Lykourgos Petropoulakis

Electrocardiogram (ECG) Biometric Authentication Using Pulse Active Ratio (PAR)

Biometric authentication is a one-to-one verification process. A successful biometric system must be capable of avoiding a fraudulent claim while at the same time ensuring the privacy of individuals. This paper presents a novel framework for using the electrocardiogram (ECG) as a biometric system for human authentication. A new feature extraction technique known as pulse active ratio (PAR) is derived and used to generate novel ECG feature vectors. The proposed method is validated by experiments on 112 subjects, performing 9800 ECG comparisons providing a 10% improvement when compared to conventional temporal and amplitude feature extraction methods.

Position control of flexible manipulator using non-linear H∞ with state-dependent Riccati equation

Abstract The paper is concerned with the control of the tip position of a single-link flexible manipulator. The non-linear model of the manipulator is derived and tested, assuming the number of model shape functions to be two. It is known that the assumed modes method introduces uncertainty to the model by neglecting higher-order dynamics. There are other sources of uncertainty, such as friction. In addition, the model is non-linear. Therefore, for the next task, which is the controller design, the H∞ approach is proposed to deal efficiently with uncertainties, and the non-linear nature of the problem is addressed by the use of the state-dependent Riccati equation (SDRE) technique. Following the SDRE approach, the state-feedback non-linear control law is derived, which minimizes a quadratic cost function. This solution is then mapped into the H∞ optimization problem. The resulting control law has been tested with the simulation model of the flexible manipulator and the results are discussed in the paper.

Wavelet based motion artifact removal for ECG signals

Motion artifact noise in ECG processing is difficult to remove since its spectrum is known to overlap the ECG signal spectrum. The combination of wavelet based denoising and high-pass/low-pass filtering is presented and shown to provide good motion artifact noise removal capabilities. The relative performance of the new technique is demonstrated using ECGs from the MIT-BIH ECG database.

ECG biometric authentication using Pulse Active Width (PAW)

This paper presents a new feature extraction method known as Pulse Active Width (PAW) implemented on electrocardiogram (ECG) for biometric authentication. This method is developed based on the concept of Pulse Width Modulation (PWM). A total of 196 ECGs from 98 subjects, taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in the simulations. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are then used to evaluate the results. It is shown that the PAW method outperforms conventional temporal feature extraction techniques.

Identification of Contaminant Type in Surface Electromyography (EMG) Signals

The ability to recognize various forms of contaminants in surface electromyography (EMG) signals and to ascertain the overall quality of such signals is important in many EMG-enabled rehabilitation systems. In this paper, new methods for the automatic identification of commonly occurring contaminant types in surface EMG signals are presented. Such methods are advantageous because the contaminant type is typically not known in advance. The presented approach uses support vector machines as the main classification system. Both simulated and real EMG signals are used to assess the performance of the methods. The contaminants considered include: 1) electrocardiogram interference; 2) motion artifact; 3) power line interference; 4) amplifier saturation; and 5) additive white Gaussian noise. Results show that the contaminants can readily be distinguished at lower signal to noise ratios, with a growing degree of confusion at higher signal to noise ratios, where their effects on signal quality are less significant.

WebClass: software to web-enable MATLAB for collaborative use

The paper describes the work carried out in Strathclyde University to web-enable MATLAB, a commonly used package in engineering applications, for Internet-based distance co-working and collaboration with full sharing functionality by all users and at all times. The software was developed with platform-independence in mind and has undergone several updates. Additional software to enhance functionality is still being developed and integrated into the original system. The paper provides an overview of the development known as WebClass.

Multi-classify Hybrid Multilayered Perceptron (HMLP) Network for Pattern Recognition Applications

This paper introduces a Hybrid Multilayered Perceptron (HMLP) based classifier known as the Multi-Classify HMLP network (MCHMLP). This network is shown to be able to enhance the performance accuracy when compared to the conventional HMLP network. The Multi-Classify HMLP network architecture is trained using a Modified Recursive Prediction Error (MRPE). This study uses three benchmark datasets in order to measure the capability of the network. The results show that the proposed Multi-Classify HMLP network provides a significant improvement over the conventional HMLP network for pattern recognition applications.

A hybrid simulation system for manufacturing processes

Describes the motivation, the initial implementation and tests carried out during the development of a combined discrete‐time and continuous‐simulation system intended primarily for the simulation of hybrid systems in manufacturing processes. The system, which is still under development, is the product of fusing two existing and independently developed packages, and the current implementation serves as a pilot design for evaluating the issues involved, both in terms of product development and in terms of the theoretical difficulties in combining discrete‐event and continuous‐time systems. The initial design has already been implemented and test simulations performed. Provides a superficial description of the system interface which is predominantly based on the existing interface of the discrete‐event simulator.

Design and development of a general purpose collaborative environment

This paper presents a system that allows any legacy computer application to be used for collaborative work over internet or wireless connections. The applicability of the system is wide and encompasses all aspects of engineering, education, manufacturing and general use. A recent report concerning the use of collaborative software worldwide, indicates that collaboration will expand and grow at a fast pace in the next few years. The development presented here has been specifically designed to address these needs in a flexible, expandable and generic manner. The product has a modular structure, which we view as essential for providing collaborative capability to applications, since it allows developers and users the ability to customise the system for individual needs.

Intelligent control using agents and fuzzy behavioural structures

The paper describes the use of agents and fuzzy behavioural structures as the basis for a hierarchical intelligent control system designed for systems operating in semi-structured environments. The paper reviews the current theories of robot control, fuzzy logic and behavioural control and proposes a structure of agents and fuzzy behaviours as an alternative system aiming at addressing issues arising from the required speed of processing, coping with partial environmental abstraction and the demands for robust control. The paper also examines some of the advantages of this approach compared to existing techniques and illustrates how the method operates in some typical applications.