Joao Monteiro
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Joao Monteiro has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Janaina Mourao-Miranda
Department of Computer Science Centre for Artificial Intelligence University College London UK
3 shared publications - Ekarani T. Silvestre
UFCG
2 shared publications - Ruan Delgado Gomes
IFPB
2 shared publications - Agoston Mihalik
Department of Psychiatry, University of Cambridge, Cambridge, UK
1 shared publication Aislinn Bowler
1 shared publicationAlexandra Hopkins
1 shared publication
Latest Publications
- Open Access
- 1 September 2025
- Published by Sociedade Brasileira de Computação
- p. 66-74
NuAppFirewall: An Open-Source macOS Application Firewall for Corporate Security
Managing network access is essential to ensure the security of both users and corporate ecosystems. On macOS, this control is implemented through Content Filters in firewall applications. However, the state of the practice consists mainly of proprietary consumer tools, while open-source alternatives lack the modularity needed for enterprise adoption. This paper introduces NuAppFirewall, an open-source application firewall developed and deployed in production at Nubank. It includes more than 250,000 automatically generated rules for macOS applications, derived from Nubank’s validated accesses, providing a security foundation that other organizations can leverage for their own implementations.
- 1 September 2025
- Published by Sociedade Brasileira de Computação
- p. 66-74
Open AccessNuAppFirewall: An Open-Source macOS Application Firewall for Corporate Security
Managing network access is essential to ensure the security of both users and corporate ecosystems. On macOS, this control is implemented through Content Filters in firewall applications. However, the state of the practice consists mainly of proprietary consumer tools, while open-source alternatives lack the modularity needed for enterprise adoption. This paper introduces NuAppFirewall, an open-source application firewall developed and deployed in production at Nubank. It includes more than 250,000 automatically generated rules for macOS applications, derived from Nubank’s validated accesses, providing a security foundation that other organizations can leverage for their own implementations.
- Open Access
- 19 May 2025
- Published by Sociedade Brasileira de Computação
- p. 382-387
Evaluating Semantic Caching in Practice: A Study on a LLM-Driven Distributed Application in a Brazilian EdTech
Large Language Models (LLMs) support various business functions, such as Alura’s use of GPT-4 to assess students’ answers. However, high computational and financial costs, along with response time issues, limit scalability. While caching mechanisms offer an alternative, traditional cache fails to evaluate queries semantically, leading to low hit rates. This work evaluates semantic caching on an Alura’s dataset of 94, 913 answers from 20, 639 students. Results show that 45.1% of LLM requests could be served from the cache, significantly reducing costs and improving response times by 4–12× for cache hits.
- 19 May 2025
- Published by Sociedade Brasileira de Computação
- p. 382-387
Open AccessEvaluating Semantic Caching in Practice: A Study on a LLM-Driven Distributed Application in a Brazilian EdTech
Large Language Models (LLMs) support various business functions, such as Alura’s use of GPT-4 to assess students’ answers. However, high computational and financial costs, along with response time issues, limit scalability. While caching mechanisms offer an alternative, traditional cache fails to evaluate queries semantically, leading to low hit rates. This work evaluates semantic caching on an Alura’s dataset of 94, 913 answers from 20, 639 students. Results show that 45.1% of LLM requests could be served from the cache, significantly reducing costs and improving response times by 4–12× for cache hits.
- Open Access
- 19 May 2025
- Published by Sociedade Brasileira de Computação
- p. 364-369
Explorando Network Slicing em Redes 5G em um Contexto Educacional
O uso de ferramentas digitais no ensino acelerou durante a pandemia, destacando plataformas como o Moodle e sistemas inteligentes para ensino personalizado. A Educação Inteligente é impulsionada pelas redes 5G, que oferecem altas taxas de dados, baixa latência e conectividade confiável, fundamentais para aplicações multimídia. Neste contexto, este artigo apresenta uma prova de conceito baseada em fatiamento de rede para otimizar recursos em um ambiente de Ensino a Distância (EAD) utilizando a plataforma Moodle. Um xApp é utilizado para monitorar a RAN e permitir o balanceamento dinâmico de carga, com base nos perfis dos usuários conectados.
- 19 May 2025
- Published by Sociedade Brasileira de Computação
- p. 364-369
Open AccessExplorando Network Slicing em Redes 5G em um Contexto Educacional
O uso de ferramentas digitais no ensino acelerou durante a pandemia, destacando plataformas como o Moodle e sistemas inteligentes para ensino personalizado. A Educação Inteligente é impulsionada pelas redes 5G, que oferecem altas taxas de dados, baixa latência e conectividade confiável, fundamentais para aplicações multimídia. Neste contexto, este artigo apresenta uma prova de conceito baseada em fatiamento de rede para otimizar recursos em um ambiente de Ensino a Distância (EAD) utilizando a plataforma Moodle. Um xApp é utilizado para monitorar a RAN e permitir o balanceamento dinâmico de carga, com base nos perfis dos usuários conectados.
- Open Access
- 1 January 2025
- Published by Sociedad Brasileira de Telecomunicacoes
A Proof of Concept for QoS-Oriented 5G Network Slicing with eBPF-TC
This paper presents a proof of concept on dynamically slicing a 5G network using TC and eBPF for granular Quality of Service (QoS). The approach ensures appropriate bandwidth for each slice based on near real-time traffic inspection and classification. eBPF handles packet inspection and classification using the Hierarchical Token Bucket (HTB) queuing discipline for bandwidth adjustment. By enabling reactive adjustments, eBPF provides granular control based on network events, essential for agile Quality of Experience (QoE) monitoring. The PoC considers four User Equipments (UEs) with throughput assessment and performance monitoring using FlexRIC. The observed slice activation and deactivation response times were 0.37s and 0.05s, respectively.
- 1 January 2025
- Published by Sociedad Brasileira de Telecomunicacoes
Open AccessA Proof of Concept for QoS-Oriented 5G Network Slicing with eBPF-TC
This paper presents a proof of concept on dynamically slicing a 5G network using TC and eBPF for granular Quality of Service (QoS). The approach ensures appropriate bandwidth for each slice based on near real-time traffic inspection and classification. eBPF handles packet inspection and classification using the Hierarchical Token Bucket (HTB) queuing discipline for bandwidth adjustment. By enabling reactive adjustments, eBPF provides granular control based on network events, essential for agile Quality of Experience (QoE) monitoring. The PoC considers four User Equipments (UEs) with throughput assessment and performance monitoring using FlexRIC. The observed slice activation and deactivation response times were 0.37s and 0.05s, respectively.
- 18 December 2024
- Published by Springer Nature
- p. 583-596
Electronic Identification of Health Professionals in Digital Health Service Provision—A Case Study in Brazil
- 18 December 2024
- Published by Springer Nature
- p. 583-596
Electronic Identification of Health Professionals in Digital Health Service Provision—A Case Study in Brazil
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 31 (9) , 3456-3470
Extracting Relational Explanations From Deep Neural Networks: A Survey From a Neural-Symbolic Perspective
The term ``explainable AI'' refers to the goal of producing artificially intelligent agents that are capable of providing explanations for their decisions. Some models (e.g., rule-based systems) are designed to be explainable, while others are less explicit ``black boxes'' for which their reasoning remains a mystery. One example of the latter is the neural network, and over the past few decades, researchers in the field of neural-symbolic integration (NSI) have sought to extract relational knowledge from such networks. Extraction from deep neural networks, however, has remained a challenge until recent years in which many methods of extracting distinct, salient features from input or hidden feature spaces of deep neural networks have been proposed. Furthermore, methods of identifying relationships between these features have also emerged. This article presents examples of old and new developments in extracting relational explanations in order to argue that the latter have analogies in the former and, as such, can be described in terms of long-established taxonomies and frameworks presented in early neural-symbolic literature. We also outline potential future research directions that come to light from this refreshed perspective.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 31 (9) , 3456-3470
Extracting Relational Explanations From Deep Neural Networks: A Survey From a Neural-Symbolic Perspective
The term ``explainable AI'' refers to the goal of producing artificially intelligent agents that are capable of providing explanations for their decisions. Some models (e.g., rule-based systems) are designed to be explainable, while others are less explicit ``black boxes'' for which their reasoning remains a mystery. One example of the latter is the neural network, and over the past few decades, researchers in the field of neural-symbolic integration (NSI) have sought to extract relational knowledge from such networks. Extraction from deep neural networks, however, has remained a challenge until recent years in which many methods of extracting distinct, salient features from input or hidden feature spaces of deep neural networks have been proposed. Furthermore, methods of identifying relationships between these features have also emerged. This article presents examples of old and new developments in extracting relational explanations in order to argue that the latter have analogies in the former and, as such, can be described in terms of long-established taxonomies and frameworks presented in early neural-symbolic literature. We also outline potential future research directions that come to light from this refreshed perspective.
- Open Access
- 8 August 2019
- Published by Springer Nature in Scientific Reports
- Vol. 9 (1) , 1-11
Brain-behaviour modes of covariation in healthy and clinically depressed young people
Understanding how variations in dimensions of psychometrics, IQ and demographics relate to changes in brain connectivity during the critical developmental period of adolescence and early adulthood is a major challenge. This has particular relevance for mental health disorders where a failure to understand these links might hinder the development of better diagnostic approaches and therapeutics. Here, we investigated this question in 306 adolescents and young adults (14–24 y, 25 clinically depressed) using a multivariate statistical framework, based on canonical correlation analysis (CCA). By linking individual functional brain connectivity profiles to self-report questionnaires, IQ and demographic data we identified two distinct modes of covariation. The first mode mapped onto an externalization/internalization axis and showed a strong association with sex. The second mode mapped onto a well-being/distress axis independent of sex. Interestingly, both modes showed an association with age. Crucially, the changes in functional brain connectivity associated with changes in these phenotypes showed marked developmental effects. The findings point to a role for the default mode, frontoparietal and limbic networks in psychopathology and depression.
- 8 August 2019
- Published by Springer Nature in Scientific Reports
- Vol. 9 (1) , 1-11
Open AccessBrain-behaviour modes of covariation in healthy and clinically depressed young people
Understanding how variations in dimensions of psychometrics, IQ and demographics relate to changes in brain connectivity during the critical developmental period of adolescence and early adulthood is a major challenge. This has particular relevance for mental health disorders where a failure to understand these links might hinder the development of better diagnostic approaches and therapeutics. Here, we investigated this question in 306 adolescents and young adults (14–24 y, 25 clinically depressed) using a multivariate statistical framework, based on canonical correlation analysis (CCA). By linking individual functional brain connectivity profiles to self-report questionnaires, IQ and demographic data we identified two distinct modes of covariation. The first mode mapped onto an externalization/internalization axis and showed a strong association with sex. The second mode mapped onto a well-being/distress axis independent of sex. Interestingly, both modes showed an association with age. Crucially, the changes in functional brain connectivity associated with changes in these phenotypes showed marked developmental effects. The findings point to a role for the default mode, frontoparietal and limbic networks in psychopathology and depression.
- Open Access
- 1 July 2019
- Published by Elsevier in NeuroImage
- Vol. 195, 215-231
Combining heterogeneous data sources for neuroimaging based diagnosis: re-weighting and selecting what is important
- 1 July 2019
- Published by Elsevier in NeuroImage
- Vol. 195, 215-231
Open AccessCombining heterogeneous data sources for neuroimaging based diagnosis: re-weighting and selecting what is important
- Open Access
- 1 September 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Prediction of clinical scores from neuroimaging data with censored likelihood gaussian processes
In this paper, we explore the use of Censored Likelihoods in Gaussian Process Regression when predicting bounded clinical scores from neuroimaging data. The standard approach, which uses a Gaussian Likelihood, does not respect the fact that the clinical scores are bounded, and so may produce suboptimal models. Conversely, Censored Likelihoods explicitly model the restricted range of such clinical scores and carry this property through inference. We apply both the standard approach and the Censored Likelihood approach to the prediction of the MMSE score from structural MRI. Overall, we find small improvements in mean squared error when using the Censored Likelihood and in addition, the censored models are more favoured from a Bayesian perspective. We also discuss the qualitative nature of the predictions of the two approaches.
- 1 September 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Open AccessPrediction of clinical scores from neuroimaging data with censored likelihood gaussian processes
In this paper, we explore the use of Censored Likelihoods in Gaussian Process Regression when predicting bounded clinical scores from neuroimaging data. The standard approach, which uses a Gaussian Likelihood, does not respect the fact that the clinical scores are bounded, and so may produce suboptimal models. Conversely, Censored Likelihoods explicitly model the restricted range of such clinical scores and carry this property through inference. We apply both the standard approach and the Censored Likelihood approach to the prediction of the MMSE score from structural MRI. Overall, we find small improvements in mean squared error when using the Censored Likelihood and in addition, the censored models are more favoured from a Bayesian perspective. We also discuss the qualitative nature of the predictions of the two approaches.