Ronaldo Cristiano Prati

I'm a Professor in Computer Science at Universidade Federal do ABC currently working on machine learning and data mining applications for various domains like smart agriculture, quantum chemistry, and music analysis. My research focuses on developing novel machine learning methods and techniques, particularly for handling imbalanced datasets, multi-label classification, and data streams. I have extensive experience working with classification algorithms, feature selection methods, and ensemble learning approaches. I've contributed significantly to the field through my work on ROC analysis, rule learning, and methods for dealing with class imbalance problems. I've collaborated with researchers worldwide on applications ranging from IoT-based smart irrigation systems to quantum chemistry data analysis. More recently, my research has expanded into applied machine learning for agricultural technology, where I work on developing intelligent irrigation systems and soil moisture prediction models. I'm also interested in applications of machine learning to music analysis, particularly in characterizing musical timbre through spectral analysis. Additionally, I continue to work on fundamental machine learning challenges like handling imbalanced data streams and developing novel classification approaches.

I believe in combining theoretical advances with practical applications to create meaningful impact across different domains. My work aims to bridge the gap between machine learning theory and real-world applications while developing robust and interpretable models.

Publications

Comparing Modern and Traditional Modeling Methods for Predicting Soil Moisture in IoT-based Irrigation Systems

Gilliard Custódio, R. Prati

Smart Agricultural Technology 2024

Ronaldo Cristiano Prati

Publications

Comparing Modern and Traditional Modeling Methods for Predicting Soil Moisture in IoT-based Irrigation Systems

Effect of Flattened Structures of Molecules and Materials on Machine Learning Model Training

Data-driven water need estimation for IoT-based smart irrigation: A survey

Similarity of Musical Timbres Using FFT-Acoustic Descriptor Analysis and Machine Learning

IoTracker: A probabilistic event tracking approach for data-intensive IoT Smart Applications

Soil moisture forecast for smart irrigation: The primetime for machine learning

Data reduction based on machine learning algorithms for fog computing in IoT smart agriculture

Naive Importance Weighting for Data Stream with Intermediate Latency

IrrigaSim: An Irrigation Simulation, Processing, and Animation Environment

Applications of FFT for timbral characterization in woodwind instruments

Systematic Investigation of Error Distribution in Machine Learning Algorithms Applied to the Quantum-Chemistry QM9 Data Set Using the Bias and Variance Decomposition

Multiple instance classification: Bag noise filtering for negative instance noise cleaning

Correlation-Based Framework for Extraction of Insights from Quantum Chemistry Databases: Applications for Nanoclusters

DTO-SMOTE: Delaunay Tessellation Oversampling for Imbalanced Data Sets

Machine Learning Prediction of Nine Molecular Properties Based on the SMILES Representation of the QM9 Quantum-Chemistry Dataset.

A Nearest Neighbors based Data Filter for Fog Computing in IoT Smart Agriculture

Water spray detection for smart irrigation systems with Mask R-CNN and UAV footage

Irony detection in Twitter with imbalanced class distributions

Advancing IoT-Based Smart Irrigation

Ab initio insights into the structural, energetic, electronic, and stability properties of mixed CenZr15-nO30 nanoclusters.

End-to-End Security in the IoT Computing Continuum: Perspectives in the SWAMP Project

Characterization of the sonority associated to woodwinds instruments through spectral analysis

Predicting the ideological orientation during the Spanish 24M elections in Twitter using machine learning

Designing an Open IoT Ecosystem

Learning from Imbalanced Data Sets

Emerging topics and challenges of learning from noisy data in nonstandard classification: a survey beyond binary class noise

Improving kNN classification under Unbalanced Data. A New Geometric Oversampling Approach

A First Study on the Use of Noise Filtering to Clean the Bags in Multi-Instance Classification

PolyWaTT: A polynomial water travel time estimator based on Derivative Dynamic Time Warping and Perceptually Important Points

Predicting the ideological orientation during the Spanish 24M elections in Twitter using machine learning

A first approach towards a fuzzy decision tree for multilabel classification

Fuzzy rule classifiers for multi-label classification

Class imbalance revisited: a new experimental setup to assess the performance of treatment methods

How Does Irony Affect Sentiment Analysis Tools?

Setting Parameters for Support Vector Machines using Transfer Learning

Mining DEOPS Records: Big Data's Insights into Dictatorship

Class imbalance revisited: a new experimental setup to assess the performance of treatment methods

Complex Network Measures for Data Set Characterization

Extending features for multilabel classification with swarm biclustering

An Experimental Design to Evaluate Class Imbalance Treatment Methods

A Complexity-Invariant Measure Based on Fractal Dimension for Time Series Classification

Combining feature ranking algorithms through rank aggregation

A Survey on Graphical Methods for Classification Predictive Performance Evaluation

Improvement on the Porter's Stemming Algorithm for Portuguese

Missing Value Imputation Using a Semi-supervised Rank Aggregation Approach

Evaluating Ranking Composition Methods for Multi-Objective Optimization of Knowledge Rules

Evolving Sets of Symbolic Classifiers into a Single Symbolic Classifier Using Genetic Algorithms

A Study with Class Imbalance and Random Sampling for a Decision Tree Learning System

Evaluating Classifiers Using ROC Curves

Potential Distribution Modelling Using Machine Learning

On the Class Distribution Labelling Step Sensitivity of CO-TRAINING

Constructing ensembles of symbolic classifiers

Balancing Strategies and Class Overlapping

ROCCER: An Algorithm for Rule Learning Based on ROC Analysis

Learning with Class Skews and Small Disjuncts

A study of the behavior of several methods for balancing machine learning training data

Class Imbalances versus Class Overlapping: An Analysis of a Learning System Behavior

Idiopathic hydrocele and absent testicular diastolic flow

A dvAncing i o T-B Ased s mArT i rrigATion

Imbalanced Classification for Big Data

Data Intrinsic Characteristics

Foundations on Imbalanced Classification

Cost-Sensitive Learning

Learning from Imbalanced Data Streams

Data Level Preprocessing Methods

Non-classical Imbalanced Classification Problems

Software and Libraries for Imbalanced Classification

Introduction to KDD and Data Science

Imbalanced Classification with Multiple Classes

Algorithm-Level Approaches

Dimensionality Reduction for Imbalanced Learning

The Comprehension of Figurative Language: What Is the Influence of Irony and Sarcasm on NLP Techniques?

An Analysis of Novelty Dynamics in News Media Coverage

QROC: A Variation of ROC Space to Analyze Item Set Costs/Benefits in Association Rules

Data mining with imbalanced class distributions: concepts and methods

Exploring Unclassified Texts Using Multiview Semisupervised Learning

A hybrid wrapper / filter approach for feature subset selection

A hybrid wrapper/lter approach for feature subset selection