Catálogo de publicaciones - libros

A novel connectionist method to feature selection is proposed in this paper to identify the optimal conditions to perform drilling tasks. The aim is to extract information from complex high dimensional data sets. The model used is based on a family of cost functions which maximizes the likelihood of identifying a specific distribution in a data set. It employs lateral connections derived from the Rectified Gaussian Distribution to enforce a more sparse representation in each weight vector. The data investigated is obtained from the sensors allocated in a robot used to drill and build industrial warehouses. It is hoped that in classifying this data related with the strength, the water volume for refrigerating, speed and time of each sample, it will help in the search of the best conditions to perform the drilling of reinforce concrete slabs. This would produce a great saving for the company which owns the drilling robot.

Recently, there has been an increase in research of system that measures traffic flow of people with the use of image processing technique. However, there is a demand for establishment of a method to accurately measure congested people flow without limiting the camera position — which is the dilemma of the existing researches. Therefore, in this research, with the use of cluster analysis, we have developed a people flow measurement system that can function even in the case of congested situation where there are no spaces between people.

When creating computational models of engineering structures, it can be very helpful to have insights into the behavior and composition of the physical system. Such insights can be gleaned using data mining techniques, where often unexpected relationships between physical quantities can be made evident.

In the context of an agent-based research project to monitor dams, a number of sensors supply a large amount of data over an extended period of time. This data can naturally be used for data mining purposes to discover new and interesting aspects about the engineering structure. In this paper, an open source data mining tool (Weka) is briefly introduced and presented to show how data mining techniques can be applied in the handling of engineering tasks.

The paper presents an IT system for costal environment control. The system has been fully in operation. The system collects, processes the real time environmental information and manage the mobile resources accordingly. The system includes a GIS system, a database, a web server, a communication system and the control application. The system is flexible and configurable. The system has been built with modularity, cross-platform and distributed nature.

The explosive growth of databases related to bridge management activities may exceed the capability of our traditional decision-making process. This paper focuses on how to integrate varieties of qualitative and quantitative data related to bridge management, and elaborates the universal architecture for information processing. The architecture consists of Bridge Markup Language (BridgeML) and knowledge management, and the prototype system has been developed.

Cellular phones were used only for wireless telephone calls in the past, but its application is expanding to use the wireless Internet. Practical use of the mobile Internet is insufficient due to its fundamental limitations. Especially, mobile resources are not sufficient because they are not closely connected under current mobile Internet services which are provided with pre-designed structure. For these reasons it will take a lot more time and effort for the use of the mobile Internet to grow as a general service. In this paper, we are focusing on how to overcome the local limitations and to enhance the ‘Sharing of Mobile Resources’ by expanding mutual connectivity between resources scattered over the mobile Internet environment. MRSS(Mobile Resource Sharing System) provides a Human Computer Interface to customers using the Mobile Internet. MRSS automatically converts single request from a user to multiple instructions based on ‘Context-Awareness’ to search for proper information. MRSS provide ‘Ubiquitous Computing’ environment which users can reach information anywhere, anytime.

Key to automated network management lies in the leveraging of the network knowledge resources to reduce the communication complexity. This paper proposes a generic framework for representing the knowledge semantics of multi-agent based data communication Network Management Systems (NMS). We focus our attention to the fault diagnosis functional area which is considered as the most crucial regarding the management of networked systems. The proposed network knowledge model adopts the holistic approach based on the CommonKADS methodology [] for modularizing the elusive structures of network knowledge to facilitate its reusability and share-ability. The network static configurational knowledge is identified as domain knowledge ontology, whereas the static status inference knowledge is represented as multi-agent based fault-state causal reasoning models. The complex experiential knowledge of network management is formalized as task knowledge ontology. We envisage this model-based diagnosis approach as the first step towards the comprehensive knowledge acquisition, representation and dissemination in the network management domain.

Composite web services that aggregate intra- or inter-enterprise web services use the standard BPEL4WS language to define the orchestration and run on the BPEL4WS engine (called an orchestration server). The orchestration server needs the activity state management function because the orchestration server executes processes in units of activities and decides the next activity based on the state of the current activity at each stage of the process. We propose an activity management scheme that makes use of context in this work. Design and implementation of the context-aware orchestration server is also presented. This orchestration server is also fault-tolerant and scalable as well as maintainable

A novel approach for collecting topic relevant web pages called the potential hub and authority first (PHA-first) approach is proposed. We use this approach to collect a base set which is used to calculate the famous hub and authority values defined by the HITS algorithm. In our pilot research, the experiment results show that our PHA-first approach is well performed than the original HITS algorithm in the precision rate. The satisfaction investigation of PHA-first based algorithms is also promising.

The proposed Fuzzy Neural Network(FNN) model uses feedforward neural network to perform fuzzy systems with the product-sum fuzzy inference mechanism. So the number of fuzzy rules directly determines the complexity and efficiency of the FNN model. Based on the Neural Network Self-configuring Learning(NNSCL) algorithm, the modified NNSCL algorithm is obtained by solving a system of linear equations with the Conjugate Gradient Preconditioned Normal Equation (CGPCNE) algorithm the unknows of which are the adjusting factors of the remaining weights. The modified NNSCL algorithm is applied in the rule-reasoning layer to simplify the structure of the FNN model, aiming at minimizing its complexity and preserving a good level of accuracy without retraining after pruning. The simulation results demonstrate the effectiveness and the feasibility of the algorithm.