Search

In the Brazilian state of São Paulo, contaminated sites (CSs) constitute threats to health, environment and socioeconomic situation of populations. Over the past two decades, the Environmental Agency of São Paulo (CETESB) has monitored these known CSs. This paper discusses the produced dataset through digitising the CETESB reports and making them accessible to the public in English. The dataset reports on qualitative aspects of contamination within the registered sites (e.g., contamination type and spread) and their management status. The data was extracted from CETESB reports using a machine-learning computer vision algorithm. It comprises two components: an optical character recognition (OCR) engine for text extraction and a convolutional neural network (CNN) image classifier to identify checked boxes. The digitisation was followed by harmonisation and quality assurance processes to ensure the consistency and validity of the data. Making this dataset accessible will allow future work on predictive analysis and decision-making and will inform the required policy-making to improve the management of the CSs in Brazil. [ABSTRACT FROM AUTHOR]

The coronavirus (COVID-19) is a disease declared a global pandemic that threatens the whole world. Since then, research has accelerated and varied to find practical solutions for the early detection and correct identification of this disease. Several researchers have focused on using the potential of Artificial Intelligence (AI) techniques in disease diagnosis to diagnose and detect the coronavirus. This paper developed deep learning (DL) and machine learning (ML) -based models using laboratory findings to diagnose COVID-19. Six different methods are used in this study: Knearest neighbor (KNN), Decision Tree (DT) and Naive Bayes (NB) as a machine learning method, and Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Long-term memory (LSTM) as DL methods. These approaches are evaluated using a dataset obtained from the Israelita Albert Einstein Hospital in Sao Paulo, Brazil. This data consists of 5644 laboratory results from different patients, with 10% being Covid-19 positive cases. The dataset includes 18 attributes that characterizeCOVID-19. We used accuracy, f1-score, recall and precision to evaluate the different developed systems. The obtained results confirmed these approaches' effectiveness in identifying COVID-19, However, ML-based classifiers couldn't performup to the standards achieved byDL-basedmodels. Among all, NB performed worst by hardly achieving accuracy above 76%,Whereas KNN and DT compete by securing 84.56% and 85% accuracies, respectively. Besides these, DL models attained better performance as CNN, DNN and LSTM secured more than 90% accuracies. The LTSM outperformed all by achieving an accuracy of 96.78% and an F1-score of 96.58%. [ABSTRACT FROM AUTHOR]

Machine learning models have recently provided great promise in diagnosis of several ophthalmic disorders, including keratoconus (KCN). Keratoconus, a noninflammatory ectatic corneal disorder characterized by progressive cornea thinning, is challenging to detect as signs may be subtle. Several machine learning models have been proposed to detect KCN, however most of the models are supervised and thus require large well-annotated data. This paper proposes a new unsupervised model to detect KCN, based on adapted flower pollination algorithm (FPA) and the k-means algorithm. We will evaluate the proposed models using corneal data collected from 5430 eyes at different stages of KCN severity (1520 healthy, 331 KCN1, 1319 KCN2, 1699 KCN3 and 579 KCN4) from Department of Ophthalmology and Visual Sciences, Paulista Medical School, Federal University of São Paulo, São Paulo in Brazil and 1531 eyes (Healthy = 400, KCN1 = 378, KCN2 = 285, KCN3 = 200, KCN4 = 88) from Department of Ophthalmology, Jichi Medical University, Tochigi in Japan and used several accuracy metrics including Precision, Recall, F-Score, and Purity. We compared the proposed method with three other standard unsupervised algorithms including k-means, Kmedoids, and Spectral cluster. Based on two independent datasets, the proposed model outperformed the other algorithms, and thus could provide improved identification of the corneal status of the patients with keratoconus. [ABSTRACT FROM AUTHOR]

To support the decision-making process of new investors, this paper aims to implement Machine Learning algorithms to generate investment indications, considering the Brazilian scenario. Three artificial intelligence techniques were implemented, namely: Multilayer Perceptron, Logistic Regression and Decision Tree, which performed the classification of investments. The database used was the one provided by the website Oceans14, containing the history of Fundamental Indicators and the history of Quotations, considering BOVESPA (São Paulo State Stock Exchange). The results of the different algorithms were compared to each other using the following metrics: accuracy, precision, recall, and F1-score. The Decision Tree was the algorithm that obtained the best classification metrics and an accuracy of 77%. [ABSTRACT FROM AUTHOR]

Background and Objective. To mitigate the spread of the virus responsible for COVID-19, known as SARS-CoV-2, there is an urgent need for massive population testing. Due to the constant shortage of PCR (polymerase chain reaction) test reagents, which are the tests for COVID-19 by excellence, several medical centers have opted for immunological tests to look for the presence of antibodies produced against this virus. However, these tests have a high rate of false positives (positive but actually negative test results) and false negatives (negative but actually positive test results) and are therefore not always reliable. In this paper, we proposed a solution based on Data Analysis and Machine Learning to detect COVID-19 infections. Methods. Our analysis and machine learning algorithm is based on most cited two clinical datasets from the literature: one from San Raffaele Hospital Milan Italia and the other from Hospital Israelita Albert Einstein São Paulo Brasilia. The datasets were processed to select the best features that most influence the target, and it turned out that almost all of them are blood parameters. EDA (Exploratory Data Analysis) methods were applied to the datasets, and a comparative study of supervised machine learning models was done, after which the support vector machine (SVM) was selected as the one with the best performance. Results. SVM being the best performant is used as our proposed supervised machine learning algorithm. An accuracy of 99.29%, sensitivity of 92.79%, and specificity of 100% were obtained with the dataset from Kaggle (https://www.kaggle.com/einsteindata4u/covid19) after applying optimization to SVM. The same procedure and work were performed with the dataset taken from San Raffaele Hospital (https://zenodo.org/record/3886927#.YIluB5AzbMV). Once more, the SVM presented the best performance among other machine learning algorithms, and 92.86%, 93.55%, and 90.91% for accuracy, sensitivity, and specificity, respectively, were obtained. Conclusion. The obtained results, when compared with others from the literature based on these same datasets, are superior, leading us to conclude that our proposed solution is reliable for the COVID-19 diagnosis. [ABSTRACT FROM AUTHOR]

This article addresses the challenges of selecting robust classifiers with increasing noise levels in real-world scenarios. We propose the WB Score methodology, which enables the identification of reliable classifiers for deployment in noisy environments. The methodology addresses four significant challenges that are commonly encountered: (i) Ensuring classifiers possess robustness to noise; (ii) Overcoming the difficulty of obtaining representative data that captures real-world noise; (iii) Addressing the complexity of detecting noise, making it challenging to differentiate it from natural variations in the data; and (iv) Meeting the requirement for classifiers capable of efficiently handling noise, allowing prompt responses for decision-making. WB Score provides a comprehensive approach for classifier assessment and selection to address these challenges. We analyze five classic datasets and one customized flooding dataset in São Paulo. The results demonstrate the practical effect of using the WB Score methodology is the enhanced ability to select robust classifiers for datasets in noisy real-world scenarios. Compared with similar techniques, the improvement centers around providing a visual and intuitive output, enhancing the understanding of classifier resilience against noise, and streamlining the decision-making process. [ABSTRACT FROM AUTHOR]

Managing the rapid growth of deprived areas (commonly known as slums, informal settlements, etc.) in cities of Low- to Middle-Income Countries (LMICs) demands detailed and consistent information that is often unavailable. Recent Earth Observation (EO) mapping approaches with supervised classification models overlook the diversity of deprived areas and require resource-intensive training sets. In this study, we analyse the potential of unsupervised machine learning (ML) models to capture intra-urban diversity of deprived areas in São Paulo, using solely open geodata. We provide a workflow of characterising deprivation at a city scale with a disaggregated approach, offering scalability and transferability potential. First, we extract a pool of spatial features from open geospatial datasets to characterise the morphological and environmental conditions of the study area. After input preparation, we train and optimise a k-means model, including a coupled feature importance tool. Four cluster types emerged with different deprivation aspects such as higher and lower accessibility to services and infrastructure, sparser and denser occupation; regular and complex morphology; flat and steep terrain. This alternative methodology to capture diversity of deprived areas with open EO-based features can inform locally targeted, thus more efficient, urban policies and interventions. [ABSTRACT FROM AUTHOR]

This study employs surface and remote sensing data jointly with deep learning techniques to examine the influence of vehicular traffic in the seasonal patterns of CO, NO2, PM2.5, and PM10 concentrations in the São Paulo municipality, as the period of physical distancing (March 2020 to December 2021), due to SARS-CoV-2 pandemic and the resumption of activities, made it possible to observe significant variations in the flow of vehicles in the city of São Paulo. Firstly, an analysis of the planetary boundary layer height and ventilation coefficient was performed to identify the seasons' patterns of pollution dispersion. Then, the variations (from 2018 to 2021) of the seasonal average values of air temperature, relative humidity, precipitation, and thermal inversion occurrence/position were compared to identify possible variations in the patterns of such variables that would justify (or deny) the occurrence of more favorable conditions for pollutants dispersion. However, no significant variations were found. Finally, the seasonal average concentrations of the previously mentioned pollutants were compared from 2018 to 2021, and the daily concentrations observed during the pandemic period were compared with a model based on an artificial neural network. Regarding the concentration of pollutants, the primarily sourced from vehicular traffic (CO and NO2) exhibited substantial variations, demonstrating an inverse relationship with the rate of social distancing. In addition, the measured concentrations deviated from the predictive model during periods of significant social isolation. Conversely, pollutants that were not primarily linked to vehicular sources (PM2.5 and PM10) exhibited minimal variation from 2018 to 2021; thus, their measured concentration remained consistent with the prediction model. [ABSTRACT FROM AUTHOR]

The particulate matter PM 10 concentrations have been impacting hospital admissions due to respiratory diseases. The air pollution studies seek to understand how this pollutant affects the health system. Since prediction involves several variables, any disparity causes a disturbance in the overall system, increasing the difficulty of the models' development. Due to the complex nonlinear behavior of the problem and their influencing factors, Artificial Neural Networks are attractive approaches for solving estimations problems. This paper explores two neural network architectures denoted unorganized machines: the echo state networks and the extreme learning machines. Beyond the standard forms, models variations are also proposed: the regularization parameter (RP) to increase the generalization capability, and the Volterra filter to explore nonlinear patterns of the hidden layers. To evaluate the proposed models' performance for the hospital admissions estimation by respiratory diseases, three cities of São Paulo state, Brazil: Cubatão, Campinas and São Paulo, are investigated. Numerical results show the standard models' superior performance for most scenarios. Nevertheless, considering divergent intensity in hospital admissions, the RP models present the best results in terms of data dispersion. Finally, an overall analysis highlights the models' efficiency to assist the hospital admissions management during high air pollution episodes. [ABSTRACT FROM AUTHOR]

Forecasting photovoltaic electricity generation is one of the key components to reducing the impacts of solar power natural variability, nurturing the penetration of renewable energy sources. Machine learning is a well-known method that relies on the principle that systems can learn from previously measured data, detecting patterns which are then used to predict future values of a target variable. These algorithms have been used successfully to predict incident solar irradiation, but the results depend on the specificities of the studied location due to the natural variability of the meteorological parameters. This paper presents an extensive comparison of the three ML algorithms most used worldwide for forecasting solar radiation, Support Vector Machine (SVM), Artificial Neural Network (ANN), and Extreme Learning Machine (ELM), aiming at the best prediction of daily solar irradiance in a São Paulo context. The largest dataset in Brazil for meteorological parameters, containing measurements from 1933 to 2014, was used to train and compare the results of the algorithms. The results showed good approximation between measured and predicted global solar radiation for the three algorithms; however, for São Paulo, the SVM produced a lower Root-Mean-Square Error (RMSE), and ELM, a faster training rate. Using all 10 meteorological parameters available for the site was the best approach for the three algorithms at this location. [ABSTRACT FROM AUTHOR]

São Paulo is the most populous state in Brazil, home to around 22% of the country's population. The total number of Covid-19-infected people in São Paulo has reached more than 1 million, while its total death toll stands at 25% of all the country's fatalities. Joining the Brazilian academia efforts in the fight against Covid-19, in this paper we describe a unified framework for monitoring and forecasting the Covid-19 progress in the state of São Paulo. More specifically, a freely available, online platform to collect and exploit Covid-19 time-series data is presented, supporting decision-makers while still allowing the general public to interact with data from different regions of the state. Moreover, a novel forecasting data-driven method has also been proposed, by combining the so-called Susceptible-Infectious-Recovered-Deceased model with machine learning strategies to better fit the mathematical model's coefficients for predicting Infections, Recoveries, Deaths, and Viral Reproduction Numbers. We show that the obtained predictor is capable of dealing with badly conditioned data samples while still delivering accurate 10-day predictions. Our integrated computational system can be used for guiding government actions mainly in two basic aspects: real-time data assessment and dynamic predictions of Covid-19 curves for different regions of the state. We extend our analysis and investigation to inspect the virus spreading in Brazil in its regions. Finally, experiments involving the Covid-19 advance in other countries are also given. [ABSTRACT FROM AUTHOR]

Riparian zones consist of important environmental regions, specifically to maintain the quality of water resources. Accurately mapping forest vegetation in riparian zones is an important issue, since it may provide information about numerous surface processes that occur in these areas. Recently, machine learning algorithms have gained attention as an innovative approach to extract information from remote sensing imagery, including to support the mapping task of vegetation areas. Nonetheless, studies related to machine learning application for forest vegetation mapping in the riparian zones exclusively is still limited. Therefore, this paper presents a framework for forest vegetation mapping in riparian zones based on machine learning models using orbital multispectral images. A total of 14 Sentinel-2 images registered throughout the year, covering a large riparian zone of a portion of a wide river in the Pontal do Paranapanema region, São Paulo state, Brazil, was adopted as the dataset. This area is mainly composed of the Atlantic Biome vegetation, and it is near to the last primary fragment of its biome, being an important region from the environmental planning point of view. We compared the performance of multiple machine learning algorithms like decision tree (DT), random forest (RF), support vector machine (SVM), and normal Bayes (NB). We evaluated different dates and locations with all models. Our results demonstrated that the DT learner has, overall, the highest accuracy in this task. The DT algorithm also showed high accuracy when applied on different dates and in the riparian zone of another river. We conclude that the proposed approach is appropriated to accurately map forest vegetation in riparian zones, including temporal context. [ABSTRACT FROM AUTHOR]

Nutrient diagnosis of orange (Citrus sinensis) groves in Brazil relies on regional information from a limited number of studies transferred to other environments under the ceteris paribus assumption. Interpretation methods are based on crude nutrient compositions that are intrinsically biased by genetics X environment interactions. Our objective was to develop accurate and unbiased nutrient diagnosis of orange groves combining machine learning (ML) and compositional methods. Fruit yield and foliar nutrients were quantified in 551 rainfed 7–15-year-old orange groves of 'Hamlin', 'Valência', and 'Pêra' in the state of São Paulo, Brazil. The data set was further documented using soil classification, soil tests, and meteorological indices. Tissue compositions were log-ratio transformed to account for nutrient interactions. Ionomes differed among scions. Regression ML models showed evidence of overfitting. Binary ML classification models showed acceptable values of areas under the curve (>0.7). Regional standards delineating the multivariate elliptical hyperspace depended on the yield cutoff. A shapeless blob hyperspace was delineated using the k-nearest successful neighbors that showed comparable features and reported realistic yield goals. Regionally derived and site-specific reference compositions may lead to differential interpretation. Large-size and diversified data sets must be collected to inform ML models along the learning curve, tackle model overfitting, and evaluate the merit of blob-scale diagnosis. [ABSTRACT FROM AUTHOR]

The new coronavirus disease (COVID-19) is a challenge for clinical decision-making and the effective allocation of healthcare resources. An accurate prognostic assessment is necessary to improve survival of patients, especially in developing countries. This study proposes to predict the risk of developing critical conditions in COVID-19 patients by training multipurpose algorithms. We followed a total of 1040 patients with a positive RT-PCR diagnosis for COVID-19 from a large hospital from São Paulo, Brazil, from March to June 2020, of which 288 (28%) presented a severe prognosis, i.e. Intensive Care Unit (ICU) admission, use of mechanical ventilation or death. We used routinely-collected laboratory, clinical and demographic data to train five machine learning algorithms (artificial neural networks, extra trees, random forests, catboost, and extreme gradient boosting). We used a random sample of 70% of patients to train the algorithms and 30% were left for performance assessment, simulating new unseen data. In order to assess if the algorithms could capture general severe prognostic patterns, each model was trained by combining two out of three outcomes to predict the other. All algorithms presented very high predictive performance (average AUROC of 0.92, sensitivity of 0.92, and specificity of 0.82). The three most important variables for the multipurpose algorithms were ratio of lymphocyte per C-reactive protein, C-reactive protein and Braden Scale. The results highlight the possibility that machine learning algorithms are able to predict unspecific negative COVID-19 outcomes from routinely-collected data. [ABSTRACT FROM AUTHOR]

Background: In a time when the incidence of severe traumatic brain injury (TBI) is increasing in low- to middle-income countries (LMICs), it is important to understand the behavior of predictive variables in an LMIC's population. There are few previous attempts to generate prediction models for TBI outcomes from local data in LMICs. Our study aim is to design and compare a series of predictive models for mortality on a new cohort in TBI patients in Brazil using Machine Learning. Methods: A prospective registry was set in São Paulo, Brazil, enrolling all patients with a diagnosis of TBI that require admission to the intensive care unit. We evaluated the following predictors: gender, age, pupil reactivity at admission, Glasgow Coma Scale (GCS), presence of hypoxia and hypotension, computed tomography findings, trauma severity score, and laboratory results. Results: Overall mortality at 14 days was 22.8%. Models had a high prediction performance, with the best prediction for overall mortality achieved through Naive Bayes (area under the curve = 0.906). The most significant predictors were the GCS at admission and prehospital GCS, age, and pupil reaction. When predicting the length of stay at the intensive care unit, the Conditional Inference Tree model had the best performance (root mean square error = 1.011), with the most important variable across all models being the GCS at scene. Conclusions: Models for early mortality and hospital length of stay using Machine Learning can achieve high performance when based on registry data even in LMICs. These models have the potential to inform treatment decisions and counsel family members. Level of evidence: This observational study provides a level IV evidence on prognosis after TBI. [ABSTRACT FROM AUTHOR]