Junia Ortiz

Junia Ortiz


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 September 2022 in Atmosphere
Verified
Journal Article
Open access
PDF file
SGStephanie Lima Jorge Galvão
Stephanie Lima Jorge Galvão
JOJunia Ortiz
Junia Ortiz
YKYasmin Kaore Lago Kitagawa
Yasmin Kaore Lago Kitagawa
FCFlávio Santos Conterato
Flávio Santos Conterato
DMDavidson Martins Moreira
Davidson Martins Moreira
Erick Giovani Sperandio NascimentoErick Giovani Sperandio Nascimento
Erick Giovani Sperandio Nascimento
The concern about air pollution in urban areas has substantially increased worldwide. One of its main components, particulate matter (PM) with aerodynamic diameter of ≤2.5 µm (PM2.5), can be inhaled and deposited in deeper regions of the respiratory system, causing adverse effects on human health, which are even more harmful to children. In this sense, the use of deterministic and stochastic models has become a key tool for predicting atmospheric behavior and, thus, providing information for decision makers to adopt preventive actions to mitigate air pollution impacts. However, stochastic models present their own strengths and weaknesses. To overcome some of disadvantages of deterministic models, there has been an increasing interest in the use of deep learning, due to its simpler implementation and its success on multiple tasks, including time series and air quality forecasting. Thus, the objective of the present study is to develop and evaluate the use of four different topologies of deep artificial neural networks (DNNs), analyzing the impact of feature augmentation in the prediction of PM2.5 concentrations by using five levels of discrete wavelet transform (DWT). The following types of deep neural networks were trained and tested on data collected from two living lab stations next to high-traffic roads in Guildford, UK: multi-layer perceptron (MLP), long short-term memory (LSTM), one-dimensional convolutional neural network (1D-CNN) and a hybrid neural network composed of LSTM and 1D-CNN. The performance of each model in making predictions up to twenty-four hours ahead was quantitatively assessed through statistical metrics. The results show that wavelets improved the forecasting results and that discrete wavelet transform is a relevant tool to enhance the performance of DNN topologies, with special emphasis on the hybrid topology that achieved the best results among the applied models.

13 December 2023
Verified
Book Chapter
Open access
PDF file
RORicardo de Oliveira
Ricardo de Oliveira
BMBruno Menezes
Bruno Menezes
JOJunia Ortiz
Junia Ortiz
Erick Giovani Sperandio NascimentoErick Giovani Sperandio Nascimento
Erick Giovani Sperandio Nascimento
This chapter aims to present a classification model for categorizing textual clinical records of breast magnetic resonance imaging, based on lexical, syntactic and semantic analysis of clinical reports according to the Breast Imaging-Reporting and Data System (BI-RADS) classification, using Deep Learning and Natural Language Processing (NLP). The model was developed from transfer learning based on the pre-trained BERTimbau model, BERT model (Bidirectional Encoder Representations from Transformers) trained in Brazilian Portuguese. The dataset is composed of medical reports in Brazilian Portuguese classified into six categories: Inconclusive; Normal or Negative; Certainly Benign Findings; Probably Benign Findings; Suspicious Findings; High Risk of Cancer; Previously Known Malignant Injury. The following models were implemented and compared: Random Forest, SVM, Naïve Bayes, BERTimbau with and without finetuning. The BERTimbau model presented better results, with better performance after finetuning.