Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
About

About

My research interests cover data management in eventual consistent settings, distributed data aggregation and causality tracking. In the last years I have collaborated with my co-authors in the development of data summary mechanisms such as Scalable Bloom Filters, causality tracking for dynamic settings with Interval Tree Clocks and Dotted Version Vectors and in predictable eventual consistency with Conflict-Free Replicated Data Types. My recent work has been applied in the Riak distributed database and in Akka distributed data, and is running in production systems serving millions of users worldwide.

Interest
Topics
Details

Details

  • Name

    Carlos Baquero
  • Role

    Area Manager
  • Since

    01st November 2011
003
Publications

2024

Performance and explainability of feature selection-boosted tree-based classifiers for COVID-19 detection

Authors
Rufino, J; Ramírez, JM; Aguilar, J; Baquero, C; Champati, J; Frey, D; Lillo, RE; Fernández Anta, A;

Publication
HELIYON

Abstract
In this paper, we evaluate the performance and analyze the explainability of machine learning models boosted by feature selection in predicting COVID-19-positive cases from self-reported information. In essence, this work describes a methodology to identify COVID-19 infections that considers the large amount of information collected by the University of Maryland Global COVID-19 Trends and Impact Survey (UMD-CTIS). More precisely, this methodology performs a feature selection stage based on the recursive feature elimination (RFE) method to reduce the number of input variables without compromising detection accuracy. A tree-based supervised machine learning model is then optimized with the selected features to detect COVID-19-active cases. In contrast to previous approaches that use a limited set of selected symptoms, the proposed approach builds the detection engine considering a broad range of features including self-reported symptoms, local community information, vaccination acceptance, and isolation measures, among others. To implement the methodology, three different supervised classifiers were used: random forests (RF), light gradient boosting (LGB), and extreme gradient boosting (XGB). Based on data collected from the UMD-CTIS, we evaluated the detection performance of the methodology for four countries (Brazil, Canada, Japan, and South Africa) and two periods (2020 and 2021). The proposed approach was assessed in terms of various quality metrics: F1-score, sensitivity, specificity, precision, receiver operating characteristic (ROC), and area under the ROC curve (AUC). This work also shows the normalized daily incidence curves obtained by the proposed approach for the four countries. Finally, we perform an explainability analysis using Shapley values and feature importance to determine the relevance of each feature and the corresponding contribution for each country and each country/year.

2024

Pondering the Ugly Underbelly, and Whether Images Are Real

Authors
Hill, RK; Baquero, C;

Publication
Commun. ACM

Abstract
[No abstract available]

2023

Using survey data to estimate the impact of the omicron variant on vaccine efficacy against COVID-19 infection

Authors
Rufino, J; Baquero, C; Frey, D; Glorioso, CA; Ortega, A; Rescic, N; Roberts, JC; Lillo, RE; Menezes, R; Champati, JP; Anta, AF;

Publication
SCIENTIFIC REPORTS

Abstract
Symptoms-based detection of SARS-CoV-2 infection is not a substitute for precise diagnostic tests but can provide insight into the likely level of infection in a given population. This study uses symptoms data collected in the Global COVID-19 Trends and Impact Surveys (UMD Global CTIS), and data on variants sequencing from GISAID. This work, conducted in January of 2022 during the emergence of the Omicron variant (subvariant BA.1), aims to improve the quality of infection detection from the available symptoms and to use the resulting estimates of infection levels to assess the changes in vaccine efficacy during a change of dominant variant; from the Delta dominant to the Omicron dominant period. Our approach produced a new symptoms-based classifier, Random Forest, that was compared to a ground-truth subset of cases with known diagnostic test status. This classifier was compared with other competing classifiers and shown to exhibit an increased performance with respect to the ground-truth data. Using the Random Forest classifier, and knowing the vaccination status of the subjects, we then proceeded to analyse the evolution of vaccine efficacy towards infection during different periods, geographies and dominant variants. In South Africa, where the first significant wave of Omicron occurred, a significant reduction of vaccine efficacy is observed from August-September 2021 to December 2021. For instance, the efficacy drops from 0.81 to 0.30 for those vaccinated with 2 doses (of Pfizer/BioNTech), and from 0.51 to 0.09 for those vaccinated with one dose (of Pfizer/BioNTech or Johnson & Johnson). We also extended the study to other countries in which Omicron has been detected, comparing the situation in October 2021 (before Omicron) with that of December 2021. While the reduction measured is smaller than in South Africa, we still found, for instance, an average drop in vaccine efficacy from 0.53 to 0.45 among those vaccinated with two doses. Moreover, we found a significant negative (Pearson) correlation of around - 0.6 between the measured prevalence of Omicron in several countries and the vaccine efficacy in those same countries. This prediction, in January of 2022, of the decreased vaccine efficacy towards Omicron is in line with the subsequent increase of Omicron infections in the first half of 2022.

2023

Time-limited Bloom Filter

Authors
Rodrigues, A; Shtul, A; Baquero, C; Almeida, PS;

Publication
38TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2023

Abstract
A Bloom Filter is a probabilistic data structure designed to check, rapidly and memory-efficiently, whether an element is present in a set. It has been vastly used in various computing areas and several variants, allowing deletions, dynamic sets and working with sliding windows, have surfaced over the years. When summarizing data streams, it becomes relevant to identify the more recent elements in the stream. However, most of the sliding window schemes consider the most recent items of a data stream without considering time as a factor. While this allows, e.g., storing the most recent 10000 elements, it does not easily translate into storing elements received in the last 60 seconds, unless the insertion rate is stable and known in advance. In this paper, we present the Time-limited Bloom Filter, a new BF-based approach that can save information of a given time period and correctly identify it as present when queried, while also being able to retire data when it becomes stale. The approach supports variable insertion rates while striving to keep a target false positive rate. We also make available a reference implementation of the data structure as a Redis module.

2023

Probabilistic Causal Contexts for Scalable CRDTs

Authors
Fernandes, PH; Baquero, C;

Publication
PROCEEDINGS OF THE 10TH WORKSHOP ON PRINCIPLES AND PRACTICE OF CONSISTENCY FOR DISTRIBUTED DATA, PAPOC 2023

Abstract
Conflict-free Replicated Data Types (CRDTs) are useful to allow a distributed system to operate on data even when partitions occur, and thus preserve operational availability. Most CRDTs need to track whether data evolved concurrently at different nodes and needs to be reconciled; this requires storing causality metadata that is proportional to the number of nodes. In this paper, we try to overcome this limitation by introducing a stochastic mechanism that is no longer linear on the number of nodes, but whose accuracy is now tied to how much divergence occurs between synchronizations. This provides a new tool that can be useful in deployments with many anonymous nodes and frequent synchronizations. However, there is an underlying trade-off with classic deterministic solutions, since the approach is now probabilistic and the accuracy depends on the configurable metadata space size.

Supervised
thesis

2023

Dynamic end-to-end reliable causal delivery middleware for geo-replicated services

Author
Georges Younes

Institution
UP-FEUP

2023

ROSES: Renaming Operations for Scalable Eventually-Consistent Sets

Author
Juliane de Lima Marubayashi

Institution
UP-FEUP

2023

Design and Implementation of Pure Operation-Based CRDTs

Author
Luís Filipe Sousa Teixeira Recharte

Institution
UP-FEUP

2022

Development of a platform for integrated clinical records of cystic fibrosis patients in a national reference center

Author
Márcia Isabel Reis Teixeira

Institution
UP-FEUP

2022

Design de Interface para uma Plataforma de Registo Clínico Integrado de Doentes com Fibrose Quística num Centro de Referência Nacional

Author
Maria Teresa Santos Quelhas Pinto Leite

Institution
UP-FEUP