publications

2025

1. ECML-PKDD

   Risk-Based Thresholding for Reliable Anomaly Detection in Concentrated Solar Power Plants

   Yorick Estievenart, Sukanya Patra, and Souhaib Ben Taieb

   In Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track and Demo Track, 2025

   Abs DOI arXiv Bib

   Efficient and reliable operation of Concentrated Solar Power (CSP) plants is essential for meeting the growing demand for sustainable energy. However, high-temperature solar receivers face severe operational risks, such as freezing, deformation, and corrosion, resulting in costly downtime and maintenance. To monitor CSP plants, cameras mounted on solar receivers record infrared images at irregular intervals ranging from one to five minutes throughout the day. Anomalous images can be detected by thresholding an anomaly score, where the threshold is chosen to optimize metrics such as the F1-score on a validation set. This work proposes a framework, using risk control, for generating more reliable decision thresholds with finite-sample coverage guarantees on any chosen risk function. Our framework also incorporates an abstention mechanism, allowing high-risk predictions to be deferred to domain experts. Second, we propose a density forecasting method to estimate the likelihood of an observed image given a sequence of previously observed images, using this likelihood as its anomaly score. Third, we analyze the deployment results of our framework across multiple training scenarios over several months for two CSP plants. This analysis provides valuable insights to our industry partner for optimizing maintenance operations. Finally, given the confidential nature of our dataset, we provide an extended simulated dataset, leveraging recent advancements in generative modeling to create diverse thermal images that simulate multiple CSP plants. Our code is publicly available.

   @inproceedings{Estievenart2025Risk-Based,
     author = {Estievenart, Yorick and Patra, Sukanya and Ben Taieb, Souhaib},
     editor = {Dutra, In{\^e}s and Pechenizkiy, Mykola and Cortez, Paulo and Pashami, Sepideh and Pasquali, Arian and Moniz, Nuno and Jorge, Al{\'i}pio M. and Soares, Carlos and Abreu, Pedro H. and Gama, Jo{\~a}o},
     title = {Risk-Based Thresholding for Reliable Anomaly Detection in Concentrated Solar Power Plants},
     booktitle = {Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track and Demo Track},
     year = {2025},
     publisher = {Springer Nature Switzerland},
     address = {Cham},
     pages = {111--128},
     isbn = {978-3-032-06129-4},
     doi = {10.1007/978-3-032-06129-4_7}
   }

2. NeurIPS

   An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contamination

   Sukanya Patra and Souhaib Ben Taieb

   In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025

   Abs arXiv Bib HTML

   Unsupervised anomaly detection (AD) methods typically assume clean training data, yet real-world datasets often contain undetected or mislabeled anomalies, leading to significant performance degradation. Existing solutions require access to the training pipelines, data or prior knowledge of the proportions of anomalies in the data, limiting their real-world applicability. To address this challenge, we propose EPHAD, a simple yet effective test-time adaptation framework that updates the outputs of AD models trained on contaminated datasets using evidence gathered at test time. Our approach integrates the prior knowledge captured by the AD model trained on contaminated datasets with evidence derived from multimodal foundation models like Contrastive Language-Image Pre-training (CLIP), classical AD methods like the Latent Outlier Factor or domain-specific knowledge. We illustrate the intuition behind EPHAD using a synthetic toy example and validate its effectiveness through comprehensive experiments across eight visual AD datasets, twenty-six tabular AD datasets, and a real-world industrial AD dataset. Additionally, we conduct an ablation study to analyse hyperparameter influence and robustness to varying contamination levels, demonstrating the versatility and robustness of EPHAD across diverse AD models and evidence pairs.

   @inproceedings{patra2025an,
     title = {An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contamination},
     author = {Patra, Sukanya and Taieb, Souhaib Ben},
     booktitle = {The Thirty-ninth Annual Conference on Neural Information Processing Systems},
     year = {2025},
   }

3. arXiv

   Segmentation-Guided CT Synthesis with Pixel-Wise Conformal Uncertainty Bounds

   David Vallmanya Poch, Yorick Estievenart, Elnura Zhalieva, and 3 more authors

   arXiv preprint, 2025

   Abs arXiv Bib

   Accurate dose calculations in proton therapy rely on high-quality CT images. While planning CTs (pCTs) serve as a reference for dosimetric planning, Cone Beam CT (CBCT) is used throughout Adaptive Radiotherapy (ART) to generate sCTs for improved dose calculations. Despite its lower cost and reduced radiation exposure advantages, CBCT suffers from severe artefacts and poor image quality, making it unsuitable for precise dosimetry. Deep learning-based CBCT-to-CT translation has emerged as a promising approach. Still, existing methods often introduce anatomical inconsistencies and lack reliable uncertainty estimates, limiting their clinical adoption. To bridge this gap, we propose STF-RUE, a novel framework integrating two key components. First, STF, a segmentation-guided CBCT-to-CT translation method that enhances anatomical consistency by leveraging segmentation priors extracted from pCTs. Second, RUE, a conformal prediction method that augments predicted CTs with pixel-wise conformal prediction intervals, providing clinicians with robust reliability indicator. Comprehensive experiments using UNet++ and Fast-DDPM on two benchmark datasets demonstrate that STF-RUE significantly improves translation accuracy, as measured by a novel soft-tissue-focused metric designed for precise dose computation. Additionally, STF-RUE provides better-calibrated uncertainty sets for synthetic CT, reinforcing trust in synthetic CTs. By addressing both anatomical fidelity and uncertainty quantification, STF-RUE marks a crucial step toward safer and more effective adaptive proton therapy.

   @article{poch2025segmentation,
     title = {Segmentation-Guided CT Synthesis with Pixel-Wise Conformal Uncertainty Bounds},
     author = {Poch, David Vallmanya and Estievenart, Yorick and Zhalieva, Elnura and Patra, Sukanya and Yaqub, Mohammad and Taieb, Souhaib Ben},
     journal = {arXiv preprint},
     year = {2025},
   }

4. PhD Thesis

   Deep Visual Anomaly Detection under Data Contamination and Anomaly Heterogeneity

   Sukanya Patra

   UMONS - University of Mons [Faculty of Sciences], Mons, Belgium, 2025

   Abs Bib HTML

   Anomaly detection (AD) is the task of identifying rare and unusual events that deviate from expected behaviour. It plays a crucial role in various high-stakes domains, including industrial quality inspection, healthcare, fraud detection, and predictive maintenance. A standard approach involves learning a "compact" representation of the normal samples. Once this notion of normality is established, instances that significantly deviate from it are identified as anomalies. Traditional shallow AD methods often struggle in high-dimensional data settings due to the curse of dimensionality, where the performance deteriorates as the number of input features grows. Consequently, deep learning-based methods have gained attention due to their ability to learn effective representations directly from the data. Despite remarkable progress in deep learning, the practical deployment of deep AD models remains hindered by several fundamental challenges. This thesis advances the field through four key contributions, each addressing specific practical limitations of existing approaches. The work is conducted as a part of the Federated Learning and Augmented Reality for Advanced Control Centres (FLARACC) project, which aims to develop solutions for real-world industrial problems. FLARACC is a collaboration among the University of Mons, the University of Namur, John Cockerill, IBA and CETIC. First, in real-world applications, different types of anomalies often occur simultaneously, rendering existing methods ineffective s they typically focus on a single anomaly type. As our first contribution, we develop a unified method for the detection of both structural and logical anomalies. The proposed method achieves competitive performance across multiple benchmark datasets, demonstrating the ability to detect co-occurring anomaly types. Second, contamination in the training dataset undermines the common assumption that training datasets are "clean", i.e. free of anomalous samples. To address this, our second contribution introduces two complementary strategies. In semi-supervised AD, we propose two risk-based estimators: a shallow method with a regularised unbiased risk estimator and a deep method employing a non-negative risk estimator, both supported by theoretical guarantees. In the fully unsupervised setting, we develop a test-time adaptation framework that dynamically adjusts model predictions using exponential tilting, improving robustness against contamination without requiring labelled data. Third, motivated by a real-world use case of AD in solar power plants from John Cockerill, we address the challenge of learning effective representations for AD given a thermal image dataset with complex temporal features such as non-stationarity, strong daily seasonal patterns, irregular sampling intervals, and temporal dependencies. Our third contribution proposes a forecasting-based AD framework, where a deep sequence model predicts the next thermal image under normal operating conditions. Then anomalies are identified as deviations between predicted and observed thermal images. This approach enables the detection of anomalous behaviours by capturing temporal dynamics and extracting meaningful representations from thermal data. Finally, while deep learning-based methods can learn expressive representations, they often produce unreliable and overly optimistic predictions, which is harmful for safety-sensitive applications. To address this, our fourth contribution proposes a risk-controlling thresholding strategy for anomaly scores that ensures finite-sample performance guarantees for any user-defined risk function, including false positive rates and F1-scores. This contribution builds upon the distribution-free Learn then Test framework and introduces two adaptive thresholds accounting for overlap between normal and anomalous score distributions. In addition, we develop a density-forecasting-based AD model using conditional normalising flows to support likelihood-based anomaly scoring. Overall, these contributions advance the methodological foundations of deep AD and strengthen its applicability to safety-critical domains, paving the way for more reliable deployment in real-world systems.

   @phdthesis{ORBi-09fa9556-d8bc-4c6b-ac8a-cc15081301d1,
     author = {Patra, Sukanya},
     eprinttype = {hdl},
     title = {Deep Visual Anomaly Detection under Data Contamination and Anomaly Heterogeneity},
     language = {English},
     year = {2025},
     school = {UMONS - University of Mons [Faculty of Sciences], Mons, Belgium},
     organization = {MecaTech},
   }

2024

1. KDD

   Detecting Abnormal Operations in Concentrated Solar Power Plants from Irregular Sequences of Thermal Images

   Sukanya Patra, Nicolas Sournac, and Souhaib Ben Taieb

   In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Barcelona, Spain, 2024

   Abs DOI arXiv Bib

   Concentrated Solar Power (CSP) plants store energy by heating a storage medium with an array of mirrors that focus sunlight onto solar receivers atop a central tower. Operating at high temperatures these receivers face risks such as freezing, deformation, and corrosion, leading to operational failures, downtime, or costly equipment damage. We study the problem of anomaly detection (AD) in sequences of thermal images collected over a year from an operational CSP plant. These images are captured at irregular intervals ranging from one to five minutes throughout the day by infrared cameras mounted on solar receivers. Our goal is to develop a method to extract useful representations from high-dimensional thermal images for AD. It should be able to handle temporal features of the data, which include irregularity, temporal dependency between images and non-stationarity due to a strong daily seasonal pattern. The co-occurrence of low-temperature anomalies that resemble normal images from the start and the end of the operational cycle with high-temperature anomalies poses an additional challenge. We first evaluate state-of-the-art deep image-based AD methods, which have been shown to be effective in deriving meaningful image representations for the detection of anomalies. Then, we introduce a forecasting-based AD method that predicts future thermal images from past sequences and timestamps via a deep sequence model. This method effectively captures specific temporal data features and distinguishes between difficult-to-detect temperature-based anomalies. Our experiments demonstrate the effectiveness of our approach compared to multiple SOTA baselines across multiple evaluation metrics. We have also successfully deployed our solution on five months of unseen data, providing critical insights for the maintenance of the CSP plant.

   @inproceedings{Patra2024Detecting,
     author = {Patra, Sukanya and Sournac, Nicolas and Taieb, Souhaib Ben},
     title = {Detecting Abnormal Operations in Concentrated Solar Power Plants from Irregular Sequences of Thermal Images},
     year = {2024},
     isbn = {9798400704901},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3637528.3671623},
     doi = {10.1145/3637528.3671623},
     booktitle = {Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
     pages = {5578–5589},
     numpages = {12},
     keywords = {concentrated solar power plants, deep image anomaly detection, irregular time-series, non-stationarity, unsupervised learning},
     location = {Barcelona, Spain},
     series = {KDD '24},
   }

2. TMLR

   Anomaly detection with semi-supervised classification based on risk estimators

   Le Thi Khanh Hien, Sukanya Patra, and Souhaib Ben Taieb

   Transactions on Machine Learning Research, 2024

   Abs arXiv Bib HTML

   A significant limitation of one-class classification anomaly detection methods is their reliance on the assumption that unlabeled training data only contains normal instances. To overcome this impractical assumption, we propose two novel classification-based anomaly detection methods. Firstly, we introduce a semi-supervised shallow anomaly detection method based on an unbiased risk estimator. Secondly, we present a semi-supervised deep anomaly detection method utilizing a nonnegative (biased) risk estimator. We establish estimation error bounds and excess risk bounds for both risk minimizers. Additionally, we propose techniques to select appropriate regularization parameters that ensure the nonnegativity of the empirical risk in the shallow model under specific loss functions. Our extensive experiments provide strong evidence of the effectiveness of the risk-based anomaly detection methods.

   @article{Hien2024AnomalyEstimators,
     title = {Anomaly detection with semi-supervised classification based on risk estimators},
     author = {Hien, Le Thi Khanh and Patra, Sukanya and Ben Taieb, Souhaib},
     journal = {Transactions on Machine Learning Research},
     issn = {2835-8856},
     year = {2024},
     note = {},
   }

3. TMLR

   Revisiting Deep Feature Reconstruction for Logical and Structural Industrial Anomaly Detection

   Sukanya Patra and Souhaib Ben Taieb

   Transactions on Machine Learning Research, 2024

   Abs arXiv Bib HTML

   Industrial anomaly detection is crucial for quality control and predictive maintenance, but it presents challenges due to limited training data, diverse anomaly types, and external factors that alter object appearances. Existing methods commonly detect structural anomalies, such as dents and scratches, by leveraging multi-scale features from image patches extracted through deep pre-trained networks. However, significant memory and computational demands often limit their practical application. Additionally, detecting logical anomalies-such as images with missing or excess elements-requires an understanding of spatial relationships that traditional patch-based methods fail to capture. In this work, we address these limitations by focusing on Deep Feature Reconstruction (DFR), a memory- and compute-efficient approach for detecting structural anomalies. We further enhance DFR into a unified framework, called ULSAD, which is capable of detecting both structural and logical anomalies. Specifically, we refine the DFR training objective to improve performance in structural anomaly detection, while introducing an attention-based loss mechanism using a global autoencoder-like network to handle logical anomaly detection. Our empirical evaluation across five benchmark datasets demonstrates the performance of ULSAD in detecting and localizing both structural and logical anomalies, outperforming eight state-of-the-art methods. An extensive ablation study further highlights the contribution of each component to the overall performance improvement.

   @article{patra2024revisiting,
     title = {Revisiting Deep Feature Reconstruction for Logical and Structural Industrial Anomaly Detection},
     author = {Patra, Sukanya and Ben Taieb, Souhaib},
     journal = {Transactions on Machine Learning Research},
     issn = {2835-8856},
     year = {2024},
     note = {},
   }

2023

1. ESANN

   Anomaly detection in irregular image sequences for concentrated solar power plants

   Sukanya Patra, Souhaib Ben Taieb, and others

   In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2023

   Abs Bib HTML

   Operations at extremely high temperatures can lead to various malfunctions in Concentrated Solar Power (CSP) plants, emphasizing the need for predictive maintenance (PdM). We study PdM as an anomaly detection (AD) problem from irregular image sequences, which represent the minute-by-minute solar receiver’s surface temperature from a CSP plant. Contrary to standard benchmark image datasets in AD research, our data shows distinct characteristics such as non-stationarity, temporal dependence, and irregular sampling, which are unaddressed by current image-based AD techniques. Therefore, we introduce a forecast-based AD method to address these characteristics, drawing inspiration from irregular sequence modelling. The results show that the proposed method outperforms classical image-based AD methods on our dataset.

   @inproceedings{patra2023anomaly,
     title = {Anomaly detection in irregular image sequences for concentrated solar power plants},
     author = {Patra, Sukanya and Taieb, Souhaib Ben and others},
     booktitle = {European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning},
     year = {2023},
   }

2019

1. Improvising singular value decomposition by KNN for use in movie recommender systems

   Sukanya Patra and Boudhayan Ganguly

   Journal of Operations and Strategic Planning, 2019

   Abs DOI Bib

   Online recommender systems are an integral part of e-commerce. There are a plethora of algorithms following different approaches. However, most of the approaches except the singular value decomposition (SVD), do not provide any insight into the underlying patterns/concepts used in item rating. SVD used underlying features of movies but are computationally resource-heavy and performs poorly when there is data sparsity. In this article, we perform a comparative study among several pre-processing algorithms on SVD. In the experiments, we have used the MovieLens 1M dataset to compare the performance of these algorithms. KNN-based approach was used to find out K-nearest neighbors of users and their ratings were then used to impute the missing values. Experiments were conducted using different distance measures, such as Jaccard and Euclidian. We found that when the missing values were imputed using the mean of similar users and the distance measure was Euclidean, the KNN-based (K-Nearest Neighbour) approach of pre-processing the SVD was performing the best. Based on our comparative study, data managers can choose to employ the algorithm best suited for their business.

   @article{patra2019improvising,
     title = {Improvising singular value decomposition by KNN for use in movie recommender systems},
     author = {Patra, Sukanya and Ganguly, Boudhayan},
     journal = {Journal of Operations and Strategic Planning},
     volume = {2},
     number = {1},
     pages = {22--34},
     year = {2019},
     publisher = {SAGE Publications Sage India: New Delhi, India},
     doi = {10.1177/2516600X19848956},
     url = {https://doi.org/10.1177/2516600X19848956}
   }