A5032133335- Machine Learning in Bioinformatics
- Online Learning and Analytics
- Anomaly Detection Techniques and Applications
- Time Series Analysis and Forecasting
- Complex Systems and Time Series Analysis
- E-Learning and Knowledge Management
- Complex Network Analysis Techniques
- Recommender Systems and Techniques
- Rough Sets and Fuzzy Logic
- Advanced Clustering Algorithms Research
- Data Mining Algorithms and Applications
- Machine Learning and Data Classification
- Evolutionary Algorithms and Applications
- Educational Innovations and Technology
- Expert finding and Q&A systems
- Advanced Text Analysis Techniques
- Advanced Statistical Methods and Models
- Semantic Web and Ontologies
- vaccines and immunoinformatics approaches
- Gene expression and cancer classification
- Computational Drug Discovery Methods
- Educational Technology and Assessment
- Fault Detection and Control Systems
Pontifícia Universidade Católica de Minas Gerais
2018-2024
Scientific collaboration improves researchers productivity by providing a way to share new ideas, learn techniques, and find research applications, increasing the chance access funding. Beyond ethics reciprocity, there are other important aspects on achieving scientific collaborations, such as interests expected gain, that paramount successful partnership. However, achieve effective collaborations is hard work can drain time. In this work, we propose recommendation approach uses different...
Purpose The scientific community shares a heritage of knowledge generated by several different fields research. Identifying how interest evolves is relevant for recording and understanding research trends society’s demands. Design/methodology/approach This article presents SciBR-M, novel method to identify evolution from bibliographic material based on Formal Concept Analysis. SciBR-M aims describe the thematic surrounding field begins hierarchically organising sub-domains within study...
Industrial environments demand constant monitoring in their activities, aiming to guarantee effectiveness concerning safety, production, and quality. The probability of failure the security issue can lead a succession other failures, which will inevitably increased risk disaster systems, causing high environmental, social, economic impact. An old proverb states, "prevention is better than cure", so we have developed methodology for detecting describing patterns that abrupt changes behavior...
Knowing the function of proteins is essential in several areas such as bioinformatics, agriculture, and others. The processes to determine protein that realized laboratories are costly require a long time be done. Therefore, it necessary provide efficient computational models aim find protein. There currently kinds researches deal with prediction problem function. However, each them presents different methodology, employing classifiers well. Based on this problem, we propose methodology...
The understanding of the variables that influence human ageing process can help in development public policies improve quality life elderly population. In previous experiments on a dataset, we applied biclustering techniques binary data order to find long-lived and non-long lived profiles, but only found profiles. Then this work, propose use Factor Analysis represent reduced dimensionality, generating three datasets where with high correlation each other belong same factor. We observed some...
The knowledge of a protein function is essential in many areas, such as bioinformatics, agriculture, and others. Therefore, it necessary to provide efficient computational models that aim find the protein. Currently, there wealth available information about protein, data from primary, secondary, tertiary quaternary structures. One repositories this Sting DB, which has physicochemical proteins, used by several authors. Our work proposes methodology using multiobjective genetic algorithm with...
Knowing the function of proteins is essential for understanding several biological systems. The experiments in laboratory to determine protein class are costly and require a long time be done. Therefore, it necessary provide efficient computational models identify which belongs. Nowadays, significant volume information regarding their structure continually being made available public data repositories. For example, STING_DB database has lot extracted from all structural levels (primary,...
The use of sensors in environments where they require constant monitoring has been increasing recent years. main goal is to guarantee the effectiveness, safety, and smooth functioning system. To identify occurrence abnormal events, we propose a methodology that aims detect patterns can lead abrupt changes behavior sensor signals. achieve this objective, provide strategy characterize time series, clustering technique analyze temporal evolution validate our methodology, clusters’ stability...