Position-sensing technologies for movement analysis in stroke rehabilitation.

Research has focused on improvement of the quality of life of stroke patients. Gait detection, kinematics and kinetics analysis, home-based rehabilitation and telerehabilitation are the areas where there has been increasing research interest. The paper reviews position-sensing technologies and their application for human movement tracking and stroke rehabilitation. The review suggests that it is feasible to build a home-based telerehabilitation system for sensing and tracking the motion of stroke patients.

Towards a web-based knowledge management system for cardiovascular disease.

The objective of this paper is to examine the efficacy of the Knowledge Management (KM) paradigm for a web-based patient administration system (PAS) for cardiovascular disease (CVD). We discuss the role of contemporary information and communication technologies (ICTs) for the management of electrocardiographic information and how this can act as a foundation for a KM-based system.

Perceptual time-frequency subtraction algorithm for noise reduction in hearing aids.

Sensorineural hearing disorders are a major and universal community health problem. In many cases, hearing aids offer the only solution for people suffering from such disorders. Unfortunately existing aids do not provide any improvement in intelligibility of the signal when background noise is present. A hearing aid system should ideally simulate auditory processes including those aspects of the speech signal that are perceptually important. This work presents a new integrated approach to the design of a digital hearing aid, based on a wavelet transform, as well as a formulation of the temporal and spectral psychoacoustic model of masking. Within the model, the Perceptual Time-Frequency Subtraction (PTFS) algorithm is developed to simulate the masking phenomena and reduce noise in single-input systems. Results show that the use of the PTFS yields a significant improvement in speech quality especially in unvoiced portions. Additionally, the noise component during periods of silence has been attenuated by up to 20 dB. This new noise reduction method is expected to be applicable in a variety of applications, including digital hearing aids and portable communication systems (e.g., cellular telephones).

Feature and classifier fusion for 12-lead ECG classification.

Two methodologies, feature and classifier fusion, for the problem of computerized 12-lead electrocardiogram classification, are investigated. Firstly, the entire classification problem is subdivided into a number of smaller bi-dimensional ones. By employing bi-group Neural Network classifiers, independent feature vectors for each diagnostic class are examined individually and the output from each classifier are fused together to produce one single result. Secondly, two classifiers, namely the aforementioned and a decision tree, are fused together through a novel approach of a Specificity Matrix. This methodology addresses the problem of unresolved conflict during fusion of classifiers and aims to exploit the merits of each classifier and suppress their weaknesses. 290 validated 12-lead electrocardiogram recordings, comprising six diagnostic classes, were used to train, validate and test both methodologies. The framework of bi-group classifiers enhanced the overall performance by 12.0% in comparison with conventional approaches. In the second instance, the fusion of the two classifiers produced a performance level of 81.3%; superior to either classifier in isolation. This approach offers a viable solution to the unresolved problem of conflict between classifiers during fusion and can be extended readily to accommodate any number of diagnostic classes and classifiers.

An intelligent framework for the classification of the 12-lead ECG.

An intelligent framework has been proposed to classify an unknown 12-Lead electrocardiogram into one of a possible number of mutually exclusive and combined diagnostic classes. The framework segregates the classification problem into a number of bi-dimensional classification problems, requiring individual bi-group classifiers for each individual diagnostic class. The bi-group classifiers were generated employing Neural Networks (NN), combined with a combination framework containing an Evidential Reasoning framework to accommodate for any conflicting situations between the bi-group classifiers. A number of different feature selection techniques were investigated with the aim of generating the most appropriate input vector for the bi-group classifiers. It was found that by reducing the original input feature vector, the generalisation ability of the classifiers, when exposed to unseen data, was enhanced and subsequently this reduced the computational requirements of the network itself. The entire framework was compared with a conventional approach to NN classification and a rule based classification approach. The framework attained a significantly higher level of classification in comparison with the other methods; 80.0% compared with 66.7% for the rule based technique and 68.00% for the conventional neural approach.

Computerised electrocardiology employing bi-group neural networks.

A configuration of bi-group neural networks (BGNN) is proposed combined with an evidential reasoning framework to interpret 12-lead electrocardiograms for three mutually exclusive classes. A number of pre-processing feature selection techniques were investigated prior to application of the input feature vector to each individual BGNN. The network outputs were discounted within a belief interval of 1 based on their performance on test data prior to combination. It was found that the application of the feature selection techniques enhanced the individual performance of the BGNN, and subsequently enhanced the overall performance. The proposed framework was compared with conventional classification techniques of multi-output neural networks and linear multiple regression. The framework attained a higher level of classification in comparison with the other methods; 70.4% compared with 66.7% for both multi-output neural and statistical techniques.

Information issues in telemedicine systems.

This paper examines the use of the Integrated Services Digital Network (ISDN) for telemedicine from the computer scientist's point of view. As increased bandwidth becomes available at reasonable cost, it becomes possible to employ graphical user interfaces in telemedicine systems. This means that human-computer interaction (HCI) techniques can be applied to the interface design. This paper describes some of these as applied to telemedicine by other authors. HCI techniques can be considered to be part of the development process of telemedicine systems. An integrated, multimedia-based telemedicine system which emulated the concept of a hospital information system would have many benefits, such as a consistent user interface with appropriate clinical metaphors, integrated patient records with facilities to store graphical information, and remote access. Telemedicine has much to offer in terms of providing higher standards of patient care through improved response times by clinicians who have the required information immediately available. The patient also benefits from convenience factors, such as being able to consult locally a remote specialist.

Acoustic analysis of infantile stridor: a review.

The review compares five methods that utilise electronic/computer acoustic processing techniques for the analysis of infantile stridor sounds. The first method uses traditional spectrographic techniques to produce time/frequency/intensity three-dimensional representation of the waveform. The second method is computer-based and uses the fast Fourier transformation (FFT) to show the frequency composition of the waveform. The third uses linear prediction coefficients (LPCs) to produce a power spectrum and inverse filtering to estimate the cross-sectional area of the human upper airway. The fourth technique employs a proprietary digital filterbank to analyse normal infant vocalisations, which may be used as a control by subsequent researchers. In the fifth method, a physiologically based digital filterbank, designed to closely model the human ear response, is proposed. It is envisaged that this approach will offer the flexibility of all the previous techniques and also closely model the analysis procedure carried out using subjective auscultation. It is concluded that none of the above techniques are sufficiently robust to provide unambiguous diagnosis of stridor type and that a reappraisal is required in terms of feature extraction so that relevant features can be identified. To this end, the authors propose that a physiologically based model of the human airway, including the vocal cords, be developed as an aid to the assessment of acoustic features.