Geanina Silviana Banu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Geanina Silviana Banu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Iustin Priescu
Department of Informatics, Faculty of Informatics, Titu Maiorescu University, 040051 Bucharest, Romania
3 shared publications - Daniela Joita
Department of Informatics, Faculty of Informatics, Titu Maiorescu University, 040051 Bucharest, Romania
2 shared publications - Catalina Mihaela Priescu
Faculty of Automatic Control and Computer Science, National University of Science and Technology Politehnica Bucharest, 060042 Bucharest, Romania
1 shared publication - Ionica Oncioiu
Faculty of Economics and Business Administration, “Eugeniu Carada” Doctoral School of Economic Sciences, University of Craiova, 200585 Craiova, Romania
1 shared publication - Marius Irinel Banu
“Ferdinand I” Military Technical Academy , Bucharest , Romania
1 shared publication - Tatiana Corina Dosescu
“Titu Maiorescu” University , Bucharest , Romania
1 shared publication
Latest Publications
- Open Access
- 13 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1206
BCI-Inspired Adaptive Agents in Human–Robot Interaction: A Structural Framework for Coordinated Interaction Design
The accelerated integration of intelligent agents in user-centered digital environments has intensified research in the field of Human–Robot Interaction, especially regarding mechanisms for adaptive, intuitive, and cognitively aligned communication. The present study develops and empirically examines a structural model of BCI-inspired adaptive agents designed to support coordinated interaction in HRI contexts. The study analyzes users’ perceptions of standardized hypothetical interaction scenarios involving BCI-inspired adaptive digital agents, where BCI inspiration is conceptual and refers to adaptive architectures interpreting behavioral cues rather than direct neural signal acquisition. The proposed model integrates four main constructs—perceived technological innovation, user involvement, agent adaptivity, and digital synergy—and examines their associations with user satisfaction in digital collaborative environments. Data were collected through an anonymous questionnaire (N = 268) and analyzed using structural equation modeling with the PLS-SEM method. The structural model demonstrates substantial explanatory power, accounting for 66.8% of the variance in user satisfaction (R2 = 0.668). The study contributes by empirically supporting a scenario-based structural evaluation framework suitable for early-stage adaptive HRI system design. The results highlight the role of digital synergy in aligning innovation, engagement, and adaptive behavior in BCI-inspired adaptive HRI systems, providing directions for the design of adaptive robotic agents oriented toward coordinated interaction, user-centered integration, and responsible use in collaborative digital ecosystems.
- 13 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1206
Open AccessBCI-Inspired Adaptive Agents in Human–Robot Interaction: A Structural Framework for Coordinated Interaction Design
The accelerated integration of intelligent agents in user-centered digital environments has intensified research in the field of Human–Robot Interaction, especially regarding mechanisms for adaptive, intuitive, and cognitively aligned communication. The present study develops and empirically examines a structural model of BCI-inspired adaptive agents designed to support coordinated interaction in HRI contexts. The study analyzes users’ perceptions of standardized hypothetical interaction scenarios involving BCI-inspired adaptive digital agents, where BCI inspiration is conceptual and refers to adaptive architectures interpreting behavioral cues rather than direct neural signal acquisition. The proposed model integrates four main constructs—perceived technological innovation, user involvement, agent adaptivity, and digital synergy—and examines their associations with user satisfaction in digital collaborative environments. Data were collected through an anonymous questionnaire (N = 268) and analyzed using structural equation modeling with the PLS-SEM method. The structural model demonstrates substantial explanatory power, accounting for 66.8% of the variance in user satisfaction (R2 = 0.668). The study contributes by empirically supporting a scenario-based structural evaluation framework suitable for early-stage adaptive HRI system design. The results highlight the role of digital synergy in aligning innovation, engagement, and adaptive behavior in BCI-inspired adaptive HRI systems, providing directions for the design of adaptive robotic agents oriented toward coordinated interaction, user-centered integration, and responsible use in collaborative digital ecosystems.
- Open Access
- 1 June 2025
- Published by Walter de Gruyter GmbH in Land Forces Academy Review
- Vol. 30 (2) , 291-302
Prompt Engineering in Cybersecurity – Achieving Technological Edge
Prompt Engineering has emerged as a critical technique for optimizing interactions with Large Language Models (LLMs), enhancing their precision and effectiveness in various applications. This paper explores the role of structured prompting techniques in cybersecurity, focusing on their potential to improve threat detection, security automation, and incident response. By leveraging Chain-of-Thought (CoT) and Multimodal CoT prompting, the study evaluates how well-crafted prompts enhance LLM capabilities in analyzing network traffic, identifying phishing attempts, automating security reporting, and conducting forensic investigations. The findings demonstrate that structured prompts significantly improve LLM performance, enabling more accurate anomaly detection, faster security incident analysis, and enhanced cyber threat intelligence. Additionally, the study outlines a framework for integrating Prompt Engineering into cybersecurity workflows, illustrating its potential for AI-driven security monitoring and defense strategies. These insights contribute to the ongoing advancement of AI applications in cybersecurity, highlighting the transformative role of LLMs and Prompt Engineering in strengthening digital security measures.
- 1 June 2025
- Published by Walter de Gruyter GmbH in Land Forces Academy Review
- Vol. 30 (2) , 291-302
Open AccessPrompt Engineering in Cybersecurity – Achieving Technological Edge
Prompt Engineering has emerged as a critical technique for optimizing interactions with Large Language Models (LLMs), enhancing their precision and effectiveness in various applications. This paper explores the role of structured prompting techniques in cybersecurity, focusing on their potential to improve threat detection, security automation, and incident response. By leveraging Chain-of-Thought (CoT) and Multimodal CoT prompting, the study evaluates how well-crafted prompts enhance LLM capabilities in analyzing network traffic, identifying phishing attempts, automating security reporting, and conducting forensic investigations. The findings demonstrate that structured prompts significantly improve LLM performance, enabling more accurate anomaly detection, faster security incident analysis, and enhanced cyber threat intelligence. Additionally, the study outlines a framework for integrating Prompt Engineering into cybersecurity workflows, illustrating its potential for AI-driven security monitoring and defense strategies. These insights contribute to the ongoing advancement of AI applications in cybersecurity, highlighting the transformative role of LLMs and Prompt Engineering in strengthening digital security measures.
- 30 August 2024
- Published by Springer Nature
- p. 649-659
The Transformative Role of Large Language Models in Medicine
- 30 August 2024
- Published by Springer Nature
- p. 649-659
The Transformative Role of Large Language Models in Medicine