Showing papers in "Engineering Applications of Artificial Intelligence in 2007"

TL;DR: A co-evolutionary particle swarm optimization approach (CPSO) for constrained optimization problems, where PSO is applied with two kinds of swarms for evolutionary exploration and exploitation in spaces of both solutions and penalty factors.

TL;DR: This paper proposes a methodology for determining the best architecture of an ANN and is based on the use of a genetic algorithm and the development of novel criteria that quantify an ANN's performance (both training and generalization) as well as its complexity.

TL;DR: A literature survey on intelligent systems for monitoring, control, and diagnosis of process systems is presented, to introduce the data-driven, analytical, and knowledge-based approaches for developing solutions in intelligent support systems, and to present research efforts of four research groups that have done extensive work in integrating the three solutions approaches.

TL;DR: Alternative approaches, artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS), are proposed to estimate the equilibrium and time-dependent scour depth with numerous reliable data base and numerical tests indicate that MLP/BP model provide a better prediction of scour Depth than RBF/OLS and ANFIS models.

TL;DR: The significant variables suggested by the ML techniques indicate chlorophyll-a (Chl-a) itself to be the most significant input in predicting the algal blooms, suggesting an auto-regressive nature or persistence in theAlgal bloom dynamics, which may be related to the long flushing time in the semi-enclosed coastal waters.

TL;DR: The paper presents the method of daily air pollution forecasting by using support vector machine (SVM) and wavelet decomposition and results of numerical experiments on the basis of the measurements made by the meteorological stations, situated in the northern region of Poland.

TL;DR: Purely based on a hierarchy of self-organizing feature maps (SOMs), an approach to network intrusion detection is investigated, finding the best performance to date of a detector based on an unsupervised learning algorithm.

TL;DR: A novel approach for recognizing and classifying positive and negative emotional changes in real time using physiological signals is presented and it is suggested that the detection mechanism outlined in this paper has all the characteristics needed to perform emotion recognition in pervasive computing.

TL;DR: The effectiveness of the interval halving and trend matching is shown through simulation studies on the fault diagnosis of the Tennessee Eastman process and a novel interval-halving method for trend extraction and a fuzzy-matching-based method for similarity estimation and inferencing are presented.

TL;DR: The method covers not only the very process of model creation in CATIA system but also the whole complexity of the process, beginning with knowledge identification and acquisition and finally with explanation system creation that facilitates and justifies the usage of generative model itself.

TL;DR: Three ways of distance measure, including Euclidean distance, perpendicular distance and vertical distance, for PIP identification are compared and both template- and rule-based pattern-matching approaches are introduced, making them particularly user friendly to ordinary data analysts like stock market investors.

TL;DR: The developed estimator using LM approach predicts the composition of distillate using column pressure, reboiler duty, and reflux flow along with the temperature profile of the distillation column as inputs and it is observed that the results obtained are significantly improved than the results obtaining from SDBP algorithm.

TL;DR: Based on an analysis of the construction on-line systems the authors of paper developed multiple criteria decision support on-lines system for construction.

TL;DR: Cohen's kappa, a meter that does compensate for random hits, was compared with accuracy, and it turned out that the average probability of a hit being the result of mere chance exceeded one third (!).

TL;DR: An attempt to build a stock buying/selling alert system using a backpropagation NN, NN5, is presented, and a best strategy for trading non-volatile stock like HSBC is recommended.

TL;DR: Experimental results show that the presented algorithm produces fuzzy rules, which can be used to construct a reliable intrusion detection system.

TL;DR: A specific architecture (DRA-FRL) is presented, which uses the emerging methodology of reinforcement learning in conjunction with fuzzy rulebases to achieve the desired objective of adaptive reconfiguration of a distributed system based on maximizing the long-term business value.

TL;DR: This study optimizes the AI-based INS/GPS integration schemes utilizing adaptive neuro-fuzzy inference system (ANFIS) by implementing, a temporal window-based cross-validation approach during the update procedure.

TL;DR: The procedures here will allow to set up linear matrix inequality conditions which are less conservative than the cited ones, by exploiting the TP structure of the membership functions.

TL;DR: Three initialization methods based on principal component analysis (PCA), fuzzy clustering and Gabor wavelets are explored either for the consideration of computational complexity or the preservation of structure in non-negative matrix factorization.

TL;DR: The inverse problems consisting in the simultaneous estimation of unknown thermophysical and/or geometrical parameters of the tumor region are solved and the evolutionary algorithm coupled with the multiple reciprocity boundary element method has been applied.

TL;DR: This paper investigates a novel approach to the designing of two-dimensional zero phase infinite impulse response (IIR) digital filters using the PSO algorithm, and demonstrates the superiority of the proposed design method by comparing it with two recently published filter design methods and two other state of the art optimization techniques.

TL;DR: A hybrid technique consisting of two strategies, a real-parameter genetic algorithm is combined with simulated annealing and adaptive mechanisms for finding the actual damages and the predicted results agree with the true solutions exactly.

TL;DR: A new backward test is proposed, based on the inverse image of an interval function, that allows checking if there exists a parameter in the uncertain parameter set that is consistent with the measured system behaviour.

TL;DR: An alternative approach to pH process control using model-free learning control (MFLC), which is based on reinforcement learning algorithms, which gives a general solution for acid-base systems, yet is simple enough to be implemented in existing control hardware without a model.

TL;DR: Results show that these wavelengths seen on the NIR spectra are not sufficient to build a machine with correct generalisation ability, so the use of a non-linear method, such as SVM and its corollary methods, kernel alignment and k-PCA is justified.

TL;DR: A hybrid neural network model, based on the integration of fuzzy ARTMAP (FAM) and the rectangular basis function network (RecBFN), which is capable of learning and revealing fuzzy rules is proposed, which is able to classify data samples incrementally and to extract rules directly from the network weights for justifying its predictions.

TL;DR: A confidence band for the input-output data, obtained in the normal operating conditions of a system, is approximated using a fuzzy model with interval parameters, based on linear programming using l"~-norm as a measure of the modelling error.

TL;DR: An integrated system for the binarization of normal and degraded printed documents for the purpose of visualization and recognition of text characters by combining their results using a Kohonen self-organizing map neural network.

TL;DR: A comparison of the proposed SGA to the traditional GA is presented to demonstrate that when the schema theorem is embedded, the performance of GA has significant improvement.