Reduction in child mortality is one of the United Nations Sustainable Development Goals for 2030.... more Reduction in child mortality is one of the United Nations Sustainable Development Goals for 2030. In Brazil, despite recent reduction in child mortality in the last decades, the neonatal mortality is a persistent problem and it is associated with the quality of prenatal, childbirth care and social-environmental factors. In a proper health system, the effect of some of these factors could be minimized by the appropriate number of newborn intensive care units, number of health care units, number of neonatal incubators and even by the correct level of instruction of mothers, which can lead to a proper care along the prenatal period. With the intent of providing knowledge resources for planning public health policies focused on neonatal mortality reduction, we propose a new data-driven machine lean- ing method for Neonatal Mortality Rate forecasting called NeMoR, which predicts neonatal mortality rates for 4 months ahead, using NeoDeathForecast, a monthly base time series dataset compos...
Infant mortality is an important health measure in a population as a crude indicator of the pover... more Infant mortality is an important health measure in a population as a crude indicator of the poverty and socioeconomic level. It also shows the availability and quality of health services and medical technology in a specific region. Although improvements have been observed in the last decades, the implementation of actions to reduce infant mortality is still a concern in many countries. To address such an important problem, this paper proposes a new support decision approach to classify newborns according to their neonatal mortality risk. Using features related to mother, newborn, and socio-demographic, we model the problem using a data-driven classification model able to provide the probability of a newborn dying until 28th days of life. More than a theoretical study, decision support tools as the one proposed here is relevant in countries in development as Brazil, because it aims at identifying risky neonates that may die to raise the attention of medical practitioners so that they can work harder to reduce the overall neonatal mortality. Overcoming an AUC of 96%, the proposed method is able to provide not just the probability of death risk but also an explicable interpretation of most important features for model decision, which is paramount in public health applications. Furthermore, we provide an extensive analysis across different rounds of experiments, including an analysis of pre and post partum features influence over data-driven model. Finally, different from previously conducted studies which rely on databases with less than 100,000 samples, our model takes advantage from a new proposed database, constructed using more than 1,400,000 samples comprising births and deaths extracted from public records in São Paulo-Brazil from 2012 to 2018.
Infant mortality is one of the most important socioeconomic and health quality indicators in the ... more Infant mortality is one of the most important socioeconomic and health quality indicators in the world. In Brazil, neonatal mortality accounts to 70% of the infant mortality. Despite its importance, neonatal mortality showed increasing signals in last years, which causes concerns about the necessity of efficient and effective methods able to help reducing it. In this paper a new approach is proposed to classify newborns that may be susceptible to neonatal mortality by applying machine learning methods using features extracted from public health datasets. The approach is evaluated in a dataset containing of 15,858 records, which were created, by linking records from SINASC and SIM, specifically from São Paulo city (Brazil), between 2012 and 2018. As results, using SVM, XGBoost, Logistic Regression and Random Forests Machine Learning algorithms, an average AUC of 0.96 was achieved when classifying samples as susceptible to death or not. Furthermore, the SHAP method was used to underst...
SPNeodeath dataset includes births and deaths of infants during the neonatal period from São Paul... more SPNeodeath dataset includes births and deaths of infants during the neonatal period from São Paulo city between 2012 and 2018, containing more than 1.4 million records. The dataset was created from SINASC and SIM Brazilian information systems for births and deaths respectively. SINASC comprises information about demographic and epidemiological data for the infant, mother, prenatal care and childbirth. SIM collects information about mortality, and it is used as the basis for the calculation of vital statistics, such as neonatal mortality rate. SIM was only used to label records from SINASC, when the death happened until 28 days of life. SPNeodeath has 23 variables with socioeconomic maternal condition features, maternal obstetrics features, newborn related features and previous care related features, besides a label feature describing if the subject survived, or not, after 28 days of life. In order to build the dataset, DBF files were downloaded from DATASUS ftp repository and converted to CSV format, the
Evaluation of Beauveria bassiana (Bals.) Vuill. and Metarhizium anisopliae (Metsch.) Sorok. to co... more Evaluation of Beauveria bassiana (Bals.) Vuill. and Metarhizium anisopliae (Metsch.) Sorok. to control Sitophilus zeamais (Coleoptera: Curculionidae) ABSTRACT-This research aimed to evaluate, under laboratory conditions, the entomopathogenic fungi Beauveria bassiana (Bals.) Vuill. and Metarhizium anisopliae (Metsch.) Sorok to control Sitophilus zeamais Mots. Bioassays were conducted to evaluate the pathogenicity of 16 isolates of B. bassiana and 2 isolates of M. anisopliae, based on virulence, vegetative growth and conidia production in Petri dishes and on rice and insect cadavers. All tested isolates were pathogenic to S. zeamais. The highest cumulative mortalities at 5th day were obtained with the isolates Unioeste 4, Unioeste 39 e Esalq 643 of B. bassiana. Regarding to the virulence, these three isolates did not differ among themselves. However, regarding to the colony average diameter, conidia production per colony and per cadaver, the isolate Esalq 643 was the most effective one. Regarding to rice conidia production, both Unioeste 4 and Esalq 643 isolates were equally productive. In general, the isolates Esalq 643 and Unioeste 4 were very effective with potential for exploiting in the microbial control of S. zeamais. KEYWORDS-microbial control, maize weevil, stored grain pests, entomopathogenic fungi RESUMO-Este trabalho teve como objetivo avaliar, em condições de laboratório, os fungos entomopatogênicos Beauveria bassiana (Bals.) Vuill. e Metarhizium anisopliae (Metsch.) Sorok. no controle de Sitophilus zeamais Mots. Foram realizados bioensaios de patogenicidade e comparação de 16 isolados de B. bassiana e 2 isolados de M. anisopliae, avaliando-se a patogenicidade, virulência, crescimento vegetativo e produção de conídios em placa-de-Petri e em arroz e cadáver dos insetos. Todos os isolados foram patogênicos a S. zeamais. As mortalidades acumuladas mais elevadas ao 5 o dia foram obtidas com os isolados Unioeste 4, Unioeste 39 e Esalq 643 de B. bassiana. Quanto à virulência, esses três isolados não diferiram entre si, no entanto, em relação ao diâmetro médio de colônia, produção de conídios por colônia e produção de conídios por cadáver, o isolado Esalq 643 foi o mais eficiente. Na produção média de conídios em arroz, os isolados Unioeste 4 e Esalq 643 não diferiram entre si, sendo ambos produtivos. Em geral, os isolados Esalq 643 e Unioeste 4 se mostraram eficientes, tendo potencial para explorar no controle microbiano de S. zeamais. PALAVRAS-CHAVE-controle microbiano, gorgulho, praga de grãos armazenados, fungo entomopatogênico Fungos Entomopatogênicos para Controle de Sitophilus zeamais Potrich et al.
2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), 2014
Automated trading has become very popular in electronic markets, such as stock market. The design... more Automated trading has become very popular in electronic markets, such as stock market. The design and evaluation of trading agents are not trivial due to the complexity and dynamics of this scenario. Using an actual and reliable dataset from the Brazilian Stock Exchange, and aiming to support the Market Making process in High-Frequency Trading, in this work we design and evaluate some models of automated agents for stock market intraday trading. The modeled strategies are inspired by the Elliot Wave Principle and based on some technical concepts commonly used by stock market analysts. The results are promising, besides it is clearly that financial gains are not trivial to acquire. A variety of results were observed, part of them providing gains for all assets in specific trading days, and other part showing losses for other trading days. A rich experimental analysis provide interesting findings and insights, which will contribute for designing more effective trading agents.
2015 International Joint Conference on Neural Networks (IJCNN), 2015
The aim of this study was to model and use machine learning techniques to maximize the chance of ... more The aim of this study was to model and use machine learning techniques to maximize the chance of a market maker be executed successfully in a stock market, that is, when their bid and ask orders are filled at the desired prices. In this context, a binary ensemble classifier was created to decide whether, at a specific time, is or not propitious to start a new market making process. Conducting the study over a large volume of data for high-frequency traders, we showed that the new proposed ensemble classifier was able to improve the efficiency of the isolated models and the precision of the models are better than random decision makers.
Reduction in child mortality is one of the United Nations Sustainable Development Goals for 2030.... more Reduction in child mortality is one of the United Nations Sustainable Development Goals for 2030. In Brazil, despite recent reduction in child mortality in the last decades, the neonatal mortality is a persistent problem and it is associated with the quality of prenatal, childbirth care and social-environmental factors. In a proper health system, the effect of some of these factors could be minimized by the appropriate number of newborn intensive care units, number of health care units, number of neonatal incubators and even by the correct level of instruction of mothers, which can lead to a proper care along the prenatal period. With the intent of providing knowledge resources for planning public health policies focused on neonatal mortality reduction, we propose a new data-driven machine lean- ing method for Neonatal Mortality Rate forecasting called NeMoR, which predicts neonatal mortality rates for 4 months ahead, using NeoDeathForecast, a monthly base time series dataset compos...
Infant mortality is an important health measure in a population as a crude indicator of the pover... more Infant mortality is an important health measure in a population as a crude indicator of the poverty and socioeconomic level. It also shows the availability and quality of health services and medical technology in a specific region. Although improvements have been observed in the last decades, the implementation of actions to reduce infant mortality is still a concern in many countries. To address such an important problem, this paper proposes a new support decision approach to classify newborns according to their neonatal mortality risk. Using features related to mother, newborn, and socio-demographic, we model the problem using a data-driven classification model able to provide the probability of a newborn dying until 28th days of life. More than a theoretical study, decision support tools as the one proposed here is relevant in countries in development as Brazil, because it aims at identifying risky neonates that may die to raise the attention of medical practitioners so that they can work harder to reduce the overall neonatal mortality. Overcoming an AUC of 96%, the proposed method is able to provide not just the probability of death risk but also an explicable interpretation of most important features for model decision, which is paramount in public health applications. Furthermore, we provide an extensive analysis across different rounds of experiments, including an analysis of pre and post partum features influence over data-driven model. Finally, different from previously conducted studies which rely on databases with less than 100,000 samples, our model takes advantage from a new proposed database, constructed using more than 1,400,000 samples comprising births and deaths extracted from public records in São Paulo-Brazil from 2012 to 2018.
Infant mortality is one of the most important socioeconomic and health quality indicators in the ... more Infant mortality is one of the most important socioeconomic and health quality indicators in the world. In Brazil, neonatal mortality accounts to 70% of the infant mortality. Despite its importance, neonatal mortality showed increasing signals in last years, which causes concerns about the necessity of efficient and effective methods able to help reducing it. In this paper a new approach is proposed to classify newborns that may be susceptible to neonatal mortality by applying machine learning methods using features extracted from public health datasets. The approach is evaluated in a dataset containing of 15,858 records, which were created, by linking records from SINASC and SIM, specifically from São Paulo city (Brazil), between 2012 and 2018. As results, using SVM, XGBoost, Logistic Regression and Random Forests Machine Learning algorithms, an average AUC of 0.96 was achieved when classifying samples as susceptible to death or not. Furthermore, the SHAP method was used to underst...
SPNeodeath dataset includes births and deaths of infants during the neonatal period from São Paul... more SPNeodeath dataset includes births and deaths of infants during the neonatal period from São Paulo city between 2012 and 2018, containing more than 1.4 million records. The dataset was created from SINASC and SIM Brazilian information systems for births and deaths respectively. SINASC comprises information about demographic and epidemiological data for the infant, mother, prenatal care and childbirth. SIM collects information about mortality, and it is used as the basis for the calculation of vital statistics, such as neonatal mortality rate. SIM was only used to label records from SINASC, when the death happened until 28 days of life. SPNeodeath has 23 variables with socioeconomic maternal condition features, maternal obstetrics features, newborn related features and previous care related features, besides a label feature describing if the subject survived, or not, after 28 days of life. In order to build the dataset, DBF files were downloaded from DATASUS ftp repository and converted to CSV format, the
Evaluation of Beauveria bassiana (Bals.) Vuill. and Metarhizium anisopliae (Metsch.) Sorok. to co... more Evaluation of Beauveria bassiana (Bals.) Vuill. and Metarhizium anisopliae (Metsch.) Sorok. to control Sitophilus zeamais (Coleoptera: Curculionidae) ABSTRACT-This research aimed to evaluate, under laboratory conditions, the entomopathogenic fungi Beauveria bassiana (Bals.) Vuill. and Metarhizium anisopliae (Metsch.) Sorok to control Sitophilus zeamais Mots. Bioassays were conducted to evaluate the pathogenicity of 16 isolates of B. bassiana and 2 isolates of M. anisopliae, based on virulence, vegetative growth and conidia production in Petri dishes and on rice and insect cadavers. All tested isolates were pathogenic to S. zeamais. The highest cumulative mortalities at 5th day were obtained with the isolates Unioeste 4, Unioeste 39 e Esalq 643 of B. bassiana. Regarding to the virulence, these three isolates did not differ among themselves. However, regarding to the colony average diameter, conidia production per colony and per cadaver, the isolate Esalq 643 was the most effective one. Regarding to rice conidia production, both Unioeste 4 and Esalq 643 isolates were equally productive. In general, the isolates Esalq 643 and Unioeste 4 were very effective with potential for exploiting in the microbial control of S. zeamais. KEYWORDS-microbial control, maize weevil, stored grain pests, entomopathogenic fungi RESUMO-Este trabalho teve como objetivo avaliar, em condições de laboratório, os fungos entomopatogênicos Beauveria bassiana (Bals.) Vuill. e Metarhizium anisopliae (Metsch.) Sorok. no controle de Sitophilus zeamais Mots. Foram realizados bioensaios de patogenicidade e comparação de 16 isolados de B. bassiana e 2 isolados de M. anisopliae, avaliando-se a patogenicidade, virulência, crescimento vegetativo e produção de conídios em placa-de-Petri e em arroz e cadáver dos insetos. Todos os isolados foram patogênicos a S. zeamais. As mortalidades acumuladas mais elevadas ao 5 o dia foram obtidas com os isolados Unioeste 4, Unioeste 39 e Esalq 643 de B. bassiana. Quanto à virulência, esses três isolados não diferiram entre si, no entanto, em relação ao diâmetro médio de colônia, produção de conídios por colônia e produção de conídios por cadáver, o isolado Esalq 643 foi o mais eficiente. Na produção média de conídios em arroz, os isolados Unioeste 4 e Esalq 643 não diferiram entre si, sendo ambos produtivos. Em geral, os isolados Esalq 643 e Unioeste 4 se mostraram eficientes, tendo potencial para explorar no controle microbiano de S. zeamais. PALAVRAS-CHAVE-controle microbiano, gorgulho, praga de grãos armazenados, fungo entomopatogênico Fungos Entomopatogênicos para Controle de Sitophilus zeamais Potrich et al.
2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), 2014
Automated trading has become very popular in electronic markets, such as stock market. The design... more Automated trading has become very popular in electronic markets, such as stock market. The design and evaluation of trading agents are not trivial due to the complexity and dynamics of this scenario. Using an actual and reliable dataset from the Brazilian Stock Exchange, and aiming to support the Market Making process in High-Frequency Trading, in this work we design and evaluate some models of automated agents for stock market intraday trading. The modeled strategies are inspired by the Elliot Wave Principle and based on some technical concepts commonly used by stock market analysts. The results are promising, besides it is clearly that financial gains are not trivial to acquire. A variety of results were observed, part of them providing gains for all assets in specific trading days, and other part showing losses for other trading days. A rich experimental analysis provide interesting findings and insights, which will contribute for designing more effective trading agents.
2015 International Joint Conference on Neural Networks (IJCNN), 2015
The aim of this study was to model and use machine learning techniques to maximize the chance of ... more The aim of this study was to model and use machine learning techniques to maximize the chance of a market maker be executed successfully in a stock market, that is, when their bid and ask orders are filled at the desired prices. In this context, a binary ensemble classifier was created to decide whether, at a specific time, is or not propitious to start a new market making process. Conducting the study over a large volume of data for high-frequency traders, we showed that the new proposed ensemble classifier was able to improve the efficiency of the isolated models and the precision of the models are better than random decision makers.
Uploads
Papers by Everton Silva