The artificial neural networks are an imitation of human brain architecture. Dendritic computing is based on the concept that dendrites are the basic building blocks for a wide range of nervous systems. Dendritic Comp...
详细信息
ISBN:
(纸本)9783642196430
The artificial neural networks are an imitation of human brain architecture. Dendritic computing is based on the concept that dendrites are the basic building blocks for a wide range of nervous systems. Dendritic computing has been proved to produce perfect approximation of any data distribution. This result guarantees perfect accuracy training. However, we have found great performance degradation when tested on conventional k-fold cross-validation schemes. In this paper we propose to modify the basic strategy of hyperbox definition in DC introducing a factor of reduction of these hyperboxes. We obtain a big increase in classification performance applying with this schema over a database of features extracted from Magnetic Resonance Imaging (MRI) including Alzheimer's Disease (AD) patients and control subjects.
This paper analyzes possible solutions and mechanisms to facilitate information retrieval in a corporate web site. It presents advantages and problems of taxonomies and folksonomies, and proposes a hybrid approach whi...
详细信息
ISBN:
(数字)9783642180293
ISBN:
(纸本)9783642180286
This paper analyzes possible solutions and mechanisms to facilitate information retrieval in a corporate web site. It presents advantages and problems of taxonomies and folksonomies, and proposes a hybrid approach which combines their benefits to adaptively improve access to a web site. This approach has been tested in a real scenario by developing the Easy Access system. This practical experience introduces the "tagsonomy" mechanism, i.e. the controlled combination of a top-down classification defined by the web site content manager, and a bottom-up classification defined by users. The peculiar feature is that the folksonomy is automatically generated on the basis of the user interaction with the system, and not as the result of an explicit tagging process.
This paper presents the results of an ongoing project that is being carried out by the Research Group in Individual Oriented Modelling (IoM) of the University Autonoma of Barcelona (UAB) with the participation of Hosp...
详细信息
ISBN:
(纸本)9783642198748
This paper presents the results of an ongoing project that is being carried out by the Research Group in Individual Oriented Modelling (IoM) of the University Autonoma of Barcelona (UAB) with the participation of Hospital Emergency Department (ED) Staff Teams. Its general objective is creating a simulator that, used as decision support system (DSS), aids the heads of the ED to make the best informed decisions possible. The defined ED model is a pure Agent-Based Model, formed entirely of the rules governing the behaviour of the individual agents which populate the system. The actions of agents and the communication between them are represented using Moore state machines extended to include probabilistic transitions. The model also includes the environment in which agents move and interact. With the aim of verifying the proposed model an initial simulation has been created using NetLogo.
This paper presents two new methods for network analysis. Ant colony optimization is a nature inspired algorithm succesfull in graph traversal and network path finding whereas network reduction based on stability intr...
详细信息
ISBN:
(数字)9783642180293
ISBN:
(纸本)9783642180286
This paper presents two new methods for network analysis. Ant colony optimization is a nature inspired algorithm succesfull in graph traversal and network path finding whereas network reduction based on stability introduces two new properties of network vertices based on their long-term behavior, their role in the network and the understanding of how memory works. We illustrate the algorithms on applications in social network analysis and information retrieval using the DBLP dataset and a small network of hyperlinked documents.
Modern web application hype revolves around a rich user interface experience. A lesser-known aspect of modern applications is the use of techniques that enable the intelligent processing of information and add value t...
详细信息
ISBN:
(纸本)9783642231629
Modern web application hype revolves around a rich user interface experience. A lesser-known aspect of modern applications is the use of techniques that enable the intelligent processing of information and add value that can't be delivered by other means. This article presents a scalable, maintainable and inter-operable approach for combining content management functionalities with natural language processing (NLP) tools. The software, based on this architecture, is open for chaining various NLP tools and integration of languages in a standardized manner. As a demonstration of the concept, we have developed two web sites using a content management system, featuring the English NLP based language processing chain. Language processing chains for Bulgarian, Croatian, German, German, Greek, Polish and Romanian languages are in a process of development and integration.
In this article the authors present the simulated trading results of a system consisting of 60 intelligent agents, each being responsible for day trading a stock listed on the NYSE or the NASDAQ stock exchange. These ...
详细信息
ISBN:
(纸本)9783642198748
In this article the authors present the simulated trading results of a system consisting of 60 intelligent agents, each being responsible for day trading a stock listed on the NYSE or the NASDAQ stock exchange. These agents were implemented according to an architecture that was previously applied to currency trading with interesting results. The performance of the stock trading agents, once integrated in a diversified investment system, showed similar promise. The trading simulation was done using out-of-sample price data for the period between February of 2006 and October of 2010. Throughout this period, the system's performance compared favorably with that of the buy-and-hold strategy, both in terms of return and maximum drawdown. These results indicate that agent technology might be of use for this particular practical application, a conclusion that should interest the investment industry.
Data gathered from real world processes include several undesired effects, like the noise in the process, the bias of the sensors and the presence of hysteresis, among other undesirable uncertainty sources. Learning m...
详细信息
ISBN:
(纸本)9783642196430
Data gathered from real world processes include several undesired effects, like the noise in the process, the bias of the sensors and the presence of hysteresis, among other undesirable uncertainty sources. Learning models using the so called Low Quality Data (LQD) is a difficult task which has been barely studied. In a previous study, a method for learning white box models in the presence of LQD that makes use of Multi Objective Simulated Annealing hybridized with genetic operators method for learning models was proposed. This research studies the role of the tree generation methods when learning LQD. The results of this study show the relevance of the role of tree generation methods in the obtained results.
Modern File systems like CLFS (Cryptographic Log Structured File System) are aimed to provide security and confidentiality. Current deployments of such File Systems do not ensure data integrity of the encrypted data t...
详细信息
ISBN:
(纸本)9783642286636;9783642286643
Modern File systems like CLFS (Cryptographic Log Structured File System) are aimed to provide security and confidentiality. Current deployments of such File Systems do not ensure data integrity of the encrypted data that is stored on disk. Due to Kernel bugs, racing conditions and arbitrary dead-locks, CLFS data on the disc can be damaged and also there is always the possibility that system users can modify the encrypted data. That's why, we considered essential to modify the way keys are stored in the system, as their safe storage is a clue point to the whole protection this system assures. Implementing a Trusted Platform Module is our suggestion to the case. So in this secure environment, our aim lies towards ensuring data integrity on CLFS without compromising the overall performance. This paper considers the standard data verification methods, with the main goal to overcome one of its major limitations, low performance of File System check-summing. CLFS matches our performance expectations, as it performs close enough to non-cryptographic file systems. To improve the performance of the check-summing process we try to study and examine various design choices and propose metadata check-summing. Several tests are made to prove that this added functionality does not significantly affect performance.
CSISE2011 is an integrated conference concentrating its focus upon Computer Scienceintelligent System and Environment. In the proceeding, you can learn much more knowledge about Computer Science, intelligent System an...
ISBN:
(数字)9783642237775
ISBN:
(纸本)9783642237768
CSISE2011 is an integrated conference concentrating its focus upon Computer Scienceintelligent System and Environment. In the proceeding, you can learn much more knowledge about Computer Science, intelligent System and Environment of researchers all around the world. The international conference will provide a forum for engineers, scientist, teachers and all researchers to discuss their latest research achievements and their future research plan. The main role of the proceeding is to be used as an exchange pillar for researchers who are working in the mentioned field. In order to meet high standard of Springers advances in intelligent and soft computing ,the organization committee has made their efforts to do the following things. Firstly, poor quality paper has been refused after reviewing course by anonymous referee experts. Secondly, periodically review meetings have been held around the reviewers about five times for exchanging reviewing suggestions. Finally, the conference organization had several preliminary sessions before the conference. Through efforts of different people and departments, the conference will be successful and fruitful. We hope that you can get much more knowledges from our CSISE2011, and we also hope that you can give us good suggestions to improve our work in the future.
The generalized vehicle routing problem (GVRP) is one of the challenging combinatorial optimization problems that finds a lot of practical applications. The GVRP is a natural extension of the classical vehicle routing...
详细信息
ISBN:
(纸本)9783642196430
The generalized vehicle routing problem (GVRP) is one of the challenging combinatorial optimization problems that finds a lot of practical applications. The GVRP is a natural extension of the classical vehicle routing problem (VRP) and it is an NP-hard optimization problem belonging to the class of generalized combinatorial optimization problems. The aim of this paper is to present a new approach to tackle this complex problem. Combining this approach with a genetic algorithm results an efficient hybrid softcomputing technique for solving the generalized vehicle routing problem. The proposed algorithm is competitive with other heuristics published to date in both solution quality and computation time. The computational results for several benchmarks problems are reported and the results point out that our proposed algorithm is an appropriate method to explore the search space of this complex problem and leads to good solutions in a reasonable amount of time.
暂无评论