Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Publications

Publications by Elsa Ferreira Gomes

2015

Using multiresolution time series motifs to classify urban sounds

Authors
Gomes, EF; Batista, F;

Publication
International Journal of Software Engineering and its Applications

Abstract
The automatic classification of urban sounds is important for environmental monitoring. In this work we employ SAX-based Multiresolution Motif Discovery to generate features for Urban Sound Classification. Our approach consists in the discovery of relevant frequent motifs in the audio signals and use the frequency of discovered motifs as characterizing attributes. We explore and evaluate different configurations of motif discovery for defining attributes. In the automatic classification step we use a decision tree based algorithm, random forests and SVM. Results obtained are compared with the ones using Mel-Frequency Cepstral Coefficients (MFCC) as features. MFCCs are commonly used in environmental sound analysis, as well as in other sound classification tasks. Experiments were performed on the Urban Sound dataset, which is publicly available. Our results indicate that we can separate difficult pairs of classes (where MFCC fails) using the motif approach for feature construction. © 2015 SERSC.

2019

Classifying Heart Sounds Using Images of Motifs, MFCC and Temporal Features

Authors
Nogueira, DM; Ferreira, CA; Gomes, EF; Jorge, AM;

Publication
JOURNAL OF MEDICAL SYSTEMS

Abstract
Cardiovascular disease is the leading cause of death in the world, and its early detection is a key to improving long-term health outcomes. The auscultation of the heart is still an important method in the medical process because it is very simple and cheap. To detect possible heart anomalies at an early stage, an automatic method enabling cardiac health low-cost screening for the general population would be highly valuable. By analyzing the phonocardiogram signals, it is possible to perform cardiac diagnosis and find possible anomalies at an early-term. Therefore, the development of intelligent and automated analysis tools of the phonocardiogram is very relevant. In this work, we use simultaneously collected electrocardiograms and phonocardiograms from the Physionet Challenge database with the main objective of determining whether a phonocardiogram corresponds to a normal or abnormal physiological state. Our main contribution is the methodological combination of time domain features and frequency domain features of phonocardiogram signals to improve cardiac disease automatic classification. This novel approach is developed using both features. First, the phonocardiogram signals are segmented with an algorithm based on a logistic regression hidden semi-Markov model, which uses electrocardiogram signals as a reference. Then, two groups of features from the time and frequency domain are extracted from the phonocardiogram segments. One group is based on motifs and the other on Mel-frequency cepstral coefficients. After that, we combine these features into a two-dimensional time-frequency heat map representation. Lastly, a binary classifier is applied to both groups of features to learn a model that discriminates between normal and abnormal phonocardiogram signals. In the experiments, three classification algorithms are used: Support Vector Machines, Convolutional Neural Network, and Random Forest. The best results are achieved when both time and Mel-frequency cepstral coefficients features are considered using a Support Vector Machines with a radial kernel.

2015

Classifying Urban Sounds using Time Series Motifs

Authors
Gomes, EF; Batista, F;

Publication

Abstract

2021

Automatic Identification of Bird Species from Audio

Authors
Carvalho, S; Gomes, EF;

Publication
INTELLIGENT INFORMATION AND DATABASE SYSTEMS, ACIIDS 2021

Abstract
Bird species identification is a relevant and time-consuming task for ornithologists and ecologists. With growing amounts of audio annotated data, automatic bird classification using machine learning techniques is an important trend in the scientific community. Analyzing bird behavior and population trends helps detect other organisms in the environment and is an important problem in ecology. Bird populations react quickly to environmental changes, which makes their real time counting and tracking challenging and very useful. A reliable methodology that automatically identifies bird species from audio would therefore be a valuable tool for the experts in different scientific and applicational domains. The goal of this work is to propose a methodology able to identify bird species by its chirp. In this paper we explore deep learning techniques that are being used in this domain, such as Convolutional Neural Networks and Recurrent Neural Networks to classify the data. In deep learning, audio problems are commonly approached by converting them into images using audio feature extraction techniques such as Mel Spectrograms and Mel Frequency Cepstral Coefficients. We propose and test multiple deep learning and feature extraction combinations in order to find the most suitable approach to this problem.

2022

MigraR: An open-source, R-based application for analysis and quantification of cell migration parameters

Authors
Shaji, N; Nunes, F; Rocha, MI; Gomes, EF; Castro, H;

Publication
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE

Abstract
Background and objective: Cell migration is essential for many biological phenomena with direct impact on human health and disease. One conventional approach to study cell migration involves the quantitative analysis of individual cell trajectories recorded by time-lapse video microscopy. Dedicated software tools exist to assist the automated or semi-automated tracking of cells and translate these into coordinate positions along time. However, cell biologists usually bump into the difficulty of plotting and computing these data sets into biologically meaningful figures and metrics. Methods: This report describes MigraR, an intuitive graphical user interface executed from the RStudio (TM) (via the R package Shiny), which greatly simplifies the task of translating coordinate positions of moving cells into measurable parameters of cell migration (velocity, straightness, and direction of movement), as well as of plotting cell trajectories and migration metrics. One innovative function of this interface is that it allows users to refine their data sets by setting limits based on time, velocity and straightness. Results: MigraR was tested on different data to assess its applicability. Intended users of MigraR are cell biologists with no prior knowledge of data analysis, seeking to accelerate the quantification and visualization of cell migration data sets delivered in the format of Excel files by available cell-tracking software. Conclusions: Through the graphics it provides, MigraR is an useful tool for the analysis of migration parameters and cellular trajectories. Since its source code is open, it can be subject of refinement by expert users to best suit the needs of other researchers. It is available at GitHub and can be easily reproduced.

2022

The Usage of Data Augmentation Strategies on the Detection of Murmur Waves in a PCG Signal

Authors
Torres, J; Oliveira, J; Gomes, EF;

Publication
BIOSIGNALS: PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES - VOL 4: BIOSIGNALS

Abstract
Cardiac auscultation is a key screening tool used for cardiovascular evaluation. When used properly, it speeds up treatment and thus improving the patient's life quality. However, the analysis and interpretation of the heart sound signals is subjective and dependent of the physician's experience and domain knowledge. A computer assistant decision (CAD) system that automatically analyse heart sound signals, can not only support physicians in their clinical decisions but also release human resources to other tasks. In this paper, and to the best of our knowledge, for the first time a SMOTE strategy is used to boost a Convolutional Neural Network performance on the detection of murmur waves. Using the SMOTE strategy, a CNN achieved an overall of 88.43%.

  • 3
  • 6