Joao Monteiro

Joao Monteiro

Auto-generated profile, based on publicly available information

Joao Monteiro

UFCG

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2019 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
JTJoseph Townsend
Joseph Townsend
TCThomas Chaton
Thomas Chaton
JMJoao M. Monteiro
Joao M. Monteiro
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.

8 August 2019 in Scientific Reports
Verified
Journal Article
Open access
PDF file
AMAgoston Mihalik
Agoston Mihalik
FFFabio S. Ferreira
Fabio S. Ferreira
MRMaria J. Rosa
Maria J. Rosa
MMMichael Moutoussis
Michael Moutoussis
GZGabriel Ziegler
Gabriel Ziegler
JMJanaina Mourão-Miranda
Janaina Mourão-Miranda
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.

1 July 2019 in NeuroImage
Verified
Journal Article
Open access
MDMichele Donini
Michele Donini
JMJoão M. Monteiro
João M. Monteiro
MPMassimiliano Pontil
Massimiliano Pontil
THTim Hahn
Tim Hahn
AFAndreas J. Fallgatter
Andreas J. Fallgatter
JMJanaina Mourão-Miranda
Janaina Mourão-Miranda
Combining neuroimaging and clinical information for diagnosis, as for example behavioral tasks and genetics characteristics, is potentially beneficial but presents challenges in terms of finding the best data representation for the different sources of information. Their simple combination usually does not provide an improvement if compared with using the best source alone. In this paper, we proposed a framework based on a recent multiple kernel learning algorithm called EasyMKL and we investigated the benefits of this approach for diagnosing two different mental health diseases. The well known Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset tackling the Alzheimer Disease (AD) patients versus healthy controls classification task, and a second dataset tackling the task of classifying an heterogeneous group of depressed patients versus healthy controls. We used EasyMKL to combine a huge amount of basic kernels alongside a feature selection methodology, pursuing an optimal and sparse solution to facilitate interpretability. Our results show that the proposed approach, called EasyMKLFS, outperforms baselines (e.g. SVM and SimpleMKL), state-of-the-art random forests (RF) and feature selection (FS) methods.

1 January 2025
Verified
Conference Paper
Open access
PDF file
ESEkarani Silvestre
Ekarani Silvestre
RMRian Melo
Rian Melo
Ruan Delgado GomesRuan Delgado Gomes
Ruan Delgado Gomes
EJEdnaldo Junior
Ednaldo Junior
JBJoão Brunet
João Brunet
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 September 2016
Verified
Conference Paper
Open access
ARAnil Rao
Anil Rao
JMJoao Monteiro
Joao Monteiro
JMJanaina Mourao-Miranda
Janaina Mourao-Miranda
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.