Deriving explanations from partial temporal information

The representation and manipulation of natural human understanding of temporal phenomena is a fundamental field of study in Computer Science, which aims both to emulate human thinking, and to use the methods of human intelligence to underpin engineering solutions. In particular, in the domain of Artificial Intelligence, temporal knowledge may be uncertain and incomplete due to the unavailability of complete and absolute temporal information. This paper introduces an inferential framework for deriving logical explanations from partial temporal information. Based on a graphical representation which allows expression of both absolute and relative temporal knowledge in incomplete forms, the system can deliver a verdict to the question if a given set of statements is temporally consistent or not, and provide understandable logical explanation of analysis by simplified contradiction and rule based reasoning.

The completeness and soundness of temporal theories

Generally speaking, the term temporal logic refers to any system of rules and symbolism for representing and reasoning about propositions qualified in terms of time. In computer science, particularly in the domain of Artificial Intelligence, there are mainly two known approaches to the representation of temporal information: modal logic approaches including tense logic and hybrid temporal logic, and predicate logic approaches including temporal arguement method and reified temporal logic. On one hand, while tense logic, hybrid temporal logic and temporal argument method enjoy formal theoretical foundations, their expressiveness has been criticised as not power enough for representing general temporal knowledge; on the other hand, although reified temporal logic provides greater expressive power, most of the current systems following the temporal reification lack of complete and sound axiomatic theories. With there observations in mind, a new reified temporal logic with clear syntax and semantics in terms of a sound and complete axiomatic formalism is introduced in this paper, which retains all the expressive power of temporal reification.

Fuzzy Coding of Genetic Algorithms

A well-cited paper suggesting fuzzy coding as an alternative to the conventional binary, grey and floating-point representations used in genetic algorithms.

A Hybrid Forward Algorithm for RBF Neural Network Construction

This paper proposes a novel hybrid forward algorithm (HFA) for the construction of radial basis function (RBF) neural networks with tunable nodes. The main objective is to efficiently and effectively produce a parsimonious RBF neural network that generalizes well. In this study, it is achieved through simultaneous network structure determination and parameter optimization on the continuous parameter space. This is a mixed integer hard problem and the proposed HFA tackles this problem using an integrated analytic framework, leading to significantly improved network performance and reduced memory usage for the network construction. The computational complexity analysis confirms the efficiency of the proposed algorithm, and the simulation results demonstrate its effectiveness

Combining multiple prioritized knowledge bases by negotiation.

Recently, several belief negotiation models have been introduced to deal with the problem of belief merging. A negotiation model usually consists of two functions: a negotiation function and a weakening function. A negotiation function is defined to choose the weakest sources and these sources will weaken their point of view using a weakening function. However, the currently available belief negotiation models are based on classical logic, which makes them difficult to define weakening functions. In this paper, we define a prioritized belief negotiation model in the framework of possibilistic logic. The priority between formulae provides us with important information to decide which beliefs should be discarded. The problem of merging uncertain information from different sources is then solved by two steps. First, beliefs in the original knowledge bases will be weakened to resolve inconsistencies among them. This step is based on a prioritized belief negotiation model. Second, the knowledge bases obtained by the first step are combined using a conjunctive operator which may have a reinforcement effect in possibilistic logic.

A new Jacobian matrix for optimal learning of single-layer neural networks

This paper investigates the learning of a wide class of single-hidden-layer feedforward neural networks (SLFNs) with two sets of adjustable parameters, i.e., the nonlinear parameters in the hidden nodes and the linear output weights. The main objective is to both speed up the convergence of second-order learning algorithms such as Levenberg-Marquardt (LM), as well as to improve the network performance. This is achieved here by reducing the dimension of the solution space and by introducing a new Jacobian matrix. Unlike conventional supervised learning methods which optimize these two sets of parameters simultaneously, the linear output weights are first converted into dependent parameters, thereby removing the need for their explicit computation. Consequently, the neural network (NN) learning is performed over a solution space of reduced dimension. A new Jacobian matrix is then proposed for use with the popular second-order learning methods in order to achieve a more accurate approximation of the cost function. The efficacy of the proposed method is shown through an analysis of the computational complexity and by presenting simulation results from four different examples.

A recursive rule base adjustment algorithm for a fuzzy logic controller

This paper introduces a recursive rule base adjustment to enhance the performance of fuzzy logic controllers. Here the fuzzy controller is constructed on the basis of a decision table (DT), relying on membership functions and fuzzy rules that incorporate heuristic knowledge and operator experience. If the controller performance is not satisfactory, it has previously been suggested that the rule base be altered by combined tuning of membership functions and controller scaling factors. The alternative approach proposed here entails alteration of the fuzzy rule base. The recursive rule base adjustment algorithm proposed in this paper has the benefit that it is computationally more efficient for the generation of a DT, and advantage for online realization. Simulation results are presented to support this thesis. (c) 2005 Elsevier B.V. All rights reserved.

TDM modelling and evaluation of different domain transforms for LSI

Latent semantic indexing (LSI) is a popular technique used in information retrieval (IR) applications. This paper presents a novel evaluation strategy based on the use of image processing tools. The authors evaluate the use of the discrete cosine transform (DCT) and Cohen Daubechies Feauveau 9/7 (CDF 9/7) wavelet transform as a pre-processing step for the singular value decomposition (SVD) step of the LSI system. In addition, the effect of different threshold types on the search results is examined. The results show that accuracy can be increased by applying both transforms as a pre-processing step, with better performance for the hard-threshold function. The choice of the best threshold value is a key factor in the transform process. This paper also describes the most effective structure for the database to facilitate efficient searching in the LSI system.

Integrated structure selection and parameter optimisation for eng-genes neural models

The eng-genes concept involves the use of fundamental known system functions as activation functions in a neural model to create a 'grey-box' neural network. One of the main issues in eng-genes modelling is to produce a parsimonious model given a model construction criterion. The challenges are that (1) the eng-genes model in most cases is a heterogenous network consisting of more than one type of nonlinear basis functions, and each basis function may have different set of parameters to be optimised; (2) the number of hidden nodes has to be chosen based on a model selection criterion. This is a mixed integer hard problem and this paper investigates the use of a forward selection algorithm to optimise both the network structure and the parameters of the system-derived activation functions. Results are included from case studies performed on a simulated continuously stirred tank reactor process, and using actual data from a pH neutralisation plant. The resulting eng-genes networks demonstrate superior simulation performance and transparency over a range of network sizes when compared to conventional neural models. (c) 2007 Elsevier B.V. All rights reserved.