Publications
-
Towards Green AI : Assessing the Robustness of Conformer and Transformer Models under Compression
Today, transformer and conformer models are commonly used in end-to-end speech recognition. Generally, conformer models are more efficient than transformers, but both suffer from large sizes, and expensive computing cost making their use environmentally unfriendly. In this paper, we propose compressing these models using quantization and pruning, evaluating size and computing time improvements while monitoring […]
-
EPT-MoE: Toward Efficient Parallel Transformers with Mixture-of-Experts for 3D Hand Gesture Recognition
The Mixture-of-Experts (MoE) is a widely known deep neural architecture where an ensemble of specialized sub-models (a group of experts) optimizes the overall performance with a constant computational cost. Especially with the rise of Mixture-of-Experts with Mixtral-8x7B Transformers, MoE architectures have gained popularity in Large Language Modeling (LLM) and Computer Vision. In this paper, we […]
-
Adaptative Reinforcement Learning Approach for Predictive Maintenance of a Smart Building Lighting System
Due to advancements in sensing technologies, enhanced IoT architectures, and expanded connectivity options, predictive maintenance has emerged as a compelling solution within the context of Industry 4.0 for industrial systems. However, within this landscape, such as in Smart Buildings (SBs), the lack of failure data poses a significant challenge for implementing traditional data-based approaches documented […]
-
Augmented Perception: Empowering Flexible Manufacturing Systems through the Digital Twin – A Novel Approach.
In the context of the Industry of the Future, manufacturing environments must be flexible and reconfigurable to continuously adapt to customers’ personalized demands and changes in the manufacturing processes. This adaptation involves the reconfiguration of the layout and the integration of new systems into the environment: production lines, manufacturing machines, robotic arms, mobile robots, etc. […]
-
Additive Manufacturing Awareness For Engineering Education in France
Additive manufacturing (AM) is one of the pillars of the Industry 4.0. Compared to traditional manufacturing, AM is a layer-by-layer construction; it provides a prototype before producing in order to optimize the design and avoid the stock market and uses strictly necessary material, which can be recyclable, at the benefit of leaning towards local production, […]
-
Incorporating Uncertain Human Behavior in Production Scheduling for Enhanced Productivity in Industry 5.0 Context
Human-centered production systems are of increasing interest to researchers, especially with the advent of the Industry 5.0 paradigm. Most research into production scheduling has long neglected human workers’ specific roles and unpredictable behavior in a production system, treating them as machines with deterministic behavior. This work studies the impact of human operational behavior on the […]
-
Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontiers
The emerging integration of IoT (Internet of Things) and AI (Artificial Intelligence) has unlocked numerous opportunities for innovation across diverse industries. However, growing privacy concerns and data isolation issues have inhibited this promising advancement. Unfortunately, traditional centralized machine learning (ML) methods have demonstrated their limitations in addressing these hurdles. In response to this ever-evolving landscape, […]
-
Scheduling Periodic Messages on a Shared Link without Buffering
Cloud-RAN, a novel architecture for modern mobile networks, relocates processing units from antenna to distant data centers. This shift introduces the challenge of ensuring low latency for the periodic messages exchanged between antennas and their respective processing units. In this study, we tackle the problem of devising an efficient periodic message assignment scheme under the […]
-
Reinforcement learning for HVAC control in intelligent buildings: A technical and conceptual review
Heating, Ventilation and Air Conditioning (HVAC) systems in buildings are a major source of global operational CO2 emissions, primarily due to their high energy demands. Traditional controllers have shown effectiveness in managing building energy use. However, they either struggle to handle complex environments or cannot incorporate learning from experience into their decision-making processes, leading to […]
-
Exploring a Knowledge-Based Approach for Predictive Maintenance of Aircraft Engines: Studying Fault Propagation through Spatial and Topological Component Relationships
Predictive maintenance has become a highly favored application in Industry 4.0, particularly in complex systems with requirements for reliability, robustness, and performance. Aircraft engines are among these systems, and several studies have been conducted to try to estimate their remaining lifespan. The C-MAPSS dataset provided by NASA has greatly served the scientific community, and several […]
-
NUMERICAL INVESTIGATION OF THE FLEXURAL BEHAVIOR OF STEEL PLATES REINFORCED WITH HYBRID FLAX/CARBON COMPOSITE PATCHES
For strengthening or rehabilitation of existing structures, patches of fiber-reinforced polymers (FRP) materials are being adhesively bonded to the existing metallic structures. So far, Carbon FRP (CFRP) are the main composite materials industrially implemented for metal structural reinforcement, due to their reliability and high mechanical performances. However, multiple researchers have highlighted the negative environmental impact […]
-
Sampled-Data Observer Design for Linear Kuramoto-Sivashinsky Systems with Non-Local Output
The aim of this paper is to provide a novel systematic methodology for the design of sampled-data observers for Linear Kuramoto-Sivashinsky systems (LK-S) with non-local outputs. More precisely, we extend the systematic sampled-data observer design approach which is based on the use of an Inter-Sample output predictor to the class of LK-S systems. By using […]
Chargement en cours…
Erreur : tout le contenu a été chargé.