Julián Luengo
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
Research Interests
Julián Luengo has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Francisco Herrera
University of Granada
51 shared publications - Salvador García
Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain
36 shared publications Francisco Herrera
21 shared publications- José Antonio Sáez
Department of Statistics and Operations Research, University of Granada, Granada, Spain
17 shared publications - Alberto Fernández
University of Granada
7 shared publications - Diego García-Gil
Andalusian Institute of Data Science and Computational Intelligence (DaSCI), University of Granada, 18012 Granada, Spain
6 shared publications
Latest Publications
- Open Access
- 15 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (12) , 1-36
A Survey on Deep Learning-Based Semi-Supervised Semantic Segmentation
Semantic segmentation is one of the most challenging tasks in computer vision. However, in many applications, a frequent obstacle is the lack of labeled images, due to the high cost of pixel-level labeling. In this scenario, it makes sense to approach the problem from a semi-supervised point of view, where both labeled and unlabeled images are exploited. In recent years this line of research has gained much interest and many approaches have been published in this direction. Therefore, the main objective of this study is to provide an overview of the current state of the art in semi-supervised semantic segmentation, offering an updated taxonomy of all existing methods to date. This is complemented by an experimentation with a variety of models representing all the categories of the taxonomy on the most widely used benchmark datasets in the literature, and a final discussion on the results obtained, the challenges and the most promising lines of future research.
- 15 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (12) , 1-36
Open AccessA Survey on Deep Learning-Based Semi-Supervised Semantic Segmentation
Semantic segmentation is one of the most challenging tasks in computer vision. However, in many applications, a frequent obstacle is the lack of labeled images, due to the high cost of pixel-level labeling. In this scenario, it makes sense to approach the problem from a semi-supervised point of view, where both labeled and unlabeled images are exploited. In recent years this line of research has gained much interest and many approaches have been published in this direction. Therefore, the main objective of this study is to provide an overview of the current state of the art in semi-supervised semantic segmentation, offering an updated taxonomy of all existing methods to date. This is complemented by an experimentation with a variety of models representing all the categories of the taxonomy on the most widely used benchmark datasets in the literature, and a final discussion on the results obtained, the challenges and the most promising lines of future research.
- Open Access
- 27 April 2026
- Published by Elsevier in Neurocomputing
- Vol. 687
RADAR: Robust anomaly detection and recognition. A unified and reproducible framework across tabular, time-series, and federated data
- 27 April 2026
- Published by Elsevier in Neurocomputing
- Vol. 687
Open AccessRADAR: Robust anomaly detection and recognition. A unified and reproducible framework across tabular, time-series, and federated data
- Open Access
- 7 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 177
STOOD-X: Explainable out-of-distribution detection via nonparametric statistical testing on large-scale datasets
- 7 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 177
Open AccessSTOOD-X: Explainable out-of-distribution detection via nonparametric statistical testing on large-scale datasets
- Open Access
- 7 February 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (3) , 528-544
X-SHIELD: Regularization for explainable Artificial Intelligence
As artificial intelligence systems become integral across domains, the demand for explainability, called eXplainable artificial intelligence (XAI), grows. Existing efforts have focused primarily on generating and evaluating explanations for black-box models, while a critical gap in directly enhancing models remains through these evaluations. It is important to consider the potential of this explanation process to improve model quality with feedback on training as well. XAI may be used to improve model performance while increasing model explainability. Under this view, this paper introduces Transformation-Selective hidden input evaluation for learning dynamics (T-SHIELD), a regularization family designed to improve model quality by hiding features of input, forcing the model to generalize without those features. Within this family, we propose XAI-SHIELD (X-SHIELD), a regularization for explainable artificial intelligence that uses explanations to select specific features to hide. In contrast to conventional approaches, X-SHIELD regularization seamlessly integrates into the objective function, enhancing model explainability while also improving performance. Experimental validation on benchmark datasets underscores X-SHIELD’s effectiveness in improving performance and overall explainability. The improvement is validated through experiments comparing models with and without X-SHIELD regularization, with further analysis exploring the rationale behind its design choices. This establishes X-SHIELD regularization as a promising pathway for developing reliable artificial intelligence regularization.
- 7 February 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (3) , 528-544
Open AccessX-SHIELD: Regularization for explainable Artificial Intelligence
As artificial intelligence systems become integral across domains, the demand for explainability, called eXplainable artificial intelligence (XAI), grows. Existing efforts have focused primarily on generating and evaluating explanations for black-box models, while a critical gap in directly enhancing models remains through these evaluations. It is important to consider the potential of this explanation process to improve model quality with feedback on training as well. XAI may be used to improve model performance while increasing model explainability. Under this view, this paper introduces Transformation-Selective hidden input evaluation for learning dynamics (T-SHIELD), a regularization family designed to improve model quality by hiding features of input, forcing the model to generalize without those features. Within this family, we propose XAI-SHIELD (X-SHIELD), a regularization for explainable artificial intelligence that uses explanations to select specific features to hide. In contrast to conventional approaches, X-SHIELD regularization seamlessly integrates into the objective function, enhancing model explainability while also improving performance. Experimental validation on benchmark datasets underscores X-SHIELD’s effectiveness in improving performance and overall explainability. The improvement is validated through experiments comparing models with and without X-SHIELD regularization, with further analysis exploring the rationale behind its design choices. This establishes X-SHIELD regularization as a promising pathway for developing reliable artificial intelligence regularization.
- Open Access
- 29 December 2025
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (1) , 7
WinStat: A Family of Trainable Positional Encodings for Transformers in Time Series Forecasting
Transformers for time series forecasting rely on positional encoding to inject temporal order into the permutation-invariant self-attention mechanism. Classical sinusoidal absolute encodings are fixed and purely geometric; learnable absolute encodings often overfit and fail to extrapolate, while relative or advanced schemes can impose substantial computational overhead without being sufficiently tailored to temporal data. This work introduces a family of window-statistics positional encodings that explicitly incorporate local temporal semantics into the representation of each timestamp. The base variant (WinStat) augments inputs with statistics computed over a sliding window; WinStatLag adds explicit lag-difference features; and hybrid variants (WinStatFlex, WinStatTPE, WinStatSPE) learn soft mixtures of window statistics with absolute, learnable, and semantic positional signals, preserving the simplicity of additive encodings while adapting to local structure and informative lags. We evaluate proposed encodings on four heterogeneous benchmarks against state-of-the-art proposals: Electricity Transformer Temperature (hourly variants), Individual Household Electric Power Consumption, New York City Yellow Taxi Trip Records, and a large-scale industrial time series from heavy machinery. All experiments use a controlled Transformer backbone with full self-attention to isolate the effect of positional information. Across datasets, the proposed methods consistently reduce mean squared error and mean absolute error relative to a strong Transformer baseline with sinusoidal positional encoding and state-of-the-art encodings for time series, with WinStatFlex and WinStatTPE emerging as the most effective variants. Ablation studies that randomly shuffle decoder inputs markedly degrade the proposed methods, supporting the conclusion that their gains arise from learned order-aware locality and semantic structure rather than incidental artifacts. A simple and reproducible heuristic for setting the sliding-window length—roughly one quarter to one third of the input sequence length—provides robust performance without the need for exhaustive tuning.
- 29 December 2025
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (1) , 7
Open AccessWinStat: A Family of Trainable Positional Encodings for Transformers in Time Series Forecasting
Transformers for time series forecasting rely on positional encoding to inject temporal order into the permutation-invariant self-attention mechanism. Classical sinusoidal absolute encodings are fixed and purely geometric; learnable absolute encodings often overfit and fail to extrapolate, while relative or advanced schemes can impose substantial computational overhead without being sufficiently tailored to temporal data. This work introduces a family of window-statistics positional encodings that explicitly incorporate local temporal semantics into the representation of each timestamp. The base variant (WinStat) augments inputs with statistics computed over a sliding window; WinStatLag adds explicit lag-difference features; and hybrid variants (WinStatFlex, WinStatTPE, WinStatSPE) learn soft mixtures of window statistics with absolute, learnable, and semantic positional signals, preserving the simplicity of additive encodings while adapting to local structure and informative lags. We evaluate proposed encodings on four heterogeneous benchmarks against state-of-the-art proposals: Electricity Transformer Temperature (hourly variants), Individual Household Electric Power Consumption, New York City Yellow Taxi Trip Records, and a large-scale industrial time series from heavy machinery. All experiments use a controlled Transformer backbone with full self-attention to isolate the effect of positional information. Across datasets, the proposed methods consistently reduce mean squared error and mean absolute error relative to a strong Transformer baseline with sinusoidal positional encoding and state-of-the-art encodings for time series, with WinStatFlex and WinStatTPE emerging as the most effective variants. Ablation studies that randomly shuffle decoder inputs markedly degrade the proposed methods, supporting the conclusion that their gains arise from learned order-aware locality and semantic structure rather than incidental artifacts. A simple and reproducible heuristic for setting the sliding-window length—roughly one quarter to one third of the input sequence length—provides robust performance without the need for exhaustive tuning.
- Open Access
- 4 November 2025
- Published by MDPI AG in Preprints.org
WinStat: A Family of Trainable Positional Encodings for Transformers in Time Series Forecasting
Transformers for time series forecasting rely on positional encoding to inject temporal order into the permutation-invariant self-attention mechanism. Classical sinusoidal absolute encodings are fixed and purely geometric; learnable absolute encodings often overfit and fail to extrapolate, while relative or advanced schemes can impose substantial computational overhead without being sufficiently tailored to temporal data. This work introduces a family of window-statistics positional encodings that explicitly incorporate local temporal semantics into the representation of each timestamp. The base variant (WinStat) augments inputs with statistics computed over a sliding window; WinStatLag adds explicit lag-difference features; and hybrid variants (WinStatFlex, WinStatTPE, WinStatSPE) learn soft mixtures of window statistics with absolute, learnable, and semantic positional signals, preserving the simplicity of additive encodings while adapting to local structure and informative lags. We evaluate proposed encodings on four heterogeneous benchmarks against state-of-the-art proposals: Electricity Transformer Temperature (hourly variants), Individual Household Electric Power Consumption, New York City Yellow Taxi Trip Records, and a large-scale industrial time series from heavy machinery. All experiments use a controlled Transformer backbone with full self-attention to isolate the effect of positional information. Across datasets, the proposed methods consistently reduce mean squared error and mean absolute error relative to a strong Transformer baseline with sinusoidal positional encoding and state-of-the-art encodings for time series, with WinStatFlex and WinStatTPE emerging as the most effective variants. Ablation studies that randomly shuffle decoder inputs markedly degrade the proposed methods, supporting the conclusion that their gains arise from learned order-aware locality and semantic structure rather than incidental artifacts. A simple and reproducible heuristic for setting the sliding-window length—roughly one quarter to one third of the input sequence length—provides robust performance without the need for exhaustive tuning.
- 4 November 2025
- Published by MDPI AG in Preprints.org
Open AccessWinStat: A Family of Trainable Positional Encodings for Transformers in Time Series Forecasting
Transformers for time series forecasting rely on positional encoding to inject temporal order into the permutation-invariant self-attention mechanism. Classical sinusoidal absolute encodings are fixed and purely geometric; learnable absolute encodings often overfit and fail to extrapolate, while relative or advanced schemes can impose substantial computational overhead without being sufficiently tailored to temporal data. This work introduces a family of window-statistics positional encodings that explicitly incorporate local temporal semantics into the representation of each timestamp. The base variant (WinStat) augments inputs with statistics computed over a sliding window; WinStatLag adds explicit lag-difference features; and hybrid variants (WinStatFlex, WinStatTPE, WinStatSPE) learn soft mixtures of window statistics with absolute, learnable, and semantic positional signals, preserving the simplicity of additive encodings while adapting to local structure and informative lags. We evaluate proposed encodings on four heterogeneous benchmarks against state-of-the-art proposals: Electricity Transformer Temperature (hourly variants), Individual Household Electric Power Consumption, New York City Yellow Taxi Trip Records, and a large-scale industrial time series from heavy machinery. All experiments use a controlled Transformer backbone with full self-attention to isolate the effect of positional information. Across datasets, the proposed methods consistently reduce mean squared error and mean absolute error relative to a strong Transformer baseline with sinusoidal positional encoding and state-of-the-art encodings for time series, with WinStatFlex and WinStatTPE emerging as the most effective variants. Ablation studies that randomly shuffle decoder inputs markedly degrade the proposed methods, supporting the conclusion that their gains arise from learned order-aware locality and semantic structure rather than incidental artifacts. A simple and reproducible heuristic for setting the sliding-window length—roughly one quarter to one third of the input sequence length—provides robust performance without the need for exhaustive tuning.
- Open Access
- 28 October 2024
- Published by Elsevier in Information Sciences
- Vol. 690
Developing Big Data anomaly dynamic and static detection algorithms: AnomalyDSD spark package
- 28 October 2024
- Published by Elsevier in Information Sciences
- Vol. 690
Open AccessDeveloping Big Data anomaly dynamic and static detection algorithms: AnomalyDSD spark package
- 29 August 2023
- Published by Springer Nature
- p. 39-48
Revisiting Histogram Based Outlier Scores: Strengths and Weaknesses
- 29 August 2023
- Published by Springer Nature
- p. 39-48
Revisiting Histogram Based Outlier Scores: Strengths and Weaknesses
- Open Access
- 2 August 2023
- Published by Elsevier in Information Fusion
- Vol. 100
Fusing anomaly detection with false positive mitigation methodology for predictive maintenance under multivariate time series
- 2 August 2023
- Published by Elsevier in Information Fusion
- Vol. 100
Open AccessFusing anomaly detection with false positive mitigation methodology for predictive maintenance under multivariate time series
- Open Access
- 1 January 2023
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2023 (1)
REVEL Framework to Measure Local Linear Explanations for Black‐Box Models: Deep Learning Image Classification Case Study
Explainable artificial intelligence is proposed to provide explanations for reasoning performed by artificial intelligence. There is no consensus on how to evaluate the quality of these explanations, since even the definition of explanation itself is not clear in the literature. In particular, for the widely known local linear explanations, there are qualitative proposals for the evaluation of explanations, although they suffer from theoretical inconsistencies. The case of image is even more problematic, where a visual explanation seems to explain a decision while detecting edges is what it really does. There are a large number of metrics in the literature specialized in quantitatively measuring different qualitative aspects, so we should be able to develop metrics capable of measuring in a robust and correct way the desirable aspects of the explanations. Some previous papers have attempted to develop new measures for this purpose. However, these measures suffer from lack of objectivity or lack of mathematical consistency, such as saturation or lack of smoothness. In this paper, we propose a procedure called REVEL to evaluate different aspects concerning the quality of explanations with a theoretically coherent development which do not have the problems of the previous measures. This procedure has several advances in the state of the art: it standardizes the concepts of explanation and develops a series of metrics not only to be able to compare between them but also to obtain absolute information regarding the explanation itself. The experiments have been carried out on four image datasets as benchmark where we show REVEL’s descriptive and analytical power.
- 1 January 2023
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2023 (1)
Open AccessREVEL Framework to Measure Local Linear Explanations for Black‐Box Models: Deep Learning Image Classification Case Study
Explainable artificial intelligence is proposed to provide explanations for reasoning performed by artificial intelligence. There is no consensus on how to evaluate the quality of these explanations, since even the definition of explanation itself is not clear in the literature. In particular, for the widely known local linear explanations, there are qualitative proposals for the evaluation of explanations, although they suffer from theoretical inconsistencies. The case of image is even more problematic, where a visual explanation seems to explain a decision while detecting edges is what it really does. There are a large number of metrics in the literature specialized in quantitatively measuring different qualitative aspects, so we should be able to develop metrics capable of measuring in a robust and correct way the desirable aspects of the explanations. Some previous papers have attempted to develop new measures for this purpose. However, these measures suffer from lack of objectivity or lack of mathematical consistency, such as saturation or lack of smoothness. In this paper, we propose a procedure called REVEL to evaluate different aspects concerning the quality of explanations with a theoretically coherent development which do not have the problems of the previous measures. This procedure has several advances in the state of the art: it standardizes the concepts of explanation and develops a series of metrics not only to be able to compare between them but also to obtain absolute information regarding the explanation itself. The experiments have been carried out on four image datasets as benchmark where we show REVEL’s descriptive and analytical power.