Konstantinos Ninos

Variable selection in nonlinear modeling based on RBF networks and evolutionary computation.

In this paper a novel variable selection method based on Radial Basis Function (RBF) neural networks and genetic algorithms is presented. The fuzzy means algorithm is utilized as the training method for the RBF networks, due to its inherent speed, the deterministic approach of selecting the hidden node centers and the fact that it involves only a single tuning parameter. The trade-off between the accuracy and parsimony of the produced model is handled by using Final Prediction Error criterion, based on the RBF training and validation errors, as a fitness function of the proposed genetic algorithm. The tuning parameter required by the fuzzy means algorithm is treated as a free variable by the genetic algorithm. The proposed method was tested in benchmark data sets stemming from the scientific communities of time-series prediction and medicinal chemistry and produced promising results.

A Radial Basis Function network training algorithm using a non-symmetric partition of the input space - Application to a Model Predictive Control configuration

This work presents the non-symmetric fuzzy means algorithm which is a new methodology for training Radial Basis Function neural network models. The method is based on a non-symmetric fuzzy partition of the space of input variables which results to networks with smaller structures and better approximation capabilities compared to other state-of-the-art training procedures. The lower modeling error and the smaller size of the produced models become particularly important when they are used in online applications. This is demonstrated by integrating the model produced by the proposed algorithm in a Model Predictive Control configuration, resulting in better control performance and shorter computational times.

Nonlinear control of a DC-motor based on radial basis function neural networks

This paper presents a nonlinear controller based on an inverse neural network model of the system under control. The neural controller is implemented as a Radial Basis Function (RBF) network trained with the powerful fuzzy means algorithm. The resulting controller is tested on a nonlinear DC motor control problem and the results illustrate the advantages of the proposed approach.

Development and evaluation of a PDA-based teleradiology terminal in thyroid nodule diagnosis

We developed a wireless personal digital assistant (PDA)-based teleradiology terminal which allowed a secure connection to the hospitals Picture Archiving and Communication System (PACS) through the DICOM protocol. Ten members of the hospitals medical staff completed a questionnaire about its mobility, usability, stability, performance and diagnostic efficiency in a real health-care environment. There was a high degree of satisfaction with the systems mobility (mean score 4.1, SD 1.0, on a five-point scale), usability (mean score 4.2, SD 1.1), stability (mean score 3.9, SD 0.4) and performance (mean score 4.2, SD 0.6). The system was evaluated as a tool for providing assistance in diagnosing thyroid nodules from ultrasound images. A total of 144 ultrasound images with thyroid nodules were assessed by an expert. Six image quality attributes were evaluated. The physician concluded that the ultrasound thyroid images on the PDA screen were of similar quality to those displayed on a diagnostic visual display unit screen. However, the expert found difficulties in diagnosing microcalcification, internal echo texture and vascularity. The PDA terminal provided rapid, secure and convenient portable access to PACS images and the image quality was sufficient for diagnostic interpretation of ultrasound images of the thyroid.

Remote monitoring of electromagnetic signals and seismic events using smart mobile devices

This study presents the design and development of a novel mobile wireless system to be used for monitoring seismic events and related electromagnetic signals, employing smart mobile devices like personal digital assistants (PDAs) and wireless communication technologies such as wireless local area networks (WLANs), general packet radio service (GPRS) and universal mobile telecommunications system (UMTS). The proposed system enables scientists to access critical data while being geographically independent of the sites of data sources, rendering it as a useful tool for preliminary scientific analysis.

Using New Technologies for Teaching Power Electronics and Assessing Students

In the Technological Educational Institution (T.E.I.) of Athens, new technologies are used for teaching electronic engineering modules for some time. This work presents the teaching of the module of power electronics by introducing a number of new methods. The educational portal, software simulations and electronic examinations support the teaching process and finally evaluate knowledge assimilation. Features and advantages of their implementation are presented and discussed

Brain imaging: Comparison of T1W FLAIR BLADE with conventional T1W SE

INTRODUCTION Although T1 weighted spin echo (T1W SE) images are widely used to study anatomical details and pathologic abnormalities of the brain, its role in delineation of lesions and reduction of artifacts has not been thoroughly investigated. BLADE is a fairly new technique that has been reported to reduce motion artifacts and improve image quality. OBJECTIVE The primary objective of this study is to compare the quality of T1-weighted fluid attenuated inversion recovery (FLAIR) images with BLADE technique (T1W FLAIR BLADE) and the quality of T1W SE images in the MR imaging of the brain. The goal is to highlight the advantages of the two sequences as well as which one can better reduce flow and motion artifacts so that the imaging of the lesions will not be impaired. MATERIALS AND METHODS Brain examinations with T1W FLAIR BLADE and T1W SE sequences were performed on 48 patients using a 1.5T scanner. These techniques were evaluated by two radiologists based on: a) a qualitative analysis i.e. overall image quality, presence of artifacts, CSF nulling; and b) a quantitative analysis of signal-to-noise ratios (SNR), contrast-to-noise ratios (CNR) and Relative Contrast. The statistical analysis was performed using the Kruskal-Wallis non-parametric system. RESULTS In the qualitative analysis, BLADE sequences had a higher scoring than the conventional sequences in all the cases. The overall image quality was better on T1W FLAIR BLADE. Motion and flow-related artifacts were lower in T1W FLAIR BLADE. Regarding the SNR measurements, T1W SE appeared to have higher values in the majority of cases, whilst T1W-FLAIR BLADE had higher values in the CNR and Relative Contrast measurements. CONCLUSION T1W FLAIR BLADE sequence appears to be superior to T1W SE in overall image quality and reduction of motion and flow-pulsation artifacts as well as in nulling CSF and has been preferred by the clinicians. T1W FLAIR BLADE may be an alternative approach in brain MRI imaging.

Direct versus indirect neural control based on radial basis function networks

This work presents a comparison between direct and indirect neural control methods based on the radial basis function (RBF) architecture. As far as direct control schemes are concerned, a novel direct inverse neural RBF controller taking into account the applicability domain criterion (INCAD) is utilized. ? model predictive control (MPC) formulation based on RBF networks is tested as an example of indirect method. The performances of the two control schemes are evaluated and compared on a highly nonlinear control problem, namely control of a continuous stirred tank reactor (CSTR) with multiple stable and unstable steady states. Results show that the INCAD controller is able to provide satisfactory performance, while performing almost instant calculation of the control actions. MPC on the other hand, outperforms the INCAD in terms of speed of responses, due to the built-in optimization capability; however, the lengthy procedure of solving online the optimization problem impedes the practical use of MPC on systems with fast dynamics.

Computer based correlation of the texture of P63 expressed nuclei with histological tumour grade, in laryngeal carcinomas.

Background. P63 immunostaining has been considered as potential prognostic factor in laryngeal cancer. Considering that P63 is mainly nuclear stain, a possible correlation between the texture of P63-stained nuclei and the tumors grade could be of value to diagnosis, since this may be related to biologic information imprinted as texture on P63 expressed nuclei. Objective. To investigate the association between P63 stained nuclei and histologic grade in laryngeal tumor lesions. Methods. Biopsy specimens from laryngeal tumour lesions of 55 patients diagnosed with laryngeal squamous cell carcinomas were immunohistochemically (IHC) stained for P63 expression. Four images were digitized from each patients IHC specimens. P63 positively expressed nuclei were identified, the percentage of P63 expressed nuclei was computed, and 118 textural, morphological, shape, and architectural features were calculated from each one of the 55 laryngeal lesions. Data were split into the low grade (21 grade I lesions) and high grade (34 grade II and grade III lesions) classes for statistical analysis. Results. With advancing grade, P63 expression decreased, P63 stained nuclei appeared of lower image intensity, more inhomogeneous, of higher local contrast, contained smaller randomly distributed dissimilar structures and had irregular shape. Conclusion. P63 expressed nuclei contain important information related to histologic grade.

An adaptive soft-sensor for non-destructive cement-based material testing, through the use of RBF networks

This paper presents the development of a soft-sensor receiving as inputs Pressure Stimulated Current (PSC) characteristics in order to predict a critical mechanical property of cement-based materials, in a non-destructive manner. The soft-sensor is based on a Radial Basis Function (RBF) network that starts with an empty hidden layer and evolves its structure and synaptic weights as new data become available. Results have shown that the proposed approach can be used successfully to evolve a predictive tool based on input-output data, whereas it is superior compared to other adaptive modeling techniques.