scispace - formally typeset
Search or ask a question
Author

Andrés Eduardo Castro-Ospina

Bio: Andrés Eduardo Castro-Ospina is an academic researcher from National University of Colombia. The author has contributed to research in topics: Cluster analysis & Spectral clustering. The author has an hindex of 6, co-authored 49 publications receiving 144 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: This paper describes, in detail, 27 techniques that mainly focus on the smoothing or elimination of speckle noise in medical ultrasound images, and describes recent techniques in the field of machine learning focused on deep learning, which are not yet well known but greatly relevant.
Abstract: In recent years, many studies have examined filters for eliminating or reducing speckle noise, which is inherent to ultrasound images, in order to improve the metrological evaluation of their biomedical applications. In the case of medical ultrasound images, said noise can produce uncertainty in the diagnosis because details, such as limits and edges, should be preserved. Most algorithms can eliminate speckle noise, but they do not consider the conservation of these details. This paper describes, in detail, 27 techniques that mainly focus on the smoothing or elimination of speckle noise in medical ultrasound images. The aim of this study is to highlight the importance of improving said smoothing and elimination, which are directly related to several processes (such as the detection of regions of interest) described in other articles examined in this study. Furthermore, the description of this collection of techniques facilitates the implementation of evaluations and research with a more specific scope. This study initially covers several classical methods, such as spatial filtering, diffusion filtering, and wavelet filtering. Subsequently, it describes recent techniques in the field of machine learning focused on deep learning, which are not yet well known but greatly relevant, along with some modern and hybrid models in the field of speckle-noise filtering. Finally, five Full-Reference (FR) distortion metrics, common in filter evaluation processes, are detailed along with a compensation methodology between FR and Non-Reference (NR) metrics, which can generate greater certainty in the classification of the filters by considering the information of their behavior in terms of perceptual quality provided by NR metrics.

28 citations

Proceedings ArticleDOI
01 Sep 2015
TL;DR: A comparison between various methods for feature extraction of EEG signals in BCI systems is presented, both at extracting frequency information from each electrode as for extracting shared information between electrodes.
Abstract: Brain-computer Interfaces (BCIs) are control and communication systems based on acquisition and processing of brain signals to control a computer or an external device. Usually, BCI is focused in recognizing acquired events by different neuroimage methods, but the most used is the electroencephalography (EEG). Feature extraction over EEG signals for BCI systems is crucial to the classification performance. In this paper a comparison between various methods for feature extraction of EEG signals in BCI systems is presented. Different methodologies were taken into account, both at extracting frequency information from each electrode as for extracting shared information between electrodes.

22 citations

Book ChapterDOI
26 Sep 2018-Scopus
TL;DR: The main objective of this study was to investigate the capability of the classifiers systems for identification pleasant and unpleasant odors from EEG signals and relations among emotion, EEG, and odors were demonstrated.
Abstract: Odor identification refers to the capability of the olfactory sense for discerning odors. The interest in this sense has grown over multiple fields and applications such as multimedia, virtual reality, marketing, among others. Therefore, objective identification of pleasant and unpleasant odors is an open research field. Some studies have been carried out based on electroencephalographic signals (EEG). Nevertheless, these can be considered insufficient due to the levels of accuracy achieved so far. The main objective of this study was to investigate the capability of the classifiers systems for identification pleasant and unpleasant odors from EEG signals. The methodology applied was carried out in three stages. First, an odor database was collected using the signals recorded with an Emotiv Epoc+ with 14 channels of electroencephalography (EEG) and using a survey for establishing the emotion levels based on valence and arousal considering that the odor induces emotions. The registers were acquired from three subjects, each was subjected to 10 different odor stimuli two times. The second stage was the feature extraction which was carried out on 5 sub-bands \(\delta \), \(\theta \), \(\alpha \), \(\beta \), \(\gamma \) of EEG signals using discrete wavelet transform, statistical measures, and other measures such as area, energy, and entropy. Then, feature selection was applied based on Rough Set algorithms. Finally, in the third stage was applied a Support vector machine (SVM) classifier, which was tested with five different kernels. The performance of classifiers was compared using k-fold cross-validation. The best result of 99.9% was achieved using the linear kernel. The more relevant features were obtained from sub-bands \(\beta \) and \(\alpha \). Finally, relations among emotion, EEG, and odors were demonstrated.

15 citations

Book ChapterDOI
17 Oct 2018-Scopus
TL;DR: This work proposes the implementation of two well known classification algorithms, namely artificial neural networks (ANN) and support vector machines (SVM), optimized by particle swarm optimization (PSO) algorithm, aimed at classifying voice signals between healthy and pathologic ones.
Abstract: Computer-aided diagnosis (CAD) systems have allowed to enhance the performance of conventional, medical diagnosis procedures in different scenarios. Particularly, in the context of voice pathology detection, the use of machine learning algorithms has proved to be a promising and suitable alternative. This work proposes the implementation of two well known classification algorithms, namely artificial neural networks (ANN) and support vector machines (SVM), optimized by particle swarm optimization (PSO) algorithm, aimed at classifying voice signals between healthy and pathologic ones. Three different configurations of the Saarbrucken voice database (SVD) are used. The effect of using balanced and unbalanced versions of this dataset is proved as well as the usefulness of the considered optimization algorithm to improve the final performance outcomes. Also, proposed approach is comparable with state-of-the-art methods.

11 citations

Journal ArticleDOI
08 Jun 2021
TL;DR: This literature review highlights recent studies that reveal existing gaps, the need to find a synergy between data fusion and IQ, several research issues, and the challenges and pitfalls in this field.
Abstract: This paper provides a comprehensive description of the current literature on data fusion, with an emphasis on Information Quality (IQ) and performance evaluation. This literature review highlights recent studies that reveal existing gaps, the need to find a synergy between data fusion and IQ, several research issues, and the challenges and pitfalls in this field. First, the main models, frameworks, architectures, algorithms, solutions, problems, and requirements are analyzed. Second, a general data fusion engineering process is presented to show how complex it is to design a framework for a specific application. Third, an IQ approach, as well as the different methodologies and frameworks used to assess IQ in information systems are addressed; in addition, data fusion systems are presented along with their related criteria. Furthermore, information on the context in data fusion systems and its IQ assessment are discussed. Subsequently, the issue of data fusion systems’ performance is reviewed. Finally, some key aspects and concluding remarks are outlined, and some future lines of work are gathered.

10 citations


Cited by
More filters
Proceedings ArticleDOI
01 Feb 2020
TL;DR: Experimental results show that the proposed model can compete with other state-of-the-art methods and can be effectively used to recognize robust human activities in terms of efficiency and accuracy.
Abstract: Human activity recognition using MotionNode sensors is getting prominence effect in our daily life logs. Providing accurate information on human's activities and behaviors is one of the most challenging tasks in ubiquitous computing and human-Computer interaction. In this paper, we proposed an efficient model for having statistical features along SMO-based random forest. Initially, we processed a 1-D Hadamard transform wavelet and 1-D LBP based extraction algorithm to extract valuable features. For activity classification, we used sequential minimal optimization along with Random Forest over two benchmarks USC-HAD dataset and IMSB datasets. Experimental results show that our proposed model can compete with other state-of-the-art methods and can be effectively used to recognize robust human activities in terms of efficiency and accuracy.

65 citations

Journal ArticleDOI
TL;DR: This work proposes a more discriminative graph learning method which can preserve the pairwise similarities between samples in an adaptive manner for the first time and unifies clustering and graph learning which can directly obtain cluster indicators from the graph itself without performing further clustering step.

56 citations

Journal ArticleDOI
TL;DR: The SVM plus AFBD method represents a useful contribution to olfactory-induced emotion recognition and is considerably higher than those of other combination methods, such as the combinations of AFBD or EEG rhythm-based features with naive Bayesian, k-nearest neighbor classification, voting-extreme learning machine, and backpropagation neural network methods.

40 citations

Journal ArticleDOI
TL;DR: A new approach for investigating the neural correlates of a cognitive task is proposed by training CNN models on raw high-dimensional EEG data and utilizing saliency maps for relevant feature extraction and recommendations for when and how to use CNN models in EEG decoding are provided.
Abstract: Objective Convolutional neural networks (CNNs) have proven successful as function approximators and have therefore been used for classification problems including electroencephalography (EEG) signal decoding for brain-computer interfaces (BCI). Artificial neural networks, however, are considered black boxes, because they usually have thousands of parameters, making interpretation of their internal processes challenging. Here we systematically evaluate the use of CNNs for EEG signal decoding and investigate a method for visualizing the CNN model decision process. Approach We developed a CNN model to decode the covert focus of attention from EEG event-related potentials during object selection. We compared the CNN and the commonly used linear discriminant analysis (LDA) classifier performance, applied to datasets with different dimensionality, and analyzed transfer learning capacity. Moreover, we validated the impact of single model components by systematically altering the model. Furthermore, we investigated the use of saliency maps as a tool for visualizing the spatial and temporal features driving the model output. Main results The CNN model and the LDA classifier achieved comparable accuracy on the lower-dimensional dataset, but CNN exceeded LDA performance significantly on the higher-dimensional dataset (without hypothesis-driven preprocessing), achieving an average decoding accuracy of 90.7% (chance level = 8.3%). Parallel convolutions, tanh or ELU activation functions, and dropout regularization proved valuable for model performance, whereas the sequential convolutions, ReLU activation function, and batch normalization components reduced accuracy or yielded no significant difference. Saliency maps revealed meaningful features, displaying the typical spatial distribution and latency of the P300 component expected during this task. Significance Following systematic evaluation, we provide recommendations for when and how to use CNN models in EEG decoding. Moreover, we propose a new approach for investigating the neural correlates of a cognitive task by training CNN models on raw high-dimensional EEG data and utilizing saliency maps for relevant feature extraction.

38 citations