Costas Neocleous

Classification capacity of a modular neural network implementing neurally inspired architecture and training rules

A three-layer neural network (NN) with novel adaptive architecture has been developed. The hidden layer of the network consists of slabs of single neuron models, where neurons within a slab-but not between slabs- have the same type of activation function. The network activation functions in all three layers have adaptable parameters. The network was trained using a biologically inspired, guided-annealing learning rule on a variety of medical data. Good training/testing classification performance was obtained on all data sets tested. The performance achieved was comparable to that of SVM classifiers. It was shown that the adaptive network architecture, inspired from the modular organization often encountered in the mammalian cerebral cortex, can benefit classification performance.

Neural networks to estimate the risk for preeclampsia occurrence

A number of neural network schemes have been applied to a large data base of pregnant women, aiming at generating a predictor for the estimation of the risk of occurrence of preeclampsia at an early stage. The database was composed of 6838 cases of pregnant women in UK, provided by the Harris Birthright Research Centre for Fetal Medicine in London. For each subject, 24 parameters were measured or recorded. Out of these, 15 parameters were considered as the most influencing at characterizing the risk of preeclampsia occurrence. A number of feedforward neural structures, both standard multi-layer and multi-slab, were tried for the prediction. The best results obtained were with a multi-slab neural structure. In the training set there was a correct classification of the 83.6% cases of preeclampsia and in the test set 93.8%. The preeclampsia cases prediction for the totally unknown verification test was 100%.

Selective Attention and Consciousness: Investigating Their Relation Through Computational Modelling

The present study aimed at investigating the possible connection between conscious awareness and attention through the implementation of a neurocomputational model of visual selective attention. The development of the model was based on recent neurophysiological findings that document the synchronization of neural activity in cortical areas of the brain and the presence of competitive interactions among stimuli at the early stages of visual processing. The model was used to simulate the findings of a behavioural experiment conducted by Naccache et al. in Psychol Sci 13:416–424 (2002), which have sparked a debate on the possible links between attention and consciousness. The model reproduced closely the pattern of the behavioural data while incorporating mechanisms that take into account the neural activity representing the early visual processing of stimuli and the effects of top–down attention. Thus, by adopting a computational approach, we present a possible explanation of the findings at the neural level of information processing. The implications of these findings for the relation between attentional processes and conscious awareness are discussed.

Fuzzy cognitive maps in estimating the repercussions of oil/gas exploration on politico-economic issues in Cyprus

Some important politico-economic dynamics, in relation to different scenarios involving the finding and exploitation of oil/gas in the exclusive economic zone of Cyprus, have been modeled and examined through the use of suitable fuzzy cognitive maps. In the interrelated dynamics, various important dynamical parameters have been taken into account, reflecting the interests of the republic of Cyprus, as well as the interests of the Greek and Turkish Cypriot communities. In some respects these interests are antagonistic, while in others could be cooperative. The interests of other countries involved in the Cyprus politico-economic problem have also been taken into account. These are primarily Greece, Turkey, United Kingdom, USA, Russia, Israel and the European Union. The main parameters involved in the interrelated dynamics are nationalism, religiousness, knowledge of history, level of educational development, tourism, unemployment, external debt, oil extraction, Anatolian settlers, and the general interests of the countries involved and those of the two communities. The system that has been developed can be used to study the effects of a change in any parameter or a combination of parameters, on the growth and stability of the remaining parameters. Different scenarios on the effects on economies, politics and military involvement have been implemented, observed and appraised.

Modeling socio-politico-economic systems with time-dependent fuzzy cognitive maps

Most of the formalisms of fuzzy cognitive maps (FCM) that had been proposed and applied in the past are relatively simple in the sense that they handle the various interacting and time-varying concepts as zeroth-order dynamical components. That is, they do not accommodate time delays and growth exponential time constants. In modeling real life systems, especially in the general domain of socio-politico-economics, the time delays are often important and need to be accounted. Also, the various sensitivities associating the system concepts may be time dependent. In the present work, a previously proposed FCM has been extended to include time delays, time constants and time-dependent sensitivities. The system has been applied to the Cyprus politico-economic dynamics, with emphasis on possible scenarios involving the finding and exploitation of oil/gas in the exclusive economic zone of Cyprus. The existence of natural gas - estimated at about 7 trillion cubic feet - has recently been preliminarily verified. In the interrelated dynamics, various important dynamical parameters have been taken into account, reflecting the interests of primarily the republic of Cyprus, as well as the interests of the Greek and Turkish Cypriot communities and other countries involved, such as Greece, Turkey, United Kingdom, USA, Russia, Israel and the European Union. The main parameters that had been considered in the interrelated dynamics are nationalism, religiousness, unemployment, external debt, oil extraction and the general interests of the countries involved and those of the two communities.

Artificial neural networks for non-invasive chromosomal abnormality screening of fetuses

A large number of different neural network structures have been constructed, trained and tested to a large data base of pregnant women characteristics, aiming at generating a classifier-predictor for the presence of chromosomal abnormalities in fetuses, namely the Trisomy 21 (Down syndrome), Trisomy 18 (Edwards syndrome), Trisomy 13 (Patau syndrome) and the Turner syndrome.

A Neural Network Computational Model of Visual Selective Attention

One challenging application for Artificial Neural Networks (ANN) would be to try and actually mimic the behaviour of the system that has inspired their creation as computational algorithms. That is to use ANN in order to simulate important brain functions. In this report we attempt to do so, by proposing a Neural Network computational model for simulating visual selective attention, which is a specific aspect of human attention. The internal operation of the model is based on recent neurophysiologic evidence emphasizing the importance of neural synchronization between different areas of the brain. Synchronization of neuronal activity has been shown to be involved in several fundamental functions in the brain especially in attention. We investigate this theory by applying in the model a correlation control module comprised by basic integrate and fire model neurons combined with coincidence detector neurons. Thus providing the ability to the model to capture the correlation between spike trains originating from endogenous or internal goals and spike trains generated by the saliency of a stimulus such as in tasks that involve top – down attention [1]. The theoretical structure of this model is based on the temporal correlation of neural activity as initially proposed by Niebur and Koch [9]. More specifically; visual stimuli are represented by the rate and temporal coding of spiking neurons. The rate is mainly based on the saliency of each stimuli (i.e. brightness intensity etc.) while the temporal correlation of neural activity plays a critical role in a later stage of processing were neural activity passes through the correlation control system and based on the correlation, the corresponding neural activity is either enhanced or suppressed. In this way, attended stimulus will cause an increase in the synchronization as well as additional reinforcement of the corresponding neural activity and therefore it will “win” a place in working memory. We have successfully tested the model by simulating behavioural data from the “attentional blink” paradigm [11].

Important issues to be considered in developing fuzzy cognitive maps

The formalism of fuzzy cognitive maps as used for the modeling of various dynamical systems is presented with a critical point of view. Various issues related to terminology, concepts, sensitivities, time dependence, iteration procedures, and stability, are systematically considered with critical mind, aiming at making the overall system models be more realistic and useful, and to initiate discussions that can lead to clarifications and to uniformities. Emphasis is given to applications in social, political, economic and engineering systems.

A Generic Tool for Building Fuzzy Cognitive Map Systems

A generic system for simulating complex dynamical systems along the paradigm of fuzzy cognitive maps (FCM) has been created and tested. The proposed system enables a user to design appropriate FCM structures, by specifying the desired concepts and the various parameters such as sensitivities, as well as a variety of shaping functions. The user is able to see the results, change the parameters, modify the functions, and rerun the system using an alteration of the final results and make new conclusions. The system is introduced and demonstrated using a simple real case. The results of a usability test of the system suggest that the system is capable of simulating complicated FCM structures in an effective manner, helping the user to reduce the degree of risks during decision making.

Prenatal Diagnosis of Aneuploidy Using Artificial Neural Networks in Relation to Health Economics

RASimAs (Regional Anaesthesia Simulator and Assistant) is a EU FP7 project that aims at increasing the application, the effectiveness and the success rates of regional anaesthesia by developing two independent but complementary systems, one system for training by using patient-specific computer models, and one for guidance in the assistance of nerve’s location during the actual intervention. In this context, the present document focuses on the training system, which will be deployed in multiple participating hospitals that will be connected to a central information system. In particular, this paper deals with the software architecture of the aforementioned integrated environment and the components that constitute it. We present indicative key components and functionalities such as the user authentication and authorization service, the user profile and performance metrics management service, the role based access control system, the VPH (Virtual Physiological Human) library, and the synchronization between the training centres and the central information system.