The aim of this talk is to explain a pioneering exploratory research endeavour that attempts to merge two completely different fields in Computer Science so as to yield very fascinating results. These are the well-est...
详细信息
ISBN:
(纸本)9783642217869
The aim of this talk is to explain a pioneering exploratory research endeavour that attempts to merge two completely different fields in Computer Science so as to yield very fascinating results. These are the well-established fields of Neural Networks (NNs) and Adaptive Data Structures (ADS) respectively. The field of NNs deals with the training and learning capabilities of a large number of neurons, each possessing minimal computational properties. On the other hand, the field of ADS concerns designing, implementing and analyzing data structures which adaptively change with time so as to optimize some access criteria. In this talk, we shall demonstrate how these fields can be merged, so that the neural elements are themselves linked together using a data structure. This structure can be a singly-linked or doubly-linked list, or even a Binary Search Tree (BST). While the results themselves are quite generic, in particular, we shall, as a prima facie case, present the results in which a Self-Organizing Map (SOM) with an underlying BST structure can be adaptively re-structured using conditional rotations. These rotations on the nodes of the tree are local and are performed in constant time, guaranteeing a decrease in the Weighted Path Length of the entire tree. As a result, the algorithm, referred to as the Tree-based Topology-Oriented SOM with Conditional Rotations (TTO-CONROT), converges in such a manner that the neurons are ultimately placed in the input space so as to represent its stochastic distribution. Besides, the neighborhood properties of the neurons suit the best BST that represents the data.
Travel mode choice forecasts receive wide attention in travel behavior analysis. Most traditional mode choice models are based on the principle of random utility maximization. Alternatively, mode choice is a pattern r...
详细信息
A method of tool wear intelligence measure based on Discrete Hidden Markov Models (DHMM) is proposed to monitor tool wear and to predict tool failure. FFT features are first extracted from the vibration signal and cut...
详细信息
This paper presents a hybrid approach to the path planning problem of autonomous robots that combines potential field (PF) method and genetic algorithm (GA). The proposed PF+GA approach takes the strength of both pote...
详细信息
ISBN:
(纸本)9783642215377;9783642215384
This paper presents a hybrid approach to the path planning problem of autonomous robots that combines potential field (PF) method and genetic algorithm (GA). The proposed PF+GA approach takes the strength of both potential field and genetic algorithm to find global optimal collision-free paths. In this integrated frame, the PF is designed as gradient-based searching strategy to exploit local optimal, and the GA is used to explore over the whole problem space. Different implementation strategies are examined through simulations in 2D scenarios. The conducted experiments show that global optimal path can be achieved effectively using the proposed approach with a strategy of high diversity and memorization.
The proceedings contain 45 papers. The topics discussed include: multiple instance learning with missing object tags;design and implementation of intelligent mesh nodes for wireless video stream sharing;three-level pr...
ISBN:
(纸本)9781450309189
The proceedings contain 45 papers. The topics discussed include: multiple instance learning with missing object tags;design and implementation of intelligent mesh nodes for wireless video stream sharing;three-level privacy control for sensing-based real-world content digital diorama;a pseudo relevance feedback based cross domain video concept detection;VideoAder: a video advertising system based on intelligent analysis of visual content;the effects of heterogeneous information combination on large scale social image search;a novel file-level continuous data protection mechanism oriented service application;adaptive multimedia service framework for health monitoring;digital watermarking and tree structure based image quality estimation;controlling privacy with trust-aware link prediction in online social networks;and robust copy-move image forgery detection using undecimated wavelets and Zernike moments.
The development of competitive artificial Poker players is a challenge to Artificial intelligence (AI) because the agent must deal with unreliable information and deception which make it essential to model the opponen...
详细信息
ISBN:
(纸本)9783642215377;9783642215384
The development of competitive artificial Poker players is a challenge to Artificial intelligence (AI) because the agent must deal with unreliable information and deception which make it essential to model the opponents to achieve good results. In this paper we propose the creation of an artificial Poker player through the analysis of past games between human players, with money involved. To accomplish this goal, we defined a classification problem that associates a given game state with the action that was performed by the player. To validate and test the defined player model, an agent that follows the learned tactic was created. The agent approximately follows the tactics from the human players, thus validating this model. However, this approach alone is insufficient to create a competitive agent, as generated strategies are static, meaning that they can't adapt to different situations. To solve this problem, we created an agent that uses a strategy that combines several tactics from different players. By using the combined strategy, the agentgreatly improved its performance against adversaries capable of modeling opponents.
In this research, a framework for building Autonomous Underwater Vehicle (AUV) control algorithms that is based on the MOOS-IvP middleware is presented. The Sidescan Sonar Sensor (SSS) is commonly used to generate son...
详细信息
ISBN:
(纸本)9783642215377;9783642215384
In this research, a framework for building Autonomous Underwater Vehicle (AUV) control algorithms that is based on the MOOS-IvP middleware is presented. The Sidescan Sonar Sensor (SSS) is commonly used to generate sonar images in which mine-like objects can be identified. A common mission specification would be to cover an entire area of seabed up to a specified confidence with the SSS. Here, a base station community is implemented that maintains a map of coverage confidence of the SSS, and provides the user with 2D and 3D simulations and the ability to implement advanced control schemes to achieve this mission. The development happens in two stages: 1) A minimalist configuration where only the necessary applications are used to develop and test outer loop control, and 2) A configuration that includes simulated hardware. The benefits are ease of use, faster development, and reduced hardware testing and cost.
The paper will discuss in detail the new possibilities for making linguistic description and semantic interpretations of 64-slice spiral CT coronary vessels visualizations with the use of AI linguistic formalisms and ...
详细信息
ISBN:
(纸本)9783642200427
The paper will discuss in detail the new possibilities for making linguistic description and semantic interpretations of 64-slice spiral CT coronary vessels visualizations with the use of AI linguistic formalisms and especially ETPL(k) graph grammar. Current research shows that a significant part of diagnostic imaging, including of coronary arteries, is still difficult to automatically assess using computer analysis techniques aimed at extracting information having semantic meaning. The proposed syntactic semantic description makes it possible to intelligently model the examined structure and then to automatically find the locations of significant stenoses in coronary arteries and identify their morphometric diagnostic parameters.
An effective rescheduling method takes an important role on improving the operational performance of a semiconductor wafer fabrication facility (fabs). In this paper, we propose a rescheduling method based on swarm in...
详细信息
ISBN:
(纸本)9783037850190
An effective rescheduling method takes an important role on improving the operational performance of a semiconductor wafer fabrication facility (fabs). In this paper, we propose a rescheduling method based on swarm intelligence. Firstly, we build a swarm intelligence based rescheduling model (SIRM) including an ant queen agent, multiple job ant agents and machine ant agents. Secondly, we design a rescheduling algorithm (CMRA) composed of three sub-algorithms: sub-algorithm-1 is used by an ant queen agent to transfer an existing static optimized scheduling plan into additional pheromones of job ant agents;sub-algorithm-2 and sub-algorithm-3 are used to convert scheduling related real-time information to dynamic pheromones of job ant agents and machine ant agents, respectively. Finally, a simplified semiconductor wafer fab model is used to verify and validate CMRA. The simulation results demonstrate that CMRA is superior to the original scheduling method to generate a static optimized scheduling plan with better performance on move, step and on-time operational due date rate under uncertain production environments.
Keyword extraction is to automatically extract keywords that capture the main topic discussed in a given document. In this paper, a new keyword extraction algorithm based on sequential patterns is proposed. By preproc...
详细信息
暂无评论