Mario Wedney de Lima Moreira

@portal.ifce.edu.br

Departmente of Teaching
Federal Institute of Education, Science, and Technology of Ceará

Mario Wedney de Lima Moreira


            Download Compact PDF  
https://researchid.co/mwedney

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Computer Vision and Pattern Recognition, Computer Science Applications, Computational Theory and Mathematics
28

Scopus Publications

Scopus Publications

  • Solution based on convolutional neural networks for automatic counting of aquatic animals
    Willian Ramon Barbosa Bessa, Francisco Milton Mendes Neto, Vinícius Nunes Barbosa, Danielly Gualberto Leite, Oton Crispin Braga, Mário Wedney de Lima Moreira, Vinícius Souza Dos Santos
    Iberian Conference on Information Systems and Technologies Cisti, 2023
    Aquaculture is the process of cultivating organisms with a predominantly aquatic habitat, being today an important activity in human food production. Despite its importance, there are still several activities that are carried out almost exclusively manually. Among them, it is possible to highlight the counting of animals. Therefore, this study presents a set of solutions to support the activity of counting aquatic animals using computer vision and machine learning techniques, through deep learning, with the differential that the end user will be able to access the solutions via a smartphone. Currently, the model is 99% accurate. A counting model based on YOLOv4 was also developed, which reached 98.50% of mAP and 98.70% of accuracy, thus obtaining an excellent result.
  • Image Filtering Model Based on Convolutional Neural Networks for Automatic Counting of Post-larvae in Aquaculture
    Willian R. B. Bessa, Vinicius N. Barbosa, Danielly G. Leite, Francisco M. M. Neto, Vinicius S. Santos, Tarcio G. Silva, Glacio S. Araujo, Mario W. L. Moreira, Oton C. Braga
    ACM International Conference Proceeding Series, 2022
    Aquaculture is an important activity for the animal protein global supply. In Brazil, this area is showing significant growth in recent years. Among the activities carried out during the production process, the counting of animals in the initial stages can be highlighted. A large number of Brazilian aquaculture farms are small, turning difficult to acquire novel solutions for the automatic count of post-larvae. To mitigate this issue, this paper intends to develop a solution based on the performance evaluation of a set of counting models for use in embedded structures. In addition, this application can be scalable for counting different species and sizes. Besides, the dataset named Vivarium and its specifications is presented as proof of concept and used in the model evaluation. Results show that the prediction model based on convolutional neural networks is capable of verifying the compliance of images, achieving an accuracy of 99%.
  • Critical examination using business intelligence on the gender gap in information technology in Brazil
    Erica L. Gallindo, Hobson A. Cruz, Mário W. L. Moreira
    Mathematics, 2021
    In the early 1990s, cyberfeminism emerged as an area of knowledge to discuss the connection between gender and technology. According to UNESCO, women are underrepresented in the field of science, technology, engineering, and mathematics and less than a third of women worldwide work in scientific research and development. However, this number has grown and this reality is constantly changing. In this context, using business intelligence techniques, this study analyzes data from the computer and information and communication technology market to characterize the impact of the performance of women in these areas. It is expected to show that this performance in the highlighted fields is still a challenge in Brazil. Based on this hypothesis, results indicates that public policies must be focused on the base, i.e., to encourage young women to work in STEM areas. This study could encourage policymakers to find solutions to the challenges presented in this research.
  • Neuro-fuzzy model for HELLP syndrome prediction in mobile cloud computing environments
    Mário W. L. Moreira, Joel J. P. C. Rodrigues, Jalal Al‐Muhtadi, Valery V. Korotaev, Victor Hugo C. de Albuquerque
    Concurrency and Computation Practice and Experience, 2021
    SummaryThe exchange of information among health professionals is a common practice among clinics, laboratories, and hospitals. Cloud‐based clinical data exchange platforms enable valuable information to be available in real time and in a secure and private manner. The increasing availability of data in health information systems allows specialists to extract knowledge using pattern recognition techniques for the identification and prediction of risk situations that could lead to severe complications for a patient. Hence, this paper proposes the use of a neuro‐fuzzy machine learning technique for predicting the most complex hypertensive disorder in pregnancy called HELLP syndrome. This classifier serves as an inference mechanism for cloud‐based mobile applications, for effective monitoring through the analysis of symptoms presented by pregnant women. Results show that the proposed model achieves excellent results regarding several indicators, such as precision (0.685), recall (0.756), the F‐measure (0.705), and the area under the receiver operating characteristic curve (0.829). This technique can accurately predict situations that could lead to the death of both a mother and fetus, at any location and time.
  • Recommender system for postpartum depression monitoring based on sentiment analysis
    Marcilio B. Carneiro, Mario W. L. Moreira, Silas S. L. Pereira, Erica L. Gallindo, Joel J. P. C. Rodrigues
    2020 IEEE International Conference on E Health Networking Application and Services Healthcom 2020, 2021
    Emotions influence all aspects of human behavior. All of these aspects shape people's lives, directly impacting their ways of life. Some diseases are directly linked to emotions. Among them, depression is one of the diseases with the greatest impact on society. Hence, faced with this problem, the objective of this study is to present a context-aware solution based on text mining for gestational depression prevention. This system uses text mining to analyze documents filled from pregnant women in order to identify their feelings through natural language processing techniques and probabilistic algorithms. As a case study, the analyzed texts were obtained from forms answered by pregnant women. The model performance is evaluated using metrics associated with the confusion matrix. The results show that the proposed model has achieved a reliable performance in all metrics, mainly when classifying new cases. Thus, the results obtained by the model can be used as support to health professionals in monitoring high-risk pregnancies.
  • Instance Segmentation in Mobile Computing Environments for Identification of Specific Characteristics in Endangered Species
    Morgana C. O. Ribeiro, Rhayane S. Monteiro, Mario W. L. Moreira, Joel J. P. C. Rodrigues
    2021 International Wireless Communications and Mobile Computing Iwcmc 2021, 2021
    The segmentation of instances is a key topic in image processing and computer vision. There are numerous applications such as medical image analysis, video surveillance, image compression among others, in which its algorithms show significant results. Due to the COVID-19 pandemic, most countries have been affected mainly by their economy. In the food production sector, including fishing and aquaculture, it was no different. In this context, this research has as main objective to contribute to the 2030 Agenda for Sustainable Development suggested by the United Nations (UN), through a fish detection and segmentation model based on the framework Detectron2, optimizing the time of professionals in identifying specific characteristics of a particular species. To achieve this objective, this research seeks to facilitate the recognition of patterns of parts of the fish from the segmentation of instances and to stimulate scientific research in the area through the morphological information collection of certain species. The results present an accuracy, based on the Intersection over Union (IoU) indicator, of 88.4%, providing an effective solution for the collection of these characteristics.
  • Video Monitoring System using Facial Recognition: A Facenet-based Approach
    Augusto F. S. Moura, Silas S. L. Pereira, Mario W. L. Moreira, Joel J. P. C. Rodrigues
    Proceedings IEEE Global Communications Conference Globecom, 2020
    Reductions in installation and storage costs have increased the demand for security systems, including video surveillance and digital authentication. The video surveillance systems, when monitored by humans, are subject to errors and are challenging to scale. Authentication systems can validate someone using a password or a card from another user. Facial recognition algorithms can solve this fault by the traffic monitoring of known individuals or intruders as well as for individual biometric authentication. Hence, this paper evaluates the FaceNet approach using the Labeled Faces in the Wild benchmark, as well as evaluates a machine learning technique known as support vector machine (SVM) for the classification of embedding generated using FaceNet. The suggested approach also models a real-time facial recognition system combining FaceNet and SVM, reaching 90% of accuracy using a medium webcam.
  • Improving Maternal Risk Analysis in Public Health Systems
    Silas S. L. Pereira, Raimundo Valter Costa Filho, Ronaldo Ramos, Mauro Oliveira, Mario W. L. Moreira, Joel J. P. C. Rodrigues, Petar Solic
    2020 5th International Conference on Smart and Sustainable Technologies Splitech 2020, 2020
    There are several efforts in intelligent approaches in the literature dealing with maternal death risk prediction. Solutions focused on surveillance and monitoring maternal health contributes to reduce mortality rates, especially in low and middle-income countries. Data required by artificial intelligence systems are usually sensitive and restricted by privacy policies. High quality and trusted maternal health data are essential to obtain reliable predictive models. This study applies the Recursive Feature Elimination (RFE) strategy associated with decision tree-based classifier identifying a relevant set of features among an extensive list of maternal predictive information considered in a decision-making process. This study applies a systematic process of data preparation, analysis, and modeling to develop trusted models from maternal Electronic health registries (eRegistries). Also, this research presents an experiment pipeline to evaluate six well-known supervised machine learning models, namely Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), Adaptive Boosting (AdaBoost), Decision Tree (DT), and Gaussian Naive Bayes (GNB), with different combinations of ranked features. Results show that the feature ranking strategy was useful to reduce data dimensionality without affecting the performance of predictive models. The RFE-based predictive models achieves high Accuracy (ACC) and Area Under the Receiver Operating Characteristic Curve (AUC) with only eight maternal features.
  • Computational Learning Approaches for Personalized Pregnancy Care
    Mario W. L. Moreira, Joel J. P. C. Rodrigues, Kashif Saleem, Valery V. Korotaev
    IEEE Network, 2020
    The increasing use of interconnected sensors to monitor patients with chronic diseases, integrated with tools for the management of shared information, can guarantee a better performance of health information systems (HISs) by performing personalized healthcare. The early diagnosis of chronic diseases such as hypertensive disorders of pregnancy represents a significant challenge in women's healthcare. Computational learning techniques are useful tools for pattern recognition in the assessment of an increasing amount of integrated data related to these diseases. Hence, in this paper, the use of machine learning (ML) techniques is proposed for the assessment of real data referred to hypertensive disorders in pregnancy. The results show that the averaged one-dependence estimator algorithm can help in the decision- making process in uncertain moments, thus improving the early detection of these chronic diseases. The best-evaluated computational learning algorithm improves the performance of HISs through its precise diagnosis. This method can be applied in electronic health (e-health) environments as a useful tool for handling uncertainty in the decision-making process related to high-risk pregnancy.
  • Performance Evaluation of Recurrent Neural Networks for Short-Term Investment Decision in Stock Market
    Alexandre P. da Silva, Silas S. L. Pereira, Mário W. L. Moreira, Joel J. P. C. Rodrigues, Ricardo A. L. Rabêlo, Kashif Saleem
    Lecture Notes in Networks and Systems, 2020
  • Biomedical data analytics in mobile-health environments for high-risk pregnancy outcome prediction
    Mário W. L. Moreira, Joel J. P. C. Rodrigues, Francisco H. C. Carvalho, Naveen Chilamkurti, Jalal Al-Muhtadi, Victor Denisov
    Journal of Ambient Intelligence and Humanized Computing, 2019
  • A Comprehensive Review on Smart Decision Support Systems for Health Care
    Mario W. L. Moreira, Joel J. P. C. Rodrigues, Valery Korotaev, Jalal Al-Muhtadi, Neeraj Kumar
    IEEE Systems Journal, 2019
  • Averaged one-dependence estimators on edge devices for smart pregnancy data analysis
    Mário W.L. Moreira, Joel J.P.C. Rodrigues, Vasco Furtado, Neeraj Kumar, Valery V. Korotaev
    Computers and Electrical Engineering, 2019
  • Classification of risk areas using a bootstrap-aggregated ensemble approach for reducing Zika virus infection in pregnant women
    Mário W.L. Moreira, Joel J.P.C. Rodrigues, Francisco H.C. Carvalho, Jalal Al-Muhtadi, Sergey Kozlov, Ricardo A.L. Rabêlo
    Pattern Recognition Letters, 2019
  • Postpartum depression prediction through pregnancy data analysis for emotion-aware smart systems
    Mário W.L. Moreira, Joel J.P.C. Rodrigues, Neeraj Kumar, Kashif Saleem, Igor V. Illin
    Information Fusion, 2019
  • Fetal Birth Weight Estimation in High-Risk Pregnancies Through Machine Learning Techniques
    Mario W. L. Moreira, Joel J. P. C. Rodrigues, Vasco Furtado, Constandinos X. Mavromoustakis, Neeraj Kumar, Isaac Woungang
    IEEE International Conference on Communications, 2019
  • Semantic interoperability and pattern classification for a service-oriented architecture in pregnancy care
    Mário W.L. Moreira, Joel J.P.C. Rodrigues, Arun K. Sangaiah, Jalal Al-Muhtadi, Valery Korotaev
    Future Generation Computer Systems, 2018
  • A Preterm Birth Risk Prediction System for Mobile Health Applications Based on the Support Vector Machine Algorithm
    Mario W. L. Moreira, Joel J. P. C. Rodrigues, Guilherme A. B. Marcondes, Augusto J. Venancio Neto, Neeraj Kumar, Isabel De La Torre Diez
    IEEE International Conference on Communications, 2018
  • Evolutionary radial basis function network for gestational diabetes data analytics
    Mário W.L. Moreira, Joel J.P.C. Rodrigues, Neeraj Kumar, Jalal Al-Muhtadi, Valeriy Korotaev
    Journal of Computational Science, 2018
  • Nature-Inspired Algorithm for Training Multilayer Perceptron Networks in e-health Environments for High-Risk Pregnancy Care
    Mário W. L. Moreira, Joel J. P. C. Rodrigues, Neeraj Kumar, Jalal Al-Muhtadi, Valery Korotaev
    Journal of Medical Systems, 2018
  • Multilayer perceptron application for diabetes mellitus prediction in pregnancy care
    Mário W. L. Moreira, Joel J. P. C. Rodrigues, Neeraj Kumar, Jianwei Niu, Arun Kumar Sangaiah
    Lecture Notes in Electrical Engineering, 2018
  • Using predictive classifiers to prevent infant mortality in the Brazilian northeast
    Ronaldo Ramos, Cristiano Silva, Mario W. L. Moreira, Joel J. P. C. Rodrigues, Mauro Oliveira, Odorico Monteiro
    2017 IEEE 19th International Conference on E Health Networking Applications and Services Healthcom 2017, 2017
  • Predicting hypertensive disorders in high-risk pregnancy using the random forest approach
    Mario W.L. Moreira, Joel J.P.C. Rodrigues, Antonio M.B. Oliveira, Kashif Saleem, Augusto J. Venancio Neto
    IEEE International Conference on Communications, 2017
  • Performance Assessment of Decision Tree-Based Predictive Classifiers for Risk Pregnancy Care
    Mario W. L. Moreira, Joel J. P. C. Rodrigues, Neeraj Kumar, Jianwei Niu, Isaac Woungang
    Proceedings IEEE Global Communications Conference Globecom, 2017
  • An inference mechanism using Bayes-based classifiers in pregnancy care
    Mario W. L. Moreira, Joel J. P. C. Rodrigues, Antonio M. B. Oliveira, Kashif Saleem, Augusto V. Neto
    2016 IEEE 18th International Conference on E Health Networking Applications and Services Healthcom 2016, 2016
  • A preeclampsia diagnosis approach using Bayesian networks
    Mario W. L. Moreira, Joel J. P. C. Rodrigues, Antonio M. B. Oliveira, Ronaldo F. Ramos, Kashif Saleem
    2016 IEEE International Conference on Communications Icc 2016, 2016
  • Smart mobile system for pregnancy care using body sensors
    Mario W. L. Moreira, Joel J. P. C. Rodrigues, Antonio M. B. Oliveira, Kashif Saleem
    2016 International Conference on Selected Topics in Mobile and Wireless Networking Mownet 2016, 2016
  • Performance evaluation of predictive classifiers for pregnancy care
    Mario W. L. Moreira, Joel J. P. C. Rodrigues, Antonio M. B. Oliveira, Kashif Saleem, Augusto Neto
    Proceedings IEEE Global Communications Conference Globecom, 2016