Pub Date : 2022-12-20DOI: 10.4025/actascitechnol.v45i1.61765
Juliana Pinto de Lima, E. E. Nunes, L. A. Borges, A. Saczk, G. Pinheiro, Paulo Rogério Siriano Borges, Eduardo Valério de Barros Vilas Boas
Puçá fruits are native to the Cerrado biome yet little explored, presenting different varieties with distinct fruit peel colors. Although puçá fruits have been known to exhibit a good source of bioactive compounds, the phenolic profile of some varieties remains unknown. Based on this context, our research aimed to evaluate the chemical composition and bioactive compounds and characterize for the first time the phenolic profile in yellow puçá, brown puçá, and black puçá by high-performance liquid chromatography coupled with diode array detection (HPLC–DAD). The three puçá varieties contained considerable quantities of important food constituents, such as high concentrations of vitamin C, carotenoids and phenolic compounds. These fruits are mostly composed of phenolic acids, with p-coumaric acid being the major compound in all varieties, while ellagic acid was detected only in the brown puçá. Moreover, (−)-epicatechin was found only in the yellow puçá. This study is the first to report the identification of the phenolic profile in puçá. Moreover, our data indicate that the three fruit varieties present a promising chemical composition, suggesting that they may serve as potential sources of natural antioxidants. In addition, these findings can contribute to the establishment of puçá as a novel ingredient for formulations with functional claims.
{"title":"Physicochemical characteristics and bioactive compounds of three puçá (Mouriri pusa Gardner) varieties, an underexploited fruit from the Brazilian Cerrado","authors":"Juliana Pinto de Lima, E. E. Nunes, L. A. Borges, A. Saczk, G. Pinheiro, Paulo Rogério Siriano Borges, Eduardo Valério de Barros Vilas Boas","doi":"10.4025/actascitechnol.v45i1.61765","DOIUrl":"https://doi.org/10.4025/actascitechnol.v45i1.61765","url":null,"abstract":"Puçá fruits are native to the Cerrado biome yet little explored, presenting different varieties with distinct fruit peel colors. Although puçá fruits have been known to exhibit a good source of bioactive compounds, the phenolic profile of some varieties remains unknown. Based on this context, our research aimed to evaluate the chemical composition and bioactive compounds and characterize for the first time the phenolic profile in yellow puçá, brown puçá, and black puçá by high-performance liquid chromatography coupled with diode array detection (HPLC–DAD). The three puçá varieties contained considerable quantities of important food constituents, such as high concentrations of vitamin C, carotenoids and phenolic compounds. These fruits are mostly composed of phenolic acids, with p-coumaric acid being the major compound in all varieties, while ellagic acid was detected only in the brown puçá. Moreover, (−)-epicatechin was found only in the yellow puçá. This study is the first to report the identification of the phenolic profile in puçá. Moreover, our data indicate that the three fruit varieties present a promising chemical composition, suggesting that they may serve as potential sources of natural antioxidants. In addition, these findings can contribute to the establishment of puçá as a novel ingredient for formulations with functional claims.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.8,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77704457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-20DOI: 10.4025/actascitechnol.v45i1.61684
A. M. Alqudah, Shoroq Qazan, Yusra M. Obeidat
Electroencephalogram (EEG) signal classification is a crucial and very difficult task. Meanwhile, extracting features that are representative and able to discriminate different types of EEG signals is a complex task. Such features are usually fed to machine learning algorithms to classify the EEG signals based on the extracted features. This paper proposed a highly accurate and real-time features extraction method that can be used to help physicians in detecting different types of seizures and states in EEG signals characterized by a set of features extracted from the power spectrum of the EEG window. This is achieved by applying the following four steps. First, the EEG signals dataset contains different classes of EEG signals: Normal Eye Closed, Normal Eye Opened, Focal Seizure, Non-Focal Seizure, and Ictal Seizure activities. Second, each EEG signal has a length of 4097 samples sampled with a sampling frequency of 173.6 Hz which resulted in 23.6 seconds in length, this signal will be truncated into windows (Sub-signals) with a length of 349 samples (Approximately 2 seconds) with a total number of 12 windows for each signal. Afterward, the Fourier Transform (FT) based power spectrum will be computed for each window, then a set of different features are extracted from each window's FT power spectrum, and these features are classified using different Machine Learning (ML) algorithms. The results showed that the proposed methodology yields around 98% accuracy for the five different classification scenarios using different ML algorithms. The suggested method is hence robust, fast, real-time, accurate, and simple.
{"title":"A novel moving window-based power spectrum features for single-channel EEG classification using machine learning","authors":"A. M. Alqudah, Shoroq Qazan, Yusra M. Obeidat","doi":"10.4025/actascitechnol.v45i1.61684","DOIUrl":"https://doi.org/10.4025/actascitechnol.v45i1.61684","url":null,"abstract":"Electroencephalogram (EEG) signal classification is a crucial and very difficult task. Meanwhile, extracting features that are representative and able to discriminate different types of EEG signals is a complex task. Such features are usually fed to machine learning algorithms to classify the EEG signals based on the extracted features. This paper proposed a highly accurate and real-time features extraction method that can be used to help physicians in detecting different types of seizures and states in EEG signals characterized by a set of features extracted from the power spectrum of the EEG window. This is achieved by applying the following four steps. First, the EEG signals dataset contains different classes of EEG signals: Normal Eye Closed, Normal Eye Opened, Focal Seizure, Non-Focal Seizure, and Ictal Seizure activities. Second, each EEG signal has a length of 4097 samples sampled with a sampling frequency of 173.6 Hz which resulted in 23.6 seconds in length, this signal will be truncated into windows (Sub-signals) with a length of 349 samples (Approximately 2 seconds) with a total number of 12 windows for each signal. Afterward, the Fourier Transform (FT) based power spectrum will be computed for each window, then a set of different features are extracted from each window's FT power spectrum, and these features are classified using different Machine Learning (ML) algorithms. The results showed that the proposed methodology yields around 98% accuracy for the five different classification scenarios using different ML algorithms. The suggested method is hence robust, fast, real-time, accurate, and simple.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.8,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87744627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Reinforced concrete is an essential material in the modern world, and the use of genetic algorithms that aim at the optimization of the structures of this material is an increasingly widespread tool. The objective of the present work was to propose a method by means of a Genetic Algorithm to find the optimized geometry of a rectangular reinforced concrete column based on its cost. The two main parts of the work were developed as: a geometry verification algorithm that received height, base, layers in x and y directions, diameters of transverse and longitudinal steel rebar as the main parameters of the proposed sections, and a genetic algorithm that generated 240 random populations and selected them, crossed among them and then generated new 100 generations of individuals, followed by selection of optimized ones by its penalized cost. The generations had more and more favorable individuals and it was possible to determine an optimized geometry for the proposed example. It is, therefore, concluded that genetic algorithms are useful tools for optimizing reinforced concrete parts with multiple parameters. The proposed algorithm methodology really checks and selects the best individuals for the sections proposed by engineers, and larger initial populations are essential to find a minimum global cost among the different options.
{"title":"Optimization of reinforced concrete columns via genetic algorithm","authors":"Isabella Silva Menezes, Vinicius Navarro Varela Tinoco, A. Christoforo, Florisvaldo Cardozo Bomfim Junior, Tarniê Vilela Nunes Narques","doi":"10.4025/actascitechnol.v45i1.61562","DOIUrl":"https://doi.org/10.4025/actascitechnol.v45i1.61562","url":null,"abstract":"Reinforced concrete is an essential material in the modern world, and the use of genetic algorithms that aim at the optimization of the structures of this material is an increasingly widespread tool. The objective of the present work was to propose a method by means of a Genetic Algorithm to find the optimized geometry of a rectangular reinforced concrete column based on its cost. The two main parts of the work were developed as: a geometry verification algorithm that received height, base, layers in x and y directions, diameters of transverse and longitudinal steel rebar as the main parameters of the proposed sections, and a genetic algorithm that generated 240 random populations and selected them, crossed among them and then generated new 100 generations of individuals, followed by selection of optimized ones by its penalized cost. The generations had more and more favorable individuals and it was possible to determine an optimized geometry for the proposed example. It is, therefore, concluded that genetic algorithms are useful tools for optimizing reinforced concrete parts with multiple parameters. The proposed algorithm methodology really checks and selects the best individuals for the sections proposed by engineers, and larger initial populations are essential to find a minimum global cost among the different options.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.8,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86352876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-19DOI: 10.4025/actascitechnol.v45i1.60117
A. Santos, Fernando Luiz de Paula Santil, S. Carbone, Claudionor Ribeiro da Silva
This study addresses the variations in surface temperature - Land Surface Temperature (LST) - in the urban network of the municipality of Paracatu, Minas Gerais State, Brazil, which has humid tropical climate of savannah (type Aw), and in the open pit mining activity located near its urban perimeter, between the years 1990 and 2019. The area was chosen because the municipality is the most important of its microregion, being an attractive pole of work due to the presence of several companies, with emphasis on the mining company Kinross Gold Corporation, which is one of the largest open pit mines and gold producers in Brazil. Images of LANDSAT-5 and 8 satellites were used, which underwent a resampling and standardization of pixels to become the same size. The satellite choice and the period of analysis was based on the beginning of mining activity in the municipality, and a year that was able to represent its current state. Subsequently, the LST calculations made available by the United States Geological Survey (USGS) were applied. When comparing the results of both areas of the first and last year of the series, there was an increase in the variation of the mean, minimum and maximum LST, a fact that is related with the suppression of vegetation for the growth of both areas. Such suppression, together with anthropic occupation, is responsible for one of the neighborhoods (28) that present the highest average variation of LST over the years. On the other hand, the neighborhood that presented the smallest variation on this parameter (47) was recently incorporated as a neighborhood in the city’s Master Plan because it is currently being occupied by the construction of an allotment, evidencing that the temporal variability of LST in the municipality occurs in relation to anthropic presence and its magnitude.
{"title":"The influence of urban and mineral expansion on surface temperature variation","authors":"A. Santos, Fernando Luiz de Paula Santil, S. Carbone, Claudionor Ribeiro da Silva","doi":"10.4025/actascitechnol.v45i1.60117","DOIUrl":"https://doi.org/10.4025/actascitechnol.v45i1.60117","url":null,"abstract":"This study addresses the variations in surface temperature - Land Surface Temperature (LST) - in the urban network of the municipality of Paracatu, Minas Gerais State, Brazil, which has humid tropical climate of savannah (type Aw), and in the open pit mining activity located near its urban perimeter, between the years 1990 and 2019. The area was chosen because the municipality is the most important of its microregion, being an attractive pole of work due to the presence of several companies, with emphasis on the mining company Kinross Gold Corporation, which is one of the largest open pit mines and gold producers in Brazil. Images of LANDSAT-5 and 8 satellites were used, which underwent a resampling and standardization of pixels to become the same size. The satellite choice and the period of analysis was based on the beginning of mining activity in the municipality, and a year that was able to represent its current state. Subsequently, the LST calculations made available by the United States Geological Survey (USGS) were applied. When comparing the results of both areas of the first and last year of the series, there was an increase in the variation of the mean, minimum and maximum LST, a fact that is related with the suppression of vegetation for the growth of both areas. Such suppression, together with anthropic occupation, is responsible for one of the neighborhoods (28) that present the highest average variation of LST over the years. On the other hand, the neighborhood that presented the smallest variation on this parameter (47) was recently incorporated as a neighborhood in the city’s Master Plan because it is currently being occupied by the construction of an allotment, evidencing that the temporal variability of LST in the municipality occurs in relation to anthropic presence and its magnitude.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.8,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76730528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-19DOI: 10.4025/actascitechnol.v45i1.60820
L. R. R. Lucena, M. L. D. M. V. Leite, Álefe Chagas de Lima Costa, João Pedro Soares Caraciolo, J. R. Silva
Forage plants are considered one of the main factors for livestock development, for they present perennial growth, resistance to drought, adaptation to hot climate regions, and wide soil diversity. The water deficit causes changes in their anatomy, physiology, and biochemistry, which can affect all stages of development and productivity. For these reasons, it is necessary to evaluate the lifetime of forage plants under water stress conditions. The design used was a factorial scheme, consisting of two types of grasses, and five levels of water replacement, with ten replications. During the experimental period, grasses were evaluated daily, with more than 70% of leaf area in senescence being considered a dead plant the one with more than 70% of leaf area in senescence. Urochloa mosambicensis lifetime was of 61 days for grasses that were not irrigated, 131 and 195 days for those that received 25% and 50% of field capacity, and greater than 240 days for those that were irrigated with 75 and 100% of field capacity. Digitaria pentzii lifetime was of 54 days for grasses that were not irrigated, 117 and 152 days for those that received 25 and 50% of field capacity, and greater than 240 days for those that were subjected to water regime 75 and 100% of field capacity. Irrigation with 25 and 50% of field capacity doubles and triplicates, respectively, the lifetime of grasses when compared to plants that did not receive irrigation. Irrigations with 75% or more of field capacity do not promote grass mortality.
{"title":"Lifetime of forage grasses submitted to different water regimes using survival analysis","authors":"L. R. R. Lucena, M. L. D. M. V. Leite, Álefe Chagas de Lima Costa, João Pedro Soares Caraciolo, J. R. Silva","doi":"10.4025/actascitechnol.v45i1.60820","DOIUrl":"https://doi.org/10.4025/actascitechnol.v45i1.60820","url":null,"abstract":"Forage plants are considered one of the main factors for livestock development, for they present perennial growth, resistance to drought, adaptation to hot climate regions, and wide soil diversity. The water deficit causes changes in their anatomy, physiology, and biochemistry, which can affect all stages of development and productivity. For these reasons, it is necessary to evaluate the lifetime of forage plants under water stress conditions. The design used was a factorial scheme, consisting of two types of grasses, and five levels of water replacement, with ten replications. During the experimental period, grasses were evaluated daily, with more than 70% of leaf area in senescence being considered a dead plant the one with more than 70% of leaf area in senescence. Urochloa mosambicensis lifetime was of 61 days for grasses that were not irrigated, 131 and 195 days for those that received 25% and 50% of field capacity, and greater than 240 days for those that were irrigated with 75 and 100% of field capacity. Digitaria pentzii lifetime was of 54 days for grasses that were not irrigated, 117 and 152 days for those that received 25 and 50% of field capacity, and greater than 240 days for those that were subjected to water regime 75 and 100% of field capacity. Irrigation with 25 and 50% of field capacity doubles and triplicates, respectively, the lifetime of grasses when compared to plants that did not receive irrigation. Irrigations with 75% or more of field capacity do not promote grass mortality.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.8,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88155831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-19DOI: 10.4025/actascitechnol.v45i1.61451
Iran Carlos Caria Sacramento, V. O. Fernandes, N. Rösch, Emerson de Andrade Marques
Fire emergencies cause severe damage to Brazilian federal universities. An appropriate and efficient tool to prevent or detect such events early is multisensory networks from the Internet of Things (IoT). In this study, we present the stages of development of a WebGIS system which integrates the IoT that allows the detection and helps manage such incidents. The approach consists of a network of multipurpose sensors that can identify different sources of fire hazards. If a potential source is registered, information about environmental conditions is transmitted in real-time to the system. Depending on the severity level, an alert is issued to WebGIS. Location is represented on a map. The entire system consists of single-board devices. Software components are based on open-source tools. The whole network only needs little power and, therefore, theoretically, could be carried out as an autonomous system powered by batteries. The entire system has been tested with flame, temperature, gas, smoke, and humidity sensors. The experiments allowed us to show its potential, formulate recommendations and indications for future studies.
{"title":"Low-cost multipurpose sensor network integrated with iot and webgis for fire safety concerns","authors":"Iran Carlos Caria Sacramento, V. O. Fernandes, N. Rösch, Emerson de Andrade Marques","doi":"10.4025/actascitechnol.v45i1.61451","DOIUrl":"https://doi.org/10.4025/actascitechnol.v45i1.61451","url":null,"abstract":"Fire emergencies cause severe damage to Brazilian federal universities. An appropriate and efficient tool to prevent or detect such events early is multisensory networks from the Internet of Things (IoT). In this study, we present the stages of development of a WebGIS system which integrates the IoT that allows the detection and helps manage such incidents. The approach consists of a network of multipurpose sensors that can identify different sources of fire hazards. If a potential source is registered, information about environmental conditions is transmitted in real-time to the system. Depending on the severity level, an alert is issued to WebGIS. Location is represented on a map. The entire system consists of single-board devices. Software components are based on open-source tools. The whole network only needs little power and, therefore, theoretically, could be carried out as an autonomous system powered by batteries. The entire system has been tested with flame, temperature, gas, smoke, and humidity sensors. The experiments allowed us to show its potential, formulate recommendations and indications for future studies.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.8,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82007298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-19DOI: 10.4025/actascitechnol.v45i1.59993
G. Cassiolato, E. Carvalho, M. Ravagnani
Water Distribution Networks (WDN) are important systems for industrial processes and urban centers. WDN can be formed by reservoirs, pipes, nodes, loops, and pumps and its complete design can be formulated as an optimization problem. The majority of published papers in the open literature use meta-heuristics for problem solution, as well as hydraulic simulators to calculate pressures and velocities. In the present study, a Mixed Integer Non-Linear Programming (MINLP) model was developed to the synthesis of WDN considering the minimization of the WDN total cost, given by the sum of installation and operational costs, which is the novelty in the paper. All the hydraulic calculations were included in the model (mass and energy balances and velocity and pressure upper and lower bounds), avoiding the use of additional software. Reformulation techniques are applied to the model considering the use of logarithms and disjunctive programming. Two case studies extracted from real WDN were used to test the model and global optimization techniques were employed to achieve the results. The results obtained show that the operational costs play an important role in the WDN system design.
{"title":"An MINLP model for the minimization of installation and operational costs in water distribution networks","authors":"G. Cassiolato, E. Carvalho, M. Ravagnani","doi":"10.4025/actascitechnol.v45i1.59993","DOIUrl":"https://doi.org/10.4025/actascitechnol.v45i1.59993","url":null,"abstract":"Water Distribution Networks (WDN) are important systems for industrial processes and urban centers. WDN can be formed by reservoirs, pipes, nodes, loops, and pumps and its complete design can be formulated as an optimization problem. The majority of published papers in the open literature use meta-heuristics for problem solution, as well as hydraulic simulators to calculate pressures and velocities. In the present study, a Mixed Integer Non-Linear Programming (MINLP) model was developed to the synthesis of WDN considering the minimization of the WDN total cost, given by the sum of installation and operational costs, which is the novelty in the paper. All the hydraulic calculations were included in the model (mass and energy balances and velocity and pressure upper and lower bounds), avoiding the use of additional software. Reformulation techniques are applied to the model considering the use of logarithms and disjunctive programming. Two case studies extracted from real WDN were used to test the model and global optimization techniques were employed to achieve the results. The results obtained show that the operational costs play an important role in the WDN system design.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.8,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88279552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-19DOI: 10.4025/actascitechnol.v45i1.56360
Edilson Marcelino Silva, S. A. Jane, F. A. Fernandes, Édipo Menezes da Silva, J. A. Muniz, T. J. Fernandes
The dynamics of organic waste decomposition in the soil can be described by nonlinear regression models, however, the theory for regression models is valid for sufficiently large samples, and in general, in small samples, these properties are unknown. One of the methods for data analysis that has been widely used to overcome this problem is the bayesian inference, as it has the advantage of being able to work with small samples, in addition to allowing the incorporation of information from previous studies, and even having a probability distribution for the parameters, consequently, to present a direct interpretation for the credibility interval. However, criticism has been made because of the effect that a prior subjective distribution can have on posterior distribution. One way of determining objective prior is through of maximum entropy prior distributions. For data of organic waste decomposition in the soil, little is known about the probability distributions of the parameters. The present study aimed to use of maximum entropy prior distributions to the parameters of the Stanford & Smith nonlinear model. In addition, using simulated data, to understand the effect that hyperparameters of prior distribution has on the posterior curve, and also to apply the methodology in the description of CO2 mineralization data from swine manure applied to the soil surface. Data analyzed came from an experiment conducted in a laboratory that evaluated the carbon mineralization of swine manure on the soil surface over time. The posterior distributions were obtained, so the bayesian methodology with maximum entropy prior was efficient in the study of the Stanford & Smith nonlinear model to the data of carbon mineralization of swine manure on the soil surface.
{"title":"Stanford & Smith nonlinear model in the description of CO2 evolved from soil treated with swine manure: maximum entropy prior","authors":"Edilson Marcelino Silva, S. A. Jane, F. A. Fernandes, Édipo Menezes da Silva, J. A. Muniz, T. J. Fernandes","doi":"10.4025/actascitechnol.v45i1.56360","DOIUrl":"https://doi.org/10.4025/actascitechnol.v45i1.56360","url":null,"abstract":"The dynamics of organic waste decomposition in the soil can be described by nonlinear regression models, however, the theory for regression models is valid for sufficiently large samples, and in general, in small samples, these properties are unknown. One of the methods for data analysis that has been widely used to overcome this problem is the bayesian inference, as it has the advantage of being able to work with small samples, in addition to allowing the incorporation of information from previous studies, and even having a probability distribution for the parameters, consequently, to present a direct interpretation for the credibility interval. However, criticism has been made because of the effect that a prior subjective distribution can have on posterior distribution. One way of determining objective prior is through of maximum entropy prior distributions. For data of organic waste decomposition in the soil, little is known about the probability distributions of the parameters. The present study aimed to use of maximum entropy prior distributions to the parameters of the Stanford & Smith nonlinear model. In addition, using simulated data, to understand the effect that hyperparameters of prior distribution has on the posterior curve, and also to apply the methodology in the description of CO2 mineralization data from swine manure applied to the soil surface. Data analyzed came from an experiment conducted in a laboratory that evaluated the carbon mineralization of swine manure on the soil surface over time. The posterior distributions were obtained, so the bayesian methodology with maximum entropy prior was efficient in the study of the Stanford & Smith nonlinear model to the data of carbon mineralization of swine manure on the soil surface.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.8,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84822321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-19DOI: 10.4025/actascitechnol.v45i1.61531
Saad Albawi, Muhanad Hameed Arif, Jumana Waleed
Medical image analysis is a significant burden for doctors, therefore, it is used to supplement image processing. Many medical images are assumed to be diagnosed as accurately as healthcare experts when the precision of image detection and recognition in an image processing approach matches that of a human being. Artificial Intelligence (AI) based predictive modelling is an important component of many healthcare solutions. This paper develops and implements a neural network-based method for skin cancer prediction to expose the neural network's strength in this field. This method determines which form of deep learning is best for diagnosing diseases with an accuracy exceeds human ability in terms of speed and accuracy, and determines the optimum number of layers and neurons in each layer for both Convolutional Neural network (CNN) and Deep Neural Network (DNN) to obtain the best possible precision. The results of the proposed method showed impressive results, especially for CNN. There is a clear superiority of CNN over DNN. The CNN (which relies on convolution filters) provides great results in extracting features due to the focus on the intended area of the image without the surrounding area region of interest. This led to a remarkable decrease in the number of parameters and the speed of attaining results with higher accuracy. The results indicated that CNN has a high accuracy rate compared with the other existing methods where the accuracy rate of CNN is 98.5%.
{"title":"Skin cancer classification dermatologist-level based on deep learning model","authors":"Saad Albawi, Muhanad Hameed Arif, Jumana Waleed","doi":"10.4025/actascitechnol.v45i1.61531","DOIUrl":"https://doi.org/10.4025/actascitechnol.v45i1.61531","url":null,"abstract":"Medical image analysis is a significant burden for doctors, therefore, it is used to supplement image processing. Many medical images are assumed to be diagnosed as accurately as healthcare experts when the precision of image detection and recognition in an image processing approach matches that of a human being. Artificial Intelligence (AI) based predictive modelling is an important component of many healthcare solutions. This paper develops and implements a neural network-based method for skin cancer prediction to expose the neural network's strength in this field. This method determines which form of deep learning is best for diagnosing diseases with an accuracy exceeds human ability in terms of speed and accuracy, and determines the optimum number of layers and neurons in each layer for both Convolutional Neural network (CNN) and Deep Neural Network (DNN) to obtain the best possible precision. The results of the proposed method showed impressive results, especially for CNN. There is a clear superiority of CNN over DNN. The CNN (which relies on convolution filters) provides great results in extracting features due to the focus on the intended area of the image without the surrounding area region of interest. This led to a remarkable decrease in the number of parameters and the speed of attaining results with higher accuracy. The results indicated that CNN has a high accuracy rate compared with the other existing methods where the accuracy rate of CNN is 98.5%.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.8,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84030502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-19DOI: 10.4025/actascitechnol.v45i1.61496
Rilton Robson Lima Vernice, Beatriz Fleury e Silva
This work aims to reflect on the impacts of COVID-19, a disease responsible for the pandemic worldwide status in 2020, on urban housing policies in Brazil, which has faced structural problems since the turn of the century. These problems were accentuated and evidenced with the onset of the pandemic. The paper sought to highlight the dismantling scenario and the setbacks of human rights that are expressed in the manner in which the federal government behaves in the face of the collapse caused by the health crisis. In addition to highlighting that, the housing problem has been sewn with patches that are not effective to supply the gigantic demand for housing in the country currently, besides they do not guarantee the security of tenure to the majority of families in socioeconomic vulnerability. In this context, the focus of the discussion is on the removals and evictions that have occurred during the pandemic, putting at risk an entire population historically neglected by the neoliberal policies of capitalism. Moreover, these policies have been accentuated as a reflection of the recent democratic inflection in the country, which has strongly threatened human and social rights, legitimized by necropolitics, during the pandemic (Mbembe, 2018). The text is presented as a theoretical study carried through an exploratory methodological structure, based on a bibliographic review and documentary analysis of the subject matter. This article does not intend to bring conclusions or final answers, but to present new elements for the debate on the dismantling of Brazilian housing policies, evidenced in the current scenario through the lack of access to decent housing or difficulty in keeping it, mainly for the lowest-income populations.
{"title":"Necropolitics and the Covid-19 pandemic: evictions and removals that mark the recurrent housing problem in Brazil","authors":"Rilton Robson Lima Vernice, Beatriz Fleury e Silva","doi":"10.4025/actascitechnol.v45i1.61496","DOIUrl":"https://doi.org/10.4025/actascitechnol.v45i1.61496","url":null,"abstract":"This work aims to reflect on the impacts of COVID-19, a disease responsible for the pandemic worldwide status in 2020, on urban housing policies in Brazil, which has faced structural problems since the turn of the century. These problems were accentuated and evidenced with the onset of the pandemic. The paper sought to highlight the dismantling scenario and the setbacks of human rights that are expressed in the manner in which the federal government behaves in the face of the collapse caused by the health crisis. In addition to highlighting that, the housing problem has been sewn with patches that are not effective to supply the gigantic demand for housing in the country currently, besides they do not guarantee the security of tenure to the majority of families in socioeconomic vulnerability. In this context, the focus of the discussion is on the removals and evictions that have occurred during the pandemic, putting at risk an entire population historically neglected by the neoliberal policies of capitalism. Moreover, these policies have been accentuated as a reflection of the recent democratic inflection in the country, which has strongly threatened human and social rights, legitimized by necropolitics, during the pandemic (Mbembe, 2018). The text is presented as a theoretical study carried through an exploratory methodological structure, based on a bibliographic review and documentary analysis of the subject matter. This article does not intend to bring conclusions or final answers, but to present new elements for the debate on the dismantling of Brazilian housing policies, evidenced in the current scenario through the lack of access to decent housing or difficulty in keeping it, mainly for the lowest-income populations.","PeriodicalId":7140,"journal":{"name":"Acta Scientiarum-technology","volume":null,"pages":null},"PeriodicalIF":0.8,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74051136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}