CV

Education

• Ph.D in Computer Sciences and Computational Mathematics, University of São Paulo, 2017
• M.S. in Computer Sciences and Computational Mathematics, University of São Paulo, 2014
• B.S. in Computer Sciences, University of São Paulo, 2011
• Technical Degree in Informatics, Colégio Técnico Industrial “Isaac Portal Roldán”, 2004

Work experience

• University of São Paulo, USP, Brazil
  • 2022 - current
  • Assistant + Associate Professor
  • Duties included: Research and Teaching
• Federal University of São Carlos, UFSCar, Brazil
  • 2017 - 2022
  • Assistant Professor
  • Duties included: Research and Teaching
• University of California, Riverside, CA, USA
  • 2015 - 2016
  • Research internship
• Columbia University, New York, NY, USA
  • 2013
  • Research internship
• Other experiences
  • 2010 - Intern at Fundação Centro de Pesquisa e Desenvolvimento em Telecomunicações (CPqD) Brazil
  • 2006-2007 - Web Developer at Planae Tecnologia da Informação, Brazil
  • 2003 - 2004 - Intern at São Paulo State University (UNESP), Brazil

Publications

Match: A Maximum-Likelihood Approach for Classification under Label Shift

Donyavi, Zahra, et al. "Match: A Maximum-Likelihood Approach for Classification under Label Shift." Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2. 2025.

Local LLM Ensembles for Zero-shot Portuguese Named Entity Recognition

Sarcinelli, João Lucas Luz Lima, and Diego Furtado Silva. "Local LLM Ensembles for Zero-shot Portuguese Named Entity Recognition." 27th Iberoamerican Congress on Pattern Recognition (2025).

MariNER: A Dataset for Historical Brazilian Portuguese Named Entity Recognition

Sarcinelli, João Lucas Luz Lima, et al. "MariNER: A Dataset for Historical Brazilian Portuguese Named Entity Recognition." Brazilian Conference on Intelligent Systems. Cham: Springer Nature Switzerland, 2025.

Exploring Data-Oriented Strategies for Training ECG Self-supervised Models

Silva, Rafael da Costa, Adilson Medronha, and Diego Furtado Silva. "Exploring Data-Oriented Strategies for Training ECG Self-supervised Models." Brazilian Conference on Intelligent Systems. Cham: Springer Nature Switzerland, 2025.

Peabiru Paths DTW: desmistificando os caminhos para o alinhamento geometrico, fisico e consistente entre sismica e poco

Araújo, Marcelus Glaucus de Souza, et al. "Peabiru Paths DTW: desmistificando os caminhos para o alinhamento geométrico, físico e consistente entre sísmica e poço." X Simpósio de Quantificação em Geociências (2025).

FCKAN: Evaluating KAN for Time Series Classification and Extrinsic Regression

da Costa Merlin, Gabriel, Adilson Junior Alves Medronha, and Diego Furtado Silva. "FCKAN: Evaluating KAN for Time Series Classification and Extrinsic Regression." Encontro Nacional de Inteligência Artificial e Computacional (ENIAC). SBC, 2025.

Multimodal Fusion Strategies for Multivariate Time Series Classification

Bastos, Samuel Thomaz, Rafael da Costa Silva, and Diego Furtado Silva. "Multimodal Fusion Strategies for Multivariate Time Series Classification." Encontro Nacional de Inteligência Artificial e Computacional (ENIAC). SBC, 2025.

One-class graph autoencoder: a new end-to-end, low-dimensional, and interpretable approach for node classification.

Golo, Marcos Paulo Silva, et al. "One-class graph autoencoder: A new end-to-end, low-dimensional, and interpretable approach for node classification." Information Sciences 708 (2025): 122060.

Fine-Tuning a Pretrained ECG Foundation Model for Chagas Disease Detection

Long, Yongchao, et al. "Fine-Tuning a Pretrained ECG Foundation Model for Chagas Disease Detection." Computing in Cardiology, 2025

Machine Learning Techniques for Improving Multiclass Anomaly Detection on Conveyor Belts.

Matos, S. N., et al. "Machine Learning Techniques for Improving Multiclass Anomaly Detection on Conveyor Belts." Proceedings of the International Instrumentation and Measurement Technology Conference, 2024.

Semi-periodic activation for time series classification.

de Medeiros Júnior, José Gilberto Barbosa, Andre Guarnier de Mitri, and Diego Furtado Silva. "Semi-periodic activation for time series classification." Brazilian Conference on Intelligent Systems. Cham: Springer Nature Switzerland, 2024.

Tackling Low-Resource ECG Classification with Self-supervised Learning.

da Costa Silva, Rafael, and Diego Furtado Silva. "Tackling Low-Resource ECG Classification with Self-supervised Learning." Brazilian Conference on Intelligent Systems. Cham: Springer Nature Switzerland, 2024.

Evaluating Sentiment Quantification Methods in Brazilian Portuguese Corpora.

dos Santos Silva, Lucas Nildaimon, Diego Furtado Silva, and Helena de Medeiros Caseli. "Evaluating Sentiment Quantification Methods in Brazilian Portuguese Corpora." Brazilian Conference on Intelligent Systems. Cham: Springer Nature Switzerland, 2024.

Unsupervised feature based algorithms for time series extrinsic regression.

Guijo-Rubio, David, et al. "Unsupervised feature based algorithms for time series extrinsic regression." Data Mining and Knowledge Discovery 38.4 (2024): 2141-2185.

Artist similarity based on heterogeneous graph neural networks.

da Silva, Angelo Cesar Mendes, Diego Furtado Silva, and Ricardo Marcondes Marcacini. "Artist similarity based on heterogeneous graph neural networks." IEEE/ACM Transactions on Audio, Speech, and Language Processing 32 (2024): 3717-3729.

Noisy Self-training With Data Augmentations For Offensive And Hate Speech Detection Tasks.

Leite, J. A., et al. "Noisy Self-training With Data Augmentations For Offensive And Hate Speech Detection Tasks." Proceedings of the Recent Advances In Natural Language Processing, 2023.

Hemoglobin Estimation From Smartphone-based Photoplethysmography With Small Data.

Silva, D. F., et al. "Hemoglobin Estimation From Smartphone-based Photoplethysmography With Small Data." Proceedings of the 36th International Symposium On Computerbased Medical Systems, 2023, pp. 75-78.

A New Time Series Framework For Forest Fire Risk Forecasting And Classification.

Santos, B. Z., et al. "A New Time Series Framework For Forest Fire Risk Forecasting And Classification." Proceedings of the International Joint Conference On Neural Networks, 2023, pp. 1-8.

Multimodal representation learning over heterogeneous networks for tag-based music retrieval.

Da Silva, A. C. M., et al. "Multimodal representation learning over heterogeneous networks for tag-based music retrieval." Expert Systems with Applications, vol. 207, 2022, p. 117969.

Smartphone-Based Screening for Cardiovascular Diseases: A Trend?

Mazzu-Nascimento, T., et al. "Smartphone-Based Screening for Cardiovascular Diseases: A Trend?" International Journal of Cardiovascular Science, vol. 35, no. 1, 2022, pp. 127-134.

Heterogeneous Graph Neural Network for Music Emotion Recognition.

Da Silva, A. C. M., et al. "Heterogeneous Graph Neural Network for Music Emotion Recognition." Proceedings of the International Society for Music Information Retrieval Conference, 2022.

Smartphone-based photo analysis for the evaluation of anemia, jaundice and COVID-19.

Mazzu-Nascimento, T., et al. "Smartphone-based photo analysis for the evaluation of anemia, jaundice and COVID-19." International Journal of Nutrology, vol. 14, no. 2, 2021, pp. 55-60.

Remote and non-invasive monitoring of patients with COVID-19 by smartphone.

Mazzu-Nascimento, T., et al. "Remote and non-invasive monitoring of patients with COVID-19 by smartphone." Scientia Medica, vol. 31, no. 1, 2021, p. e39340.

CurL-AutoML: Curriculum Learning-based AutoML.

Silva, L. C., et al. "CurL-AutoML: Curriculum Learning-based AutoML." Proceedings of the IEEE International Conference On Machine Learning And Applications, 2021, pp. 766-771.

MetaPrep: Data preparation pipelines recommendation via meta-learning.

Zagatti, F. R., et al. "MetaPrep: Data preparation pipelines recommendation via meta-learning." Proceedings of the IEEE International Conference On Machine Learning And Applications, 2021, pp. 1197-1202.

Financial Time Series Forecasting Enriched with Textual Information.

Cruz, L. F. S. A., & Silva, D. F. "Financial Time Series Forecasting Enriched with Textual Information." Proceedings of the IEEE International Conference On Machine Learning And Applications, 2021, pp. 385-390.

Instance Selection for Music Genre Classification using Heterogeneous Networks.

da Silva, A. C. M., et al. "Instance Selection for Music Genre Classification using Heterogeneous Networks." Proceedings of the Brazilian Symposium on Computer Music, 2021, pp. 11-18.

Fusion of Multiple Audio Representations for Music Genre Classification.

Silva, D. F., et al. "Fusion of Multiple Audio Representations for Music Genre Classification." Proceedings of the Brazilian Symposium on Computer Music, 2021, pp. 40-47.

On Generalist and Domain-Specific Music Classification Models and Their Impacts on Brazilian Music Genre Recognition.

Silva, D. F., et al. "On Generalist and Domain-Specific Music Classification Models and Their Impacts on Brazilian Music Genre Recognition." Proceedings of the Brazilian Symposium on Computer Music, 2021, pp. 63-70.

Named Entity Recognition for Brazilian Portuguese Product Titles.

Silva, D. F., et al. "Named Entity Recognition for Brazilian Portuguese Product Titles." Proceedings of the Brazilian Conference on Intelligent Systems, 2021, pp. 526-541.

Committee of NAS-based models.

Sette, B. S., et al. "Committee of NAS-based models." Proceedings of the IEEE International Joint Conference on Neural Networks, 2021.

The Swiss army knife of time series data mining: ten useful things you can do with the matrix profile and ten lines of code.

Zhu, Y., et al. "The Swiss army knife of time series data mining: ten useful things you can do with the matrix profile and ten lines of code." Data Mining and Knowledge Discovery, vol. 34, no. 1, 2020, pp. 949-979.

Mobile Health (mHealth) and Advances in Noninvasive Diagnosis of Anemia: An Overview.

Mazzu-Nascimento, T., et al. "Mobile Health (mHealth) and Advances in Noninvasive Diagnosis of Anemia: An Overview." International Journal of Nutrology, vol. 13, no. 2, 2020, pp. 42-47.

Noninvasive Self-monitoring of Blood Glucose at Your Fingertips, Literally!: Smartphone-Based Photoplethysmography.

Mazzu-Nascimento, T., et al. "Noninvasive Self-monitoring of Blood Glucose at Your Fingertips, Literally!: Smartphone-Based Photoplethysmography." International Journal of Nutrology, vol. 13, no. 2, 2020, pp. 48-52.

4mula: A Multitask, Multimodal, And Multilingual Dataset Of Music Lyrics And Audio Features.

da Silva, A. C. M., et al. "4mula: A Multitask, Multimodal, And Multilingual Dataset Of Music Lyrics And Audio Features." Proceedings of the Brazilian Symposium On Multimedia And The Web, 2020, pp. 145-148.

Towards an Instance-Level Meta-learning-Based Ensemble for Time Series Classification.

Ueno, C. L. R. S., & Silva, D. F. "Towards an Instance-Level Meta-learning-Based Ensemble for Time Series Classification." Proceedings of the Brazilian Conference on Intelligent Systems, 2020, pp. 426-441.

Benchmarking Machine Learning Solutions In Production.

Silva, L. C., et al. "Benchmarking Machine Learning Solutions In Production." Proceedings of the IEEE International Conference On Machine Learning And Applications, 2020, pp. 626-633.

Towards Logical Association Rule Mining On Ontology-based Semantic Trajectories.

Petri, A. C. F., & Silva, D. F. "Towards Logical Association Rule Mining On Ontology-based Semantic Trajectories." Proceedings of the IEEE International Conference On Machine Learning And Applications, 2020, pp. 586-591.

Toxic Language Detection In Social Media For Brazilian Portuguese: New Dataset And Multilingual Analysis.

Leite, J. A., et al. "Toxic Language Detection In Social Media For Brazilian Portuguese: New Dataset And Multilingual Analysis." Proceedings of the International Joint Conference On Natural Language Processing, 2020, pp. 914-924.

Measuring What Counts: the Case Of Rumour Stance Classification.

Scarton, C. E., et al. "Measuring What Counts: the Case Of Rumour Stance Classification." Proceedings of the International Joint Conference On Natural Language Processing, 2020, pp. 925-932.

On Convolutional Autoencoders To Speed Up Similarity-based Time Series Mining.

Silva, Y. G. A., & Silva, D. F. "On Convolutional Autoencoders To Speed Up Similarity-based Time Series Mining." Proceedings of the IEEE International Conference On Big Data, 2020.

Measuring Disruption in Song Similarity Networks.

Falcão, F. V., et al. "Measuring Disruption in Song Similarity Networks." Proceedings of the International Society for Music Information Retrieval Conference, 2020, pp. 30-37.

Knowledge Discovery In Brazilian Soccer Championship Scout Data.

Ortolan, L. F., & Silva, D. F. "Knowledge Discovery In Brazilian Soccer Championship Scout Data." Encontro Nacional De Inteligência Artificial e Computacional, 2020, pp. 626-637.

A Combination of Local Approaches for Hierarchical Music Genre Classification.

Parmezan, A. S., et al. "A Combination of Local Approaches for Hierarchical Music Genre Classification." Proceedings of the International Society for Music Information Retrieval Conference, 2020, pp. 740-747.

Fast similarity matrix profile for music analysis and exploration.

Silva, D. F., et al. "Fast similarity matrix profile for music analysis and exploration." IEEE Transactions on Multimedia, vol. 21, no. 1, 2019, pp. 29-38.

Da-TACOS: A Dataset for Cover Song Identification and Understanding.

Yesiler, F., et al. "Da-TACOS: A Dataset for Cover Song Identification and Understanding." Proceedings of the 20th International Society for Music Information Retrieval Conference, 2019, pp. 327-334.

On Combining Diverse Models for Lyrics-Based Music Genre Classification.

Ueno, C. L. R. S., & Silva, D. F. "On Combining Diverse Models for Lyrics-Based Music Genre Classification." Proceedings of the Brazilian Conference on Intelligent Systems, 2019, pp. 138-143.

Speeding up similarity search under dynamic time warping by pruning unpromising alignments.

Silva, D. F., et al. "Speeding up similarity search under dynamic time warping by pruning unpromising alignments." Data Mining and Knowledge Discovery, vol. 32, 2018, pp. 988-1016.

Time Series Joins, Motifs, Discords and Shapelets: a Unifying View that Exploits the Matrix Profile.

Yeh, C. M., et al. "Time Series Joins, Motifs, Discords and Shapelets: a Unifying View that Exploits the Matrix Profile." Data Mining and Knowledge Discovery, vol. 32, 2018, pp. 83-123.

Optimizing Dynamic Time Warping’s Window Width For Time Series Data Mining Applications.

Dau, H. A., et al. "Optimizing Dynamic Time Warping's Window Width For Time Series Data Mining Applications." Data Mining and Knowledge Discovery, vol. 32, 2018, pp. 1074-1120.

Classifying and Counting with Recurrent Contexts.

Reis, D. M., et al. "Classifying and Counting with Recurrent Contexts." Proceedings of the 24th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2018, pp. 1983-1992.

Exploring Musical Relations Using Association Rule Networks.

Padua, R., et al. "Exploring Musical Relations Using Association Rule Networks." Proceedings of the 19th International Society for Music Information Retrieval Conference, 2018, pp. 400-406.

Elastic Time Series Motifs and Discords.

Silva, D. F., & Batista, G. E. A. P. A. "Elastic Time Series Motifs and Discords." Proceedings of the 17th IEEE International Conference on Machine Learning and Applications, 2018, pp. 237-242.

Summarizing and Comparing Music Data and its Application on Cover Song Identification.

Silva, D. F., et al. "Summarizing and Comparing Music Data and its Application on Cover Song Identification." Proceedings of the 19th International Society for Music Information Retrieval Conference, 2018, pp. 732-739.

Improved assessment of accuracy and performance indicators in paper-based ELISA.

Mazzu-Nascimento, T., et al. "Improved assessment of accuracy and performance indicators in paper-based ELISA." Analytical methods, vol. 9, no. 1, 2017, pp. 2644-2653.

Judicious Setting of Dynamic Time Warping’s Window Width Allows More Accurate Classification of Time Series.

Dau, H. A., et al. "Judicious Setting of Dynamic Time Warping's Window Width Allows More Accurate Classification of Time Series." Proceedings of the IEEE International Conference on Big Data, 2017, pp. 917-922.

Improved Time Series Classification with Representation Diversity and SVM.

Giusti, R., et al. "Improved Time Series Classification with Representation Diversity and SVM." Proceedings of the 15th IEEE International Conference on Machine Learning and Applications, 2016, pp. 1-6.

MatrixProfile I: All Pairs Similarity Joins for Time Series.

Yeh, C. M., et al. "MatrixProfile I: All Pairs Similarity Joins for Time Series." Proceedings of the IEEE International Conference on Data Mining, 2016, pp. 1317-1322.

Speeding Up All-Pairwise Dynamic Time Warping Matrix Calculation.

Silva, D. F., & Batista, G. E. A. P. A. "Speeding Up All-Pairwise Dynamic Time Warping Matrix Calculation." Proceedings of the SIAM International Conference on Data Mining, 2016, pp. 837-845.

SiMPle: Assessing Music Similarity Using Subsequences Joins.

Silva, D. F., et al. "SiMPle: Assessing Music Similarity Using Subsequences Joins." Proceedings of the 17th International Society for Music Information Retrieval Conference, 2016, pp. 23-29.

Prefix and Suffix Invariant Dynamic Time Warping.

Silva, D. F., et al. "Prefix and Suffix Invariant Dynamic Time Warping." Proceedings of the IEEE International Conference on Data Mining, 2016, pp. 1209-1214.

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

Prati, R. C., et al. "Class imbalance revisited: a new experimental setup to assess the performance of treatment methods." Knowledge and Information Systems, vol. 45, no. 1, 2015, pp. 247-270.

Exploring Low Cost Laser Sensors to Identify Flying Insect Species.

Silva, D. F., et al. "Exploring Low Cost Laser Sensors to Identify Flying Insect Species." Journal of Intelligent & Robotic Systems, vol. 80, no. 1, 2015, pp. 313-330.

Time Series Classification with Representation Ensembles.

Giusti, R., et al. "Time Series Classification with Representation Ensembles." International Symposium on Intelligent Data Analysis, 2015, pp. 108-119.

Classification of Evolving Data Streams with Infinitely Delayed Labels.

Souza, V. M. A., et al. "Classification of Evolving Data Streams with Infinitely Delayed Labels." Proceedings of the 14th IEEE International Conference on Machine Learning and Applications, 2015, pp. 214-219.

Data Stream Classification Guided by Clustering on Nonstationary Environments.

Souza, V. M. A., et al. "Data Stream Classification Guided by Clustering on Nonstationary Environments." Proceedings of the SIAM International Conference on Data Mining, 2015, pp. 873-881.

Music Shapelets for Fast Cover Song Recognition.

Silva, D. F., et al. "Music Shapelets for Fast Cover Song Recognition." Proceedings of the 16th International Society for Music Information Retrieval Conference, 2015, pp. 441-447.

Adding Diversity to Rank Examples in Anytime Nearest Neighbor Classification.

Lemes, C. I., et al. "Adding Diversity to Rank Examples in Anytime Nearest Neighbor Classification." Proceedings of the 13th IEEE International Conference on Machine Learning and Applications, 2014, pp. 129-134.

Extracting Texture Features for Time Series Classification.

Souza, V. M. A., et al. "Extracting Texture Features for Time Series Classification." Proceedings of the 22nd International Conference on Pattern Recognition, 2014, pp. 1425-1430.

Music Classification by Transductive Learning Using Bipartite Heterogeneous Networks.

Silva, D. F., et al. "Music Classification by Transductive Learning Using Bipartite Heterogeneous Networks." Proceedings of the 15th International Society for Music Information Retrieval Conference, 2014, pp. 113-118.

A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English.

Silva, D. F., et al. "A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English." Acta Scientiarum Technology, vol. 35, no. 4, 2013, pp. 621-628.

Classification of Data Streams Applied to Insect Recognition.

Souza, V. M. A., et al. "Classification of Data Streams Applied to Insect Recognition: Initial Results." Proceedings of the Brazilian Conference on Intelligent Systems, 2013, pp. 76-81.

Avaliação de Classificadores para o Reconhecimento Automático de Insetos.

Souza, V. M. A., et al. "Avaliação de Classificadores para o Reconhecimento Automático de Insetos." Anais do Encontro Nacional de Inteligência Artificial e Computacional, 2013, pp. 1-12.

Applying Machine Learning and Audio Analysis Techniques to Insect Recognition in Intelligent Traps.

Silva, D. F., et al. "Applying Machine Learning and Audio Analysis Techniques to Insect Recognition in Intelligent Traps." Proceedings of the 12th IEEE International Conference on Machine Learning and Applications, 2013, pp. 99-104.

A Video Compression-based Approach To Measure Music Structural Similarity.

Silva, D. F., et al. "A Video Compression-based Approach To Measure Music Structural Similarity." Proceedings of the 14th International Society for Music Information Retrieval Conference, 2013, pp. 95-100.

Time Series Classification Using Compression Distance of Recurrence Plots.

Silva, D. F., et al. "Time Series Classification Using Compression Distance of Recurrence Plots." Proceedings of the IEEE International Conference on Data Mining, 2013, pp. 687-696.

An Experimental Design to Evaluate Class Imbalance Treatment Methods.

Batista, G. E. A. P. A., et al. "An Experimental Design to Evaluate Class Imbalance Treatment Methods." Proceedings of the 11th IEEE International Conference on Machine Learning and Applications, 2012, pp. 95-101.

Spoken Digit Recognition in Portuguese Using Line Spectral Frequencies.

Silva, D. F., et al. "Spoken Digit Recognition in Portuguese Using Line Spectral Frequencies." Proceedings of the 13th Ibero-American Conference on Artificial Intelligence, 2012, pp. 241-250.

Resultados Preliminares na Classificação de Insetos Utilizando Sensores Ópticos.

Silva, D. F., et al. "Resultados Preliminares na Classificação de Insetos Utilizando Sensores Ópticos." Anais do XXXI Congresso da Sociedade Brasileira de Computação, 2011, pp. 749-760.

Uma Comparação Experimental de Métodos de Imputação de Valores Desconhecidos.

Silva, D. F., & Batista, G. E. A. P. A. "Uma Comparação Experimental de Métodos de Imputação de Valores Desconhecidos." Anais do IV Congresso da Academia Trinacional de Ciências, 2009, pp. 1-10.

How k-Nearest Neighbor Parameters Affect its Performance.

Batista, G. E. A. P. A., & Silva, D. F. "How k-Nearest Neighbor Parameters Affect its Performance." Proceedings of the Argentine Symposium on Artificial Intelligence, 2009, pp. 1-12.

Services to the academic community

• Associate Editor - Machine Learning Journal (Springer)
• PC Chair of the Brazilian Conference on Intelligent Systems (BRACIS) 2025
• PC Chair of the Encontro Nacional de Inteligência Artificial e Computacional (ENIAC) 2024
• PC Chair of the Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) 2022
• Editorial chair of the International Conference on Computational Processing of Portuguese (PROPOR) 2022
• PC co-Chair of the Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) 2021