Navegando por Assunto "Artificial intelligence"

Agora exibindo 1 - 12 de 12

Acesso aberto (Open Access)
Algoritmos para seleção de metodologias de avaliação de softwares educacionais
(Universidade Federal do Pará, 2023-09-26) CASTILHO, Janize Monteiro de; FARIAS, Fabricio de Souza; http://lattes.cnpq.br/1521079293982268; https://orcid.org/0000-0003-4344-6953
In order to assist the teaching-learning processes, many teachers have decided to use Educational Software (ES) in their classrooms. However, to choose a ES as a teaching resource it is essential to endorse the methodology used by the teacher, once it needs to be pedagogically and functionally appropriate to meet the needs and objectives present in the classroom. Also, it is necessary to use mechanisms that the ES endorses to verify its adequacy to the professor’s objectives. Currently, it is verified that there are various techniques and methodologies available in the literature for ES assessment, but there is still no solution for decision making and selection of a ES that fully addresses the profiles of users and their different needs to be met by certain methodological application, or that arises from demand originating from the development of solutions based on demand and with a low capacity for generalization in terms of practical application. In this way, solutions are available without standardization and that several times do not take into consideration criteria relating to quality, measurement scales and verification procedures of the ES. This heterogeneity makes the evaluation of an ES very difficult, since the subjectivity in the selection of ES evaluation methodology can produce inconclusive results. Given this context, this work created a quality model that considers 24 ES assessment methodologies available in the literature and aims to automate the selection of ES assessment methodology based on the application of artificial intelligence (AI) algorithms, reducing the possibility of subjectivity in the screening process. During the investigation we used Natural Language Processing (NLP), Random Forest, k-Nearest Neighbors and Artificiais Neurais Networks. In all research scenarios, the natural language algorithm was combined with other algorithms, offering a solution based on the application of hybrid and loosely coupled AI algorithms, with excellent results. In this way, simulations were carried out considering NLP+Random Forest, NLP+k-Nearest Neighbors and NLP+Artificial Neurais Networks. After the simulations, the results indicate that it is possible to determine the best ES assessment methodology using AI algorithms, with the best results obtained with the combination of NLP+Random Forest.
Acesso aberto (Open Access)
Análise e classificação de severidade de COVID-19 usando aprendizado de máquina
(Universidade Federal do Pará, 2022-08-16) LIMA, Marco Antonio Loureiro; CARDOSO, Diego Lisboa; http://lattes.cnpq.br/0507944343674734
In the last years, with the alarming growth of COVID-19 cases, a highly contagious viral disease, new forms of diagnosis and control for this sickness have become necessary to the spread decreases until the population is effectively vaccinated. In this context, Artificial Intelligence (AI) and its subfields appear as possible alternatives to help and provides a response to combat the virus. Some Machine Learning (ML) methods are shown as an answer to control this disease, these methods can perform an analysis based on a set of symptoms presented by the patient and consequently indicating the diagnosis, as well as streamline the treatment process. To achieve this goal in this paper, three models that uses ML methods to predict COVID-19 severity on different degrees are proposed, unlike other works whose purpose was to diagnose only the presence or absence of COVID-19, this paper aims to improve the classification of the patient’s disease state. The results in each of these models are evaluated through the metrics established in this work. Furthermore, there are distinct suggestions to improve the analysis and make predictions with greater accuracy..
Acesso aberto (Open Access)
Analysis of classical and advanced control techniques tuned with reinforcement learning
(Universidade Federal do Pará, 2023-09-01) SILVA, Daniel Abreu Macedo da; SILVEIRA, Antonio da Silva; http://lattes.cnpq.br/1828468407562753
Control theory is used to stabilize systems and obtain specific responses for each type of process. Classic controllers, such as the PID used in this research, are spread globally in industries because they have well studied topologies in the literature and are easily applied in microcontrollers or programmable lógic devices; advanced ones,such as GMV, GPC and LQR, also used in this work, have some resistance in common applications in base industries, but are widely used in energy, aerospace and robotic systems, since the complexity and structure of these methods generate robustness and reach satisfactory performances for processes that are difficult to control. In this work, these methods are studied and evaluated with a tuning approach that uses re inforcement learning. The tuning methods are used in two forms and are applied to the controllers, these are the Repeat and Improve method and the Differential Games method. The first works using offline iterations, where the process agent is the chosen control technique, which selects performance and robustness indexes as an environment (metric of how the process is evolving), being able to organize an adjustment policy for the controller, which is based on rewarding the weighting factor until reaching the process stopping criterion (desired response). The second method uses reinforcement strategies that reward the controller as the response changes, so the LQR learns the ideal control policies, adapting to changes in the environment, which allows for better performance by recalculating the traditional gains found. With the Ricatti equation for tuning the regulator; in this method, differential games are used as a framework to model and analyze dynamic systems with multiple agents. To validate what is presented, the Tachogenerator Motor and the Ar Drone have been chosen. The Tachogenerator Motor is modeled with least squares estimation in an ARX-SISO topology, in order to evaluate the first tuning method. The Ar Drone is modeled with a state space approach to evaluate the second tuning method.
Acesso aberto (Open Access)
Avaliação de modelos de inteligência artificial híbridos na estimativa de precipitações
(Universidade Federal do Pará, 2022-03-18) GOMES, Evanice Pinheiro; BLANCO, Claudio José Cavalcante; http://lattes.cnpq.br/8319326553139808
The hydrological analyzes carried out from rainfall in the Amazon are essential due to its importance in climate regulation, regional and global atmospheric circulation. However, in this region, there are limitations related to data series with short periods and many flaws, especially in the daily scale. Despite significant advances in science and technology, practical and accurate predictions have been a major concern due to their complexity. Therefore, several conceptual models, empirical or hybrid, have been tested to forecast rain with greater precision. Among empirical models, those that incorporate artificial intelligence (AI) methods are potentially useful approaches to simulate the precipitation process. Artificial Neural Networks (ANN), as AI models, are able to establish a relationship between historical inputs (rain, flow, etc.) and the desired outputs, through a non-linear function composed of several factors that are adjusted to the observed data, allowing your prediction. Thus, to improve the precipitation analysis, hybrid models were developed, involving Artificial Neural Network (ANN) of the type with Time Delay (TDNN), ELMAN network, Radial Base network (RBF) and Adaptive Neuro-Fuzzy Inference System (ANFIS), coupled with Maximum Overlap Discrete Wavelet (MODWT). Six rainfall gauge station were adopted, which are located in different biomes of the region, and satellite data (CMORPH). Rainfall data were evaluated by seasonal periods (rainy and dry). The results obtained demonstrated that the MODWT-ANFIS model had the best capacity to simulate the daily precipitation of the evaluated rainfall gauge station, even for dry periods, which are known to be more difficult to be simulated in relation to the rainy periods. In this case, data entries lagged by 4 days and 5 days performed better, with Nash values close to 1.0 and root mean square errors below 0.001.
Acesso aberto (Open Access)
Desenvolvimento de Ferramentas de IA para o Monitoramento da Dinâmica de Colmeias de Abelhas Canudo (Scaptotrigona spp)
(Universidade Federal do Pará, 2024-12-16) CAMPOS NETO, Manoel Freitas; OLIVEIRA, Marcos Enê Chaves; http://lattes.cnpq.br/9052059910078575; OLIVEIRA, Roberto Célio Limão de; http://lattes.cnpq.br/4497607460894318; https://orcid.org/0000-0002-6640-3182
Native social bees have shown a high agronomic potential in the pollination of plants in Brazil, with bees of the genus Scaptotrigona standing out for improving the productivity of açaí palm (Euterpe oleracea) by up to 70% and coffee plants (Coffea arabica) by up to 30%, with the help of these pollinators. However, a drastic reduction in bee populations has been observed, attributed to several causes, such as the destruction of natural habitats, the increase in agricultural practices, deforestation leading to the loss of plant diversity, climate change, and the use of pesticides. These threats not only directly affect the bees but also compromise pollination, which is essential for maintaining ecosystems and food production worldwide. Considering this scenario, this work aims to monitor the behavior of Scaptotrigona bees, also known as "canudo" bees, using Artificial Intelligence (AI) tools to obtain information that will support further research for the technological development of beekeeping and the dissemination of knowledge about bees and their importance. For this, a new image acquisition methodology was developed, using 3D printing, to create an unprecedented database with 7,806 images of canudo bees, containing 19,954 annotations, which supported the construction of a neural network model using the YOLOv8 network to classify the scapto, scapto_garbage and scapto_polen classes, with 96% accuracy in this task. Additionally, the model demonstrated great potential for estimating hive populations, selecting the most hygienic hives, and analyzing the bees' preference for certain blooms, while also indirectly assisting in botanical studies to better understand the flowering period.
Acesso aberto (Open Access)
Indústria 4.0: a inteligência artificial aliada aos cuidados com a saúde no atendimento ao paciente em hospitais universitários federais no âmbito da Amazônia Legal
(Universidade Federal do Pará, 2023-07-17) NOGUEIRA, Vanessa Letícia de Vasconcelos; CARMO, Annibal José Roris Rodriguez Scavarda do; http://lattes.cnpq.br/6070280268935110; SCHIMITH, Cristiano Descovi; http://lattes.cnpq.br/7017921569470426; https://orcid.org/0000-0002-2545-942X
Research into the subject of Artificial Intelligence (AI) has grown over the last five years as a result of an event known as the 4th Industrial Revolution, or also known as Industry 4.0. Artificial intelligence is playing an increasingly important role in the treatment of patients in various areas of medicine. The aim of this research was to identify how the use of Artificial Intelligence (AI) has contributed to patient care. To this end, a literature review was carried out in order to research the theoretical framework that underpins the construction of the research. A framework was then drawn up based on the main theoretical approaches in the current literature. In conjunction, field research was carried out, which included an empirical investigation in the place where the phenomenon occurs, using a semi-structured interview script with health professionals working in Federal University Hospitals (HUFs) located in the Legal Amazon region. The research is justified by the need to improve patient care in the HUFs, with the aim of contributing to new models of service provision. The data obtained from the interviews with professionals at these hospitals was compared with the results from the literature review, and the empirical characteristics of the research brought out positive and negative points in relation to their use of AI in patient care. As a solution, this research presents a model to support patient care with the insertion of AI in HUFS, considering the concept of mimetic isomorphism, in which this practice tends to be homogenized or standardized imminently through its consolidation in the market.
Acesso aberto (Open Access)
Inteligência Artificial, Museus e Patrimônio: entrevista com Lucia Santaella
(Universidade de Brasília, 2021-12) SILVA, Carmen Lucia Souza da
Lucia Santaella is a CNPq researcher 1 A. She is a full professor in the Graduate Program in Communication and Semiotics at Pontifícia Universidade Católica de São Paulo (PUC- -SP), with a PhD in Literary Theory at PUC- -SP and a “Livre-Docência” in Communication Sciences at Escola de Comunicações e Artes of Universidade de São Paulo (ECA-USP). She is the Graduate Coordinator in Intelligence Technologies and Digital Design. She received the Jabuti Award in 2002, 2009, 2011 and 2014, the Sergio Motta, Liber Award, in Art and Technology, in 2005, and the Luiz Beltrão - academic maturity award, in 2010. Since 1996 she has been doing post-doctoral internships in Kassel, Berlin and Dagstuhl, Germany, under the auspices of DAAD/Fapesp. She has 51 published books, six of which are co-authored and two critical studies. She organized 26 books and published close to 500 articles in Brazil and abroad. Her most recent areas of research are: Communication, Cognitive and Computational Semiotics, Artificial Intelligence, Technological Aesthetics and Philosophy and Methodology of Science. In this interview, Lucia Santaella speak about Artificial Intelligence and the ongoing technological changes that affect Museums and Cultural Heritage, encompassing epistemological and social issues.
Acesso aberto (Open Access)
Introdução à neurociência computacional com a linguagem python
(Universidade Federal do Pará, 2023-12-29) NASCIMENTO, Weverson Vieira do; PEREIRA JÚNIOR, Antonio; http://lattes.cnpq.br/3239362677711162
This work presents a proposal for an introductory course on computational neuroscience, using the Python programming language. The brain is a complex organ, and there is significant interest in understanding the biological mechanisms underlying its functioning. Computational neuroscience is one of the fields of study that seeks to contribute to this understanding. The introductory course is aimed at undergraduate students interested in acquiring basic knowledge in Computational Neuroscience. The course initially provides a theoretical foundation in both neurophysiology and mathematics, as well as algorithmic concepts, to enable students from diverse backgrounds to benefit from its content with minimal prerequisites. The course then introduces models of neurons, ranging from simple to more elaborate ones, and explores how these neurons connect with each other, including some well-known neural connection circuits and how learning is implemented in these neuron networks. It also includes content on artificial intelligence, such as neural and neuromorphic networks, the latter using the models mentioned initially. The course utilizes interactive Python code, which is free and open-source, for simulating the presented content.
Acesso aberto (Open Access)
Modelo de rádio propagação em UHF para ambientes não homogêneos e climas distintos utilizando técnica de aprendizagem de máquina
(Universidade Federal do Pará, 2015-08-20) GOMES, Cristiane Ruiz; CAVALCANTE, Gervásio Protásio dos Santos; http://lattes.cnpq.br/2265948982068382
The digital TV broadcasts have greatly increased worldwide in recent years, especially in Brazil. The establishment and improvement of these transmission systems rely on models that take into account, among other factors, the geographical characteristics of the region, as these contribute to signal degradation. In Brazil, there is a great diversity of scenery and climates. For years several propagation models have been studied many for several frequency bands and types of paths. This thesis proposes an outdoor empirical radio propagation model for UHF band, which is used in digital TV. The proposed model estimates received power values can be applied to non-homogeneous paths and different climates, this latter presents innovative character for the UHF band. Different artificial intelligence techniques were chosen for theoretical and computational basis for having the ability to introduce, organize and describe quantitative and qualitative data quickly and efficiently, making it possible to determine the received power in a variety of settings and climates. The proposed model was applied to a city in the Amazon region with heterogeneous paths and wooded urban areas, fractions of freshwater among others. Measurement campaigns were conducted to obtain data signals from two digital TV stations in the metropolitan area of the city of Belém-Pará to model, compare and validate the model. The results are consistent. The model depicts a distinct difference between the two seasons of the studied year and small RMS errors for all cases studied. The validation of the model was based on the comparison with empirical and deterministic models.
Acesso aberto (Open Access)
Reconhecimento facial de alunos de Escola Pública no uso de ônibus escolar em cidade inteligente
(Universidade Federal do Pará, 2023-08-04) ROCHA, Jessé da Costa; ARAÚJO, Jasmine Priscyla Leite de; http://lattes.cnpq.br/4001747699670004; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
In the present days, the disappearance of children and adolescents and school dropout are major problems faced by countries worldwide, in particular, developing countries. This work proposes an intelligent platform for monitoring students' steps as a tool to mitigate these problems. This platform can identify students and notify those responsible and competent authorities in various situations of school life, such as: entering and leaving the school bus, entering and leaving school, entering the school cafeteria, etc. The first application aims to control access to the school bus through facial recognition. Facial recognition, in turn, employs different artificial intelligence techniques to recognize students, such as: HOG (Histograms of Oriented Gradients), SVM (Support Vector Machine), CNN (Convolutional Neural Network) and KNN (K-Nearest Neighbors). In the tests carried out, the recognition system achieved excellent results in all metrics: accuracy 98.10%, weighted average precision 99%, weighted average recall 98%, and weighted average f1-score 98%.
Acesso aberto (Open Access)
Simulação de missões de VANTs em ambientes 3D fictícios e gêmeos digitais com georreferenciamento direto de pixels
(Universidade Federal do Pará, 2023-08-14) CONDE, Lucas dos Santos; KLAUTAU JÚNIOR, Aldebaro Barreto da Rocha; http://lattes.cnpq.br/1596629769697284
The world is rapidly entering a reality where Artificial Intelligence is becoming increasingly present in various systems, from the domestic environment to sectors such as industry, urban mobility, and agriculture. In this context, with the advancement of computational power, sim ulators for developing and testing autonomous systems have garnered significant interest from large companies and the scientific community due to the visual and physical fidelity they offer. These simulators are often regarded as "digital twins" of real scenarios and systems and have brought significant advantages in terms of cost and time, saving physical and human resources during the conception and improvement of algorithms. Among these systems are Unmanned Aerial Vehicles (UAVs), which have proven to be of great utility in contexts such as urban and rural mobility and monitoring. They are applied, for example, in detecting defects in photovoltaic panels, identifying weeds in crops, extending the mobile network and in search and rescue missions. Therefore, this work presents the conception of a methodology that integrates realistic mission simulation with UAVs, using the AirSim simulator in conjunction with the Unreal Engine graphics engine and computer vision capabilities. The objective is to perform object detection (employing the YOLO AI model) associated with their georeferenced location and generate geolocated image files that are compatible with commercial software for aerial image processing. The results were evaluated using the WebODM software for scene recon struction from geolocated image files (generating orthophotos). And to evaluate the direct pixel georeferencing algorithm, the ability of the drone to return to the position of the detected person (or object) after the algorithm provided the GPS position was tested, with errors smaller than 5 meters in relation to the real position (in UTM coordinates) of the element in the 3D environment
Acesso aberto (Open Access)
Simulation of machine learning-based 6G systems in virtual worlds
(International Telecommunication Union, 2021) OLIVEIRA, Ailton Pinto de; NASCIMENTO, Arthur Matheus do; COSTA, Walter Tadeu Neves Frazão da; TRINDADE, Isabela Pamplona; BASTOS, Felipe Henrique Bastos e; GOMES, Diego de Azevedo; MÜLLER, Francisco Carlos Bentes Frey; KLAUTAU JÚNIOR, Aldebaro Barreto da Rocha
Digital representations of the real world are being used in many applications, such as augmented reality. 6G systems will not only support use cases that rely on virtual worlds but also benefit from their rich contextual information to improve performance and reduce communication overhead. This paper focuses on the simulation of 6G systems that rely on a 3D representation of the environment, as captured by cameras and other sensors. We present new strategies for obtaining paired MIMO channels and multimodal data. We also discuss trade-offs between speed and accuracy when generating channels via ray tracing. We finally provide beam selection simulation results to assess the proposed methodology.