Dimitrios I. Fotiadis

Epileptic Seizure Detection in EEGs Using Time–Frequency Analysis

The detection of recorded epileptic seizure activity in EEG segments is crucial for the localization and classification of epileptic seizures. However, since seizure evolution is typically a dynamic and nonstationary process and the signals are composed of multiple frequencies, visual and conventional frequency-based methods have limited application. In this paper, we demonstrate the suitability of the time-frequency ( t-f) analysis to classify EEG segments for epileptic seizures, and we compare several methods for t- f analysis of EEGs. Short-time Fourier transform and several t-f distributions are used to calculate the power spectrum density (PSD) of each segment. The analysis is performed in three stages: 1) t-f analysis and calculation of the PSD of each EEG segment; 2) feature extraction, measuring the signal segment fractional energy on specific t-f windows; and 3) classification of the EEG segment (existence of epileptic seizure or not), using artificial neural networks. The methods are evaluated using three classification problems obtained from a benchmark EEG dataset, and qualitative and quantitative results are presented.

Artificial neural networks for solving ordinary and partial differential equations

We present a method to solve initial and boundary value problems using artificial neural networks. A trial solution of the differential equation is written as a sum of two parts. The first part satisfies the initial/boundary conditions and contains no adjustable parameters. The second part is constructed so as not to affect the initial/boundary conditions. This part involves a feedforward neural network containing adjustable parameters (the weights). Hence by construction the initial/boundary conditions are satisfied and the network is trained to satisfy the differential equation. The applicability of this approach ranges from single ordinary differential equations (ODEs), to systems of coupled ODEs and also to partial differential equations (PDEs). In this article, we illustrate the method by solving a variety of model problems and present comparisons with solutions obtained using the Galekrkin finite element method for several cases of partial differential equations. With the advent of neuroprocessors and digital signal processors the method becomes particularly interesting due to the expected essential gains in the execution speed.

Automatic seizure detection based on time-frequency analysis and artificial neural networks

The recording of seizures is of primary interest in the evaluation of epileptic patients. Seizure is the phenomenon of rhythmicity discharge from either a local area or the whole brain and the individual behavior usually lasts from seconds to minutes. Since seizures, in general, occur infrequently and unpredictably, automatic detection of seizures during long-term electroencephalograph (EEG) recordings is highly recommended. As EEG signals are nonstationary, the conventional methods of frequency analysis are not successful for diagnostic purposes. This paper presents a method of analysis of EEG signals, which is based on time-frequency analysis. Initially, selected segments of the EEG signals are analyzed using time-frequency methods and several features are extracted for each segment, representing the energy distribution in the time-frequency plane. Then, those features are used as an input in an artificial neural network (ANN), which provides the final classification of the EEG segments concerning the existence of seizures or not. We used a publicly available dataset in order to evaluate our method and the evaluation results are very promising indicating overall accuracy from 97.72% to 100%.

Hydrodynamics of magnetic drug targeting

Among the proposed techniques for delivering drugs to specific locations within the human body, magnetic drug targeting surpasses due to its non-invasive character and its high targeting efficiency. Although the method has been proposed almost 30 years ago, the technical problems obstruct possible applications. It is the aim of the present work to classify the emerging problems and propose satisfactory answers. A general phenomenological theory is developed and a model case is studied, which incorporates all the physical parameters of the problem.

Machine learning applications in cancer prognosis and prediction.

Cancer has been characterized as a heterogeneous disease consisting of many different subtypes. The early diagnosis and prognosis of a cancer type have become a necessity in cancer research, as it can facilitate the subsequent clinical management of patients. The importance of classifying cancer patients into high or low risk groups has led many research teams, from the biomedical and the bioinformatics field, to study the application of machine learning (ML) methods. Therefore, these techniques have been utilized as an aim to model the progression and treatment of cancerous conditions. In addition, the ability of ML tools to detect key features from complex datasets reveals their importance. A variety of these techniques, including Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Support Vector Machines (SVMs) and Decision Trees (DTs) have been widely applied in cancer research for the development of predictive models, resulting in effective and accurate decision making. Even though it is evident that the use of ML methods can improve our understanding of cancer progression, an appropriate level of validation is needed in order for these methods to be considered in the everyday clinical practice. In this work, we present a review of recent ML approaches employed in the modeling of cancer progression. The predictive models discussed here are based on various supervised ML techniques as well as on different input features and data samples. Given the growing trend on the application of ML methods in cancer research, we present here the most recent publications that employ these techniques as an aim to model cancer risk or patient outcomes.

Toward Emotion Recognition in Car-Racing Drivers: A Biosignal Processing Approach

In this paper, we present a methodology and a wearable system for the evaluation of the emotional states of car-racing drivers. The proposed approach performs an assessment of the emotional states using facial electromyograms, electrocardiogram, respiration, and electrodermal activity. The system consists of the following: 1) the multisensorial wearable module; 2) the centralized computing module; and 3) the systems interface. The system has been preliminary validated by using data obtained from ten subjects in simulated racing conditions. The emotional classes identified are high stress, low stress, disappointment, and euphoria. Support vector machines (SVMs) and adaptive neuro-fuzzy inference system (ANFIS) have been used for the classification. The overall classification rates achieved by using tenfold cross validation are 79.3% and 76.7% for the SVM and the ANFIS, respectively.

An arrhythmia classification system based on the RR-interval signal

OBJECTIVE This paper proposes a knowledge-based method for arrhythmic beat classification and arrhythmic episode detection and classification using only the RR-interval signal extracted from ECG recordings. METHODOLOGY A three RR-interval sliding window is used in arrhythmic beat classification algorithm. Classification is performed for four categories of beats: normal, premature ventricular contractions, ventricular flutter/fibrillation and 2 degrees heart block. The beat classification is used as input of a knowledge-based deterministic automaton to achieve arrhythmic episode detection and classification. Six rhythm types are classified: ventricular bigeminy, ventricular trigeminy, ventricular couplet, ventricular tachycardia, ventricular flutter/fibrillation and 2 degrees heart block. RESULTS The method is evaluated by using the MIT-BIH arrhythmia database. The achieved scores indicate high performance: 98% accuracy for arrhythmic beat classification and 94% accuracy for arrhythmic episode detection and classification. CONCLUSION The proposed method is advantageous because it uses only the RR-interval signal for arrhythmia beat and episode classification and the results compare well with more complex methods.

Transport phenomena in vertical reactors for metalorganic vapor phase epitaxy: I. Effects of heat transfer characteristics, reactor geometry, and operating conditions

Abstract Effects of operating conditions, reactor geometry, and heat transfer characteristics on flow patterns and growth rate uniformity in vertical, axisymmetric reactors for metalorganic vapor phase epitaxy (MOVPE) are described. Finite element solutions of two- and three-dimensional models of transport phenomena in vertical MOVPE reactors identify regions of inlet flow rates, susceptor rotations, and pressures where flow recirculations due to natural convection are minimized and good deposition rate uniformity is achieved. Particular attention is placed on understanding the influence of reactor geometry and heat transfer characteristics on flow fields and film thickness variations. The numerical computations demonstrate that modifications in the orientation of the reactor, the inlet size and its distance from the susceptor as well as the shape of the reactor enclosure can be used effectively to optimize reactor performance. Baffles can also be used advantageously to improve uniformity in existing reactor enclosures but at the expense of more complex flow patterns. The simulations underscore the importance of including accurate heat transfer treatments in MOVPE models by illustrating that different flow fields result from the commonly used thermal boundary conditions and a detailed heat transfer model. The model predictions are shown to be in good agreement with experimentally observed flow fields, wall temperatures and growth rates for GaAs. Nonlinear transport phenomena lead to the existence of multiple steady flows for the same operating parameters as well as the breaking of axisymmetry and development of fully three-dimensional flow patterns. An example of a non-axisymmetric flow field is given and the assumption of axisymmetry in models of vertical reactors is discussed.

Characterization of clustered microcalcifications in digitized mammograms using neural networks and support vector machines

OBJECTIVE Detection and characterization of microcalcification clusters in mammograms is vital in daily clinical practice. The scope of this work is to present a novel computer-based automated method for the characterization of microcalcification clusters in digitized mammograms. METHODS AND MATERIAL The proposed method has been implemented in three stages: (a) the cluster detection stage to identify clusters of microcalcifications, (b) the feature extraction stage to compute the important features of each cluster and (c) the classification stage, which provides with the final characterization. In the classification stage, a rule-based system, an artificial neural network (ANN) and a support vector machine (SVM) have been implemented and evaluated using receiver operating characteristic (ROC) analysis. The proposed method was evaluated using the Nijmegen and Mammographic Image Analysis Society (MIAS) mammographic databases. The original feature set was enhanced by the addition of four rule-based features. RESULTS AND CONCLUSIONS In the case of Nijmegen dataset, the performance of the SVM was Az=0.79 and 0.77 for the original and enhanced feature set, respectively, while for the MIAS dataset the corresponding characterization scores were Az=0.81 and 0.80. Utilizing neural network classification methodology, the corresponding performance for the Nijmegen dataset was Az=0.70 and 0.76 while for the MIAS dataset it was Az=0.73 and 0.78. Although the obtained high classification performance can be successfully applied to microcalcification clusters characterization, further studies must be carried out for the clinical evaluation of the system using larger datasets. The use of additional features originating either from the image itself (such as cluster location and orientation) or from the patient data may further improve the diagnostic value of the system.

Automated Diagnosis of Coronary Artery Disease Based on Data Mining and Fuzzy Modeling

A fuzzy rule-based decision support system (DSS) is presented for the diagnosis of coronary artery disease (CAD). The system is automatically generated from an initial annotated dataset, using a four stage methodology: 1) induction of a decision tree from the data; 2) extraction of a set of rules from the decision tree, in disjunctive normal form and formulation of a crisp model; 3) transformation of the crisp set of rules into a fuzzy model; and 4) optimization of the parameters of the fuzzy model. The dataset used for the DSS generation and evaluation consists of 199 subjects, each one characterized by 19 features, including demographic and history data, as well as laboratory examinations. Tenfold cross validation is employed, and the average sensitivity and specificity obtained is 62% and 54%, respectively, using the set of rules extracted from the decision tree (first and second stages), while the average sensitivity and specificity increase to 80% and 65%, respectively, when the fuzzification and optimization stages are used. The system offers several advantages since it is automatically generated, it provides CAD diagnosis based on easily and noninvasively acquired features, and is able to provide interpretation for the decisions made.