Gustavo De Assis Costa
IFG, Computer Science, Faculty Member
- INESC TEC, formerly INESC PORTO, LIAAD, Post-DocInstituto Tecnológico de Aeronáutica, Computer Engineering, Undergraduateadd
- I'm currently a Professor at the Federal Institute of Education, Science, and Technology of Goiás, Jataí campus, Brazil. I have a Ph.D. in Electronic Engineering and Computer Sc... moreI'm currently a Professor at the Federal Institute of Education, Science, and Technology of Goiás, Jataí campus, Brazil. I have a Ph.D. in Electronic Engineering and Computer Science (ITA - Aeronautics Institute of Technology) and completed Postdoctoral Research Fellowship at INESC TEC. I have strong experience in teaching (Computer Science, Electrical Engineering, Associate Degree, and Vocational Technical Courses in Computer Science) and academic management. I occupied some positions as Head of Engineering and Computer Science Departments and Course Coordinator. I led several projects for bachelor's course design as vocational and undergraduate courses. After finishing my doctorate in 2015, I started research projects involving technologies such as Semantic Web, Entity Resolution, NLP, Data Mining, Machine Learning, and Big Data. For many years I dedicated myself to the evolution and growth of a public educational institution in Brazil. In addition, to experiment with a new culture, I am willing to seek new directions that can leverage my career towards excellence.edit
- João Gamaedit
In the last few years, many works have addressed Predictive Maintenance (PdM) by the use of Machine Learning (ML) and Deep Learning (DL) solutions, especially the latter. The monitoring and logging of industrial equipment events, like... more
In the last few years, many works have addressed Predictive Maintenance (PdM) by the use of Machine Learning (ML) and Deep Learning (DL) solutions, especially the latter. The monitoring and logging of industrial equipment events, like temporal behavior and fault events—anomaly detection in time series—can be obtained from records generated by sensors installed in different parts of an industrial plant. However, such progress is incipient because we still have many challenges, and the performance of applications depends on the appropriate choice of method. This article presents a survey of existing ML and DL techniques for handling PdM in the railway industry. This survey discusses the main approaches for this specific application within a taxonomy defined by the type of task, employed methods, metrics of evaluation, the specific equipment or process, and datasets. Lastly, we conclude and outline some suggestions for future research.
Research Interests:
This chapter presents an overview of standards and solutions around healthcare semantic models and the impact of remote monitoring devices and sensors in this domain. We give a presentation about Electronic Health Record (EHR) systems,... more
This chapter presents an overview of standards and solutions around healthcare semantic models and the impact of remote monitoring devices and sensors in this domain. We give a presentation about Electronic Health Record (EHR) systems, the main technologies used to address the interoperability issue, and the role of semantic models in this context. After that, we discuss connected objects in the health domain and the importance of semantic web technologies to overcome interoperability between devices. Interoperability has been a research challenge in the last few years, and its importance is increasing due to the also increasing number of new devices and also to the existing different EHR systems. Semantic web tools have been widely adopted to face this problem despite the advances already achieved. There are just a few proposals in the literature regarding the interoperability between connected objects and EHR systems. A discussion about existing works is presented later in the chapter. Through a use case, we intend to highlight the importance of this approach during the text. We want to bring the reader some ideas about opportunities for advancement in research.