10th Symposium on Neural Network Applications in Electrical Engineering最新文献_第5页

A class of neural adaptive FIR filters for complex-valued load prediction 一类用于复杂负荷预测的神经自适应FIR滤波器

10th Symposium on Neural Network Applications in Electrical Engineering Pub Date : 2010-11-29 DOI: 10.1109/NEUREL.2010.5644047

I. Krcmar, P. Maric, M. Bozic

引用次数: 2

Image objects detection based on boosting neural network 基于增强神经网络的图像目标检测

10th Symposium on Neural Network Applications in Electrical Engineering Pub Date : 2010-11-29 DOI: 10.1109/NEUREL.2010.5644063

Ning Liang, H. Hegt, V. Mladenov

引用次数: 1

Multi-threading protein surface functional description 多线程蛋白表面功能描述

10th Symposium on Neural Network Applications in Electrical Engineering Pub Date : 2010-11-29 DOI: 10.1109/NEUREL.2010.5644109

Paul Dan Cristea, R. Tuduce, O. Arsene, D. Nicolau, F. Fulga

引用次数: 5

Cluster based weighted SVM for the recognition of Farsi handwritten digits 基于聚类的加权支持向量机波斯语手写体数字识别

10th Symposium on Neural Network Applications in Electrical Engineering Pub Date : 2010-11-29 DOI: 10.1109/NEUREL.2010.5644059

Mehdi Salehpour, A. Behrad

引用次数: 13

Analysis, design, and selected applications of multiple winners-take-all networks 多赢家通吃网络的分析、设计和选择应用

10th Symposium on Neural Network Applications in Electrical Engineering Pub Date : 2010-11-29 DOI: 10.1109/NEUREL.2010.5644053

Jun Wang

引用次数: 0

Using neural clustering for business improvement companies 将神经聚类应用于企业业务改进

10th Symposium on Neural Network Applications in Electrical Engineering Pub Date : 2010-11-29 DOI: 10.1109/NEUREL.2010.5644087

U. Marovac, A. Crnišanin, Mirslav D. Lutovac

引用次数: 0

Classification of room impulse responses with self-organizing maps 基于自组织地图的房间脉冲响应分类

10th Symposium on Neural Network Applications in Electrical Engineering Pub Date : 2010-11-29 DOI: 10.1109/NEUREL.2010.5644055

D. Ristić, M. Pavlović, I. Reljin

引用次数: 0

Advances in cognitive robotics, achievements and challenge 认知机器人的进展、成就和挑战

10th Symposium on Neural Network Applications in Electrical Engineering Pub Date : 2010-11-29 DOI: 10.1109/NEUREL.2010.5644095

Dusko Katie

{"title":"Advances in cognitive robotics, achievements and challenge","authors":"Dusko Katie","doi":"10.1109/NEUREL.2010.5644095","DOIUrl":"https://doi.org/10.1109/NEUREL.2010.5644095","url":null,"abstract":"The contemporary robotics technology is broadening its applications from factory to more general-purpose applications in domestic and public use, e.g., partner to the elderly, rehabilitations, search and rescue, etc. If robotics technology is to be successful in such complex, unstructured, dynamic environments with high level of uncertainties, it will need to meet new levels of robustness, physical dexterity and cognitive capability. This presentation discusses an emerging field called cognitive robotics. The one solution for building cognitive robots in order to cope with imprecise, incomplete, and inconsistent information that arises in complex technical systems, is computational intelligence that uses biologically inspired soft-computing techniques, like artificial neural networks, evolutionary approaches, and swarm intelligence. Research topics, features and challenges of cognitive robotics will be introduced. Key challenges in constructing these robots include the systematic treatment of uncertainties, the modeling of the environmental state, the coordination of teams of cooperating robots in dynamic environments, the interaction with humans, development, and learning. It is important to notice that in order to realize cognitive robots many overlapping disciplines are needed, e.g. robotics, artificial intelligence, cognitive science, neuroscience, biology, psychology, and cybernetics. Some important research topics from this area will be specially analyzed: Advanced perception (vision, tactile sensing, haptic sensing, multi-sensor fusion), Advanced locomotion and manipulation, SLAM, Learning including imitation learning, reinforcement learning, supervised learning, Human-robot interaction, Reasoning and Making Decisions, Intelligent planning and navigation, Swarm intelligence, etc. A case study of cognitive methods applied for humanoid and service mobile robots will be introduced.","PeriodicalId":227890,"journal":{"name":"10th Symposium on Neural Network Applications in Electrical Engineering","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116220060","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: 3

From nature to methods and back to nature 从自然到方法，再回到自然

10th Symposium on Neural Network Applications in Electrical Engineering Pub Date : 2010-11-29 DOI: 10.1109/NEUREL.2010.5644069

Petar Durić

{"title":"From nature to methods and back to nature","authors":"Petar Durić","doi":"10.1109/NEUREL.2010.5644069","DOIUrl":"https://doi.org/10.1109/NEUREL.2010.5644069","url":null,"abstract":"A fundamental challenge in today's arena of complex systems is the design and development of accurate and robust signal processing methods. These methods should be capable to adapt quickly to unexpected changes in the data and operate under minimal model assumptions. Systems in Nature also do signal processing and often do it optimally. Therefore, it makes much sense to understand what Nature does and try to mimic it and do even better. In return, the results of better signal processing methods may lead to new advancements in science and technology and in understanding Nature. In this presentation methods for signal processing that borrow concepts and principles found in Nature are addressed including ant optimization, swarm intelligence and genetic algorithms. However, the emphasis of the presentation is on Monte Carlo-based methods, and in particular, methods related to particle filtering, cost-reference particle filtering, and population Monte Carlo. In the past decade and a half, Monte Carlo-based methods have gained considerable popularity in dealing with nonlinear and/or non-Gaussian systems. The three groups of methods share the feature that they explore spaces of unknowns using particles and weights (costs) assigned to the particles. In most versions of these methods, particles move independently and in accordance with the dynamics of the assumed model of the states. Interactions among particles only occur through the process of resampling rather than through local interactions as is common in physical and biological systems. Such interactions can improve the performance of the methods and can allow for coping with more challenging problems with better efficiency and accuracy. We show how we apply these methods to problems in engineering, economics, and biology.","PeriodicalId":227890,"journal":{"name":"10th Symposium on Neural Network Applications in Electrical Engineering","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129012259","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

Consistent generalization of classical Boolean two-valued into real-valued theories 经典布尔二值理论在实值理论中的一致推广

10th Symposium on Neural Network Applications in Electrical Engineering Pub Date : 2010-11-29 DOI: 10.1109/NEUREL.2010.5644068

D. Radojevic

{"title":"Consistent generalization of classical Boolean two-valued into real-valued theories","authors":"D. Radojevic","doi":"10.1109/NEUREL.2010.5644068","DOIUrl":"https://doi.org/10.1109/NEUREL.2010.5644068","url":null,"abstract":"Consistent Boolean generalization of two-valued into a real-valued theory means preservation of all of its algebraic — value indifferent characteristics: Boolean axioms and theorems. Actually two-valued theories in Boolean frame (classical logic, theory of classical sets, theory of classical relations, etc.) are based on the celebrated two-valued realization of Boolean algebra (BA) and their real-valued consistent generalization should be based on a real-valued realization of BA. The conventional real-valued theories: fuzzy sets, fuzzy logic, fuzzy relations, fuzzy probability, etc., are not in Boolean frame. Interpolative Boolean algebra (IBA) is a real-valued realization of atomic or finite BA. IBA is based on generalized Boolean polynomials (GBP) as a unique figure of every element of finite Boolean algebra. GBP is able to process values from real unit interval so to preserve all algebraic characteristics on a value level as corresponding arithmetic properties (for example: relation ⊆ as ≤). The real-valued realization of atomic or finite BA is adequate for any real problem since gradation offers superior expressiveness in comparison to the black-white outlook. Consistent Boolean generalization is illustrated on representative examples.","PeriodicalId":227890,"journal":{"name":"10th Symposium on Neural Network Applications in Electrical Engineering","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130363277","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: 0