46,231 Works

Sea State Estimation with Neural Networks based on the Motion of a Moored FPSO subjected to Campos Basin Metocean Conditions

, Eduardo Aoun Tannuri, Gustavo Bisinotto, Lucas Cotrim & Fábio Gagliardi Cozman
Important information for the design and operation of oceanic systems can be obtained by assessing local sea state parameters such as significant height, peak period and incidence direction. Techniques for motion-based inference and their possible drawbacks have been extensively discussed in the literature (their motivation coming from the simplicity of the required instrumentation when compared to traditional measuring systems), and machine learning approaches are now appearing in a few investigations. This paper addresses the estimation...

Detecting Early Signs of Insufficiency in COVID-19 Patients from CBC Tests Through a Supervised Learning Approach

& Tiago Colliri
One important task in the COVID-19 clinical protocol involves the constant monitoring of patients to detect possible signs of insufficiency, which may eventually rapidly progress to hepatic, renal or respiratory failures. Hence, a prompt and correct clinical decision not only is critical for patients prognosis, but also can help when making collective decisions regarding hospital resource management. In this work, we present a network-based high-level classification technique to help healthcare professionals on this activity, by...

Universal Dependencies-based PoS Tagging Refinement through Linguistic Resources

, Magali Duran, Lucelene Lopes & Thiago Pardo
This paper presents a technique that employs linguistic resources to refine PoS tagging using the Universal Dependencies (UD) model. The technique is based on the development and use of lists of non-ambiguous single tokens and non-ambiguous co-occuring tokens in Portuguese (regardless of whether they constitute multiword expressions or not). These lists are meant to automatilly correct the tags for such tokens after tagging. The technique is applied over the output of two well-known state of...

Identification of Emotions in Spoken Language Using Deep Learning

, Yasmin M. M. Oliveira & Carlos M. S. Figueiredo
Emotions are one of the pillars of human communication, especially spoken language. In emotional speech, they can be identified by inherent attributes of the voice, such as pitch, frequency, intensity etc. In this paper, a model based on artificial data augmentation and Deep Learning, more specifically a Convolutional Recurrent Neural Network, was proposed to automate this emotion identification task by being trained on the RAVDESS database with cross-validation technique. Evaluated by the accuracy and F1-Score...

Improving a genetic clustering approach with a CVI-based objective function.

& Igor Matheus Moreira
Genetic-based clustering meta-heuristics are important bioinspired algorithms. One such technique, termed Genetic Algorithm for Decision Boundary Analysis (GADBA), was proposed to support Structural Health Monitoring (SHM) processes in bridges. GADBA is an unsupervised, non-parametric approach that groups data into natural clusters by means of a specialized objective function. Albeit it allows a competent identification of damage indicators of SHM-related data, it achieves lackluster results on more general clustering scenarios. This study improves the objective function...

Ethics of AI: Do the face detection models act with prejudice?

& Ricardo Araújo Rios
This work presents a study on an ethical issue in Artificial Intelligence related to the presence of racist biases by detecting faces in images. Our analyses were performed on a real-world system designed to detect fraud in public transportation in Salvador (Brazil). Our experiments were conducted by taking into account three steps. Firstly, we individually analyzed a sample of images and added specific labels related to the users' gender and race. Then, we used well-defined...

Supervised Training of a Simple DIgital Assistant for a Free Crop Clinic

, Mariana Barros, Edna Barros, Rosana Blawid, Stefan Blawid, Ladson Gomes, Igor Moura & Antonio Netto
Family farming represents a critical segment of Brazilian agriculture, involving more than 5 million properties and generating 74% of rural jobs in the country. Yield losses caused by crop diseases and pests can be devastating for small-scale producers. However, successful disease control requires correct identi cation, which challenges smallholders, who often lack technical assistance. The present work proposes a system that detects disease symptoms in images of plant leaves to assist phytopathology experts. The objective...

Uma Abordagem de Agrupamento Automático de Dados Baseada na Otimização por Busca em Grupo Memética

, Teresa Bernarda Ludermir & Luciano Pacifico
As one of the most primitive pattern organization tasks, clustering is a hard grouping problem in exploratory data analysis. Most standard clustering algorithms are easily trapped into local minima points from the problem search space, once such models lack good global search capabilities. In this work, a memetic Swarm Intelligence (SIs) algorithm is presented, based on Group Search Optimization and K-Means, called MGSO, that attempts both finding the best number of final clusters and the...

Interpretability of Attention in Question and Answering System about the Blue Amazon in Portuguese.

, Flávio Cação, Fábio Gagliardi Cozman, Marcos Menon, André Seidel Oliveira & Stéfano Spindola
Abstract. The Brazilian Exclusive Economic Zone, or the “Blue Amazon”, with its extensive maritime area, is the primary means of transport for the country’s foreign trade and is important due to its oil reserves, gas and other mineral resources, in addition to the significant influence on the Brazilian climate. We have manually built a question answering (QA) dataset based on crawled arti- cles and have applied an off-the-shelf QA system based on a fine-tuned BERTim-...

The Challenges of Modeling and Predicting Online Review Helpfulness

, Thiago Pardo & Rogério Sousa
Predicting review helpfulness is an important task in Natural Language Processing. It is useful for dealing with the huge amount of online reviews on varied domains and languages, helping and guiding users on what to read and consider in their daily decisions. However, there are limited initiatives to investigate the nature of this task and how hard it is. This paper aims to fulfill this gap, providing a better understanding of it. Two complementary experiments...

Fake news detection about Covid-19 in the Portuguese language

, Máverick André Dionísio Ferreira, Débora da Conceição Araújo, Paulo Neto & Anísio Pereira Batista Filho
Fake news propagation has been a problem noted in several areas of society, for example, in the fight against the pandemic caused by the new coronavirus (Sars-Cov-2). Combating misinformation, especially on social networks, is fundamental to control the spread of the virus and, consequently, the pandemic. Therefore, this work built supervised learning models focused on identifying fake news about the Sars-Cov-2. As a result, 18 models were built and rated, their reached 0.62%, 0.82%, and...

Evaluation of Neural Architecture Search Approaches for Offshore Platform Offset Prediction

, Eduardo Aoun Tannuri, Rodrigo Barreira, Lucas Cotrim, Eric Gomes, Edson Gomi, Henrique Oliveira, Anna Helena Reali Costa, Amir Sa'ad, Ismael Santos & Tomaz Suller
We propose a solution based on Multi-Layer Perceptron (MLP) to predict the offset of the center of gravity of an offshore platform. We also perform a comparative study with three optimization algorithms – Random Search, Simulated Annealing, and Bayesian Optimization (BO) – to find the best MLP architecture. Although BO obtained the best architecture in the shortest time, ablation studies developed with hyperparameters of the optimization process showed that the result is sensitive to them...

A lightweight approach for predicting errors in chess matches

, Giovanni Comarela & Davi da Silva
Chess is becoming more popular and accessible by the day. For instance, online chess enables matches between players from different parts of the world, bringing new ways of learning the game and interacting with other Web users. With this growth in popularity, there is a possibility to empower amateur players with rich computer analysis and tools, which may assist them in their learning process. One of the ways to analyze chess matches is through the...

Time Series Classification using Shape Features based on Angle Statistics

, Daniel Pedronette & Bionda Rozin
Time series have great applicability in the most diverse scenarios, including the scientific, agricultural, economic domains, among others. Therefore, creating effective representations of a time series is a challenging task, as it allows more accurate analysis and, consequently, more assertive results and conclusions in various machine learning tasks. One of the main tasks is classification, which can be performed from different computational representations of time series. The main objective of this work is to improve...

Descrição de numerais segundo modelo Universal Dependencies e sua anotação no português

, Magali Duran, Lucelene Lopes & Thiago Pardo
Apresentamos a instanciação que realizamos das diretrizes do modelo Universal Dependencies (UD) para a anotação de Numerais em português. Apresentamos as diferenças do conceito da classe de numerais na Nomenclatura Gramatical Brasileira e Portuguesa e nas diretrizes da UD. Apresentamos os principais problemas detectados . Os resultados da combinação das diretrizes da UD com as características dos numerais em português são apresentados em detalhes, com exemplos, juntamente com os argumentos que amparam cada decisão tomada.

Efeitos da variação linguística na decisão lexical

, Raquel Meister Ko. Freitag & Victor Renê Andrade Souza
This study presents a new version of the lexical decision test designed to capture the social appreciation of variable phonological phenomena [Freitag and Souza 2019]. The effects of lexical decision were tested in standard and non-standard variants of the phenomena of monophthongtion descending and increasing, denasalization of final unstressed nasal diphthong and palatalization of alveolar stops, in progressive and regressive environment, in a sample of 25 university students from Sergipe. The results reinforce what has...

Sentiment Analysis in Portuguese Texts from Online Health Community Forums: Data, Model and Evaluation

, Thiago Castro Ferreira, Yohan Bonescki Gumiel, Isabela Lee, Adriana Pagano & Tayane Arantes Soares
This study introduces novel data and models for the task of Sentiment Analysis in Portuguese texts about Diabetes Mellitus. The corpus contains 1290 posts retrieved from online health community forums in Portuguese and annotated by two annotators according to 3 sentiment categories (e.g. Positive, Neutral and Negative). Evaluation of traditional (Support Vector Machine, Decision Tree, Random Forest and Logistic Regression classifiers) and state-ofthe- art (BERT-based models) machine learning classifiers for the task showed the advantage...

Utilizando BERTimbau para a Classificação de Emoções em Português

, Luiz Otávio Alves Hammes & Larissa Freitas
Apresentamos nosso trabalho no qual realizamos o fine-tuning dos modelos BERTimbau-base e BERTimbau-large na tarefa de classificação de 27 tipos de emoções em sentenças, baseado no dataset GoEmotions traduzido para a língua portuguesa, por meio de ferramentas de traducão automática. Comparamos os resultados de nossos experimentos com os resultados disponibilizados pelos autores do dataset GoEmotions e obtivemos um ganho de desempenho ao qual atribuímos ao algoritmo de balanceamento utilizado. Além disso avaliamos o modelo BERTimbau...

Modified Posterior Exenteration

https://gynaefellow.com/surgical-techniques/modified-posterior-exenteration-with-end-to-end-anastomosis-ovarian-cancer/

SARS-CoV-2 Antivirals: A Study in Open Science, FAIR Data, and Other Challenges in R&D (BioIT 2021 recording)

Christopher Southan
Despite the success of SARS-CoV-2 vaccines, there is a crucial need for new antiviral drugs, especially since the virus is likely to become globally endemic, and the leading target for SARS-CoV-2 antivirals is the M-Protease. This talk will address the history of the SARS-CoV-2 M-Protease as an antiviral drug target and complex research policy issues, including Open Science vs. closed drug development, FAIR data, open access, repurposing, and reproducibility

Creating an accessible syllabus

Interview with Elmer Bonomo

Elmer Bonomo
Interview with Elmer Bonomo

Interview with Elizabeth & Margaret Strannigan

Elizabeth Strannigan & Margaret Strannigan
Interview with Elizabeth & Margaret Strannigan

Interview with Elizabeth & Margaret Strannigan

Elizabeth Strannigan & Margaret Strannigan
Interview with Elizabeth & Margaret Strannigan

Interview with Edwin Keimig

Edwin Keimig
Interview with Edwin Keimig

Registration Year

  • 2021
    46,231

Resource Types

  • Audiovisual
    46,231

Affiliations

  • UNSW Sydney
    64
  • Zurich University of the Arts
    44
  • Technological University Dublin
    15
  • University of Virginia
    5
  • University of Southampton
    5
  • University of Birmingham
    3
  • University of Sheffield
    3
  • Méditerranée Infection Foundation
    2
  • Southern Oregon University
    2
  • University of Nottingham
    2