Publications
-
Evidential Counterfactual Explanations for Instance-Based Classification under the Belief Function Framework
Explainability is now an essential requirement for deploying artificial intelligence systems in sensitive environments. While neighborhood based models such as k-NN are naturally interpretable, they remain limited in their ability to handle uncertainty. The Evidential k-NN (EKNN) classifier, based on the Dempster–Shafer theory, introduces belief func tions that explicitly model uncertainty between neighbors. However, this […]
-
MSAF-NeXt: A Unified Multi-Scale Feature Fusion Framework for Facial Emotion Recognition Across Benchmark and Autism-Related Datasets
Facial Emotion Recognition (FER) is fundamental in computer vision, with applications in human–computer interaction, healthcare, and assistive technologies. Despite significant progress, FER remains challenging due to pose, illumination, occlusions, and subtle expression dynamics. In this paper, we propose MSAF-NeXt, a unified framework that integrates spatial alignment, hierarchical feature fusion, and lightweight attention within a ConvNeXt […]
-
Empirical OCV Model Benchmarking for ECM Identification in LFP Battery Management Systems
Accurate battery models are essential for the safe and efficient management of lithium-ion cells in electric ve- hicles. Equivalent circuit models (ECMs) are widely used in embedded battery management systems, and the accuracy of these models depends heavily on the open-circuit voltage (OCV) model used as the voltage baseline. This paper presents an empirical benchmarking […]
-
OptiPINN: A two-stage NSGA-II multi-objective optimization framework for solving 2D transient non-linear heat transfer problems with coupled convection and radiation
Transient non-linear heat transfer with coupled convection, radiation, and localized heat generation is challenging due to strong non-linearities, sharp thermal gradients, and asymmetric boundary conditions. Conventional Physics-Informed Neural Networks (PINNs) typically require manual tuning of the network architecture. The adjustment of weight coefficients for various loss terms is also time-consuming and can lead to unstable […]
-
A Dual-Teacher Cross-Modal Knowledge Distillation Framework Integrating Visual and Textual Modalities for Neonatal Jaundice Diagnosis
textbf{Background and Objective:} Neonatal jaundice remains a major health challenge, particularly in resource-limited environments where reliable diagnosis is not readily accessible. While image-based and AI-driven approaches have demonstrated encouraging diagnostic performance, their limited generalizability across different datasets, populations, and clinical settings remains a major challenge.\ textbf{Methods:} This study proposes a Dual-Teacher Cross-Modal Knowledge Distillation (DT-CMKD) […]
-
Multi-objective Energy-efficient Flexible Flow Shop Scheduling Problem : Integrating Renewable Energy and Demand Response Programs
This study tackles an energy-efficient flexible flow shop scheduling problem motivated by the increasing need for sustainable manufacturing under volatile energy markets. The proposed framework jointly integrates photovoltaic generation, energy storage systems, Time-of-Use pricing, and demand bidding mechanisms, while explicitly accounting for machine On/Off strategies with realistic turn-on time constraints. A bi-objective mixed-integer linear programming […]
-
Generative and Foundation-Model Artificial Intelligence in Food Safety Analysis, Authenticity Identification, and Quality Control: A Systematic Review of Validation and Decision Readiness
Generative and foundation-model artificial intelligence can strengthen food analysis, but computational performance does not establish decision readiness. This systematic review examines applications and validation requirements in food safety, authenticity, and quality control. A Scopus search on 13 June 2026 identified 438 records; 65 publications were retained, including 41 direct analytical reports and 24 supporting publications. […]
-
Integrating lean and green optimisation into decisionmaking frameworks in construction logistics: a systematic literature review
Logistics plays a decisive role in the performance of construction projects, owing to its central position within supply chains and the complexity of the trade-offs it involves. These decisions involve a wide range of stakeholders and require the reconciliation of operational, environmental and organisational constraints that are often interdependent. Against this backdrop, this study presents […]
-
Towards Context-Driven Approaches to Visual Affordance Recognition : A Comprehensive Survey
With the rise of robotics, affordance detection has become a key element for improving and strengthening human and robot object interactions. Thanks to recent progress in deep learning, affordance detection has become more precise and versatile. However, with the increasing use of Large Language Models (LLMs) and Visual Transformers (ViTs), the research focus shifted from […]
-
FLASH: Efficient Impact Fall Detection with Unified Hypergraph State-Space Model
Falls represent a critical public health challenge, and accurate detection of the impact moment when an individual hits the ground is crucial for timely intervention. Existing skeleton-based methods rely on graph neural networks modeling only pairwise joint connections, failing to capture multi-joint coordination characteristic of fall impacts, while transformer-based temporal models suffer from quadratic complexity […]
-
Momentum-Guided Federated Split Distillation for Personalized Temporal Edge Intelligence
We propose a momentum-guided federated split distillation framework for personalized, efficient, and autonomous temporal edge intelligence. We introduce TeRR-SAtt, our novel temporal reservoir student attention design that combines fixed reservoir representations, a lightweight temporal student, and personalized output modules. We also present AMGF, our anticipatory momentum-guided fusion mechanism that clusters clients through learning momentum and […]
-
Computational Efficiency through Momentum-Guided Split Distillation: Rethinking Federated Learning for Edge Autonomy
IoT ecosystems increasingly require adaptive intelligence under heterogeneous data and resource conditions [1]. In such distributed, privacy-sensitive, and evolving environments, Federated Learning (FL) enables collaborative edge intelligence without transmitting raw data [2]. However, IoT intelligence requires temporal reasoning to capture evolving and context-dependent dynamics [3]. This makes temporal reasoning valuable yet costly for constrained devices. […]