Melvin Ayala

University of Miami | UM · Department of Mathematics

This study evaluates the sensitivity, specificity and accuracy in associating scalp EEG to either control or epileptic patients by means of artificial neural networks (ANNs) and support vector machines (SVMs). A confluence of frequency and temporal parameters are extracted from the EEG to serve as input features to well-configured ANN and SVM netwo...

An automatic Artificial Neural Network-Aided Diagnosis (ANNAD) system is designed in this study for initial scalp EEG screening to establish whether a given subject is epileptic or not. A unique ANNAD-based decision-making process is devised to make this distinction by 1) computing all standard EEG parameters in both time and frequency domain and 2...

To study the neural networks reorganization in pediatric epilepsy, a consortium of imaging centers was established to collect functional imaging data. Common paradigms and similar acquisition parameters were used. We studied 122 children (64 control and 58 LRE patients) across five sites using EPI BOLD fMRI and an auditory description decision task...

This study describes a new method for offline seizure detection using intracranial EEG (iEEG). The proposed method integrated two interrelated steps: (1) establishing a decisional space on the basis of the interelectrode mean of the spectral power in the gamma frequencies after a thorough evaluation of temporal and frequency-based features and (2)...

This study proposes a new approach for offline seizure detection in intracranial (subdural) electroencephalogram recordings using nonlinear decision functions. It implements well-established features that are designed to deal with complex signals, such as brain recordings, and proposes a two-dimensional (2D) domain of analysis that overcomes the di...

Pattern recognition applied to blood samples for diagnosing leukemia remains an extremely difficult task which frequently leads to misclassification errors due in large part to the inherent problem of data overlap. A novel artificial neural network (ANN) algorithm is proposed for optimizing the classification of multidimensional data, focusing on a...

This study develops a Windows application for processing huge tabular text files. The tool has been especially designed for handling EEG files. As a consequence, tables with more than 65,536 rows and 256 columns, which is a limitation found in Microsoft's Excel, can be loaded, visualized and processed with no more restrictions than the ones imposed...

This study is a comparative evaluation of nonlinear classification methods with a focus on nonlinear decision functions and the standard method of support vector machines for seizure detection. These nonlinear classification methods are used on key features that were extracted on subdural EEG data after a thorough evaluation of all the frequency ba...

This study provides a performance evaluation of the correlation sum in terms of accuracy, sensitivity, and specificity in its ability to classify seizure files from non-seizure files. The main thrust of the study is whether computable properties ("metrics") of EEG tracings over time allow a seizure to be detected. This study evaluates raw intracran...

This paper describes a novel multimedia tool to facilitate visual assessment of Functional Magnetic Resonance Imaging (fMRI) activation patterns by human experts. A great effort is placed by radiologists and neurologists to present a consistent methodology to provide assessment for brain activation map images. Since each radiologist has his own way...

The use of image processing in research represents a challenge to the scientific community interested in its various applications but is not familiar with this area of expertise. In academia as well as in industry, fundamental concepts such as image transformations, filtering, noise removal, morphology, convolution/deconvolution among others requir...

Purpose This study reports a new application of the Principal Component Analysis (PCA) as a data driven decision mechanism to automatically extract brain activation patterns from a given population that is asked to perform an Auditory Description Decision Test (ADDT) paradigm with no previous knowledge of the population. Method Functional Mag...

The central aim of this study is to develop an adaptive real-time eye-gaze tracking (EGT) system that serves as an assistive tool for persons with motor challenges access computers with optimal practicality. The novelty of the proposed method is that it adapts to the different and changing jitter characteristics of each specific user, through the c...

In this paper, we present the results obtained applying the Lateralization Index (LI) concept to assess the activation pattern obtained during the execution of the language network oriented paradigm referred as "auditory description decision task" (ADDT) paradigm on control and epileptic subjects. 114 datasets were analyzed obtaining activation on...

The objective of this study was to design an adaptive, real-time assistive system as an alternate HCI that will give computer access to individuals with severe motor disabilities by means of eye gazing only. It focused on the implementation of an algorithm to smooth out abrupt and unwanted jerky behavior of the mouse cursor due to the saccadic natu...

This study developed an adaptive real-time human-computer interface (HCI) that serves as an assistive technology tool for people with severe motor disability. The proposed HCI design uses eye gaze as the primary computer input device. Controlling the mouse cursor with raw eye coordinates results in sporadic motion of the pointer because of the sacc...

This study introduces an integrated algorithm for the purpose of discriminating between EEG channels (electrodes) leading or not to an ictal state, using interictal subdural EEG data. The importance of this study is in determining among all of these channels, all containing interictal spikes, why some electrodes eventually lead to seizure while oth...

Human computer interfaces (HCI) for assisting persons with disabilities may employ eye gazing as the primary computer input mechanism. These systems rely on the use of remote eye-gaze tracking (EGT) devices to compute the direction of gaze and employ it to control the mouse cursor. Regrettably, the performance of these interfaces is traditionally a...

Autism is characterized as a spectrum of neurodevelopment impairments in communicative, social behavioural, and sensory motor skills. Public concerns about autism have grown in recent years due to the prevalence of its diagnosis in 1 out of 150 young children. Though many researches have been carried out to analyse autistic patients' EEG behaviour,...

Epilepsy is characterized by an unexpected and frequent malfunction of the brain. Electrical activity in the brain has been studied for years in an attempt to predict seizures. This paper processes raw intracranial EEG recordings from different subjects in the time prior to seizure. A set of indicators is extracted from non-overlapping scrolling wi...

Epilepsy is a neurological disorder, a physical condition, which causes sudden bursts of electrical energy in the brain. Electrical activity in the brain has been studied for years in an attempt to detect seizures. This paper processes raw intracranial electroencephalographic recordings in the time prior and during a seizure.This study focuses on t...

The objective of this research was the design and implementation of a writing module that is integrated with a myoelectrical-based gripper as a potential prosthetic device that could help amputees recover some of their writing abilities. The developed module would hence offer increased functionality to current prostheses. This novel device required...

The algorithm developed in this study integrates a frequency analysis of key frequency bands (alpha, beta, delta, and theta) with an inverse solution using the principal component analysis (PCA) to validate brain functional mappings associated with the characterization effects of an auditory/comprehension task. The results are found to be consisten...

Distributed computing is used to solve computational complexity problems. This paper explores the suitability of the .NET platform and XML Web services for distributed computing applications. This study demonstrates the practical feasibility of a .NET Web-services application in distributed computing and it also exposes APIs on the Internet. Thus f...

This study introduces an algorithm for a new application dedicated at discriminating between electrodes leading to a seizure onset and those that do not lead to seizure using interictal subdural EEG data. The significance of this study is in determining among all of these channels, all containing interictal spikes that are asynchronously, independe...

Accurate classification of human blood cells plays a decisive role in the diagnosis and treatment of diseases. Artificial Neural Networks (ANN) have been consistently used as a trusted classification tool for this type of analysis. In this study, a new Artificial Neural Network approach is proposed for the multidimensional classification of two of...

Accurate epileptic focus localization using single photon emission computed tomography (SPECT) images has proven to be a challenging endeavor. First, commonly used radiopharmaceuticals such as hexamethylpropylene amine oxime (HMPAO) quantitatively underestimate large blood flows, leading to subtracted SPECT images that do not reflect the true cereb...

This study adapted the CURRY program and assessed the relationship of the 3-D spike sources to focal lesions evident on MRI scans. The subgroup is selected as it represents an initial step in determining the merit of this technique in the presurgical evaluation of children. Further studies comparing reconstructed spike sources with intracranial ele...

This study introduces a new algorithm to optimize the pattern recognition of different white blood cell types in flow cytometry. The behavior of parametric data clusters in a multidimensional space is analyzed using the learning system known as Support Vector Machines (SVM). Beckman-Coulter Corporation supplied flow cytometry data of numerous patie...

Accurate classification of human blood cells plays a decisive role in the diagnosis and treatment of diseases. Artificial Neural Networks (ANNs) have been consistently used as a trusted classification tool for this type of analysis. In the present case study, two approaches are implemented on two different parametric data clusters in a multidimensi...

This study proposes an inverse solution in estimating the 3-D localization of interictal spike activity in epileptogenic data. Sensory modalities for data analysis include electroencephalographs (EEG) superimposed on magnetic resonance imagery (MRI) in a pediatric population with extra-temporal lesional epileptic foci. In this integrated approach,...

This study introduces an integrated approach to the 3-D localization of brain activity related to epileptic seizures by merging electroencephalographs (EEG) and magnetic resonance imagery (MRI) data. Several patients (11) are used in this study to determine the merit of such 3-D localization mechanisms in relation to actual epileptic foci, knowing...

This study integrates a spectral analysis of key frequency bands (Alpha, Beta, Delta, and Theta) with an eigensystem-based study in order to validate brain functional mappings associated with the characterization effects of an Auditory/Comprehension paradigm. This numerical characterization supported by topographic functional maps brings added insi...

This MATLAB interface is aimed at analyzing and integrating two different imaging modalities optical topography system (OTS) and magnetic resonance imaging (MRI). MRI provides information about the anatomical structure of the brain, while OTS displays the changes in the cerebral blood flow in the form of a topographic image. Eight subjects underwen...

This study introduces an integrated algorithm based on the Walsh transform to detect interictal spikes and artifactual data in epileptic patients using recorded EEG data. The algorithm proposes a unique mathematical use of Walsh-transformed EEG signals to identify those criteria that best define the morphologic characteristics of interictal spikes....

Current speech recognition (SR) systems have evolved technologically to begin having an impact in human computer interface (HCI) designs that can be used by persons with motor disabilities. This study presents a real-time user-friendly programming HCI able to convert voice commands into computer actions. To this end, an interface was developed for...

State of the Art human computer interfaces (HCI) for assisting individuals with severe motor disabilities employ remote eye-gaze tracking (EGT) systems which obtain eye coordinates and convert them into mouse-pointer coordinates. The performance of those systems is traditionally affected by mouse-pointer jitter and miscalibration due to head moveme...

This work has been motivated by the increasing effort currently required in educational institutions while using computational tools for teaching Artificial Neural Networks (ANN). An appropriate and user-friendly programming tool is proposed with the aim to redress the situation in this important information science discipline. The programming envi...

The objective of this study was to evaluate the feasibility of using the Walsh transformation to detect interictal spikes in electroencephalogram (EEG) data. Walsh operators were designed to formulate characteristics drawn from experimental observation, as provided by medical experts. The merits of the algorithm are: 1) in decorrelating the data to...

This study focuses on the design of orthogonal operators based on unique Electroencephalograph (EEG) signal decompositions in order to detect interictal spikes that characterize epileptic seizures in EEG data. The merits of the algorithm are: (a) in elaborating a unique analysis scheme that scrutinizes EEG data through orthogonal operators designed...

This study introduces a simplified approach for the implementation of artificial neural networks (ANN) for the recognition of epileptic data in electroencephalograph (EEG) recordings. The training set construction is based on a trend-adaptive polygon which simplifies the search process as it reduces the size of the training set. This data reduction...

The algorithm developed in this study integrates a frequency analysis of key frequency bands (Alpha, Beta, Delta, and Theta) with an inverse solution using the principal component analysis (PCA) to validate brain functional mappings associated with the characterization effects of an Auditory/Comprehension task, consistent with earlier findings invo...

The existing programming tools do not combine the attributes of easy to use and affordability. The existing procedures for spike detection consist mostly of sequences of tasks such as manual data preparation, followed by the use of multiple software packages (for example, from a commercial EEG recording program into MATLAB). The programming tool pr...

This study introduces a new artificial neural network (ANN) system dedicated to the automatic recognition of epileptic foci in electroencephalograph (EEG) recordings. This ANN is based on a trend-adaptive polygon which optimizes the search process and more importantly reduces the size of the training set by an impressive 74% or better, yielding as...

Accurate epileptic focus localization using SPECT images has proven itself to be a challenging endeavor. Firstly, this is partly due to the fact that radiopharmaceuticals such as hexamethylpropylene amine oxime (HMPAO) quantitatively underestimate large blood flows; this may lead to SPECT images that do not reflect the true physiological conditions...

This paper introduces a method for the supervision and control of devices in electric substations using fuzzy logic and artificial neural networks. An automatic knowledge acquisition process is included which allows the on-line processing of operator actions and the extraction of control rules to replace gradually the human operator. Some experimen...

Electric substations are facilities in charge of transform the voltage into safe and effective energy for the final consumers. This operation has to be carried out with enough quality assurance and without damaging the equipment. The associated cost to ensure this quality and security is high. Automatic mechanisms are used, however, they mostly ope...

The control of a substation is a very complex task due to the great number of related problems and, therefore, the decision variables that can influence the substation performance. Under such circumstances, the use of learning control systems can be very useful. The difficulties associated with the application of artificial intelligence techniques...

This study proposes an inverse solution in estimating the 3-D localization of interictal spike activity in epileptogenic data. Sensory modalities for data analysis include electroencephalographs (EEG) superimposed on magnetic resonance imagery (MRI) in a pediatric population with extra-temporal lesional epileptic foci. In this integrated approach,...

This study presents a user friendly programming tool developed to assist persons with motor disabilities in communicating with computers via voice commands. The main purpose of the study was to develop a human computer interface (HCI) able to convert voice commands into computer actions. To this end, an interface was developed for facilitating the...

Zittau, Ingenieurhochsch., Diss. A, 1988 (Nicht f.d. Austausch).

This dissertation established a state-of-the-art programming tool for designing and training artificial neural networks (ANNs) and showed its applicability to brain research. The developed tool, called NeuralStudio, allows users without programming skills to conduct studies based on ANNs in a powerful and very user friendly interface. A series of u...