M. Morando

An Adaptive Momentum Back Propagation (AMBP)

An algorithm for fast minimum search is proposed, which achieves very satisfying performance harmonising the Vogls and the Conjugate Gradient algorithms. Such effectiveness is achieved by making adaptive, in a very simple and satisfactory way, both the learning rate and the momentum term, and by executing controls and corrections both on the possible cost function increase and on moves opposite to the direction of the negative of the gradient. Thanks to these improvements, we can obtain a good scaling relationship in learning. As regards the real world context, a musical application showed favourable results: besides the good convergence speed, a high generalisation capability has been achieved, as confirmed both by subjective musical evaluations and by objective tests.

GROWING UP: EMERGING COMPLEXITY IN LIVING BEING

ABSTRACT Biological systems live and grow. Many aspects are inherent to the concept of living, such as the adaptation, the interaction with the environment, and the ability to deal with limited resources. Living systems present multiple levels of organization, with elements at one level interacting and aggregating to create more complex behavior at a higher level. In recent years, many new techniques used to investigate the spatio-temporal activity in living being have demonstrated the presence of features common to the behavior of self organizing dynamical systems. Thus a question arises: Is this chaos useful to model living beings? The answer is very difficult to find. Many experimental data support the dynamic chaotic modelling of living systems. Complex behaviors such as perceiving, intending, acting, learning, and remembering arise as metastable spatio-temporal patterns of brain activity that are themselves produced by the cooperative interactions among neural clusters. In this article we present and discuss that question, and we try to give indication for a possible answer, with the aim of defining the basic features of a behavioral kernel for living artefacts.

Neural network for automatic anomalous QRS complex detection

An application of the back-propagation (BP) neural network (NN) for the discrimination between normal and pathological electrocardiogram (ECG) complexes is presented. The BP is used as a part of an unsupervised method: the network output has not been used to discriminate normal and pathological complexes, but only to extract the prototype complex of the analyzed ECG. An attempt is made to automatically individualize a pathological QRS morphology on those ECGs where anomalous premature ventricular contraction (PVC) beats were less than 15%. Results show a sensitivity of 0.991 and a specificity of 0.985.<<ETX>>

Study on the influence of a noisy environment on the ECG correlation dimension determination; possible use for noise estimation

It is shown how the determination of the correlation dimension (D/sub 2/), an algorithm which allows the estimation of a nonlinear system degrees of freedom, is affected by the presence of noise. The poor accuracy in computing D/sub 2/ is related to the noise fraction of the signal measurement. A very simple empirical way to adjust the D/sub 2/ value is presented. Some preliminary results on a rough way for the noise fraction estimation are given. This study has been done mainly on a Henon attractor, and D/sub 2/ adjustments have been tried on electrocardiogram (ECG) signals, yielding D/sub 2/ values ranging between 1 and 2, in healthy subjects.<<ETX>>

An Integrated Approach to the Well-Being of the Elderly People at Home

The paper presents the outline and the preliminary developments of NINFA (iNtelligent Integrated Network For Aged people), a project for the well-being of the elderly people at home. This architecture is based on a service platform suited for elder people called the Virtual Village Network, whose user interface allows to deliver different services at home, namely: user supervision, communication and interaction among users for social inclusion, exergame delivering, monitoring of the wellness status. After the discussion of some results of the investigation on the acceptability issues of the ICT technologies related to the project, the User Interface (UI) and the novel Human Computer Interface (HCI) have been developed. The HCI is particularly suited for elderly people and motor impaired patients because the interaction is managed only by finger/hand gestures and by vocal control through simple commands. A set of preliminary exergames developed for the user training and monitoring are presented. During the exergame execution, the user interface allows the real-time acquisition of a set of motor, linguistic and cognitive parameters related to the user performance. The analysis of the verbal production of each subject is used to observe its language evolution and to detect the onset of any cognitive deficit. The relationship between some parameters and the neurological/wellness status of the user is discussed.

Methods for intracardiac electrogram compression suitable with implantable devices

Studies methods for intracardiac electrogram compression that are suitable for implementation in implantable devices. The algorithms are based on piecewise linear approximation (PLA) methods and beat detection (the peak method). Intracardiac electrograms were obtained, from the right atrium and ventricle, during electrophysiological studies. The total atrial set consists of 5060 s of bipolar recordings and 680 s of unipolar electrograms; the ventricular data set contains 1210 s of bipolar and 480 s of unipolar signals. The peak method clearly performs better than the others to compress bipolar signals, while PLA methods are needed in order to have reliably compressed unipolar data. Performances over the whole bipolar database (including atrial and ventricular sets) reached an average compression ratio (CR) of 7.6, while first-order piecewise linear approximation on unipolar electrograms reached CR=6.6. These preliminary results show that time consumption can be reduced suitably with real-time compression for implantable devices. The ability to compress and store intracardiac electrograms in implantable devices allows detailed verification of appropriate intervention of the device and it might open up new perspectives in the study of the mechanisms involved in the onset of malignant tachyarrhythmias.

A new method for fibrillation detection from endocardial electrograms

A new approach is presented for automatic efficient detection of atrial fibrillation not based on heart rate, but on morphologic analysis of the electrogram. Endocardiac signals have been collected from 9 patients (4 of them affected by chronic atrial fibrillation and 5 affected by other disturbances of the rhythm) during human cardiac electrophysiologic (EP) studies using a Manta Mennen Poligraph and cut into short intervals of different duration (from 0.5 to 20 seconds). 1018 seconds of sinus rhythm (SR) and 726 seconds of atrial fibrillation (AF) have been analyzed. Then the authors divided all segments in two separate groups: the training group to define appropriate discrimination threshold and the test group to quantify results. Results for the 4-seconds decision time show 94 and 96 values of 94 The method is straightforward and compatible with implantable devices (easy implementation and real time).

Caltech Hypercube MIMD Computer Performances Measurements in a Physical Mathematical Application

A Caltech Hypercube has been characterized using known methods to obtain performance figures from a MIMD computer. Speed-up, efficiency and communication cost have been evaluated versus the number of used processors and the physical problem dimensions.

Complex dielectric constants of human sera protein-bound water behaviour in bowel cancer patients

Abstract The complex dielectric constants of human sera have been measured in the frequency range 50–1000 MHz using a Hewlett-Packard 4191A RF Impedance Analyzer. The properties of water bound to the proteins are investigated and the implications to the pathological conditions of the subjects are studied. The proteins from cancer patients are significantly more hydrated than normal ones. This is particularly noticeable for gamma-globulins, thus suggesting an immunological defect in cancer patients.