Ahmed Nabil Belbachir
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ahmed Nabil Belbachir has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Gautam Srivastava
Sogang University, Seoul, Republic of Korea
10 shared publications - Youcef Djenouri
Department of Microsystems, University of South-Eastern Norway, Kongsberg, Norway
10 shared publications - Tomasz Michalak
University of Warsaw
9 shared publications Asma Belhadi
Department of Information Technology, OsloMet University, Oslo, Norway
4 shared publications- Asma Belhadi
Oslo Metropolitan University Faculty of Technology Art and Design, Oslo, Norway
3 shared publications - Assia Belbachir
NORCE Research AS, 4879 Grimstad, Norway
3 shared publications
Latest Publications
- Open Access
- 3 November 2026
- Published by Elsevier in Results in Engineering
- Vol. 32
Robotic disassembly in consumer E-waste management: A systematic review toward sustainable and circular economy solutions
- 3 November 2026
- Published by Elsevier in Results in Engineering
- Vol. 32
Open AccessRobotic disassembly in consumer E-waste management: A systematic review toward sustainable and circular economy solutions
- Open Access
- 11 October 2026
- Published by Springer Nature in Journal of Nondestructive Evaluation
- Vol. 45 (4) , 143
Economic Feasibility of Acoustic Emission Monitoring in CO2 Pipelines: An Experimental Study
- 11 October 2026
- Published by Springer Nature in Journal of Nondestructive Evaluation
- Vol. 45 (4) , 143
Open AccessEconomic Feasibility of Acoustic Emission Monitoring in CO2 Pipelines: An Experimental Study
- Open Access
- 7 March 2026
- Published by Springer Nature
- p. 1-10
AI, Data, and Robotics: A Structured Overview of Contributions and Priorities
This chapter provides a comprehensive overview of the rapidly evolving fields of artificial intelligence, data, and robotics (ADR), introducing the foundational concepts, transformative applications, and forward-looking frameworks that structure the book. Positioned within Europe’s broader digital innovation landscape, it highlights how ADR technologies are reshaping key sectors (including manufacturing, healthcare, mobility, and environmental sustainability) while underscoring the importance of ethical, human-centric, and sustainable approaches to their development. Organized around three core themes, Foundations, Transformations, and Future Directions, the chapter situates the contributions of each subsequent section, tracing current research priorities, emerging technological trajectories, and real-world deployments. By emphasizing multidisciplinary collaboration and strategic foresight, it outlines how integrating technical excellence with societal values can foster trustworthy, equitable, and resilient digital ecosystems. Serving as a roadmap for the chapters that follow, this overview aims to inspire coordinated efforts among researchers, industry leaders, policymakers, and citizens to harness the full potential of AI, data, and robotics for the benefit of society.
- 7 March 2026
- Published by Springer Nature
- p. 1-10
Open AccessAI, Data, and Robotics: A Structured Overview of Contributions and Priorities
This chapter provides a comprehensive overview of the rapidly evolving fields of artificial intelligence, data, and robotics (ADR), introducing the foundational concepts, transformative applications, and forward-looking frameworks that structure the book. Positioned within Europe’s broader digital innovation landscape, it highlights how ADR technologies are reshaping key sectors (including manufacturing, healthcare, mobility, and environmental sustainability) while underscoring the importance of ethical, human-centric, and sustainable approaches to their development. Organized around three core themes, Foundations, Transformations, and Future Directions, the chapter situates the contributions of each subsequent section, tracing current research priorities, emerging technological trajectories, and real-world deployments. By emphasizing multidisciplinary collaboration and strategic foresight, it outlines how integrating technical excellence with societal values can foster trustworthy, equitable, and resilient digital ecosystems. Serving as a roadmap for the chapters that follow, this overview aims to inspire coordinated efforts among researchers, industry leaders, policymakers, and citizens to harness the full potential of AI, data, and robotics for the benefit of society.
- Open Access
- 7 March 2026
- Published by Springer Nature
- p. 13-28
Shaping Europe’s Future: The Convergence of AI, Data, and Robotics
This chapter explores the convergence of generative AI and robotics within the broader context of Europe’s AI, data, and robotics (ADR) strategy. It examines how these powerful general-purpose technologies are reshaping innovation across strategic sectors while also presenting complex challenges in safety, trustworthiness, and sustainability. The chapter highlights Europe’s distinct approach anchored in values-driven innovation, technological sovereignty, and strategic autonomy and outlines the role of the ADRA partnership in steering this transformation. Through initiatives such as the SRIDA, high-impact pilots, and challenge-based innovation, ADRA is fostering a resilient European ecosystem that supports responsible, human-centric development of GenAI and Robotics. The chapter concludes by emphasizing the need for coordinated investment, policy alignment, and bold action to ensure Europe remains at the forefront of this rapidly evolving technological landscape.
- 7 March 2026
- Published by Springer Nature
- p. 13-28
Open AccessShaping Europe’s Future: The Convergence of AI, Data, and Robotics
This chapter explores the convergence of generative AI and robotics within the broader context of Europe’s AI, data, and robotics (ADR) strategy. It examines how these powerful general-purpose technologies are reshaping innovation across strategic sectors while also presenting complex challenges in safety, trustworthiness, and sustainability. The chapter highlights Europe’s distinct approach anchored in values-driven innovation, technological sovereignty, and strategic autonomy and outlines the role of the ADRA partnership in steering this transformation. Through initiatives such as the SRIDA, high-impact pilots, and challenge-based innovation, ADRA is fostering a resilient European ecosystem that supports responsible, human-centric development of GenAI and Robotics. The chapter concludes by emphasizing the need for coordinated investment, policy alignment, and bold action to ensure Europe remains at the forefront of this rapidly evolving technological landscape.
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (2) , 1978-1987
Uncertainty-Aware Drone Swarm Disruption for Threat Mitigation
This study tackles the challenge of neutralizing a malicious drone swarm targeting critical infrastructure. Given the impracticality of destroying all drones, we propose an uncertainty-aware threat assessment method, modeling payload size and positional uncertainties probabilistically. We study node removal as the core decision problem to fragment communication and reduce attack power. The threat of each drone is quantified by its expected payload and distance-based probabilistic model. We also assess the probabilistic connectivity between drones to evaluate the swarm’s robustness. A novel evaluation function integrates these factors, and we introduce a probabilistic greedy search algorithm to minimize the swarm’s threat. We evaluate against centrality-based and weight-augmented dismantling heuristics, a recent DQN policy, and a small-n brute-force oracle. Our approach achieves a 70% reduction in attack power and near-optimal performance, deviating by less than 5% from the best possible outcomes under uncertainty.
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (2) , 1978-1987
Uncertainty-Aware Drone Swarm Disruption for Threat Mitigation
This study tackles the challenge of neutralizing a malicious drone swarm targeting critical infrastructure. Given the impracticality of destroying all drones, we propose an uncertainty-aware threat assessment method, modeling payload size and positional uncertainties probabilistically. We study node removal as the core decision problem to fragment communication and reduce attack power. The threat of each drone is quantified by its expected payload and distance-based probabilistic model. We also assess the probabilistic connectivity between drones to evaluate the swarm’s robustness. A novel evaluation function integrates these factors, and we introduce a probabilistic greedy search algorithm to minimize the swarm’s threat. We evaluate against centrality-based and weight-augmented dismantling heuristics, a recent DQN policy, and a small-n brute-force oracle. Our approach achieves a 70% reduction in attack power and near-optimal performance, deviating by less than 5% from the best possible outcomes under uncertainty.
- Open Access
- 5 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 21355-21366
Game-Theoretic Consensus Deep Learning for Adaptive Flood Prediction in Digital Twin Environments
We propose Game-Theoretic Consensus Deep Learning (GTCDL), an adaptive AI framework designed to enhance disaster prediction and response through dynamic model consensus. This approach addresses two critical challenges in disaster management by integrating with Digital Twin infrastructures and spatio-temporal remote sensing data. First, handling heterogeneous data distributions across different disaster phases from pre-event to recovery. Second, enabling real-time model adaptation to evolving ground conditions. The method operates through a two-level architecture beginning with multi-model ensemble training, where deep learning models for flood prediction are evaluated via game-theoretic performance attribution using Shapley Values to quantify their context-specific utility. This is followed by a dynamic model selection phase that intelligently matches real-time remote sensing observations against both historical loss patterns and current model competencies, optimizing the ensemble for emerging disaster conditions. Our validation studies demonstrate GTCDL's effectiveness in flood prediction scenarios using Sentinel-1 SAR time series within a river basin Digital Twin environment. The framework achieved 92% AUC in damage forecasting, representing a 6% improvement over static baselines. The full code is available at https://github.com/YousIA/GTCDL/
- 5 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 21355-21366
Open AccessGame-Theoretic Consensus Deep Learning for Adaptive Flood Prediction in Digital Twin Environments
We propose Game-Theoretic Consensus Deep Learning (GTCDL), an adaptive AI framework designed to enhance disaster prediction and response through dynamic model consensus. This approach addresses two critical challenges in disaster management by integrating with Digital Twin infrastructures and spatio-temporal remote sensing data. First, handling heterogeneous data distributions across different disaster phases from pre-event to recovery. Second, enabling real-time model adaptation to evolving ground conditions. The method operates through a two-level architecture beginning with multi-model ensemble training, where deep learning models for flood prediction are evaluated via game-theoretic performance attribution using Shapley Values to quantify their context-specific utility. This is followed by a dynamic model selection phase that intelligently matches real-time remote sensing observations against both historical loss patterns and current model competencies, optimizing the ensemble for emerging disaster conditions. Our validation studies demonstrate GTCDL's effectiveness in flood prediction scenarios using Sentinel-1 SAR time series within a river basin Digital Twin environment. The framework achieved 92% AUC in damage forecasting, representing a 6% improvement over static baselines. The full code is available at https://github.com/YousIA/GTCDL/
- Open Access
- 28 July 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (6)
Advancing Point Cloud Perception: A Focus on People Detection
Point-cloud data have become pivotal for three-dimensional scene analysis, yet robust real-time detection of humans remains challenging due to data sparsity, irregular sampling, and occlusions. In this study, we present a feature-engineered pipeline that uses a Random Forest Classifier (RFC) for efficient people detection in high-resolution LiDAR point clouds. Our contributions include: (1) detailed parameterization of a ground-removal algorithm using region growing; a compact feature set of 15 geometric and intensity-based descriptors; (3) comprehensive evaluation metrics on two datasets; and (4) comparative analysis against MLP and PointNet baselines. Experiments demonstrate that our RFC achieves good results. These results validate the practical applicability of our approach for real-time, on-device human detection in point-cloud environments.
- 28 July 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (6)
Open AccessAdvancing Point Cloud Perception: A Focus on People Detection
Point-cloud data have become pivotal for three-dimensional scene analysis, yet robust real-time detection of humans remains challenging due to data sparsity, irregular sampling, and occlusions. In this study, we present a feature-engineered pipeline that uses a Random Forest Classifier (RFC) for efficient people detection in high-resolution LiDAR point clouds. Our contributions include: (1) detailed parameterization of a ground-removal algorithm using region growing; a compact feature set of 15 geometric and intensity-based descriptors; (3) comprehensive evaluation metrics on two datasets; and (4) comparative analysis against MLP and PointNet baselines. Experiments demonstrate that our RFC achieves good results. These results validate the practical applicability of our approach for real-time, on-device human detection in point-cloud environments.
- Open Access
FishProx: Proximate conspecific interaction of Atlantic salmon ( Salmo salar ) for behavioural analysis through instance segmentation masks
In modern fish production and experimental facilities, camera installations are increasingly common for monitoring animal welfare. This opens up a new alley of autonomous tracking systems levering streamed data. However, the substantial amount of data necessitates condensation for human operators. In this paper, we present the out-of-the-box pipeline called FishProx that starts with the imagery of fish in tanks and ends in the calculation of welfare impacting factors through anomaly scores. The utilisation of the Segment Anything Model (SAM) is the basis for the identification of feeding behaviour and also (ab)normal behaviour through analysing snapshots of the fish tanks to infer metrics such as fish cohesion and cluster alignment, alongside the detection count. Our method employs automatic and robust algorithms for camera systems, making additional labelled data unnecessary, thereby saving energy and costs. Furthermore, automatic fish observation coupled with integrated analytical capabilities can lead to a sensible autonomous decision-making process. Lastly, by providing objective metrics, our approach might guide the enabling of automatic quantification of fish states, making comparative studies possible.
Open AccessFishProx: Proximate conspecific interaction of Atlantic salmon ( Salmo salar ) for behavioural analysis through instance segmentation masks
In modern fish production and experimental facilities, camera installations are increasingly common for monitoring animal welfare. This opens up a new alley of autonomous tracking systems levering streamed data. However, the substantial amount of data necessitates condensation for human operators. In this paper, we present the out-of-the-box pipeline called FishProx that starts with the imagery of fish in tanks and ends in the calculation of welfare impacting factors through anomaly scores. The utilisation of the Segment Anything Model (SAM) is the basis for the identification of feeding behaviour and also (ab)normal behaviour through analysing snapshots of the fish tanks to infer metrics such as fish cohesion and cluster alignment, alongside the detection count. Our method employs automatic and robust algorithms for camera systems, making additional labelled data unnecessary, thereby saving energy and costs. Furthermore, automatic fish observation coupled with integrated analytical capabilities can lead to a sensible autonomous decision-making process. Lastly, by providing objective metrics, our approach might guide the enabling of automatic quantification of fish states, making comparative studies possible.
- Open Access
- 12 June 2025
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 37 (5) , 1875-1890
COGNIMAN Digital Twin Architecture for Flexible Manufacturing
Despite recent progresses in smart manufacturing, existing architectures often fail to meet the comprehensive demands of modern manufacturing environments, such as flexibility, scalability, and seamless human-machine interaction. The COGNitive Industries for smart MANufacturing (COGNIMAN) architecture addresses these gaps by integrating advanced technologies with a focus on human-centric design. This article introduces COGNIMAN architecture as an essential pillar for Industry 5.0, enhancing operational efficiency through continuous monitoring, real-time data analysis, and predictive insights powered by machine learning. Its modular design optimizes resource utilization, reduces waste, and improves energy efficiency, aligning with eco-conscious manufacturing trends. By integrating sensors, robotics, digital twins, simulation, and AI, COGNIMAN offers a flexible, resilient, and sustainable platform adaptable to various manufacturing processes. The novelty of COGNIMAN architecture lies in its comprehensive approach, addressing key requirements such as flexibility, interoperability, maintainability, and adaptability. It fosters inclusive and safer working environments while supporting sustainable manufacturing practices. A case study in glass fiber manufacturing demonstrates COGNIMAN’s architecture applicability across different fields, enhancing the global competitiveness of European technology and manufacturing sectors.
- 12 June 2025
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 37 (5) , 1875-1890
Open AccessCOGNIMAN Digital Twin Architecture for Flexible Manufacturing
Despite recent progresses in smart manufacturing, existing architectures often fail to meet the comprehensive demands of modern manufacturing environments, such as flexibility, scalability, and seamless human-machine interaction. The COGNitive Industries for smart MANufacturing (COGNIMAN) architecture addresses these gaps by integrating advanced technologies with a focus on human-centric design. This article introduces COGNIMAN architecture as an essential pillar for Industry 5.0, enhancing operational efficiency through continuous monitoring, real-time data analysis, and predictive insights powered by machine learning. Its modular design optimizes resource utilization, reduces waste, and improves energy efficiency, aligning with eco-conscious manufacturing trends. By integrating sensors, robotics, digital twins, simulation, and AI, COGNIMAN offers a flexible, resilient, and sustainable platform adaptable to various manufacturing processes. The novelty of COGNIMAN architecture lies in its comprehensive approach, addressing key requirements such as flexibility, interoperability, maintainability, and adaptability. It fosters inclusive and safer working environments while supporting sustainable manufacturing practices. A case study in glass fiber manufacturing demonstrates COGNIMAN’s architecture applicability across different fields, enhancing the global competitiveness of European technology and manufacturing sectors.
- Open Access
- 12 May 2025
- Published by Springer Nature
- p. 35-49
Multimodal Computer Vision Techniques for Wooden Utility Pole Density Estimation with Contact-Free Sensing
In this work, we propose a novel way of performing remote inspection of wooden utility poles, based on state-of-the-art computer vision techniques. We collect regular pictures, LiDAR scans and hyperspectral scans from a set of five poles, and apply state-of-the-art deep learning algorithms to detect and crop the poles in the pictures and scans to extract features from these. We then study the correlations of these features with pole density and surface depth by employing linear models. Our results show that our features can be used to predict density and depth with good accuracy, a MAE between 500 and 900 for a density range of 14000–22000 (unitless) and a MAE of 0.04 for a depth range of 0.6–0.9. This study emphasises the potential of both remote sensing and state-of-the-art deep learning for wooden pole inspection, with techniques suitable for real-world automation.
- 12 May 2025
- Published by Springer Nature
- p. 35-49
Open AccessMultimodal Computer Vision Techniques for Wooden Utility Pole Density Estimation with Contact-Free Sensing
In this work, we propose a novel way of performing remote inspection of wooden utility poles, based on state-of-the-art computer vision techniques. We collect regular pictures, LiDAR scans and hyperspectral scans from a set of five poles, and apply state-of-the-art deep learning algorithms to detect and crop the poles in the pictures and scans to extract features from these. We then study the correlations of these features with pole density and surface depth by employing linear models. Our results show that our features can be used to predict density and depth with good accuracy, a MAE between 500 and 900 for a density range of 14000–22000 (unitless) and a MAE of 0.04 for a depth range of 0.6–0.9. This study emphasises the potential of both remote sensing and state-of-the-art deep learning for wooden pole inspection, with techniques suitable for real-world automation.