A Stage Model for NPD Process Maturity and IKMS Implementation

The objective of this chapter is to provide an analytical tool to assist organizations in their implementations of Intelligent Knowledge Management Systems (IKMS) along the new product development (NPD) process. Indeed, organizations rely on a variety of systems using Artificial Intelligence to support the NPD process that depends on the maturity stage of both the process and type of knowledge managed. Our framework outlines the technological and organizational path that organizations have to follow to integrate and manage knowledge effectively along their new product development process. In doing so, we also address the main limitations of the systems used to date and suggest the evolution towards a new category of KMS based on artificial intelligence that we refer to as Intelligent Knowledge Management Systems. We illustrate our framework with an analysis of several case studies.

Document-Driven Design for Distributed CAD Services

Current CAD systems only support interactive geometry generation, which is not ideal for distributed engineering services in enterprise-to-enterprise collaboration with a generic thin-client service-oriented architecture. This chapter presents a new feature-based modeling mechanism, document-driven design, to enable batch mode geometry construction for distributed CAD systems. A semantic feature model is developed to represent informative and communicative design intent. Feature semantics is explicitly captured as trinary relation, which provides good extensibility and prevents semantics loss. Data interoperability between domains is enhanced by schema mapping and multi-resolution semantics. This mechanism aims to enable asynchronous communication in distributed CAD environments with ease of design alternative evaluation and reuse, and improved system throughput and utilization

Intelligent Remote Monitoring and Maintenance Systems

Internet-based intelligent fault diagnosis and maintenance technologies are keys for enterprises to achieve global leadership in market competition and manufacturing productivity for business in the 21st century. e-Products, e-Manufacturing and e-Service have been the goals of enterprises: 1) Next generation products must be network-based products—e–products. The vast developments of IT technology based hardware and software make the controller of internet based products cheaper; 2) Common facilities such as internet and World Wide Web, 3G (GPS, GPRS and GIS) make e-maintenance or e-service cheaper and easier; and 3) “Server-web-user” methodology makes e-manufacturing possible, convenient and efficient. To achieve these goals, smart software and NetWare are needed to provide proactive maintenance capabilities such as performance degradation measurement, fault recovery, self-maintenance, and remote diagnostics. This chapter presents methodologies and techniques for the development of an Internet server controller based intelligent remote monitoring and maintenance system. Discussion involves on how to make innovations and develop products and manufacturing systems using internet-based intelligent technologies and how to ensure product quality, coordinate activities, reduce costs and change maintenance practice from the breakdown reaction to prevention. A hybrid intelligent approach using hardware and software agents (watchdog agent) is adopted. The server controller is web-enabled and its core is an embedded network model. The software agent is implemented through a package of Smart Prognostics Algorithms. The package consists of embedded computational prognostic algorithms developed using neural network based, time-series based, wavelet-based and hybrid joint time-frequency methods, etc. and a software toolbox for predicting degradation of devices and systems. The effectiveness of the proposed scheme is verified in a real testbed system

An Agent Based Formal Approach for Modeling and Verifying Integrated Intelligent Information Systems

In this chapter a formal agent based approach for the modeling and verification of intelligent information systems using Coloured Petri Nets is presented. The use of a formal method allows analysis techniques such as automatic simulation and verification, increasing the confidence on the system behavior. The agent based modelling allows separating distribution, integration and intelligent features of the system, improving model reuse, flexibility and maintenance. As a case study an intelligent information control system for parking meters price is presented.

An Evolutionary Framework for Nonlinear Time-Series Prediction with Adaptive Gated Mixtures of Experts

A probabilistic learning technique, known as gated mixture of experts (MEs), is made more adaptive by employing a customized genetic algorithm based on the concepts of hierarchical mixed encoding and hybrid training. The objective of such effort is to promote the automatic design (i.e., structural configuration and parameter calibration) of whole gated ME instances more capable to cope with the intricacies of some difficult machine learning problems whose statistical properties are time-variant. In this chapter, we outline the main steps behind such novel hybrid intelligent system, focusing on its application to the nontrivial task of nonlinear time-series forecasting. Experiment results are reported with respect to three benchmarking time-series problems, and confirmed our expectation that the new integrated approach is capable to outperform, both in terms of accuracy and generalization, other conventional approaches, such as single neural networks and non-adaptive, handcrafted gated MEs.

Intelligent Ant Colony System for Traveling Salesman Problem and Clustering

Processes that simulate natural phenomena have successfully been applied to a number of problems for which no simple mathematical solution is known or is practicable. Such meta-heuristic algorithms include genetic algorithms, particle swarm optimization and ant colony systems and have received increasing attention in recent years. This work parallelizes the ant colony systems and introduces the communication strategies so as to reduce the computation time and reach the better solution for traveling salesman problem. We also extend ant colony systems and discuss a novel data clustering process using Constrained Ant Colony Optimization (CACO). The CACO algorithm extends the ant colony optimization algorithm by accommodating a quadratic distance metric, the Sum of K Nearest Neighbor Distances (SKNND) metric, constrained addition of pheromone and a shrinking range strategy to improve data clustering. We show that the CACO algorithm can resolve the problems of clusters with arbitrary shapes, clusters with outliers and bridges between clusters

Automated Object Detection and Tracking for Intelligent Visual Surveillance Based on Sensor Network

The aim of this research was to apply an agent approach to wireless sensor network in order to construct a distributed, automated scene surveillance. Wireless sensor network using visual nodes is used as a framework for developing a scene understanding system to perform smart surveillance. Current methods of visual surveillance depend on highly train personnel to detect suspicious activity. However, the attention of most individuals degrades after 20 minutes of evaluating monitor-screens. Therefore current surveillance systems are prompt to failure. An automated object detection and tracking was developed in order to build a reliable visual surveillance system. Object detection is performed by means of a background subtraction technique known as Wronskian change detection. After discovery, a multi-agent tracking system tracks and follows the movement of each detected object. The proposed system provides a tool to improve the reliability and decrease the cost related to the personnel dedicated to inspect the monitor-screens

Neural Networks and 3D Edge Genetic Template Matching for Real-Time Face Detection and Recognition

This chapter describes a novel system that can track and recognize faces in real time using neural networks and genetic algorithms. The main feature of this system is a 3D facemask that combined with a neural network based face detector and adaptive template matching using genetic algorithms, is capable of detecting and recognizing faces in real time. Neural network learning and template matching enable size and pose invariant face detection and recognition while the genetic algorithm optimizes the searching algorithms enabling real time usage of the system. It is hoped that this chapter will show how and why neural networks and genetic algorithms are well suited to solve complex pattern recognition problems like the one presented in this chapter.

Information Networks as Complex Systems

Complex network such as scale-free networks and small-world networks have been studied with the dynamics when the information percolates through the networks. This chapter reports the problem of spreading the normal state (rather than spreading of the abnormal state) that is formalized as cleaning a contaminated network by mutual copying. Repairing by copying is the “double edged sword” that could spread contamination when properly used. A framework for controlling copying involving a spatial Prisoner’s Dilemma is introduced. Adaptive character to the network environment has been observed.

An Integrated Intelligent System Model and Its Applications in Virtual Product Design and Development

In this Chapter, a novel integrated intelligent framework is first proposed for virtual engineering design and development based on the soft computing and hybrid intelligent techniques. Then, an evolutionary neuro-fuzzy (EFNN) model is developed and used for supporting modeling, analysis and evaluation, and optimization tasks in the design process, which combines fuzzy logic with neural networks and genetic algorithms. The developed system HIDS-EFNN provides a unified integrated intelligent environment for virtual engineering design and simulation. The focus of this Chapter is to present a hybrid intelligent approach with evolutionary neuro-fuzzy modeling and its applications in virtual product design, customization and simulation (product performance prediction). Case studies are provided to illustrate and verify the proposed model and approach.