Armindo Lobo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Armindo Lobo has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Paulo Novais
University of Minho
2 shared publications - Paulo Sampaio
Department of Production and Systems, University of Minho, Braga, Portugal
2 shared publications - Ali Abbasi
DTx—Digital Transformation CoLab, University of Minho, 4800-058 Guimarães, Portugal
1 shared publication - Andrew Humphrey
Instituto de Astrofísica e Ciências do Espaço, Universidade do Porto, CAUP, Rua das Estrelas, 4150-762 Porto, Portugal
1 shared publication - Duarte Fernandes
DTx-Digital Transformation CoLab, University of Minho, Azurm Campus, Guimares, Portugal
1 shared publication - Emanuel Demetrio Mendes Gouveia
Laboratório de Instrumentação e Física Experimental de Partículas — LIP
1 shared publication
Latest Publications
- Open Access
- 9 February 2026
- Published by Elsevier in SSRN Electronic Journal
Anomaly detection in aggregates of grouped time series, composed of high-dimensional and high-frequency event sequences
Motivation: As enterprise information systems collect increasingly diverse event streams, the automatic detection of anomalous events is essential for applications like network security, system monitoring, and fraud detection.Methods: This study aims to develop robust techniques for automatically and computationally efficiently identifying anomalous behavior within high-dimensional event sequences, where events occur at specific timestamps (e.g., number of events per hour). The proposed frameworkleverages machine learning to detect anomalies within high-dimensional, high-frequency event sequence time series. By dynamically grouping time series based on shared categorical dimensions, the framework enables scalable anomaly detection across varying levels of aggregation, while maintaining detection sensitivity and specificity.Results: The framework has been validated using real-world telecommunications event data sets and evaluated against the case where no aggregation is performed (‘fully disaggregated’). In the case of our ‘minimum aggregation’ method, the training time is reduced by a factor of∼ 300, and inference time is reduced by a factor of 8. For our other method, ‘ideal aggregation’, the training time is reduced by a factor of 6.5, and the inference time is reduced by a factor of 7.6. The quality of anomaly detection is generally preserved across different aggregation levels of grouped high-dimensional data.Conclusions: This research advances anomaly detection techniques in grouped high-dimensional event sequence data, a complex yet increasingly common data format in fields like network security and system monitoring. The framework’s dimensional aggregation techniques enable efficient pattern recognition while maintaining detection sensitivity and specificity, critical for applications requiring faster anomaly detection response.
- 9 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAnomaly detection in aggregates of grouped time series, composed of high-dimensional and high-frequency event sequences
Motivation: As enterprise information systems collect increasingly diverse event streams, the automatic detection of anomalous events is essential for applications like network security, system monitoring, and fraud detection.Methods: This study aims to develop robust techniques for automatically and computationally efficiently identifying anomalous behavior within high-dimensional event sequences, where events occur at specific timestamps (e.g., number of events per hour). The proposed frameworkleverages machine learning to detect anomalies within high-dimensional, high-frequency event sequence time series. By dynamically grouping time series based on shared categorical dimensions, the framework enables scalable anomaly detection across varying levels of aggregation, while maintaining detection sensitivity and specificity.Results: The framework has been validated using real-world telecommunications event data sets and evaluated against the case where no aggregation is performed (‘fully disaggregated’). In the case of our ‘minimum aggregation’ method, the training time is reduced by a factor of∼ 300, and inference time is reduced by a factor of 8. For our other method, ‘ideal aggregation’, the training time is reduced by a factor of 6.5, and the inference time is reduced by a factor of 7.6. The quality of anomaly detection is generally preserved across different aggregation levels of grouped high-dimensional data.Conclusions: This research advances anomaly detection techniques in grouped high-dimensional event sequence data, a complex yet increasingly common data format in fields like network security and system monitoring. The framework’s dimensional aggregation techniques enable efficient pattern recognition while maintaining detection sensitivity and specificity, critical for applications requiring faster anomaly detection response.
- Open Access
- 19 June 2024
- Published by Emerald Publishing in The TQM Journal
- Vol. 36 (9) , 175-192
Enhancing quality 4.0 and reducing costs in lot-release process with machine learning-based complaint prediction
Purpose: This study proposes a machine learning framework to predict customer complaints from production line tests in an automotive company's lot-release process, enhancing Quality 4.0. It aims to design and implement the framework, compare different machine learning (ML) models and evaluate a non-sampling threshold-moving approach for adjusting prediction capabilities based on product requirements.Design/methodology/approach: This study applies the Cross-Industry Standard Process for Data Mining (CRISP-DM) and four ML models to predict customer complaints from automotive production tests. It employs cost-sensitive and threshold-moving techniques to address data imbalance, with the F1-Score and Matthews correlation coefficient assessing model performance.Findings: The framework effectively predicts customer complaint-related tests. XGBoost outperformed the other models with an F1-Score of 72.4% and a Matthews correlation coefficient of 75%. It improves the lot-release process and cost efficiency over heuristic methods.Practical implications: The framework has been tested on real-world data and shows promising results in improving lot-release decisions and reducing complaints and costs. It enables companies to adjust predictive models by changing only the threshold, eliminating the need for retraining.Originality/value: To the best of our knowledge, there is limited literature on using ML to predict customer complaints for the lot-release process in an automotive company. Our proposed framework integrates ML with a non-sampling approach, demonstrating its effectiveness in predicting complaints and reducing costs, fostering Quality 4.0.
- 19 June 2024
- Published by Emerald Publishing in The TQM Journal
- Vol. 36 (9) , 175-192
Open AccessEnhancing quality 4.0 and reducing costs in lot-release process with machine learning-based complaint prediction
Purpose: This study proposes a machine learning framework to predict customer complaints from production line tests in an automotive company's lot-release process, enhancing Quality 4.0. It aims to design and implement the framework, compare different machine learning (ML) models and evaluate a non-sampling threshold-moving approach for adjusting prediction capabilities based on product requirements.Design/methodology/approach: This study applies the Cross-Industry Standard Process for Data Mining (CRISP-DM) and four ML models to predict customer complaints from automotive production tests. It employs cost-sensitive and threshold-moving techniques to address data imbalance, with the F1-Score and Matthews correlation coefficient assessing model performance.Findings: The framework effectively predicts customer complaint-related tests. XGBoost outperformed the other models with an F1-Score of 72.4% and a Matthews correlation coefficient of 75%. It improves the lot-release process and cost efficiency over heuristic methods.Practical implications: The framework has been tested on real-world data and shows promising results in improving lot-release decisions and reducing complaints and costs. It enables companies to adjust predictive models by changing only the threshold, eliminating the need for retraining.Originality/value: To the best of our knowledge, there is limited literature on using ML to predict customer complaints for the lot-release process in an automotive company. Our proposed framework integrates ML with a non-sampling approach, demonstrating its effectiveness in predicting complaints and reducing costs, fostering Quality 4.0.
- 13 December 2022
- Published by Springer Nature
- p. 280-290
Cost-Sensitive Learning and Threshold-Moving Approach to Improve Industrial Lots Release Process on Imbalanced Datasets
- 13 December 2022
- Published by Springer Nature
- p. 280-290
Cost-Sensitive Learning and Threshold-Moving Approach to Improve Industrial Lots Release Process on Imbalanced Datasets