Publications
-
Implementation of an AI-driven dynamic control system to optimize excess photovoltaic energy management in grid-connected sustainable BIPV
This study proposes an integrated approach for optimizing grid-connected photovoltaic (PV) systems through AI-based forecasting and a Dynamic Automatic Control System (DACS). Using Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and a hybrid CNN-LSTM model, we predict PV production and building energy demand. The CNN-LSTM model achieved the best performance for PV forecasting […]
-
An enhanced genetic algorithm for optimized task allocation and planning in heterogeneous multi-robot systems
Efficient task allocation and path planning in heterogeneous multi-robot systems (MRS) remains a significant challenge in industrial inspection contexts, particularly when robots exhibit diverse sensing capabilities and must operate across spatially distributed sites. To address the limitations of exact methods and conventional heuristics, we propose a novel two-phase enhanced genetic algorithm (EGA) tailored for capability-constrained […]
-
Automatic learning of physics-constrained space heterogeneous PDEs for defect identification in slender mechanical structures
This contribution explores the opportunities offered by physics-constrained automatic PDE learning, see for example [1], for identifying defects in mechanical structures. In this framework, defects are seen as limited zones in a domain where the constitutive law is different from that of the healthy material. One challenge in defect localization is that the impact of […]
-
Multi-LOD generative approach for multi-objective sustainability optimization from the early stages of building design
Given the urgency of reducing the buildings’ environmental impact, this article focuses on optimizing sustainability from the earliest design phases, when decisions have the greatest influence. To address the challenges posed by the coarse granularity of digital models during the sketching phase and the often-conflicting nature of sustainability criteria, a generative workflow is proposed. This […]
-
Channel Estimation for OFDM Systems Over Doubly Selective Channels Based on CEHNet
In dynamic scenarios, time-frequency doubly selective channels challenge accurate estimation. Deep learning based method emerges as a promising way by leveraging temporal correlation and local time-frequency features characterized by wireless channels. To enhance adaptability in dynamic channels with fewer pilots, this letter proposes a novel channel estimation algorithm based on a channel-enhanced deep Horblock network […]
-
A Divisive Unsupervised Feature Selection Approach for Explainable Remaining Useful Life Prediction
Predicting the Remaining Useful Life (RUL) in maintenance often encounters challenges such as high dimensionality, feature redundancy, and limited explainability. This paper presents a novel approach that combines Interpretable Divisive Feature Clustering (IDFC) with Long Short-Term Memory (LSTM) networks. The IDFC algorithm leverages the strengths of variable clustering methods (VARCLUS) and the Clustering of Variables […]
-
Investigating the sustainable design of a shipping container building using advanced building energy modeling and Bayesian inference
Modular buildings demonstrate environmental benefits in raw material usage but vary in energy performance by climate. Our research evaluates the energy performance of a modular educational building by calibrating a Building Energy Model (BEM) with operational data and Bayesian inference. As expected, this case study reveals that energy model calibration is not required when sufficient […]
-
Structured pruning for efficient systolic array accelerated cascade Speech-to-Text Translation
We present in this paper a simple method for pruning tiles of weights in sparse matrices, that do not require fine-tuning or retraining. This method is applied here to the feed-forward layers of transformers. We assess in a first experiment the impact of such pruning on the performances of speech recognition, machine translation, and the […]
-
Integrating industry 4.0 technologies and maintenance 4.0 for sustainable manufacturing: a systematic literature review
The integration of Industry 4.0 (I4.0) technologies with Maintenance 4.0 (M4.0) practices holds strong potential for advancing sustainable manufacturing (SM). While these technologies promise improvements in resource efficiency, waste reduction, and alignment with sustainability objectives, research on their synergistic implementation remains limited. This study addresses this gap through a Systematic Literature Review (SLR) of 75 […]
-
Collaborative Semantic Mapping for Updating the Digital Twin in controlled Indoor Environment
Efficient management of indoor spaces is increasingly critical for applications such as security, evacuation planning, and roboticdeployment. Digital twin technology has emerged as a transformative solution, providing a real-time link between the physicalenvironment and its virtual counterpart to enable monitoring, simulation, analysis, and performance optimization. This paperintroduces a novel collaborative approach to semantic mapping that […]
-
Towards a dynamic model of collective intelligence: Theoretical integration, nonverbal interaction and temporality
Most existing research on Collective Intelligence (CI) tends to emphasize final performance indicators or sums of individual cognitive traits, giving insufficient attention to how teams dynamically construct their collective capacity through ongoing interactions. In this paper, we propose an integrative perspective that draws on multiple existing approaches, ranging from conceptual frameworks (IMOI, TSM-CI) to measurement-oriented […]
-
Augmented Perception: a real-time digital twin based approach to enhance robotic perception.
This paper introduces an Augmented Perception (AP) framework to enhance robotic perception in resilient manufacturing systems (MS) by integrating Digital Twin (DT) data directly at the sensor level in real time. Inspired by augmented reality, this approach enables robots to perceive both physical and virtual entities within a unified representation. To ensure real-time performance, we […]