Florent Forest
YOU?
Author Swipe
View article: Interpretable prognostics with concept bottleneck models
Interpretable prognostics with concept bottleneck models Open
View article: Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers
Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers Open
View article: Calibrated Adaptive Teacher for Domain-Adaptive Intelligent Fault Diagnosis
Calibrated Adaptive Teacher for Domain-Adaptive Intelligent Fault Diagnosis Open
Intelligent fault diagnosis (IFD) based on deep learning can achieve high accuracy from raw condition monitoring signals. However, models usually perform well on the training distribution only, and experience severe performance drops when …
View article: Assessing Aircraft Engine Wear through Simulation Techniques
Assessing Aircraft Engine Wear through Simulation Techniques Open
In the field of aeronautical engineering, understanding and simulating aircraft engine performance is critical, especially for improving operational safety, efficiency, and sustainability. At Safran Aircraft Engines, we were able to demons…
View article: Exploiting Semantic Scene Reconstruction for Estimating Building Envelope Characteristics
Exploiting Semantic Scene Reconstruction for Estimating Building Envelope Characteristics Open
Achieving the EU's climate neutrality goal requires retrofitting existing buildings to reduce energy use and emissions. A critical step in this process is the precise assessment of geometric building envelope characteristics to inform retr…
View article: Knowledge-based and Expert Systems in Prognostics and Health Management: a Survey
Knowledge-based and Expert Systems in Prognostics and Health Management: a Survey Open
Prognostics and Health Management (PHM) has become increasingly popular in recent years, and data-driven methods and artificial intelligence have emerged as dominant tools within the PHM field. This trend is mainly due to the increasing us…
View article: Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights
Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights Open
This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research h…
View article: From classification to segmentation with explainable AI: A study on crack detection and growth monitoring
From classification to segmentation with explainable AI: A study on crack detection and growth monitoring Open
View article: Interpretable Prognostics with Concept Bottleneck Models
Interpretable Prognostics with Concept Bottleneck Models Open
Deep learning approaches have recently been extensively explored for the prognostics of industrial assets. However, they still suffer from a lack of interpretability, which hinders their adoption in safety-critical applications. To improve…
View article: Health Prediction for Lithium-Ion Batteries Under Unseen Working Conditions
Health Prediction for Lithium-Ion Batteries Under Unseen Working Conditions Open
Battery health prediction is significant while challenging for intelligent battery management. This article proposes a general framework for both short-term and long-term predictions of battery health under unseen dynamic loading and tempe…
View article: ThermoNeRF: Joint RGB and Thermal Novel View Synthesis for Building Facades using Multimodal Neural Radiance Fields
ThermoNeRF: Joint RGB and Thermal Novel View Synthesis for Building Facades using Multimodal Neural Radiance Fields Open
Thermal scene reconstruction holds great potential for various applications, such as analyzing building energy consumption and performing non-destructive infrastructure testing. However, existing methods typically require dense scene measu…
View article: Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression
Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression Open
Unsupervised Domain Adaptation for Regression (UDAR) aims to adapt models from a labeled source domain to an unlabeled target domain for regression tasks. Traditional feature alignment methods, successful in classification, often prove ine…
View article: Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis
Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis Open
Intelligent Fault Diagnosis (IFD) based on deep learning has proven to be an effective and flexible solution, attracting extensive research. Deep neural networks can learn rich representations from vast amounts of representative labeled da…
View article: From Classification to Segmentation with Explainable AI: A Study on Crack Detection and Growth Monitoring
From Classification to Segmentation with Explainable AI: A Study on Crack Detection and Growth Monitoring Open
Monitoring surface cracks in infrastructure is crucial for structural health monitoring. Automatic visual inspection offers an effective solution, especially in hard-to-reach areas. Machine learning approaches have proven their effectivene…
View article: Predictive health assessment for lithium-ion batteries with probabilistic degradation prediction and accelerating aging detection
Predictive health assessment for lithium-ion batteries with probabilistic degradation prediction and accelerating aging detection Open
View article: Calibrated Self-Training for Cross-Domain Bearing Fault Diagnosis
Calibrated Self-Training for Cross-Domain Bearing Fault Diagnosis Open
Fault diagnosis of rolling bearings is a crucial task in Prognostics and Health Management, as rolling elements are ubiquitous in industrial assets.Data-driven approaches based on deep neural networks have made significant progress in this…
View article: Selecting the Number of Clusters K with a Stability Trade-off: An Internal Validation Criterion
Selecting the Number of Clusters K with a Stability Trade-off: An Internal Validation Criterion Open
View article: Segmenting Without Annotating: Crack Segmentation and Monitoring via Post-Hoc Classifier Explanations
Segmenting Without Annotating: Crack Segmentation and Monitoring via Post-Hoc Classifier Explanations Open
Monitoring the cracks in walls, roads and other types of infrastructure is essential to ensure the safety of a structure, and plays an important role in structural health monitoring. Automatic visual inspection allows an efficient, costeff…
View article: Transformer-based conditional generative adversarial network for multivariate time series generation
Transformer-based conditional generative adversarial network for multivariate time series generation Open
Conditional generation of time-dependent data is a task that has much interest, whether for data augmentation, scenario simulation, completing missing data, or other purposes. Recent works proposed a Transformer-based Time series generativ…
View article: Unsupervised Learning of Data Representations and Cluster Structures : Applications to Large-scale Health Monitoring of Turbofan Aircraft Engines
Unsupervised Learning of Data Representations and Cluster Structures : Applications to Large-scale Health Monitoring of Turbofan Aircraft Engines Open
Cette thèse porte sur des méthodes d’apprentissage statistique non supervisées et leurs applications à la surveillance de santé (health monitoring) des moteurs d’avion à une échelle industrielle. Notre premier objectif est de faire passer …
View article: A Survey and Implementation of Performance Metrics for Self-Organized Maps
A Survey and Implementation of Performance Metrics for Self-Organized Maps Open
Self-Organizing Map algorithms have been used for almost 40 years across various application domains such as biology, geology, healthcare, industry and humanities as an interpretable tool to explore, cluster and visualize high-dimensional …
View article: A Survey and Implementation of Performance Metrics for Self-Organized\n Maps
A Survey and Implementation of Performance Metrics for Self-Organized\n Maps Open
Self-Organizing Map algorithms have been used for almost 40 years across\nvarious application domains such as biology, geology, healthcare, industry and\nhumanities as an interpretable tool to explore, cluster and visualize\nhigh-dimension…
View article: Large-scale Vibration Monitoring of Aircraft Engines from Operational Data using Self-organized Models
Large-scale Vibration Monitoring of Aircraft Engines from Operational Data using Self-organized Models Open
Vibration analysis is an important component of industrial equipment health monitoring. Aircraft engines in particular are complex rotating machines where vibrations, mainly caused by unbalance, misalignment, or damaged bearings, put engin…
View article: Carte SOM profonde : Apprentissage joint de représentations et auto-organisation
Carte SOM profonde : Apprentissage joint de représentations et auto-organisation Open
International audience
View article: Deep Embedded SOM: Joint Representation Learning and Self-Organization
Deep Embedded SOM: Joint Representation Learning and Self-Organization Open
View article: Selecting the Number of Clusters $K$ with a Stability Trade-off: an Internal Validation Criterion
Selecting the Number of Clusters $K$ with a Stability Trade-off: an Internal Validation Criterion Open
Model selection is a major challenge in non-parametric clustering. There is no universally admitted way to evaluate clustering results for the obvious reason that no ground truth is available. The difficulty to find a universal evaluation …