A5080629879- Spectroscopy and Chemometric Analyses
- Identification and Quantification in Food
- Advanced Chemical Sensor Technologies
- Probiotics and Fermented Foods
- Machine Learning and Data Classification
- Metabolomics and Mass Spectrometry Studies
- Anomaly Detection Techniques and Applications
- Food Supply Chain Traceability
- Online Learning and Analytics
- Data Mining Algorithms and Applications
- Imbalanced Data Classification Techniques
- Biochemical effects in animals
Universidade Federal de Mato Grosso do Sul
2019-2023
Instituto Federal de Educação, Ciência e Tecnologia de Mato Grosso
2018-2022
Fraudulent milk adulteration is a dangerous practice in the dairy industry that harmful to consumers since one of most consumed food products. Milk quality can be assessed by Fourier Transformed Infrared Spectroscopy (FTIR), simple and fast method for obtaining its compositional information. The spectral data produced this technique explored using machine learning methods, such as neural networks decision trees, order create models represent characteristics pure adulterated samples.Thousands...
Demand for low lactose milk and products has been increasing worldwide due to the high number of people with intolerance. These dairy foods require fast, low-cost efficient methods sugar quantification. However, available do not meet all these requirements. In this work, we propose association FTIR (Fourier Transform Infrared) spectroscopy artificial intelligence identify quantify residual other sugars in milk. Convolutional neural networks (CNN) were built from infrared spectra without...
Cheese whey addition to milk is a type of fraud with high prevalence and severe economic effects, resulting in low yield for dairy products, nutritional reduction milk-derived even some safety concerns. Nevertheless, methods detect fraudulent cheese are expensive time consuming, thus ineffective as screening methods. The Fourier-transform infrared (FTIR) spectroscopy technique promising alternative identify this because large number data generated, useful information might be extracted used...
In this study the application of data mining in an academic database is presented, aiming identification reasons student dropouts by preventing failures Programming Language class from Internet Systems course Federal Institute Mato Grosso do Sul (IFMS). The classification task used, as well decision tree technique and J4.8 algorithm, wich run with three different options and, each option pruned unpruned trees are generated. results show that most realistic test Cross-validation, a success...
Designing adequate and precise neural architectures is a challenging task, often done by highly specialized personnel. AutoML machine learning field that aims to generate good performing models in an automated way. Spectral data such as those obtained from biological analysis have generally lot of important information, these are specifically well suited Convolutional Neural Networks (CNN) due their image-like shape. In this work we present NASirt, methodology based on Architecture Search...
Demand for low lactose milk and products has been increasing worldwide due to the high number of people with intolerance. These dairy foods require fast, low-cost efficient methods sugars quantification. However, available do not meet all these requirements. In this work, we propose association FTIR (Fourier Transform Infrared) spectroscopy artificial intelligence identify quantify residual other in milk. Convolutional neural networks (CNN) were built from infrared spectra without...