George Alex Stelea
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
George Alex Stelea has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Dan Robu
Department of Electronics and Computers “Transilvania” University of Brasov, Romania
4 shared publications - Florin Sandu
Department of Electronics and Computers “Transilvania” University of Brasov, Romania
4 shared publications - Vlad Popescu
Transilvania University of Braşov, Romania
4 shared publications - Maurizio Murroni
University of Cagliari, Italy
3 shared publications - Vlad Fernoaga
Faculty of Electrical Engineering and Computer Science, Transilvania University, Brasov 500036, Romania
3 shared publications Florin Sandu
Department of Electronics and Computers, “Transilvania” University, Brasov, Romania
2 shared publications
Latest Publications
- Open Access
- 29 August 2025
- Published by MDPI AG in Education Sciences
- Vol. 15 (9) , 1125
AccessiLearnAI: An Accessibility-First, AI-Powered E-Learning Platform for Inclusive Education
Online education has become an important channel for extensive, inclusive and flexible learning experiences. However, significant gaps persist in providing truly accessible, personalized and adaptable e-learning environments, especially for students with disabilities, varied language backgrounds, or limited bandwidth. This paper presents AccessiLearnAI, an AI-driven platform, which converges accessibility-first design, multi-format content delivery, advanced personalization, and Progressive Web App (PWA) offline capabilities. Our solution is compliant with semantic HTML5 and ARIA standards, and incorporates features such as automatic alt-text generation for images using Large Language Models (LLMs), real-time functionality for summarization, translation, and text-to-speech capabilities. The platform, built on top of a modular MVC and microservices-based architecture, also integrates robust security, GDPR-aligned data protection, and a human-in-the-loop to ensure the accuracy and reliability of AI-generated outputs. Early evaluations indicate that AccessiLearnAI improves engagement and learning outcomes across multiple ranges of users, suggesting that responsible AI and universal design can successfully coexist to bring equity through digital education.
- 29 August 2025
- Published by MDPI AG in Education Sciences
- Vol. 15 (9) , 1125
Open AccessAccessiLearnAI: An Accessibility-First, AI-Powered E-Learning Platform for Inclusive Education
Online education has become an important channel for extensive, inclusive and flexible learning experiences. However, significant gaps persist in providing truly accessible, personalized and adaptable e-learning environments, especially for students with disabilities, varied language backgrounds, or limited bandwidth. This paper presents AccessiLearnAI, an AI-driven platform, which converges accessibility-first design, multi-format content delivery, advanced personalization, and Progressive Web App (PWA) offline capabilities. Our solution is compliant with semantic HTML5 and ARIA standards, and incorporates features such as automatic alt-text generation for images using Large Language Models (LLMs), real-time functionality for summarization, translation, and text-to-speech capabilities. The platform, built on top of a modular MVC and microservices-based architecture, also integrates robust security, GDPR-aligned data protection, and a human-in-the-loop to ensure the accuracy and reliability of AI-generated outputs. Early evaluations indicate that AccessiLearnAI improves engagement and learning outcomes across multiple ranges of users, suggesting that responsible AI and universal design can successfully coexist to bring equity through digital education.
- Open Access
- 21 June 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (7) , 274
Accessible IoT Dashboard Design with AI-Enhanced Descriptions for Visually Impaired Users
The proliferation of the Internet of Things (IoT) has led to an abundance of data streams and real-time dashboards in domains such as smart cities, healthcare, manufacturing, and agriculture. However, many current IoT dashboards emphasize complex visualizations with minimal textual cues, posing significant barriers to users with visual impairments who rely on screen readers or other assistive technologies. This paper presents AccessiDashboard, a web-based IoT dashboard platform that prioritizes accessible design from the ground up. The system uses semantic HTML5 and WAI-ARIA compliance to ensure that screen readers can accurately interpret and navigate the interface. In addition to standard chart presentations, AccessiDashboard automatically generates long descriptions of graphs and visual elements, offering a text-first alternative interface for non-visual data exploration. The platform supports multi-modal data consumption (visual charts, bullet lists, tables, and narrative descriptions) and leverages Large Language Models (LLMs) to produce context-aware textual representations of sensor data. A privacy-by-design approach is adopted for the AI integration to address ethical and regulatory concerns. Early evaluation suggests that AccessiDashboard reduces cognitive and navigational load for users with vision disabilities, demonstrating its potential as a blueprint for future inclusive IoT monitoring solutions.
- 21 June 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (7) , 274
Open AccessAccessible IoT Dashboard Design with AI-Enhanced Descriptions for Visually Impaired Users
The proliferation of the Internet of Things (IoT) has led to an abundance of data streams and real-time dashboards in domains such as smart cities, healthcare, manufacturing, and agriculture. However, many current IoT dashboards emphasize complex visualizations with minimal textual cues, posing significant barriers to users with visual impairments who rely on screen readers or other assistive technologies. This paper presents AccessiDashboard, a web-based IoT dashboard platform that prioritizes accessible design from the ground up. The system uses semantic HTML5 and WAI-ARIA compliance to ensure that screen readers can accurately interpret and navigate the interface. In addition to standard chart presentations, AccessiDashboard automatically generates long descriptions of graphs and visual elements, offering a text-first alternative interface for non-visual data exploration. The platform supports multi-modal data consumption (visual charts, bullet lists, tables, and narrative descriptions) and leverages Large Language Models (LLMs) to produce context-aware textual representations of sensor data. A privacy-by-design approach is adopted for the AI integration to address ethical and regulatory concerns. Early evaluation suggests that AccessiDashboard reduces cognitive and navigational load for users with vision disabilities, demonstrating its potential as a blueprint for future inclusive IoT monitoring solutions.
- Open Access
- 5 February 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (2) , 67
When Cybersecurity Meets Accessibility: A Holistic Development Architecture for Inclusive Cyber-Secure Web Applications and Websites
In today’s technology-centric era, digital transformation has made accessibility and cybersecurity critical components for developing inclusive web applications that are essential in daily operations. However, current development models often treat accessibility and cybersecurity separately, leading to solutions that may excel in one area while lacking in the other. This paper addresses this gap by proposing the Holistic Security and Accessibility Layered Architecture (HSALA), a novel architectural model that integrates accessibility and cybersecurity throughout the development process. HSALA consists of five interconnected layers, each paired with a corresponding security layer, ensuring that both accessibility and security are embedded at every level. We conduct a theoretical and analytical case study comparing HSALA with the traditional three-layered architecture, demonstrating HSALA’s superiority in addressing contemporary challenges related to accessibility, cybersecurity, scalability, and user experience. The findings indicate that HSALA provides a robust framework for developing secure and inclusive web applications, promoting a more equitable digital ecosystem. We outline a roadmap for future work, including empirical validation and practical implementation strategies. HSALA represents a significant advancement in web application development, fostering inclusivity and trust in an increasingly digital society.
- 5 February 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (2) , 67
Open AccessWhen Cybersecurity Meets Accessibility: A Holistic Development Architecture for Inclusive Cyber-Secure Web Applications and Websites
In today’s technology-centric era, digital transformation has made accessibility and cybersecurity critical components for developing inclusive web applications that are essential in daily operations. However, current development models often treat accessibility and cybersecurity separately, leading to solutions that may excel in one area while lacking in the other. This paper addresses this gap by proposing the Holistic Security and Accessibility Layered Architecture (HSALA), a novel architectural model that integrates accessibility and cybersecurity throughout the development process. HSALA consists of five interconnected layers, each paired with a corresponding security layer, ensuring that both accessibility and security are embedded at every level. We conduct a theoretical and analytical case study comparing HSALA with the traditional three-layered architecture, demonstrating HSALA’s superiority in addressing contemporary challenges related to accessibility, cybersecurity, scalability, and user experience. The findings indicate that HSALA provides a robust framework for developing secure and inclusive web applications, promoting a more equitable digital ecosystem. We outline a roadmap for future work, including empirical validation and practical implementation strategies. HSALA represents a significant advancement in web application development, fostering inclusivity and trust in an increasingly digital society.
- Open Access
- 20 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 153578-153588
From Things to Services: A Social IoT Approach for Tourist Service Management
In the context of Internet of Things (IoT), the cooperation and synergy between varied and disparate communicating objects is strained by trustworthiness, confidentiality and interoperability concerns. These restrictions can limit the development of IoT-based applications especially considering the emergent boost in the number of communicating objects and their growing itinerant nature in a collective service context. A new perspective arises with the paradigm of Social Internet of Things (SIoT), that relies on the implementation of semi-independent communicating objects with cooperation assessed by social relations and social feed-back. In this article, we present the development and expansion of the IoT concept towards SIoT in the context of the interactions between tourist services as communicating objects. As a proof-of-concept we propose a composition of services as virtualized social objects and the interaction between them, by taking into consideration the balance, trustworthiness, cooperation and synergy of services. Furthermore we present a solution to integrate also accessibility in SIoT services. The presented concept is presented using a demonstrator build for tourist services.
- 20 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 153578-153588
Open AccessFrom Things to Services: A Social IoT Approach for Tourist Service Management
In the context of Internet of Things (IoT), the cooperation and synergy between varied and disparate communicating objects is strained by trustworthiness, confidentiality and interoperability concerns. These restrictions can limit the development of IoT-based applications especially considering the emergent boost in the number of communicating objects and their growing itinerant nature in a collective service context. A new perspective arises with the paradigm of Social Internet of Things (SIoT), that relies on the implementation of semi-independent communicating objects with cooperation assessed by social relations and social feed-back. In this article, we present the development and expansion of the IoT concept towards SIoT in the context of the interactions between tourist services as communicating objects. As a proof-of-concept we propose a composition of services as virtualized social objects and the interaction between them, by taking into consideration the balance, trustworthiness, cooperation and synergy of services. Furthermore we present a solution to integrate also accessibility in SIoT services. The presented concept is presented using a demonstrator build for tourist services.
- 11 August 2019
- Published by Springer Nature
- p. 361-372
Enhanced Resource Management for Web Based Thin Clients Using Cross-Platform Progressive Offline Capabilities
- 11 August 2019
- Published by Springer Nature
- p. 361-372
Enhanced Resource Management for Web Based Thin Clients Using Cross-Platform Progressive Offline Capabilities
- Open Access
- 24 May 2019
- Published by Henri Coanda Air Force Academy in Review of the Air Force Academy
- Vol. 17 (1) , 71-78
MOBILE ACCESSIBLE RICH INTERNET WEB APPLICATION ENHANCED WITH AMP PUBLISHING TECHNOLOGY
- 24 May 2019
- Published by Henri Coanda Air Force Academy in Review of the Air Force Academy
- Vol. 17 (1) , 71-78
Open AccessMOBILE ACCESSIBLE RICH INTERNET WEB APPLICATION ENHANCED WITH AMP PUBLISHING TECHNOLOGY
- 19 April 2019
- Published by Romania ADL Association
INTELLIGENT EDUCATION ASSISTANT POWERED BY CHATBOTS
Over the last decade, the technology advancements were quickly absorbed and integrated into education processes and eLearning which enabled the development of efficient and innovative solutions able to act as customer tailored learning resources. One of the most ground-breaking innovations in the eLearning field is the integration of Chatbots technology into teaching experience, which acts as an intelligent bridge between education and technology. Chatbots technology can be used in a wide spectrum of fields due to its flexibility and ability to adapt to the pace at which each individual feels comfortable, without causing overwhelming or exhaustion. This paper aims to blend e-Assisted learning and communication into classrooms, introducing Chatbots as real-time educational assistants for the teacher - they are designed to distribute interactivity with students and to manage it at individualized level. This approach adds a highly increased degree of interactivity and personalization to the learning experience, aspects which are critical from the student point of view as each individual has its own learning and understanding capabilities. The authors combined modern software technologies such as Cloud based development, micro-services, Java technologies and Chatbots to create an automated closed loop for the teaching pace and adaptive complexity in a classroom. The proposed solution avoids putting the teacher in a secondary position, shadowed by technology - it rather empowers him with e-Assistants that give him access to a real time and relevant statistic of individual students’ understanding level - a valuable feedback for personalized education which leads to an improved mentorship quality.
- 19 April 2019
- Published by Romania ADL Association
INTELLIGENT EDUCATION ASSISTANT POWERED BY CHATBOTS
Over the last decade, the technology advancements were quickly absorbed and integrated into education processes and eLearning which enabled the development of efficient and innovative solutions able to act as customer tailored learning resources. One of the most ground-breaking innovations in the eLearning field is the integration of Chatbots technology into teaching experience, which acts as an intelligent bridge between education and technology. Chatbots technology can be used in a wide spectrum of fields due to its flexibility and ability to adapt to the pace at which each individual feels comfortable, without causing overwhelming or exhaustion. This paper aims to blend e-Assisted learning and communication into classrooms, introducing Chatbots as real-time educational assistants for the teacher - they are designed to distribute interactivity with students and to manage it at individualized level. This approach adds a highly increased degree of interactivity and personalization to the learning experience, aspects which are critical from the student point of view as each individual has its own learning and understanding capabilities. The authors combined modern software technologies such as Cloud based development, micro-services, Java technologies and Chatbots to create an automated closed loop for the teaching pace and adaptive complexity in a classroom. The proposed solution avoids putting the teacher in a secondary position, shadowed by technology - it rather empowers him with e-Assistants that give him access to a real time and relevant statistic of individual students’ understanding level - a valuable feedback for personalized education which leads to an improved mentorship quality.
- Open Access
When Social Networks Meet D2D Communications: A Survey
In the last few years, one of the main characteristics of the current technological development is the constantly increasing need for data exchange among various types of devices, both mobile and fixed. Within this context, the direct communications between devices has the potential to create new, location-based peer-to-peer applications and services, as well as to help offload traffic from the congested traditional cellular networks. The main hurdles for this kind of Device to Device (D2D) communications are throughput, spectral efficiency, latency and fairness. Most of these hurdles can be overcome by the use of the new Social IoT (SIoT) paradigm, of things and people involved together in the network, guided autonomously by social relationships following the rules set by their owners. This paper aims to investigate the state of the art of socially-driven D2D communications. Upon an initial analysis, we perform an in-deep literature investigation of the main directions in which social ties can improve D2D communication, draw conclusions and identify the research topics left open.
Open AccessWhen Social Networks Meet D2D Communications: A Survey
In the last few years, one of the main characteristics of the current technological development is the constantly increasing need for data exchange among various types of devices, both mobile and fixed. Within this context, the direct communications between devices has the potential to create new, location-based peer-to-peer applications and services, as well as to help offload traffic from the congested traditional cellular networks. The main hurdles for this kind of Device to Device (D2D) communications are throughput, spectral efficiency, latency and fairness. Most of these hurdles can be overcome by the use of the new Social IoT (SIoT) paradigm, of things and people involved together in the network, guided autonomously by social relationships following the rules set by their owners. This paper aims to investigate the state of the art of socially-driven D2D communications. Upon an initial analysis, we perform an in-deep literature investigation of the main directions in which social ties can improve D2D communication, draw conclusions and identify the research topics left open.
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 398-403
OCR-based Solution for The Integration of Legacy And-Or Non-Electric Counters in Cloud Smart Grids
Optical Character Recognition (OCR) can provide tele-measurement for legacy utility meters (water, natural gas, electricity etc) and can be accepted as a low-cost extension for the capabilities of these counters and for their time of life. On the other side, the “galvanic separation” provided by optical acquisition of displayed counter values offers the confidence of secure reading - for natural gas meters and similar instruments. Our cost-effective solution enables simple snapshots of counters displays (with simple devices like an “ArdtrCarn” - camera for Arduino embedded solutions), local “edge computing” for image packing (in. BMP format) and tele-transmission via the WiFi hot-spot of the intelligent building. At the server-side, National Instruments software sub-systems - NI Vision Development Module and LabView- provide OCR and cloud aggregation of measured values. Our solution is related to a research project for cloud-based smart metering (the LabVIEW sub-system belongs to the communications work-package). Specific to our contribution is the re-balancing of local and centralized processing, involving an assisted learning phase for the OCR.
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 398-403
OCR-based Solution for The Integration of Legacy And-Or Non-Electric Counters in Cloud Smart Grids
Optical Character Recognition (OCR) can provide tele-measurement for legacy utility meters (water, natural gas, electricity etc) and can be accepted as a low-cost extension for the capabilities of these counters and for their time of life. On the other side, the “galvanic separation” provided by optical acquisition of displayed counter values offers the confidence of secure reading - for natural gas meters and similar instruments. Our cost-effective solution enables simple snapshots of counters displays (with simple devices like an “ArdtrCarn” - camera for Arduino embedded solutions), local “edge computing” for image packing (in. BMP format) and tele-transmission via the WiFi hot-spot of the intelligent building. At the server-side, National Instruments software sub-systems - NI Vision Development Module and LabView- provide OCR and cloud aggregation of measured values. Our solution is related to a research project for cloud-based smart metering (the LabVIEW sub-system belongs to the communications work-package). Specific to our contribution is the re-balancing of local and centralized processing, involving an assisted learning phase for the OCR.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 397-402
Communication Solutions for Power Measurement in the Cloud
Development in both embedded systems and industrial communications brings a new challenge in re-balancing Edge computing and Cloud computing, particularly in the Smart Grids. This paper presents two sets of solutions for intelligent electricity “Cloud-counters” with local power measurement and with the tele-transmission of acquired voltage and current samples for the central active and reactive power computation in a smart-metering Cloud server with virtual instrumentation capabilities. Both solutions are using low-cost Wi-Fi interfacing, TCP transmission and centralized data logging and analytics based on National Instruments LabVIEW and DIAdem interoperability. For the transmission of data between the processing and the analytics layer a database was used as interface. DIAdem is able to retrieve raw information about measured data form the database and correlates this with attached meta information like timestamp and device MAC address. The limitations in the length of TCP transmission units are dealt with a quasi-PLL computation of the exact number of samples/period and a special time-domain formula of the reactive power involving the Hilbert transform of the voltage.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 397-402
Communication Solutions for Power Measurement in the Cloud
Development in both embedded systems and industrial communications brings a new challenge in re-balancing Edge computing and Cloud computing, particularly in the Smart Grids. This paper presents two sets of solutions for intelligent electricity “Cloud-counters” with local power measurement and with the tele-transmission of acquired voltage and current samples for the central active and reactive power computation in a smart-metering Cloud server with virtual instrumentation capabilities. Both solutions are using low-cost Wi-Fi interfacing, TCP transmission and centralized data logging and analytics based on National Instruments LabVIEW and DIAdem interoperability. For the transmission of data between the processing and the analytics layer a database was used as interface. DIAdem is able to retrieve raw information about measured data form the database and correlates this with attached meta information like timestamp and device MAC address. The limitations in the length of TCP transmission units are dealt with a quasi-PLL computation of the exact number of samples/period and a special time-domain formula of the reactive power involving the Hilbert transform of the voltage.