Virginie F. Ruiz

Investigation of support vector machine for the detection of architectural distortion in mammographic images

This paper investigates detection of architectural distortion in mammographic images using support vector machine. Hausdorff dimension is used to characterise the texture feature of mammographic images. Support vector machine, a learning machine based on statistical learning theory, is trained through supervised learning to detect architectural distortion. Compared to the Radial Basis Function neural networks, SVM produced more accurate classification results in distinguishing architectural distortion abnormality from normal breast parenchyma.

Resting tremor classification and detection in Parkinson's disease patients

Parkinson is a neurodegenerative disease, in which tremor is the main symptom. This paper investigates the use of different classification methods to identify tremors experienced by Parkinsonian patients. Some previous research has focussed tremor analysis on external body signals (e.g., electromyography, accelerometer signals, etc.). Our advantage is that we have access to sub-cortical data, which facilitates the applicability of the obtained results into real medical devices since we are dealing with brain signals directly. Local field potentials (LFP) were recorded in the subthalamic nucleus of 7 Parkinsonian patients through the implanted electrodes of a deep brain stimulation (DBS) device prior to its internalization. Measured LFP signals were preprocessed by means of splinting, down sampling, filtering, normalization and rectification. Then, feature extraction was conducted through a multi-level decomposition via a wavelet transform. Finally, artificial intelligence techniques were applied to feature selection, clustering of tremor types, and tremor detection. The key contribution of this paper is to present initial results which indicate, to a high degree of certainty, that there appear to be two distinct subgroups of patients within the group-1 of patients according to the Consensus Statement of the Movement Disorder Society on Tremor. Such results may well lead to different resultant treatments for the patients involved, depending on how their tremor has been classified. Moreover, we propose a new approach for demand driven stimulation, in which tremor detection is also based on the subtype of tremor the patient has. Applying this knowledge to the tremor detection problem, it can be concluded that the results improve when patient clustering is applied prior to detection.

Identifying tremor-related characteristics of basal ganglia nuclei during movement in the Parkinsonian patient

Local field potential (LFP) and Electromyographic (EMG) signals were recorded from 12 Parkinsonian patients with tremor-dominant symptoms as they performed passive and voluntary movements. The LFP signals were categorised into episodes of tremorous and atremorous activity (identified through EMG power spectra), then divided into delta (2-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), and beta (13-30 Hz) frequency bands. Modulation of LFP oscillatory activity in these frequency bands were compared between the subthalamic nucleus (STN) and the globus pallidus internus (GPi) to determine if differential tremor-related characteristics were identifiable for either target. Our results suggest that such local characteristic activity is identifiable in the STN, and thus could be a target for initial development of a closed-loop demand driven stimulator device which capitalises on such activity to trigger stimulation, even during voluntary movement activity.

An 8/spl times/8-block based motion estimation using Kalman filter

It is now quite common in the pel-recursive approaches for motion estimation, to find applications of the Kalman filtering technique both in time and frequency domains. In the block-based approach, very few approaches are available of this technique to refine the estimation of motion vectors resulting from fast algorithms such as the three step on a 16/spl times/16-block basis. This paper proposes an 8/spl times/8-block based motion estimation which uses the Kalman filtering technique to improve the motion estimates resulting from both the three step algorithm and the previous 16/spl times/16-block based Kalman application of Kuo et al. (1996). The state-space representation uses a first order auto-regressive model. Comparative results obtained for different classes of video sequences are presented.

Parkinsonian tremor identification with multiple local field potential feature classification.

This paper explores the development of multi-feature classification techniques used to identify tremor-related characteristics in the Parkinsonian patient. Local field potentials were recorded from the subthalamic nucleus and the globus pallidus internus of eight Parkinsonian patients through the implanted electrodes of a Deep brain stimulation (DBS) device prior to device internalization. A range of signal processing techniques were evaluated with respect to their tremor detection capability and used as inputs in a multi-feature neural network classifier to identify the activity of Parkinsonian tremor. The results of this study show that a trained multi-feature neural network is able, under certain conditions, to achieve excellent detection accuracy on patients unseen during training. Overall the tremor detection accuracy was mixed, although an accuracy of over 86% was achieved in four out of the eight patients.

Compensation of observability problem in a multi-robot localization scenario using CEKF

Many localization techniques today rely on absolute landmark measurements to efficiently track the robots position in space. Although absolute landmarks are essential for correctly estimating its position, they might be rare in an unknown environment. This means that the robot would have to traverse long distances without any outside reference point resulting in system degradation. In case of a robot team though, each robot can rely on both absolute or relative position measurements between robots. This paper describes an approach for a multi-robot localization system, based on a single centralized extended Kalman filter (CEKF) to track the position and orientation changes of a group of robots. Moreover, it is shown that if the robots in the group collect only relative measurements the system suffers from observability problem. It is proven that an increasing number of mobile robots capable of relative measurements only, reduces the observability problem and compensates for the need of external absolute landmarks thus providing efficient localization.

Robust classification of SAR imagery

In this work the G/sub A//sup 0/ distribution is assumed as the universal model for amplitude synthetic aperture radar (SAR) imagery data under the multiplicative model. The observed data, therefore, is assumed to obey a G/sub A//sup 0/ (/spl alpha/, /spl gamma/, n) law, where the parameter n is related to the speckle noise, and (/spl alpha/, /spl gamma/) are related to the ground truth, giving information about the background. Therefore, maps generated by the estimation of (/spl alpha/, /spl gamma/) in each coordinate can be used as the input for classification methods. Maximum likelihood estimators are derived and used to form estimated parameter maps. This estimation can be hampered by the presence of corner reflectors, man-made objects used to calibrate SAR images that produce large return values. In order to alleviate this contamination, robust (M) estimators are also derived for the universal model. Gaussian maximum likelihood classification is used to obtain maps using hard-to-deal-with simulated data, and the superiority of robust estimation is quantitatively assessed.

Experimental analysis of the Reynolds flocking model

The classic Reynolds flocking model is formally analysed, with results presented and discussed. Flocking behaviour was investigated through the development of two measurements of flocking, flock area and polarisation, with a view to applying the findings to robotic applications. Experiments varying the flocking simulation parameters individually and simultaneously provide new insight into the control of flock behaviour.

Identifying problematic classes in text classification

Real-world text classification tasks often suffer from poor class structure with many overlapping classes and blurred boundaries. Training data pooled from multiple sources tend to be inconsistent and contain erroneous labelling, leading to poor performance of standard text classifiers. The classification of health service products to specialized procurement classes is used to examine and quantify the extent of these problems. A novel method is presented to analyze the labelled data by selectively merging classes where there is not enough information for the classifier to distinguish them. Initial results show the method can identify the most problematic classes, which can be used either as a focus to improve the training data or to merge classes to increase confidence in the predicted results of the classifier.

Motion estimation through approximated densities

Many techniques are currently used for motion estimation. In the block-based approaches the most common procedure applied is the block-matching based on various algorithms. To refine the motion estimates resulting from the full search or any coarse search algorithm, one can find few applications of Kalman filtering, mainly in the intraframe scheme. The Kalman filtering technique applicability for block-based motion estimation is rather limited due to discontinuities in the dynamic behaviour of the motion vectors. Therefore, we propose an application of the concept of the filtering by approximated densities (FAD). The FAD, originally introduced to alleviate limitations due to conventional Kalman modelling, is applied to interframe block-motion estimation. This application uses a simple form of FAD involving statistical characteristics of multi-modal distributions up to second order.