Nelson Neto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nelson Neto has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
- Cassio Batista
Federal University of Para
7 shared publications - Marcelle Pereira Mota
UFPA
6 shared publications - Bianchi Serique Meiguins
Federal University of Para
5 shared publications - Jefferson Morais
Federal University of Para
5 shared publications Aldebaro Klautau
4 shared publicationsAnderson Marques
3 shared publications
Latest Publications
- Open Access
- 20 January 2026
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 32 (1) , 1416-1427
Identification of Vulnerable Areas to Domestic Violence: A Multicriteria Decision-Making Approach
This study proposes a multicriteria approach to classify municipalities based on to their vulnerability to Domestic and Family Violence Against Women (DFVAW). Using data from IBGE and violence records, the ELECTRE Tri-B method was applied based on socioeconomic criteria and the Assistance and Protection Index (IAP), which aggregates municipal indicators on specialized victim support services. Municipalities were grouped into four vulnerability levels, allowing the identification of regions with greater shortages of support and unfavorable socioeconomic conditions. The case study in the Metropolitan Region of Belém indicated that areas with better infrastructure recorded more reports, suggesting a relationship between access to services and violence reporting. Compared to the FCM-TOPSIS method, ELECTRE Tri-B demonstrated greater accuracy in differentiating vulnerabilities. The results highlight the usefulness of this approach as a tool to support public policies and optimize resource allocation in combating domestic violence.
- 20 January 2026
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 32 (1) , 1416-1427
Open AccessIdentification of Vulnerable Areas to Domestic Violence: A Multicriteria Decision-Making Approach
This study proposes a multicriteria approach to classify municipalities based on to their vulnerability to Domestic and Family Violence Against Women (DFVAW). Using data from IBGE and violence records, the ELECTRE Tri-B method was applied based on socioeconomic criteria and the Assistance and Protection Index (IAP), which aggregates municipal indicators on specialized victim support services. Municipalities were grouped into four vulnerability levels, allowing the identification of regions with greater shortages of support and unfavorable socioeconomic conditions. The case study in the Metropolitan Region of Belém indicated that areas with better infrastructure recorded more reports, suggesting a relationship between access to services and violence reporting. Compared to the FCM-TOPSIS method, ELECTRE Tri-B demonstrated greater accuracy in differentiating vulnerabilities. The results highlight the usefulness of this approach as a tool to support public policies and optimize resource allocation in combating domestic violence.
- 28 June 2025
- Published by Springer Nature
- p. 250-267
Name Pattern Recognition: A Model Proposal Applied to the Anonymization of Unstructured Data
- 28 June 2025
- Published by Springer Nature
- p. 250-267
Name Pattern Recognition: A Model Proposal Applied to the Anonymization of Unstructured Data
- Open Access
- 14 July 2024
- Published by Elsevier in Data in Brief
- Vol. 55, 110678
HornBase: An audio dataset of car horns in different scenarios and positions
- 14 July 2024
- Published by Elsevier in Data in Brief
- Vol. 55, 110678
Open AccessHornBase: An audio dataset of car horns in different scenarios and positions
- Open Access
- 30 June 2024
- Published by AISTI in RISTI - Revista Ibérica de Sistemas e Tecnologias de Informação
- No. 54,p. 121-137
Uma Aplicacão para Explicabilidade de Predições de um SVM em Tweets de COVID-19
Este trabalho propõe uma aplicação web que usa um modelo de caixa preta Support Vector Machine (SVM) com 79% de acurácia para classificar o sentimento de tweets sobre a COVID-19 integrando o framework LIME de forma interativa para explicar decisões sobre previsões. Além do ganho de transparência em relação à avaliação de amostras falso-positivas, notou-se também que o modelo SVM tende a falhar ao associar um teste positivo de COVID-19 a um bom sentimento e se confunde em previso˜es envolvendo palavras sobre a COVID-19, como Omicron, que indica falta de representatividade na base de dados. Além disso, a partir dos resultados do LIME, foi possível melhorar a acura´cia do modelo para 81% ao incluir as stopwords ”not” e ”no”.
- 30 June 2024
- Published by AISTI in RISTI - Revista Ibérica de Sistemas e Tecnologias de Informação
- No. 54,p. 121-137
Open AccessUma Aplicacão para Explicabilidade de Predições de um SVM em Tweets de COVID-19
Este trabalho propõe uma aplicação web que usa um modelo de caixa preta Support Vector Machine (SVM) com 79% de acurácia para classificar o sentimento de tweets sobre a COVID-19 integrando o framework LIME de forma interativa para explicar decisões sobre previsões. Além do ganho de transparência em relação à avaliação de amostras falso-positivas, notou-se também que o modelo SVM tende a falhar ao associar um teste positivo de COVID-19 a um bom sentimento e se confunde em previso˜es envolvendo palavras sobre a COVID-19, como Omicron, que indica falta de representatividade na base de dados. Além disso, a partir dos resultados do LIME, foi possível melhorar a acura´cia do modelo para 81% ao incluir as stopwords ”not” e ”no”.
- Open Access
- 1 January 2024
- Published by Sociedade Brasileira de Computação in Journal on Interactive Systems
- Vol. 15 (1) , 323-332
Application of a multicriteria decision model for the classification of Paraíba’s municipalities as to the occurrence of domestic and family violence against women
The objective of the present work is to classify the municipalities of the state of Paraíba according to the propensity for the occurrence of Domestic and Family Violence Against Women. Data used come from the Municipal Basic Information Survey (MUNIC, in Portuguese), performed in 2019, by the Brazilian Institute of Geography and Statistics (IBGE, in Portuguese). Additionally, the records of cases of violence from the Women’s Assistance Center (Ligue 180) were used to evaluate the classification. The ELECTRE Tri-B method was applied for the classification task, considering a set of socioeconomic criteria, to group municipalities into four classes: Low, Medium, High and Very High. The results suggest that more than 80% of the municipalities in Paraíba were classified as having a high propensity, which means that they have a lack of services and strategies to protect women, demanding, therefore, greater attention of the state for the implementation of assistance services.
- 1 January 2024
- Published by Sociedade Brasileira de Computação in Journal on Interactive Systems
- Vol. 15 (1) , 323-332
Open AccessApplication of a multicriteria decision model for the classification of Paraíba’s municipalities as to the occurrence of domestic and family violence against women
The objective of the present work is to classify the municipalities of the state of Paraíba according to the propensity for the occurrence of Domestic and Family Violence Against Women. Data used come from the Municipal Basic Information Survey (MUNIC, in Portuguese), performed in 2019, by the Brazilian Institute of Geography and Statistics (IBGE, in Portuguese). Additionally, the records of cases of violence from the Women’s Assistance Center (Ligue 180) were used to evaluate the classification. The ELECTRE Tri-B method was applied for the classification task, considering a set of socioeconomic criteria, to group municipalities into four classes: Low, Medium, High and Very High. The results suggest that more than 80% of the municipalities in Paraíba were classified as having a high propensity, which means that they have a lack of services and strategies to protect women, demanding, therefore, greater attention of the state for the implementation of assistance services.
- 1 January 2023
- Published by Editora Science
- p. 169
NAVEGAR COM SEGURANÇA: SEGURANÇA DA INFORMAÇÃO E PREVENÇÃO DE GOLPES PARA A TERCEIRA IDADE
Este capítulo apresenta o projeto de extensão “Navegar com Segurança”, voltado à educação em segurança da informação e à prevenção de golpes digitais entre pessoas com mais de 60 anos da região metropolitana de Belém (PA). Entre abril e maio de 2026, foram realizadas seis oficinas presenciais, com metodologia ativa, em cinco módulos temáticos: riscos digitais, senhas seguras e autenticação, verificação de informações, golpes e fraudes contra idosos e crimes digitais com canais de denúncia. A competência digital percebida foi medida por um questionário de 20 itens, em escala de 1 a 5, aplicado antes e depois das oficinas a oito participantes: a nota média passou de 2,67 para 3,78, com melhora individual em sete dos oito respondentes. Das 31 pessoas inscritas, 20 (65%) atingiram o critério mínimo de duas presenças e receberam certificado, ao passo que a taxa média de comparecimento foi de 39%, afetada pela troca de salas durante a execução. Os resultados indicam que oficinas presenciais, com linguagem acessível e foco em situações reais de golpe, contribuem para a autoproteção digital de pessoas idosas e que a estabilidade do espaço físico é condição relevante para a permanência do público.
- 1 January 2023
- Published by Editora Science
- p. 169
NAVEGAR COM SEGURANÇA: SEGURANÇA DA INFORMAÇÃO E PREVENÇÃO DE GOLPES PARA A TERCEIRA IDADE
Este capítulo apresenta o projeto de extensão “Navegar com Segurança”, voltado à educação em segurança da informação e à prevenção de golpes digitais entre pessoas com mais de 60 anos da região metropolitana de Belém (PA). Entre abril e maio de 2026, foram realizadas seis oficinas presenciais, com metodologia ativa, em cinco módulos temáticos: riscos digitais, senhas seguras e autenticação, verificação de informações, golpes e fraudes contra idosos e crimes digitais com canais de denúncia. A competência digital percebida foi medida por um questionário de 20 itens, em escala de 1 a 5, aplicado antes e depois das oficinas a oito participantes: a nota média passou de 2,67 para 3,78, com melhora individual em sete dos oito respondentes. Das 31 pessoas inscritas, 20 (65%) atingiram o critério mínimo de duas presenças e receberam certificado, ao passo que a taxa média de comparecimento foi de 39%, afetada pela troca de salas durante a execução. Os resultados indicam que oficinas presenciais, com linguagem acessível e foco em situações reais de golpe, contribuem para a autoproteção digital de pessoas idosas e que a estabilidade do espaço físico é condição relevante para a permanência do público.
- 16 June 2022
- Published by Springer Nature
- p. 261-272
A Review of Framework for Machine Learning Interpretability
- 16 June 2022
- Published by Springer Nature
- p. 261-272
A Review of Framework for Machine Learning Interpretability
- 16 March 2022
- Published by Springer Nature
- p. 323-332
Forced Phonetic Alignment in Brazilian Portuguese Using Time-Delay Neural Networks
- 16 March 2022
- Published by Springer Nature
- p. 323-332
Forced Phonetic Alignment in Brazilian Portuguese Using Time-Delay Neural Networks
- Open Access
- 19 February 2022
- Published by Springer Nature in EURASIP Journal on Advances in Signal Processing
- Vol. 2022 (1) , 1-32
Free resources for forced phonetic alignment in Brazilian Portuguese based on Kaldi toolkit
Phonetic analysis of speech, in general, requires the alignment of audio samples to its phonetic transcription. This could be done manually for a couple of files, but as the corpus grows large, it becomes infeasibly time-consuming. This paper describes the evolution process toward creating free resources for phonetic alignment in Brazilian Portuguese (BP) using Kaldi, a toolkit that achieves state of the art for open-source speech recognition, within a toolkit we call UFPAlign. The contributions of this work are then twofold: developing resources to perform forced alignment in BP, including the release of scripts to train acoustic models via Kaldi, as well as the resources themselves under open licenses; and bringing forth a comparison to other two phonetic aligners that provide resources for BP, namely EasyAlign and Montreal Forced Aligner (MFA), the latter being also Kaldi-based. Evaluation took place in terms of phone boundary and intersection over union metrics over a dataset of 385 hand-aligned utterances, and results show that Kaldi-based aligners perform better overall, and that UFPAlign models are more accurate than MFA’s. Furthermore, complex deep-learning-based approaches still do not improve performance compared to simpler models.
- 19 February 2022
- Published by Springer Nature in EURASIP Journal on Advances in Signal Processing
- Vol. 2022 (1) , 1-32
Open AccessFree resources for forced phonetic alignment in Brazilian Portuguese based on Kaldi toolkit
Phonetic analysis of speech, in general, requires the alignment of audio samples to its phonetic transcription. This could be done manually for a couple of files, but as the corpus grows large, it becomes infeasibly time-consuming. This paper describes the evolution process toward creating free resources for phonetic alignment in Brazilian Portuguese (BP) using Kaldi, a toolkit that achieves state of the art for open-source speech recognition, within a toolkit we call UFPAlign. The contributions of this work are then twofold: developing resources to perform forced alignment in BP, including the release of scripts to train acoustic models via Kaldi, as well as the resources themselves under open licenses; and bringing forth a comparison to other two phonetic aligners that provide resources for BP, namely EasyAlign and Montreal Forced Aligner (MFA), the latter being also Kaldi-based. Evaluation took place in terms of phone boundary and intersection over union metrics over a dataset of 385 hand-aligned utterances, and results show that Kaldi-based aligners perform better overall, and that UFPAlign models are more accurate than MFA’s. Furthermore, complex deep-learning-based approaches still do not improve performance compared to simpler models.
- 28 November 2021
- Published by Springer Nature
- p. 465-479
Experiments on Kaldi-Based Forced Phonetic Alignment for Brazilian Portuguese
- 28 November 2021
- Published by Springer Nature
- p. 465-479
Experiments on Kaldi-Based Forced Phonetic Alignment for Brazilian Portuguese