Nikolaos I. Dourvas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Nikolaos I. Dourvas has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Georgios Christou Sirakoulis
Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi Greece
4 shared publications - Andrew Adamatzky
Unconventional Computing Laboratory, University of the West of England, UK
3 shared publications Georgios Ch. Sirakoulis
Department of Electrical & Computer Engineering, Democritus University of Thrace, Xanthi, Greece
3 shared publications- Konstantinos Ioannidis
Centre for Research and Technology Hellas, Information Technologies Institute
3 shared publications Michail-Antisthenis I. Tsompanas
University of the West of England
2 shared publications- Stefanos Vrochidis
Center for Research and Technology Hellas
2 shared publications
Latest Publications
- Open Access
- 31 October 2026
- Published by Springer Nature
- p. 818-826
Enhanced Safety Criteria Catalogue for Urban and Secondary Roads
Within iDriving Horizon Europe project, the enhanced safety criteria catalogue for the assessment of safety on secondary and urban roads is developed. The project addresses the need for innovative approaches in road safety assessment, driven by the EU’s 2021–2030 policy and Vision Zero target. The paper presents holistic safety KPI framework that is building on top of the existing framework with the focus on the integration of digital KPIs, domain expertise from pilot project partners, and continuous feedback from end-users. The framework is structured into four categories, namely road users, vehicles, infrastructure, communication and traffic management. The novel concept of KPIs is that they are tailored to the specific needs of secondary and urban road networks. The real-time data integration, AI-driven analytics, and dynamic KPI based safety evaluation and visualization is enabled in the iDriving platform. Tangible societal benefits such as the reduction of collisions, lowering of maintenance costs, and alleviation of traffic congestion are aimed to be achieved through the usage of dynamic safety KPIs.
- 31 October 2026
- Published by Springer Nature
- p. 818-826
Open AccessEnhanced Safety Criteria Catalogue for Urban and Secondary Roads
Within iDriving Horizon Europe project, the enhanced safety criteria catalogue for the assessment of safety on secondary and urban roads is developed. The project addresses the need for innovative approaches in road safety assessment, driven by the EU’s 2021–2030 policy and Vision Zero target. The paper presents holistic safety KPI framework that is building on top of the existing framework with the focus on the integration of digital KPIs, domain expertise from pilot project partners, and continuous feedback from end-users. The framework is structured into four categories, namely road users, vehicles, infrastructure, communication and traffic management. The novel concept of KPIs is that they are tailored to the specific needs of secondary and urban road networks. The real-time data integration, AI-driven analytics, and dynamic KPI based safety evaluation and visualization is enabled in the iDriving platform. Tangible societal benefits such as the reduction of collisions, lowering of maintenance costs, and alleviation of traffic congestion are aimed to be achieved through the usage of dynamic safety KPIs.
- Open Access
- 27 September 2025
- Published by Elsevier in Data in Brief
- Vol. 63, 112101
SIAP: Synthetic dataset for maritime vessel risk profiling and illegal activity prediction
- 27 September 2025
- Published by Elsevier in Data in Brief
- Vol. 63, 112101
Open AccessSIAP: Synthetic dataset for maritime vessel risk profiling and illegal activity prediction
- 4 June 2025
- Published by Springer Nature
- p. 345-411
Design and Implementation of Cellular Automata Computing Architectures
- 4 June 2025
- Published by Springer Nature
- p. 345-411
Design and Implementation of Cellular Automata Computing Architectures
- Open Access
- 3 June 2025
- Published by Sociedade Brasileira de Computação
- p. 96-106
Digital Twin Development for Cultural Heritage Buildings: A Multimodal Approach to Simulating Energy Performance
Cultural heritage buildings represent invaluable historical and architectural assets, but their preservation often conflicts with the need for modern energy efficiency. This paper presents a novel framework for digital twin development that adopts a multimodal approach to provide an open-source environment of a CH building with the goal to simulate and optimize energy performance in heritage structures. By integrating diverse data modalities, such as structural analysis, environmental monitoring, and multimedia documentation, the proposed digital twin provides a comprehensive, dynamic representation of the building’s energy behavior. This approach enables more accurate simulations of energy performance, facilitating informed decision-making for sustainable retrofitting while respecting the unique constraints of cultural heritage conservation. The application of this framework in a real case study demonstrates the potential of multimodal digital twins to bridge the gap between preservation and energy efficiency, to increase immersiveness and to highlight their role in advancing sustainable management practices for heritage sites. The findings underscore the transformative potential of digital twin technology in fostering sustainable, data-driven solutions for cultural heritage conservation.
- 3 June 2025
- Published by Sociedade Brasileira de Computação
- p. 96-106
Open AccessDigital Twin Development for Cultural Heritage Buildings: A Multimodal Approach to Simulating Energy Performance
Cultural heritage buildings represent invaluable historical and architectural assets, but their preservation often conflicts with the need for modern energy efficiency. This paper presents a novel framework for digital twin development that adopts a multimodal approach to provide an open-source environment of a CH building with the goal to simulate and optimize energy performance in heritage structures. By integrating diverse data modalities, such as structural analysis, environmental monitoring, and multimedia documentation, the proposed digital twin provides a comprehensive, dynamic representation of the building’s energy behavior. This approach enables more accurate simulations of energy performance, facilitating informed decision-making for sustainable retrofitting while respecting the unique constraints of cultural heritage conservation. The application of this framework in a real case study demonstrates the potential of multimodal digital twins to bridge the gap between preservation and energy efficiency, to increase immersiveness and to highlight their role in advancing sustainable management practices for heritage sites. The findings underscore the transformative potential of digital twin technology in fostering sustainable, data-driven solutions for cultural heritage conservation.
- Open Access
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Nanotechnology
- Vol. 5, 163-172
Colloidal Spin Ice Cellular Automata for Logic Design
An engineered system that exhibits a variety of interesting properties, such as collective dynamics that are not inherited in their building blocks, is the artificial spin ice (ASI) meta-materials. The building block of such a system is a dipolar nanomagnet with sub-micrometer dimensions. These nanomagnets are arranged in specific designs usually in square or kagome shape and are coupled together by their magnetic interactions. With external magnetic fields, it is possible to create magnetic moments or monopoles that cause a frustration to the system. Because of the local interactions, those moments travel through the topology. The observation of such structures is a very challenging procedure, because of the extremely fast flipping process of the spins. This is why the researchers use mesoscopic systems with materials such as colloids or spheres of nanomagnets which are placed inside of islands in periodic lattices that generate frustration by design. The interactions between those nanomagnets are based on Coulomb forces and are usually modeled by Brownian equations. In this paper, we propose a simple yet effective Cellular Automata (CA) model that can describe effectively the dynamics between nanomagnets in a square lattice structure. The manipulation of the initial positions of nanomagnets via an external magnetic field and the movement of magnetic moments from one site to another are capable to create Boolean logic. Using the CA model we propose the design of logic gates, computing structures such as half adders and rewritable memory elements.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Nanotechnology
- Vol. 5, 163-172
Open AccessColloidal Spin Ice Cellular Automata for Logic Design
An engineered system that exhibits a variety of interesting properties, such as collective dynamics that are not inherited in their building blocks, is the artificial spin ice (ASI) meta-materials. The building block of such a system is a dipolar nanomagnet with sub-micrometer dimensions. These nanomagnets are arranged in specific designs usually in square or kagome shape and are coupled together by their magnetic interactions. With external magnetic fields, it is possible to create magnetic moments or monopoles that cause a frustration to the system. Because of the local interactions, those moments travel through the topology. The observation of such structures is a very challenging procedure, because of the extremely fast flipping process of the spins. This is why the researchers use mesoscopic systems with materials such as colloids or spheres of nanomagnets which are placed inside of islands in periodic lattices that generate frustration by design. The interactions between those nanomagnets are based on Coulomb forces and are usually modeled by Brownian equations. In this paper, we propose a simple yet effective Cellular Automata (CA) model that can describe effectively the dynamics between nanomagnets in a square lattice structure. The manipulation of the initial positions of nanomagnets via an external magnetic field and the movement of magnetic moments from one site to another are capable to create Boolean logic. Using the CA model we propose the design of logic gates, computing structures such as half adders and rewritable memory elements.
- Open Access
- 8 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (18) , 3806
Predicting Consumer Service Price Evolution during the COVID-19 Pandemic: An Optimized Machine Learning Approach
This research analyzes the impact of the COVID-19 pandemic on consumer service pricing within the European Union, focusing on the Transportation, Accommodation, and Food Service sectors. Our study employs various machine learning models, including multilayer perceptron, XGBoost, CatBoost, and random forest, along with genetic algorithms for comprehensive hyperparameter tuning and price evolution forecasting. We incorporate coronavirus cases and deaths as factors to enhance prediction accuracy. The dataset comprises monthly reports of COVID-19 cases and deaths, alongside managerial survey responses regarding company estimations. Applying genetic algorithms for hyperparameter optimization across all models results in significant enhancements, yielding optimized models that exhibit RMSE score reductions ranging from 3.35% to 5.67%. Additionally, the study demonstrates that XGBoost yields more accurate predictions, achieving an RMSE score of 17.07.
- 8 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (18) , 3806
Open AccessPredicting Consumer Service Price Evolution during the COVID-19 Pandemic: An Optimized Machine Learning Approach
This research analyzes the impact of the COVID-19 pandemic on consumer service pricing within the European Union, focusing on the Transportation, Accommodation, and Food Service sectors. Our study employs various machine learning models, including multilayer perceptron, XGBoost, CatBoost, and random forest, along with genetic algorithms for comprehensive hyperparameter tuning and price evolution forecasting. We incorporate coronavirus cases and deaths as factors to enhance prediction accuracy. The dataset comprises monthly reports of COVID-19 cases and deaths, alongside managerial survey responses regarding company estimations. Applying genetic algorithms for hyperparameter optimization across all models results in significant enhancements, yielding optimized models that exhibit RMSE score reductions ranging from 3.35% to 5.67%. Additionally, the study demonstrates that XGBoost yields more accurate predictions, achieving an RMSE score of 17.07.
- 19 March 2020
- Published by Springer Nature
- p. 445-456
Cellular Automata Model for Crowd Behavior Management in Airports
- 19 March 2020
- Published by Springer Nature
- p. 445-456
Cellular Automata Model for Crowd Behavior Management in Airports
- Open Access
- 9 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 98306-98318
Parallel Accelerated Virtual Physarum Lab Based on Cellular Automata Agents
Self-aware and self-expressive physical systems are inspiring new methodologies for engineering solutions of complex computing problems. Among many other examples, the slime mold Physarum Polycephalum exhibits self-awareness and self-expressiveness while adapting to changes in its dynamical environment and solving resource-consuming problems like shortest path, proximity graphs or optimization of transport networks. As such, the modeling of the slime mold’s behaviour is essential when designing bio-inspired algorithms and hardware prototypes. The goal of this paper is to combine one of the powerful parallel computational tools, Cellular Automata (CA) with the adaptive potential of Physarum slime mould. Namely, we propose a CA model and multi-agent approach to imitate the behaviour of the plasmodium. We then test the efficacy of the proposed model on graph problems such as the maze problem or the Traveling Salesman Problem (TSP). Finally, the virtual Physarum model is evaluated on a data set for pattern recognition purposes and achieves to form very effectively the letters of the alphabet, especially when compared with real experiments performed to prove the efficacy of the proposed model. Furthermore, in order to exploit the CA’s inherent parallelism and make the model’s responses faster, both GPU and hardware implementations are proposed and compared. As a result, an accelerated virtual lab is developed which uses a multi-agent CA model to describe the behavior of plasmodium and can be used as an intelligent, autonomous, self-adaptive system in various heterogeneous and unknown environments spanning from different types of graph problems up to real life-time applications.
- 9 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 98306-98318
Open AccessParallel Accelerated Virtual Physarum Lab Based on Cellular Automata Agents
Self-aware and self-expressive physical systems are inspiring new methodologies for engineering solutions of complex computing problems. Among many other examples, the slime mold Physarum Polycephalum exhibits self-awareness and self-expressiveness while adapting to changes in its dynamical environment and solving resource-consuming problems like shortest path, proximity graphs or optimization of transport networks. As such, the modeling of the slime mold’s behaviour is essential when designing bio-inspired algorithms and hardware prototypes. The goal of this paper is to combine one of the powerful parallel computational tools, Cellular Automata (CA) with the adaptive potential of Physarum slime mould. Namely, we propose a CA model and multi-agent approach to imitate the behaviour of the plasmodium. We then test the efficacy of the proposed model on graph problems such as the maze problem or the Traveling Salesman Problem (TSP). Finally, the virtual Physarum model is evaluated on a data set for pattern recognition purposes and achieves to form very effectively the letters of the alphabet, especially when compared with real experiments performed to prove the efficacy of the proposed model. Furthermore, in order to exploit the CA’s inherent parallelism and make the model’s responses faster, both GPU and hardware implementations are proposed and compared. As a result, an accelerated virtual lab is developed which uses a multi-agent CA model to describe the behavior of plasmodium and can be used as an intelligent, autonomous, self-adaptive system in various heterogeneous and unknown environments spanning from different types of graph problems up to real life-time applications.
- 27 April 2018
- Published by Springer Nature
- p. 199-237
Cellular Automata Applications in Shortest Path Problem
- 27 April 2018
- Published by Springer Nature
- p. 199-237
Cellular Automata Applications in Shortest Path Problem
- Open Access
Cellular Automata Applications in Shortest Path Problem
Cellular Automata (CAs) are computational models that can capture the essential features of systems in which global behavior emerges from the collective effect of simple components, which interact locally. During the last decades, CAs have been extensively used for mimicking several natural processes and systems to find fine solutions in many complex hard to solve computer science and engineering problems. Among them, the shortest path problem is one of the most pronounced and highly studied problems that scientists have been trying to tackle by using a plethora of methodologies and even unconventional approaches. The proposed solutions are mainly justified by their ability to provide a correct solution in a better time complexity than the renowned Dijkstra's algorithm. Although there is a wide variety regarding the algorithmic complexity of the algorithms suggested, spanning from simplistic graph traversal algorithms to complex nature inspired and bio-mimicking algorithms, in this chapter we focus on the successful application of CAs to shortest path problem as found in various diverse disciplines like computer science, swarm robotics, computer networks, decision science and biomimicking of biological organisms' behaviour. In particular, an introduction on the first CA-based algorithm tackling the shortest path problem is provided in detail. After the short presentation of shortest path algorithms arriving from the relaxization of the CAs principles, the application of the CA-based shortest path definition on the coordinated motion of swarm robotics is also introduced. Moreover, the CA based application of shortest path finding in computer networks is presented in brief. Finally, a CA that models exactly the behavior of a biological organism, namely the Physarum's behavior, finding the minimum-length path between two points in a labyrinth is given.
Open AccessCellular Automata Applications in Shortest Path Problem
Cellular Automata (CAs) are computational models that can capture the essential features of systems in which global behavior emerges from the collective effect of simple components, which interact locally. During the last decades, CAs have been extensively used for mimicking several natural processes and systems to find fine solutions in many complex hard to solve computer science and engineering problems. Among them, the shortest path problem is one of the most pronounced and highly studied problems that scientists have been trying to tackle by using a plethora of methodologies and even unconventional approaches. The proposed solutions are mainly justified by their ability to provide a correct solution in a better time complexity than the renowned Dijkstra's algorithm. Although there is a wide variety regarding the algorithmic complexity of the algorithms suggested, spanning from simplistic graph traversal algorithms to complex nature inspired and bio-mimicking algorithms, in this chapter we focus on the successful application of CAs to shortest path problem as found in various diverse disciplines like computer science, swarm robotics, computer networks, decision science and biomimicking of biological organisms' behaviour. In particular, an introduction on the first CA-based algorithm tackling the shortest path problem is provided in detail. After the short presentation of shortest path algorithms arriving from the relaxization of the CAs principles, the application of the CA-based shortest path definition on the coordinated motion of swarm robotics is also introduced. Moreover, the CA based application of shortest path finding in computer networks is presented in brief. Finally, a CA that models exactly the behavior of a biological organism, namely the Physarum's behavior, finding the minimum-length path between two points in a labyrinth is given.