on Cellular Automata 基于元胞自动机的多处理机任务调度中的知识提取与重用
2012 Brazilian Symposium on Neural Networks Pub Date : 2012-10-20 DOI: 10.1109/SBRN.2012.46
M. Carneiro, G. Oliveira
{"title":"SCAS-IS: Knowledge Extraction and Reuse in Multiprocessor Task Scheduling Based on Cellular Automata","authors":"M. Carneiro, G. Oliveira","doi":"10.1109/SBRN.2012.46","DOIUrl":"https://doi.org/10.1109/SBRN.2012.46","url":null,"abstract":"Static Task Scheduling Problem (STSP) in multiprocessors is a NP-Complete problem. Cellular Automata (CA) have been recently proposed to solve STSP. The main feature of CA-based models to STSP is the extraction of knowledge while scheduling an application and its subsequent reuse in other instances. Previous works showed this approach is promising. However some desirable features have not been successfully exploited yet, such as: (i) the usage of an arbitrary number of processors, (ii) the massive parallelism inherent to CA and (iii) the reuse of evolved rules with competitive results. This paper presents a new model called SCAS-IS (Synchronous Cellular Automata Scheduler with Initialization Strategies). Its major innovation is the employment of fixed initialization strategies to start up CA dynamics. Parallel program graphs found in literature and others randomly generated were used to test the new model. Results show SCAS-IS overcame related models both in make span obtained as computational performance. It is also competitive with meta-heuristics.","PeriodicalId":303166,"journal":{"name":"2012 Brazilian Symposium on Neural Networks","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121401312","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}
引用次数: 4
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书