You can also find my articles on my Google Scholar profile. The source code of all publications is available in the Publications GitHub Repository.
Published in UNDER SUBMISSION, 2023
In this paper we analyse tabular and latent space synthetic data generation algorithms.
Recommended citation: Fonseca, J., Bacao, F. (2023). Tabular and Latent Space Synthetic Data Generation: A Literature Review. Under Submission.
Published in UNDER SUBMISSION, 2023
In this paper, we propose Geometric SMOTE for Nominal and Continuous features (G-SMOTENC), based on a combination of G-SMOTE and SMOTENC.
Recommended citation: Fonseca, J., & Bacao, F. (2023). Geometric SMOTE for Imbalanced Datasets with Nominal and Continuous Features. Under Submission.
Published in International Journal of Intelligent Systems, 2023
This paper proposes a new AL framework, which relies on the effective use of artificial data.
Recommended citation: Fonseca, J., & Bacao, F. (2023). Improving Active Learning Performance through the Use of Data Augmentation. International Journal of Intelligent Systems, 2023. https://doi.org/10.1155/2023/7941878
Published in arXiv, 2022
In this paper we identify the main areas of application of data augmentation algorithms, the types of algorithms used, significant research trends, their progression over time and research gaps in data augmentation literature.
Recommended citation: Fonseca, J., & Bacao, F. (2022). Research Trends and Applications of Data Augmentation Algorithms. arXiv preprint arXiv:2207.08817. https://arxiv.org/abs/2207.08817
Published in Remote Sensing, 2021
In this paper, we introduce a new component to the typical AL framework, the data generator, a source of artificial data to reduce the amount of user-labeled data required in AL.
Recommended citation: Fonseca, J., Douzas, G., Bacao, F. (2021). Increasing the Effectiveness of Active Learning: Introducing Artificial Data Generation in Active Learning for Land Use/Land Cover Classification. Remote Sensing, 13(13), 2619. https://doi.org/10.3390/rs13132619
Published in Information, 2021
In this paper, we address the imbalanced learning problem, by using K-means and the Synthetic Minority Oversampling TEchnique (SMOTE) as an improved oversampling algorithm. K-Means SMOTE improves the quality of newly created artificial data by addressing both the between-class imbalance, as traditional oversamplers do, but also the within-class imbalance, avoiding the generation of noisy data while effectively overcoming data imbalance.
Recommended citation: Fonseca, J., Douzas, G., Bacao, F. (2021). Improving Imbalanced Land Cover Classification with K-Means SMOTE: Detecting and Oversampling Distinctive Minority Spectral Signatures. Information, 12(7), 266. https://doi.org/10.3390/info12070266
Published in IJCAI 2021 Workshop on AI for Social Good, 2021
In this paper, we contribute two novel methodologies that leverage Twitter discourse to characterize narratives and identify unmet needs in response to Cyclone Amphan, which affected 18 million people in May 2020.
Recommended citation: Crayton A, Fonseca J, Mehra K, Ng M, Ross J, Sandoval-Castañeda M, von Gnecht R. (2021). Narratives and Needs: Analyzing Experiences of Cyclone Amphan Using Twitter Discourse, in IJCAI 2021 Workshop on AI for Social Good. https://crcs.seas.harvard.edu/publications/narratives-and-needs-analyzing-experiences-cyclone-amphan-using-twitter-discourse
Published in Remote Sensing, 2019
In this paper, we address the imbalanced learning problem, a common and difficult conundrum in remote sensing that affects the quality of classification results, by proposing Geometric-SMOTE, a novel oversampling method, as a tool for addressing the imbalanced learning problem in remote sensing.
Recommended citation: Douzas, G., Bacao, F., Fonseca, J., & Khudinyan, M. (2019). Imbalanced Learning in Land Cover Classification: Improving Minority Classes’ Prediction Accuracy Using the Geometric SMOTE Algorithm. Remote Sensing, 11(24), 3040. https://doi.org/10.3390/rs11243040