Vassilis Kodogiannis

EEG Signal Classification Using Wavelet Feature Extraction and Neural Networks

Decision support systems have been utilised since 1960, providing physicians with fast and accurate means towards more accurate diagnoses and increased tolerance when handling missing or incomplete data. This paper describes the application of neural network models for classification of electroencephalogram (EEG) signals. Decision making was performed in two stages: initially, a feature extraction scheme using the wavelet transform (WT) has been applied and then a learning-based algorithm classifier performed the classification. The performance of the neural model was evaluated in terms of training performance and classification accuracies and the results confirmed that the proposed scheme has potential in classifying the EEG signals

Forecasting Financial Time Series using Neural Network and Fuzzy System-based Techniques

Forecasting currency exchange rates are an important financial problem that is receiving increasing attention, especially because of its intrinsic difficulty and practical applications. During the last few years, a number of nonlinear models have been proposed for obtaining accurate prediction results, in an attempt to ameliorate the performance of the traditional linear approaches. Among them, neural network models have been used with encouraging results. This paper presents improved neural network and fuzzy models used for exchange rate prediction. Several approaches, including multi-layer perceptions, radial basis functions, dynamic neural networks and neuro-fuzzy systems, have been proposed and discussed. Their performances for one-step and multiple step ahead predictions have been evaluated through a study, using real exchange daily rate values of the US Dollar vs. British Pound.

Artificial Odor Discrimination System Using Electronic Nose and Neural Networks for the Identification of Urinary Tract Infection

Current clinical diagnostics are based on biochemical, immunological, or microbiological methods. However, these methods are operator dependent, time-consuming, expensive, and require special skills, and are therefore, not suitable for point-of-care testing. Recent developments in gas-sensing technology and pattern recognition methods make electronic nose technology an interesting alternative for medical point-of-care devices. An electronic nose has been used to detect urinary tract infection from 45 suspected cases that were sent for analysis in a U.K. Public Health Registry. These samples were analyzed by incubation in a volatile generation test tube system for 4-5 h. Two issues are being addressed, including the implementation of an advanced neural network, based on a modified expectation maximization scheme that incorporates a dynamic structure methodology and the concept of a fusion of multiple classifiers dedicated to specific feature parameters. This study has shown the potential for early detection of microbial contaminants in urine samples using electronic nose technology.

A neuro-fuzzy-based system for detecting abnormal patterns in wireless-capsule endoscopic images

Wireless capsule endoscopy (WCE) constitutes a recent technology in which a capsule with micro-camera attached to it, is swallowed by the patient. This paper presents an integrated methodology for detecting abnormal patterns in WCE images. Two issues are being addressed, including the extraction of texture features from the texture spectra in the chromatic and achromatic domains from each colour component histogram of WCE images and the concept of a fusion of multiple classifiers. The implementation of an advanced neuro-fuzzy learning scheme has been also adopted in this paper. The high detection accuracy of the proposed system provides thus an indication that such intelligent schemes could be used as a supplementary diagnostic tool in WCE.

The usage of soft-computing methodologies in interpreting capsule endoscopy

Computerised processing of medical images can ease the search of the representative features in the images. The endoscopic images possess rich information expressed by texture and regions affected by diseases, such as ulcer or coli, may have different texture features. In this paper schemes have been developed to extract features from the texture spectra in the chromatic and achromatic domains for a selected region of interest from each colour component histogram of images acquired by the M2A Swallowable Imaging Capsule. The implementation of neural network schemes and the concept of fusion of multiple classifiers have been also adopted in this paper. The preliminary test results support the feasibility of the proposed method.

A study of advanced learning algorithms for short-term load forecasting

Neural networks are currently finding practical applications, ranging from ‘soft’ regulatory control in consumer products, to the accurate modelling of nonlinear systems. This paper presents the development of improved neural-network-based short-term electric load forecasting models for the power system of the Greek island of Crete. Several approaches, including radial basis function networks, dynamic neural networks and fuzzy-neural-type networks, have been proposed, and are discussed in this paper. Their performances are evaluated through a simulation study, using metered data provided by the Greek Public Power Corporation. The results indicate that the load-forecasting models developed in this way provide more accurate forecasts, compared with conventional backpropagation network forecasting models. Finally, the embedding of the new model capability in a modular forecasting system is presented.

Neural Network Modelling and Control for Underwater Vehicles

Neural networks are currently finding practical applications ranging from ‘soft’ regulatory control in consumer products to accurate control of non-linear plant in the process industries. This paper describes the application of neural networks to modelling and control of a prototype underwater vehicle, as an example of a system containing severe non-linearities. The most common implementation strategy for neural control is model predictive control, where a model of the process is developed first and is used off-line to design an appropriate compensator. The accuracy and robustness of this control strategy relies on the quality of the non-linear process model, in particular its ability to predict the plant response accurately multiple-steps ahead. In this paper, several neural network architectures are used to evaluate a long-range model predictive control structure, both in simulation and for on-line control of vehicle depth, achieving accurate control with a smooth actuator signal.

The use of gas-sensor arrays to diagnose urinary tract infections.

Sensorial analysis based on the utilisation of human senses, is one of the most important and straightforward investigation methods in food and chemical analysis. An electronic nose has been used to detect in vivo Urinary Tract Infections from 45 suspected cases that were sent for analysis in a UK Health Laboratory environment. These samples were analysed by incubation in a volatile generation test tube system for 4-5 h. The volatile production patterns were then analysed using an electronic nose system with 14 conducting polymer sensors. An intelligent model consisting of an odour generation mechanism, rapid volatile delivery and recovery system, and a classifier system based on learning techniques has been considered. The implementation of an Extended Normalised Radial Basis Function network with advanced features for determining its size and parameters and the concept of fusion of multiple classifiers dedicated to specific feature parameters has been also adopted in this study. The proposed scheme achieved a very high classification rate of the testing dataset, demonstrating in this way the efficiency of the proposed scheme compared with other approaches. This study has shown the potential for early detection of microbial contaminants in urine samples using electronic nose technology.

Computer-aided diagnosis in clinical endoscopy using neuro-fuzzy systems

An innovative detection system to support medical diagnosis and detection of abnormal lesions by processing endoscopic images is presented. The images used in this study have been obtained using the new M2A swallowable imaging capsule - a patented, video colour-imaging disposable capsule. Schemes have been developed to extract new texture features from the texture spectra in the chromatic and achromatic domains for a selected region of interest from each colour component histogram of endoscopic images. The implementation of an advanced fuzzy inference neural network which combines fuzzy systems and artificial neural networks and the concept of fusion of multiple classifiers dedicated to specific feature parameters have been also adopted in this paper. The detection accuracy of the proposed system has reached to 100%, providing thus an indication that such intelligent schemes could be used as a supplementary diagnostic tool in endoscopy.

Data Mining an EEG Dataset With an Emphasis on Dimensionality Reduction

The human brain is obviously a complex system, and exhibits rich spatiotemporal dynamics. Among the non-invasive techniques for probing human brain dynamics, electroencephalography (EEG) provides a direct measure of cortical activity with millisecond temporal resolution. Early attempts to analyse EEG data relied on visual inspection of EEG records. Since the introduction of EEG recordings, the volume of data generated from a study involving a single patient has increased exponentially. Therefore, automation based on pattern classification techniques have been applied with considerable success. In this study, a multi-step approach for the classification of EEG signal has been adopted. We have analysed sets of EEG time series recording from healthy volunteers with open eyes and intracranial EEG recordings from patients with epilepsy during ictal (seizure) periods. In the present work, we have employed a discrete wavelet transform to the EEG data in order to extract temporal information in the form of changes in the frequency domain over time - that is they are able to extract non-stationary signals embedded in the noisy background of the human brain. Principal components analysis (PCA) and rough sets have been used to reduce the data dimensionality. A multi-classifier scheme consists of LVQ2.1 neural networks have been developed for the classification task. The experimental results validated the proposed methodology