Navegando por Assunto "Redes bayesianas"

Agora exibindo 1 - 9 de 9

Acesso aberto (Open Access)
Análise de correlação de focos de queimadas com variáveis climáticas no município de Marabá
(Universidade Federal do Pará, 2016-03-10) ARANHA, Priscila Siqueira; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
The Amazon is composed of a wide variety of ecosystems and forms of occupation, taking a wide variety of settings, including spatial, social, economic, agronomic, which vary from region to region. From this perception of the Amazon region, this work presents an investigative study scenarios and their correlations, in order to quantify and qualify the strength of relationships and dependencies between the different variables involved, such as meteorological factors (relative humidity, rainfall, speed wind and temperature) and the number of fire outbreaks, in order to enable the analysis of the reasons that influence the environmental degradation of the study area. In order to validate the proposed methodology, we conducted a study in the city of Maraba area of settlement projects, whose focus is to analyze the correlation between climate variables and fire outbreaks in the region, using three study scenarios. Therefore, we use some statistical parameters, the Pearson correlation and Bayesian networks in order to establish the degree of dependency between the different variables of interest. From such studies, it is possible to make a set of inferences about the problem under study and possible alternatives, which more balance scenarios for the benefit of environmental sustainability.
Acesso aberto (Open Access)
Uma análise sócio-demográfica da incidência de hanseníase na Amazônia legal brasileira: abordagem baseada em redes bayesianas
(Universidade Federal do Pará, 2019-02-08) GOMES, José Maria da Silveira; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
Leprosy is a millenarian contagious disease, with chronic and stigmatizing characteristics, from the remotest times of humanity until today. It is characterized as a disease of the poor and Brazil is the second country in the world with the highest incidence. The lack of public policies aimed at reducing poverty through the improvement of socio-economic factors in the country is directly related to the incidence of the disease in Brazil. Strategies for control and monitoring should follow intelligent actions. One of the solutions for monitoring the disease is the use of Bayesian networks as a probabilistic method for taking decisions on both the control and the procedures to adopt in order to reduce the incidence of the disease. The objective of the present study is to analyse the association of leprosy incidence in relation to indicators of human development, habitation and income level, considering the Brazilian Amazon region in relation to the entire country. An ecological study, based on data obtained on cases of leprosy in Brazil for the year 2010, obtained from the Information System of Hardship Notifications (SINAN) through the Informatics Department of the National Health Service (DATASUS) and the socio-economic indicators found in the Demographic Census Research database of the Brazilian Institute for Geographical and Statistical Survey – IBGE, as well as information from the Municipal Human Development Index, regarding education and income, obtained from the website of the Human Development Atlas of Brazil, also for the year 2010. The methodology combined data mining with the analysis of spatial distribution. The Bayesian network technique was used aimed at measuring the association between variables of the domain of the problem as well as to establish the analogy of the data between the municipalities under study with data for all other Brazilian municipalities. Applying the algorithm K2 relevant associations were found for the following indicators applied in the investigation: Brazilian Legal Amazon, Municipal Human Development Index of Income and Education and Household Housing Condition. Using the Bayesian network model adopted, there is a significant association between the percentage of homes with more than 2 inhabitants and the rate of incidence of leprosy. Although the relationship between the rate of incidence, socio-economic factors (no water supply, no toilet, poverty and overcrowding of the home), low educational indices and income has already been reported in several studies, the insertion of the indicators that considers population density of the home was a novel proposition of the present study and the indicators of greatest most significance of this investigation. The analysis of leprosy incidence with respect to spatial distribution, comparing the Amazon region with the entire country, revealed that public policies for habitation in the studied region were almost non-existent, since the population density of homes is very high, facilitating the appearance of contagious diseases such as leprosy.
Acesso aberto (Open Access)
Estratégia de otimização para a melhoria da interpretabilidade de redes bayesianas: aplicações em sistemas elétricos de potência
(Universidade Federal do Pará, 2009-12-10) ROCHA, Cláudio Alex Jorge da; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
The study of methods, techniques and tools that can aid the decision processes in power systems, in its many sections, is a subject of great interest. This decision support can be accomplished through many different techniques, particularly those based on computational intelligence, given their applicability on domains with uncertainty. In this proposal, Bayesian networks are used for the extraction of knowledge models from the available data on power systems. Moreover, given the demands of these systems and some limitations imposed to the inferences in Bayesian networks, a method is proposed, using genetic algorithms, capable of extending the power of comprehensibility of the patterns discovered; it aims at finding the optimal scenario in order to attain a given target, considering the incorporation of a priori knowledge from domain specialists, identifying the most influent variables in the domain for the maximization of the target variable.
Acesso aberto (Open Access)
Estratégia do planejamento e otimização de sistemas sem fio, considerando redes interferentes: abordagem baseada em cross-layer
(Universidade Federal do Pará, 2011-06-30) ARAÚJO, Jasmine Priscyla Leite de; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
In spite of the significant increase of the use of Wireless Local Area Network (WLAN) experienced in the last years, design aspects and capacity planning are still systematically neglected during the network implementation. Typically, a wireless local area network is designed and installed by networking professionals. These individuals are familiar with wired networks, but are often unfamiliar with wireless networks. Thus, wireless local area networks installations are prejudiced by the lack of an accurate performance evaluation model and to determine the location of the access point (AP), besides important factors of the environment are not considered in the project. These factors become more important when several APs are installed, sometimes without a frequency planning, to cover a unique building. Faults such as these can cause interference among cells generated by each PA. Therefore, the network will not obtain the QoS patterns required for each service. The present work provides a planning proposal to wireless networks regarding the influence of interference using computational intelligence just as Bayesian Networks. An extensive measurement campaign was done to evaluate the performance of two access points (PAs) under a multi user and interference scenarios. The data collected in the measurement campaign was used as input of the Bayesian networks and confirmed the influence of the interference in the QoS parameters. A genetic algorithm technique was used as a hybrid approach to wireless planning. Another technique, called particle swarm optimization (PSO) was used to compare the optimizations results from the QoS parameters to find the best distance from the AP to the receiver to guarantee the QoS ITU-T recommendations.
Acesso aberto (Open Access)
Estratégia para análise da concentração de infraestrutura de acesso às tecnologias da informação e comunicação nos municípios da Amazônia legal Brasileira
(Universidade Federal do Pará, 2016-03-31) BRITO, Silvana Rossy de; COSTA, João Crisóstomo Weyl Albuquerque; http://lattes.cnpq.br/9622051867672434; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
Access to information is a fundamental right in democratic societies, essential for economic development, social equality, improvement of social, health care, education services and governance. This study is situated on the Concentration of Access to Information and Communication Technologies (ICT) in the municipalities of the Brazilian Legal Amazon. For this, we developed the conceptual model from which we identify the main variables of ICT infrastructure in urban and rural households. Our strategy is to (i) analyze the ICT infrastructure concentration in Brazilian municipalities; (ii) analyze the spatial distribution of ICT infrastructure concentration in urban and rural households in Brazilian municipalities; and (iii) search for associations between parameters describing the ownership of ICT resources in urban and rural households with indicators for income, education, population size, and the existence of electricity in municipalities. To understand these associations at the municipality level, we use Bayesian Networks to reveal dependencies among the variables studied. The results of applying the proposed strategy show that for urban households, the average concentration in the municipalities of the Amazon for computers and Internet access and for fixed phones is lower than in other regions of the country; meanwhile, that for no access and mobile phones is higher than in any other region. For rural households, the average concentration in the municipalities of the Amazon for computers and Internet access, mobile phones, and fixed phones is lower than in any other region of the country; meanwhile, that for no access is higher than in any other region. The study shows that education, income, and population size are determinants of inequality in accessing ICT in Brazilian households. In addition, we advance to analyze the association between teenage motherhood and the representative variables of income, education, and computer and Internet access in the municipalities of the Brazilian Legal Amazon compared to other regions of the country. These networks pointed to the region as the influential variable on the high percentages of teenage mothers and households with computer and Internet access.
Acesso aberto (Open Access)
Uma metodologia para predição do campo elétrico de radiodifusão sonora em ondas médias utilizando inferências bayesianas
(Universidade Federal do Pará, 2013-06-11) COSTA, Juliana Santiago Monteiro; ARAÚJO, Jasmine Priscyla Leite de; http://lattes.cnpq.br/4001747699670004; CAVALCANTE, Gervásio Protásio dos Santos; http://lattes.cnpq.br/2265948982068382
The adoption of digital sound broadcasting systems, which are under testing in the country, allows new studies aimed a better planning for the implementation of new stations, which means to reassess the major existing radio propagation models or propose new alternatives to meet demands inherent in digital systems. The current models, as Recommendations ITU-R P. 1546 and ITU-R P. 1812, do not match closely with the reality of some regions of Brazil, especially in the tropical regions, such as the Amazon Region, due to the high rainfall and the vast existing flora. Using models suited to the propagation channel, it becomes feasible to develop planning tools covering most accurate and efficient. The use of these tools is applicable both to ANATEL, for the elaboration of the basic plans, as distribution channels for broadcasters. This paper presents a methodology using a computational intelligence based in Bayesian Networks for prediction of electric field intensity, which can be applied to planning or expanding coverage areas in broadcasting systems for frequencies in the range of medium wave (300 kHz to 3 MHz). This methodology generates electric field values estimated from the values of terrain altitude (through analysis of conditional probability tables) and provides a comparison of these values with the measured electric field. The data used in this study were collected in Brazil’s central region, nearby the city of Brasilia. The transmitted signal was an AM radio signal transmitted at a frequency of 980 kHz. With the data collected during the measurement campaigns, simulations were performed using conditional probability tables generated by Bayesian Networks. Thus, it’s proposed a method for predicting values of electric field based on the correlation between the measured electric field and the altitude through the use of artificial intelligence. Compared to numerous studies in the literature that have the same goal, the results found in this study validate the use of the methodology to determine the electric field in medium wave radio broadcasting using Bayesian Networks.
Acesso aberto (Open Access)
Métricas de QoE/QoS de vídeo em redes sem fio para auxilio ao planejamento de ambientes indoor utilizando uma abordagem bayesiana
(Universidade Federal do Pará, 2015-03-30) CARVALHO, André Augusto Pacheco de; CAVALCANTE, Gervásio Protásio dos Santos; http://lattes.cnpq.br/2265948982068382
The evolution of applications on wireless networks has grown in recent years, due to the increased number of smartphone users, tablets and others. The availability of demanding services such as video transmission, affects Quality Experience (QoE) and Quality of Service (QoS) provided to domestic users and trade, this had stimulated the study of new resource management techniques networks, aiming to provide quality services to a customer each increasingly demanding. This thesis presents a methodology Intelligence Artificial using a Bayesian network with a hybrid evaluation strategy analyzing the behavior metrics QoE and QoS in the LAN network design wireless. The diversity of the place of Measurements chosen compound materials such as brick, glass, wood and concrete. It was necessary first to map all the points to be measured before and after deliberately placing each barrier outdated the signal. Metrics as level Receiver Signal Strength Intensity signal (RSSI) Jitter, delay end to end network for the video transmission, PeakSignal-to-NoiseRatio (PSNR) and Structural Similarity (SSIM) were collected during the Measurements. And using the Bayesian Network inferences were made for each metric and could not find satisfactory results for the proposed solution assist the wireless network planning in indoor environments. Enabling demonstrate that up to 10 meters away from the transmitter, the signal has its best power, and delay metrics in order to have more than 65% probability that the lower delay range and following this optimum performance the Jitter has more than 65% probability in this lower range. And the QE metrics, PSRN and SSIM have a similar behavior and has more than 80% probability of getting your greater value, and consequently the video has its best reception. These results show that does not preclude the use of this proposal in other situations.
Acesso aberto (Open Access)
Mineração de dados educacionais: um estudo sobre os dados socioeconômicos na educação na base de dados do INEP
(Universidade Federal do Pará, 2019-04-09) SANTOS, Aurea Milene Teixeira Barbosa dos; SILVA, Marcelino Silva da; http://lattes.cnpq.br/7080513172499497
This work investigates the profiles of the third year students of the Brazilian high school of the public and private school network, in order to identify which extracurricular and interscholastic factors influence the student to have a good performance in the National High School Examination (ENEM). In this way, two case studies were carried out, one with the socioeconomic records containing tens of thousands of samples from the students who took the exam, divided by each Brazilian region, making possible an analysis of the influential socioeconomic (extra-school) factors in each region. And the other study analyzed the attributes related to the conditions of school infrastructure offered by public (state) high schools in the state of Pará, for this study was related each note that the student obtained in the examination of enem with the base of the school census, that is, this database details the conditions of the secondary schools corresponding to each student who participated in the test of the enem both 2016. In order to reach the proposed objective, the two case studies were submitted to the process of Knowledge Discovery in Database, the educational data mining (EDM). In the MDE process, the main component analysis (PCA) technique was used in the preprocessing stage, in order to reduce the number of variables without losing the information provided by the total set, using this technique it was possible to decrease from 43 to 22 the number of variables analyzed in case study one, and 39 to 9 in the second case study, with a percentage of 0.8226% and 0.9099% respectively. This technique was used to propitiate the execution of another technique applied in the research, the Bayesian Networks, being used in the data mining stage, the choice for this technique was made possible by it to reason about uncertainties, especially in causes and effects having as presupposition the relationship of the variables and their probabilities of occurrences. Another inherent aspect is its structure, which concerns the comprehensibility of representation and results, which generate subsidies aimed at allowing specialists and users in the field to carry out more in-depth analysis on the subject treated by the data. The results showed the success of this methodology and the techniques used, the research allowed us to have a national analysis of the students of the third year of high school in Brazil, where no study performs this analysis at the Brazilian level when dealing with enem data. Strong influences of socioeconomic variables were pointed out highlighting as direct influential factors in student performance the difference if he studied in public, private or federal schools. Allied to this variable is the question of family income, if the student left or failed in elementary school, if he has access to the computer and internet in his residence and the shift in which he studied in high school, from these variables it was possible to perform inferences and analyze the probabilistic behavior of the grades obtained by the student with each one of these variables. When analyzing the influence of the school structure on the performance of the Paraense student of the public school, the variables library and science laboratory were highlighted. When analyzing only the state of Pará, it was verified that more than 80% of the students in the public network performed poorly, taking notes equal to or less than 450 in the enem, even though in their school the two variables were considered as influential.
Acesso aberto (Open Access)
Otimização do processo de aprendizagem da estrutura gráfica de Redes Bayesianas em BigData
(Universidade Federal do Pará, 2014-02-20) FRANÇA, Arilene Santos de; SANTANA, Ádamo Lima de; http://lattes.cnpq.br/4073088744952858
Automation at data management and analysis has been a crucial factor for companies which need efficient solutions in an each more competitive corporate world. The explosion of the volume information, which has remained increasing in recent years, has demanded more and more commitment to seek strategies to manage and, especially, to extract valuable strategic informations from the use of data mining algorithms, which commonly need to perform exhausting queries at the database in order to obtain statistics that solve or optimize the parameters of the model of knowledge discovery selected; process which requires intensive computing to perform calculations and frequent access to the database. Given the effectiveness of uncertainty treatment, Bayesian networks have been widely used for this process, however, as the amount of data (records and/or attributes) increases, it becomes even more costly and time consuming to extract relevant information in a knowledge base. The goal of this work is to propose a new approach to optimization of the Bayesian Network structure learning in the context of BigData, by using the MapReduce process, in order to improve the processing time. To that end, it was generated a new methodology that includes the creation of an Intermediary Database, containing all the necessary probabilities to the calculations of the network structure. Through the analyzes presented at this work, it is shown that the combination of the proposed methodology with the MapReduce process is a good alternative to solve the scalability problem of the search frequency steps of K2 algorithm and, as a result, to reduce the response time generation of the network.