Tshilidzi Marwala

The use of genetic algorithms and neural networks to approximate missing data in database

Missing data creates various problems in analysing and processing data in databases. In this paper we introduce a new method aimed at approximating missing data in a database using a combination of genetic algorithms and neural networks. The proposed method uses genetic algorithm to minimise an error function derived from an auto-associative neural network. Multi-layer perceptron (MLP) and radial basis function (RBF) networks are employed to train the neural networks. Our focus also lies on the investigation of using the proposed method in accurately predicting missing data as the number of missing cases within a single record increases. It is observed that there is no significant reduction in accuracy of results as the number of missing cases in a single record increases. It is also found that results obtained using RBF are superior to MLP.

Water Demand Prediction using Artificial Neural Networks and Support Vector Regression

Computational Intelligence techniques have been proposed as an efficient tool for modeling and forecasting in recent years and in various applications. Water is a basic need and as a result, water supply entities have the responsibility to supply clean and safe water at the rate required by the consumer. It is therefore necessary to implement mechanisms and systems that can be employed to predict both short-term and long-term water demands. The increasingly growing field of computational intelligence techniques has been proposed as an efficient tool in the modeling of dynamic phenomena. The primary objective of this paper is to compare the efficiency of two computational intelligence techniques in water demand forecasting. The techniques under comparison are Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs). In this study it was observed that ANNs perform significantly better than SVMs. This performance is measured against the generalization ability of the two techniques in water demand prediction.

Multiple-criterion method for determining structural damage

A new multiple-criterion updating method that minimizes the Euclidean norm of the error vector obtained by adding the normalized eigenproblem equation and equation of motion with equal weighting functions is proposed. The method is applied to detecting damage in structures and is tested on an unsymmetrical H-shaped structure. It is found that the multiple-criterion updating method predicts the presence, the position, and the extent of damage. The multiple-criterion method is compared to the frequency-response function method and the modal property-based method by using the coordinate modal assurance criterion and the modal assurance criterion. The multiple-criterion method was found to give better results than the other two methods. This is because it was better able to detect damage on the structure than the modal property method (which failed to detect multiple-damage cases) and gave results that were less noisy, i.e., less updating to undamaged elements, than the frequency-response method.

Physico-chemical, Tensile, and Thermal Characterization of Napier Grass (Native African) Fiber Strands

This article presents the extraction and effect of alkali treatment on the physical, chemical, tensile, and thermal characteristics of fiber strands obtained from Napier grass, a renewable biomass. In order to improve these properties, the Napier grass fiber strands were treated with sodium hydroxide. The alkali treatment was carried out using NaOH solution at three different concentrations (5, 10, and 15%) for 2 h. Characterization of untreated and alkali-treated Napier grass fiber strands was carried out by studying the chemical composition, surface morphology, functional group variation, crystallinity, and tensile and thermal behavior. It was found that untreated fiber strands have lower cellulose content, crystallinity, tensile properties, and thermal stability than alkali-treated fiber strands. Napier grass fiber strands treated with 10% NaOH showed optimum tensile strength, modulus, and percentage elongation with an improvement of 51.9, 47.3, and 12.1% respectively. Based on the properties determined for alkali-treated Napier grass fiber strands, we expect that these fibers will be suitable for use as a reinforcement in natural fiber composites.

Bayesian training of neural networks using genetic programming

Bayesian neural network trained using Markov chain Monte Carlo (MCMC) and genetic programming in binary space within Metropolis framework is proposed. The algorithm proposed here has the ability to learn using samples obtained from previous steps merged using concepts of natural evolution which include mutation, crossover and reproduction. The reproduction function is the Metropolis framework and binary mutation as well as simple crossover, are also used. The proposed algorithm is tested on simulated function, an artificial taster using measured data as well as condition monitoring of structures and the results are compared to those of a classical MCMC method. Results confirm that Bayesian neural networks trained using genetic programming offers better performance and efficiency than the classical approach.

Artificial Neural Networks and Support Vector Machines for water demand time series forecasting

Water plays a pivotal role in many physical processes, and most importantly in sustaining human life, animal life and plant life. Water supply entities therefore have the responsibility to supply clean and safe water at the rate required by the consumer. It is therefore necessary to implement mechanisms and systems that can be employed to predict both short-term and long-term water demands. The increasingly growing field of computational intelligence techniques has been proposed as an efficient tool in the modelling of dynamic phenomena. The primary objective of this paper is to compare the efficiency of two computational intelligence techniques in water demand forecasting. The techniques under comparison are Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs). In this study it was observed that ANNs perform better than SVMs. This performance is measured against the generalisation ability of the two.

A dynamic programming approach to missing data estimation using neural networks

This paper develops and presents a novel technique for missing data estimation using a combination of dynamic programming, neural networks and genetic algorithms (GA) on suitable subsets of the input data. The method proposed here is well suited for decision making processes and uses the concept of optimality and the Bellmans equation to estimate the missing data. The proposed approach is applied to an HIV/AIDS database and the results shows that the proposed method significantly outperforms a similar method where dynamic programming is not used. This paper also suggests a different way of formulating a missing data problem such that the dynamic programming is applicable to estimate the missing data.

Probabilistic Fault Identification Using a Committee of Neural Networks and Vibration Data

Bayesian-formulated neural network architecture is implemented using a hybrid Monte Carlo method for probabilistic fault identification in a population of ten nominally identical cylindrical shells using vibration data. Each cylinder is divided into three substructures. Holes of 12 mm in diameter are introduced in each of the substructures. Vibration data are measured by impacting the cylinders at selected positions using a modal hammer and measuring the acceleration responses at a fixed position. Modal energies, defined as the integrals of the real and imaginary components of the frequency response function over 12-Hz frequency bandwidths, are extracted and transformed into the coordinate modal energy assurance criterion. This criterion and the identity of faults are used to train the frequency response function (FRF) neural network. Modal analysis is then employed to identify modal properties. Mode shapes are transformed into the coordinate modal assurance criterion. The natural frequencies and the coordinate modal assurance criterion, as well as the identities of faults, are utilized to train the modal-property neural network. The weighted average of the modal-property network and the FRF network form a committee of two networks. The committee approach is observed to give lower mean square errors and standard deviations (thus, a higher probability of giving the correct solution) than the individual methods. This approach gives accurate identities of damage and their respective confidence intervals while requiring affordable computational resources.

Hidden Markov Models and Gaussian Mixture Models for Bearing Fault Detection Using Fractals

Bearing vibration signals features are extracted using time domain fractal based feature extraction technique. This technique uses multi-scale fractal dimension (MFD) estimated using box-counting dimension. The extracted features are then used to classify faults using Gaussian mixture models (GMM) and hidden Markov models (HMM). The results obtained show that the proposed feature extraction technique does extract fault specific information. Furthermore, the experimentation shows that HMM outperforms GMM. However, the disadvantage of HMM is that it is computationally expensive to train compared to GMM. It is therefore concluded that the proposed framework gives enormous improvement to the performance of the bearing fault detection and diagnosis, but it is recommended to use the GMM classifier when time is the major issue.

Agent-based modelling: a case study in HIV epidemic

This research presents an agent-based, bottom-up modelling approach to develop a simulation tool for estimating and predicting the spread of the human immunodeficiency virus (HIV) in a given population. HIV is mainly a sexually transmitted disease (STD) causing a serious problem to human health. The virus is transmitted from an infected person to another who was previously healthy through different biological, social and environmental factors. The research develops the simulation tool by modelling these factors by agents. Although research has and is being conducted to estimate and predict the spread of the HIV epidemic, the proposed research seeks to investigate the spread using a different approach. The previous models used a top-down modelling approach. They are built from the general characteristics and behaviours of the population. They have not explored the potential use of agent technology. This research attempts to investigate the flexibility that the multi-agent system offers. Agent-based models are close to the situations that exist in a given real system that consists of autonomous components interacting with each other. The modelling approach has the advantage of observing the interaction made between agents, which is a difficult task in the top-down modelling approach. The research investigates the performance of the tool and presents the first results obtained.