This work describes a method that uses artificial neural networks, specially a Self-Organising Map (SOM), to determine the correct meaning of a word. By using a distributed architecture, we take advantages of the para...
详细信息
ISBN:
(纸本)9783642004865
This work describes a method that uses artificial neural networks, specially a Self-Organising Map (SOM), to determine the correct meaning of a word. By using a distributed architecture, we take advantages of the parallelism in the different levels of the Natural Language Processing system, for modeling a community of conceptually autonomous agents. Every agent has an individual representation of the environment, and they are related through the coordinating effect of communication between agents with partial autonomy. The aim of our linguistic agents is to participate in a society of entities with different skills, and to collaborate in the interpretation of natural language sentences in a prototype of an Automatic German-Spanish Translator.
We use some machine learning methods to build classifiers of pigmented skin lesion images. We take advantage of natural induction methods based on the attributional calculus (AQ21) and MLP and SVM supervised methods t...
详细信息
ISBN:
(纸本)9783642032011
We use some machine learning methods to build classifiers of pigmented skin lesion images. We take advantage of natural induction methods based on the attributional calculus (AQ21) and MLP and SVM supervised methods to discover patterns in the melanocytic skin lesion images. This methodology can be treated as a non-invasive approach to early diagnosis of melanoma. Our feature set is composed of wavelet-based multi-resolution filters of the dermatoscopic images. Our classifiers show good efficiency and may potentially be important diagnostic aids.
This paper presents a multiagent system for decision support in the diagnosis of leukemia patients. The core of the system is a type of agent that integrates a novel strategy based on a case-based reasoning mechanism ...
详细信息
ISBN:
(纸本)9783642004865
This paper presents a multiagent system for decision support in the diagnosis of leukemia patients. The core of the system is a type of agent that integrates a novel strategy based on a case-based reasoning mechanism to classify leukemia patients. This agent is a variation of the CBP agents and proposes a new model of reasoning agent. where the complex processes are modeled as external services. The agents act as coordinators of Web services that implement the four stages of the case-based reasoning cycle. The multiagent system has been implemented in a real scenario. and the classification strategy includes a novel ESOINN neuronal network and statistics methods to analyze the patient's data. The results obtained are presented within this paper and demonstrate the effectiveness of the proposed agent model, as well as the appropriateness of using multiagent systems to resolve medical problems in a distributed way.
Object-oriented software development methodologies have adopted a model-driven approach to analysis and design phases. Currently. a similar approach is being adopted for Multi-Agent Systems to improve the development ...
详细信息
ISBN:
(纸本)9783642004865
Object-oriented software development methodologies have adopted a model-driven approach to analysis and design phases. Currently. a similar approach is being adopted for Multi-Agent Systems to improve the development process and the quality of the agent-based software. Model-Driven Development is a technique that allows to obtain executable code by means of transformations from models and meta-models. This work presents a transformation process that allows to generate automatically the code of an agent over his execution platform. That is, an agent is developed under the MDD approach in an easy and transparent way for the user. The code obtained from the transformations is executed over ANDROMEDA and JADE-Leap embedded agent platforms.
In multi-agent based simulations, providing various and consistent behaviors for the agents is an important issue to produce realistic and valid results. However, it is difficult for the simulations users to manage si...
详细信息
ISBN:
(纸本)9783642004865
In multi-agent based simulations, providing various and consistent behaviors for the agents is an important issue to produce realistic and valid results. However, it is difficult for the simulations users to manage simultaneously these two elements, especially when the exact influence of each behaviorial parameter remains unknown. We propose in this paper a generic model designed to deal with this issue: easily generate various and consistent behaviors for the agents. The behaviors are described using a normative approach, which allows increasing the variety by introducing violations. The generation engine controls the determinism of the creation process, and a mechanism based on unsupervised learning allows managing the behaviors consistency. The model has been applied to traffic simulation with the driving simulation software used at Renault, SCANeR (c) II, and experimental results are presented to demonstrate its validity.
One important factor that contributes to create good or bad relationships between individuals inside human societies is the notion of trust. In particular, some research works have proved the influence of trust in the...
详细信息
ISBN:
(纸本)9783642004865
One important factor that contributes to create good or bad relationships between individuals inside human societies is the notion of trust. In particular, some research works have proved the influence of trust in the performance of the activities that team-members perform jointly. This paper presents our initial theoretical work to include the trust factor into our TEAKS (TEAm Knowledge-based Structuring) model. TEAKS is an agent-based model to simulate the interaction between individuals when working together in the development of a project. Each team-member is represented through a set of pre-selected human characteristics: the emotional state, social characteristics. cognitive abilities, and personality types. The main outcome of the TEAKS simulation is statistical information about the possible performance at the individual and team levels. In this context we use two (emotional state and personality traits) of the four modelled human characteristics to introduce a model of trust into TEAKS to analyse the impact of trust in the results of the team.
The Airline Operations Control Center (AOCC) tries to solve unexpected problems that might occur during the airline operation. Problems related to aircrafts. crewmembers and passengers are common and the actions towar...
详细信息
ISBN:
(纸本)9783642004865
The Airline Operations Control Center (AOCC) tries to solve unexpected problems that might occur during the airline operation. Problems related to aircrafts. crewmembers and passengers are common and the actions towards the solution of these problems are usually known as operations recovery. In this paper we present the implementation of a Distributed Multi-Agent System (MAS) representing the existing roles in an AOCC. This MAS has several specialized software agents that implement different algorithms, competing to find the best solution for each problem and that include not only operational costs but, also, quality costs so that passenger satisfaction can be considered in the final decision. We present a real case Study where a crew recovery problem is solved. We show that it is possible to find valid solutions, with better passenger satisfaction and, in certain conditions, without increasing significantly the operational costs.
The development of nano- and picosatellites for educational and scientific purposes becomes more and more popular. As these satellites are very small, high-integrated devices and are therefore not equipped with high-g...
详细信息
ISBN:
(纸本)9783540896180
The development of nano- and picosatellites for educational and scientific purposes becomes more and more popular. As these satellites are very small, high-integrated devices and are therefore not equipped with high-gain antennas, data transmission between ground and satellite is vulnerable to several ascendancies in both directions. Another handicap is the lower earth orbit wherein the satellites are usually located as it keeps the communication time frame very short. To counter these disadvantages, ground station networks have been established. One input size for optimal scheduling of timeframes for the communication between a ground station and a satellite is the predicted quality of the satellite links. This paper introduces a satellite link quality prediction approach based on machine learning.
This purpose of this study is a combined use of socio economic, remote sensing and GIS data for developing a technique for landslide susceptibility mapping using artificial neural networks and then to apply the techni...
详细信息
ISBN:
(纸本)9783540896180
This purpose of this study is a combined use of socio economic, remote sensing and GIS data for developing a technique for landslide susceptibility mapping using artificial neural networks and then to apply the technique to the selected study areas at Nilgiris district in Tamil Nadu and to analyze the socio economic impact in the landslide locations. Landslide locations are identified by interpreting the satellite images and field survey data, and a spatial database of the topography, soil, forest, and land use. Then the landslide-related factors are extracted from the spatial database. These factors are then used with an artificial neural network (ANN) to analyze landslide susceptibility. Each factor's weight is determined by the back-propagation training method. Different training sets will be identified and applied to analyze and verify the effect of training. The landslide susceptibility index will be calculated by back propagation method and the susceptibility map will be created with a GIS program. The results of the landslide susceptibility analysis are verified using landslide location data. In this research GIS is used to analysis the vast amount of data very efficiently and an ANN to be an effective tool to maintain precision and accuracy. Finally the artificial neural network will prove it's an effective tool for analyzing landslide susceptibility compared to the conventional method of landslide mapping. The Socio economic impact is analyzed by the questionnaire method. Direct survey has been conducted with the people living in the landslide locations through different set of questions. This factor is also used as one of the landslide causing factor for preparation of landslide hazard map.
This paper presents a genetic fuzzy system for identification of Pareto-optimal Mamdani fuzzy models (FMs) for function estimation problems. The method simultaneously optimizes the parameters of fuzzy sets and selects...
详细信息
ISBN:
(纸本)9783540896180
This paper presents a genetic fuzzy system for identification of Pareto-optimal Mamdani fuzzy models (FMs) for function estimation problems. The method simultaneously optimizes the parameters of fuzzy sets and selects rules and rule conditions. Selection of rules and rule conditions does not rely only on genetic operators, but it is aided by heuristic rule and rule conditions removal. Instead of initializing the population by commonly used Wang-Mendel algorithm, we propose a modification to decision tree initialization. Experimental results reveal that our FMs are more accurate and consist of less rules and rule conditions than the FMs obtained by two recently published genetic fuzzy systems [2, 3].
暂无评论