Maria Trigka
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Maria Trigka has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Elias Dritsas
University of West Attica, Athens, Greece
66 shared publications - Phivos Mylonas
Department of Informatics and Computer Engineering, University of West Attica, 12243 Egaleo, Greece
13 shared publications - Andreas Kanavos
Department of Informatics, Ionian University, 49100 Corfu, Greece
5 shared publications - Gerasimos Vonitsanos
University of West Attica, Hellenic Graphic-Media Research Lab – GRAPHMEDLAB, Greece; Hellenic Open University, School of Applied Arts and Sustainable Design, Greece
5 shared publications - Spyros Sioutas
CEID, University of Patras
3 shared publications - Athanasios Tsakalidis
University of Patras
2 shared publications
Latest Publications
- 22 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 708
Affective large language models for mental health: Emotion modeling, multimodal intelligence, and ethical constraints
- 22 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 708
Affective large language models for mental health: Emotion modeling, multimodal intelligence, and ethical constraints
- 3 September 2026
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 22 (1) , 292
Big Data–driven machine learning for 6G communications: from algorithmic promises to system-level realities
- 3 September 2026
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 22 (1) , 292
Big Data–driven machine learning for 6G communications: from algorithmic promises to system-level realities
- 30 August 2026
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 19 (5) , 145
Intelligent agents: architectures, learning paradigms, deployment models, and applications
- 30 August 2026
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 19 (5) , 145
Intelligent agents: architectures, learning paradigms, deployment models, and applications
- Open Access
- 5 July 2026
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 59 (11)
Symmetry-aware learning in machine intelligence: architectural principles and deployment trade-offs
Symmetry-aware machine learning (ML) embeds invariance and equivariance constraints directly into model architectures, providing principled inductive biases that can improve generalization, sample efficiency, and alignment with data-generating processes. This survey presents a principled synthesis of symmetry-aware architectures, treating symmetry as the core architectural design axis, rather than as an auxiliary modeling property. We introduce a structured taxonomy of symmetry types by mapping discrete, continuous, and statistical group actions to their architectural realizations, including group-equivariant convolutions, equivariant graph networks and attention mechanisms, neural operators, and symmetry-constrained generative models. Beyond architectural categorization, the survey examines how symmetry constraints shape the representation capacity, training stability, robustness, and computational behavior. Representative deployment scenarios are analyzed across molecular modeling, scientific ML, three-dimensional (3D) vision, and relational reasoning, with explicit attention to symmetry-aligned benchmarks, evaluation protocols, performance regimes, inference costs, hardware compatibility, and interactions with low-precision quantization. In addition to conceptual synthesis, the survey consolidates representative empirical indicators reported in the literature, including benchmark outcomes and computational complexity characteristics across major symmetry-aware-architecture families. Across multiple domains, reported studies frequently indicate improved sample efficiency, robustness under symmetry-preserving transformations, and reduced prediction error compared with unconstrained models when symmetry assumptions align with the underlying data-generating processes. In contrast to prior studies that emphasize abstract formalism or isolated domains, this work integrates theoretical foundations, architectural mechanisms, empirical evidence, and system-level considerations into a unified analytical framework, highlighting emerging directions in scalable symmetry-aware learning and hardware-aware co-design.
- 5 July 2026
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 59 (11)
Open AccessSymmetry-aware learning in machine intelligence: architectural principles and deployment trade-offs
Symmetry-aware machine learning (ML) embeds invariance and equivariance constraints directly into model architectures, providing principled inductive biases that can improve generalization, sample efficiency, and alignment with data-generating processes. This survey presents a principled synthesis of symmetry-aware architectures, treating symmetry as the core architectural design axis, rather than as an auxiliary modeling property. We introduce a structured taxonomy of symmetry types by mapping discrete, continuous, and statistical group actions to their architectural realizations, including group-equivariant convolutions, equivariant graph networks and attention mechanisms, neural operators, and symmetry-constrained generative models. Beyond architectural categorization, the survey examines how symmetry constraints shape the representation capacity, training stability, robustness, and computational behavior. Representative deployment scenarios are analyzed across molecular modeling, scientific ML, three-dimensional (3D) vision, and relational reasoning, with explicit attention to symmetry-aligned benchmarks, evaluation protocols, performance regimes, inference costs, hardware compatibility, and interactions with low-precision quantization. In addition to conceptual synthesis, the survey consolidates representative empirical indicators reported in the literature, including benchmark outcomes and computational complexity characteristics across major symmetry-aware-architecture families. Across multiple domains, reported studies frequently indicate improved sample efficiency, robustness under symmetry-preserving transformations, and reduced prediction error compared with unconstrained models when symmetry assumptions align with the underlying data-generating processes. In contrast to prior studies that emphasize abstract formalism or isolated domains, this work integrates theoretical foundations, architectural mechanisms, empirical evidence, and system-level considerations into a unified analytical framework, highlighting emerging directions in scalable symmetry-aware learning and hardware-aware co-design.
- 3 June 2026
- Published by Springer Nature
- p. 360-383
EEG-Based Engagement Prediction in e-Learning Environments Using Machine Learning Techniques
- 3 June 2026
- Published by Springer Nature
- p. 360-383
EEG-Based Engagement Prediction in e-Learning Environments Using Machine Learning Techniques
- Open Access
- 13 May 2026
- Published by MDPI AG in Electronics
- Vol. 15 (10) , 2074
Resource-Aware Deep Reinforcement Learning for Joint Caching and Service Placement in Multi-Access Edge Computing
Multi-access edge computing (MEC) enables low-latency service provisioning by placing computation closer to mobile users. However, efficient service placement remains challenging due to dynamic user mobility, limited edge resources, and the need to manage service migration as system conditions evolve. This study proposes a resource-aware, cache-enabled service placement framework based on deep reinforcement learning (DRL) to dynamically select edge nodes for hosting services. The approach jointly considers user location, resource availability, and cache status within a unified decision framework, enabling efficient and adaptive service placement in dynamic MEC environments. The problem is formulated as a Markov decision process (MDP) and solved using deep Q-network (DQN)-based methods, with a reward function that balances latency, resource utilization, and cache efficiency. The proposed framework is evaluated in a simulated MEC environment with mobile users and multiple edge nodes. Experimental results demonstrate that the approach achieves lower latency, improved resource utilization, and enhanced cache efficiency compared to baseline strategies. Among the evaluated models, the dueling double deep Q-network (DDDQN) achieves the most balanced overall performance. The proposed framework provides an adaptive and scalable solution for service management in dynamic MEC environments.
- 13 May 2026
- Published by MDPI AG in Electronics
- Vol. 15 (10) , 2074
Open AccessResource-Aware Deep Reinforcement Learning for Joint Caching and Service Placement in Multi-Access Edge Computing
Multi-access edge computing (MEC) enables low-latency service provisioning by placing computation closer to mobile users. However, efficient service placement remains challenging due to dynamic user mobility, limited edge resources, and the need to manage service migration as system conditions evolve. This study proposes a resource-aware, cache-enabled service placement framework based on deep reinforcement learning (DRL) to dynamically select edge nodes for hosting services. The approach jointly considers user location, resource availability, and cache status within a unified decision framework, enabling efficient and adaptive service placement in dynamic MEC environments. The problem is formulated as a Markov decision process (MDP) and solved using deep Q-network (DQN)-based methods, with a reward function that balances latency, resource utilization, and cache efficiency. The proposed framework is evaluated in a simulated MEC environment with mobile users and multiple edge nodes. Experimental results demonstrate that the approach achieves lower latency, improved resource utilization, and enhanced cache efficiency compared to baseline strategies. Among the evaluated models, the dueling double deep Q-network (DDDQN) achieves the most balanced overall performance. The proposed framework provides an adaptive and scalable solution for service management in dynamic MEC environments.
- 22 February 2026
- Published by Springer Nature in AI and Ethics
- Vol. 6 (2) , 163
Multidimensional challenges of affective computing in virtual and augmented reality: ethical, technical, and social implications
- 22 February 2026
- Published by Springer Nature in AI and Ethics
- Vol. 6 (2) , 163
Multidimensional challenges of affective computing in virtual and augmented reality: ethical, technical, and social implications
- Top Cited Papers
- 24 January 2026
- Published by Elsevier in Computer Science Review
- Vol. 60
Advances in geospatial artificial intelligence for remote sensing applications
- 24 January 2026
- Published by Elsevier in Computer Science Review
- Vol. 60
Top Cited PapersAdvances in geospatial artificial intelligence for remote sensing applications
- Open Access
- 22 January 2026
- Published by Elsevier in Annual Reviews in Control
- Vol. 61
Control theory in the era of intelligent systems: Applications, trends, and future directions
- 22 January 2026
- Published by Elsevier in Annual Reviews in Control
- Vol. 61
Open AccessControl theory in the era of intelligent systems: Applications, trends, and future directions