Bilal Said
Research Subjects
Bilal Said has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
Lilia Cheniti-Belcadhi
Higher Institution of Computer Science and Communication Techniques, University of Sousse,Tunisia
4 shared publicationsGhada A. El Khayat
Inf. Res. Inst., Alexandria, Egypt
3 shared publicationsGhada El Khayat
3 shared publications- Hugo Bruneliere
IMT Atlantique, LS2N (UMR CNRS 6004), Nantes, France
2 shared publications - Khaleel Mershad
Lebanese American University
2 shared publications Lilia Cheniti
2 shared publications
Latest Publications
- Open Access
- 3 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 188-199
Towards LLM-Assisted Business Process Modeling in an Industrial Modeling Tool: An Experience Report
Business Process Modeling (BPM) is a key and complex activity in Software and Systems Engineering. As a consequence, any relevant assistance integrated into the BPM tooling can be highly beneficial. Historically, Natural Language Processing (NLP) techniques have already been used in this context. However, the recent developments around Large Language Models (LLMs) offer promising new perspectives. In this paper, we report on our practical experience of integrating state-of-the-art LLMs within the industrial modeling tool Modelio. In particular, we experiment with the automated generation of BPMN models from natural-language instructions. To this end, we consider two different solutions: 1) The direct generation of BPMN creation scripts that call the modeling tool API; 2) The generation of intermediate representations that use a BPMN helper library. We first validate our approach with 7 industrial partners on 24 scenarios from the MATISSE collaborative project. In addition, we evaluate this approach with 3 different LLMs across 55 BPM scenarios from an open dataset. We demonstrate that using an intermediate representation (expressed in a compact DSL) globally improves performance, especially in more complex cases. We also share practical lessons learned and guidelines for the potential adoption of our approach by practitioners and researchers.
- 3 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 188-199
Open AccessTowards LLM-Assisted Business Process Modeling in an Industrial Modeling Tool: An Experience Report
Business Process Modeling (BPM) is a key and complex activity in Software and Systems Engineering. As a consequence, any relevant assistance integrated into the BPM tooling can be highly beneficial. Historically, Natural Language Processing (NLP) techniques have already been used in this context. However, the recent developments around Large Language Models (LLMs) offer promising new perspectives. In this paper, we report on our practical experience of integrating state-of-the-art LLMs within the industrial modeling tool Modelio. In particular, we experiment with the automated generation of BPMN models from natural-language instructions. To this end, we consider two different solutions: 1) The direct generation of BPMN creation scripts that call the modeling tool API; 2) The generation of intermediate representations that use a BPMN helper library. We first validate our approach with 7 industrial partners on 24 scenarios from the MATISSE collaborative project. In addition, we evaluate this approach with 3 different LLMs across 55 BPM scenarios from an open dataset. We demonstrate that using an intermediate representation (expressed in a compact DSL) globally improves performance, especially in more complex cases. We also share practical lessons learned and guidelines for the potential adoption of our approach by practitioners and researchers.
- Open Access
- 2 August 2024
- Published by Elsevier in Journal of Systems and Software
- Vol. 217
An architecture for model-based and intelligent automation in DevOps
- 2 August 2024
- Published by Elsevier in Journal of Systems and Software
- Vol. 217
Open AccessAn architecture for model-based and intelligent automation in DevOps
- 12 January 2022
- Published by Springer Nature in Education and Information Technologies
- Vol. 27 (4) , 4955-4985
DIAMOND: A tool for monitoring the participation of students in online lectures
The principle of traditional education has transformed fundamentally within the last few years. The growth of new computer and communication technologies has provided learners with access to a variety of quality online education. Many educational institutions have shifted partially or completely to distance learning and online lectures as their major instruction methods. With these new models, various difficulties related to classroom management and students’ monitoring during online lectures face many instructors worldwide. In addition, educational administrators, such as school principals and university deans, find it very difficult to assure that students are participating and actively engaging during online lectures. In this paper, we present a framework that can be utilized to monitor online lectures and deduce important figures, such as the degree of students’ involvement, the percentage of students who are participating, and the amount of engagement of each student during each lecture. The proposed system analyzes the recorded lectures and performs voice diarization on the audio signals to produce the required outputs. The system was tested during five online courses in multiple majors. The results illustrate the importance of monitoring the online lectures of distance learning courses to ensure satisfactory students’ participation.
- 12 January 2022
- Published by Springer Nature in Education and Information Technologies
- Vol. 27 (4) , 4955-4985
DIAMOND: A tool for monitoring the participation of students in online lectures
The principle of traditional education has transformed fundamentally within the last few years. The growth of new computer and communication technologies has provided learners with access to a variety of quality online education. Many educational institutions have shifted partially or completely to distance learning and online lectures as their major instruction methods. With these new models, various difficulties related to classroom management and students’ monitoring during online lectures face many instructors worldwide. In addition, educational administrators, such as school principals and university deans, find it very difficult to assure that students are participating and actively engaging during online lectures. In this paper, we present a framework that can be utilized to monitor online lectures and deduce important figures, such as the degree of students’ involvement, the percentage of students who are participating, and the amount of engagement of each student during each lecture. The proposed system analyzes the recorded lectures and performs voice diarization on the audio signals to produce the required outputs. The system was tested during five online courses in multiple majors. The results illustrate the importance of monitoring the online lectures of distance learning courses to ensure satisfactory students’ participation.
- Open Access
- 26 October 2021
- Published by Springer Nature in Education and Information Technologies
- Vol. 27 (4) , 4501-4520
What do you mean by learning lab?
Digital and innovation competencies are nowadays highly required for students and faculty members in higher education institutions. We therefore need environments that incubate innovative learning scenarios to develop these competencies. We conducted a design-based research with the dual objective to develop learning labs in four universities and to document the design and implementation process and the addressed challenges. In this paper, we describe the concept of learning lab and the process of its setting up based on the experiments and observations conducted in the four learning labs in Lebanon, Egypt, Tunisia and Switzerland. A learning lab is defined as a physical, digital and human space for observation, experimentation and evaluation, to rethink and enrich learning and teaching attitudes and practices at the university. A learning lab is an incubator of pedagogical innovation and digital learning structured on three dimensions: spaces, activities and communities. We also identify the main challenges for the design and implementation of a learning lab. These challenges consist of the institutionnalisation of the learning lab and building, growing and nurturing a learning community.
- 26 October 2021
- Published by Springer Nature in Education and Information Technologies
- Vol. 27 (4) , 4501-4520
Open AccessWhat do you mean by learning lab?
Digital and innovation competencies are nowadays highly required for students and faculty members in higher education institutions. We therefore need environments that incubate innovative learning scenarios to develop these competencies. We conducted a design-based research with the dual objective to develop learning labs in four universities and to document the design and implementation process and the addressed challenges. In this paper, we describe the concept of learning lab and the process of its setting up based on the experiments and observations conducted in the four learning labs in Lebanon, Egypt, Tunisia and Switzerland. A learning lab is defined as a physical, digital and human space for observation, experimentation and evaluation, to rethink and enrich learning and teaching attitudes and practices at the university. A learning lab is an incubator of pedagogical innovation and digital learning structured on three dimensions: spaces, activities and communities. We also identify the main challenges for the design and implementation of a learning lab. These challenges consist of the institutionnalisation of the learning lab and building, growing and nurturing a learning community.
- 1 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Utilizing Roadside Units and Software Defined Networking to Route Packets Efficiently in Internet of Vehicles
Software-Defined Networking (SDN) is becoming the most dominant method for network management. By decoupling the control plane from the data plane, SDN provides a centralized view and more flexibility, scalability, and global knowledge of the entire network. In a previous paper, the authors presented ROAMER, a routing protocol that exploits Roadside Units (RSUs) in order to route messages within Vehicular Ad hoc Networks (VANETs). ROAMER combines two famous routing methods that have been extensively used in VANETs, which are geographical and carry-and-forward routing paradigms. In this paper, we upgrade ROAMER by shifting the routing operations into the SDN. Hence, we present SURFER, a routing protocol for Internet of Vehicles (IoV) that makes use of a distributed SDN architecture within the RSU network in order to route packets efficiently. We describe the extensive simulations that we performed to test SURFER and compare it to two very recent routing protocols for IoV. The simulation results illustrated the high efficiency of SURFER in terms of packet delivery, latency, and network overhead.
- 1 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Utilizing Roadside Units and Software Defined Networking to Route Packets Efficiently in Internet of Vehicles
Software-Defined Networking (SDN) is becoming the most dominant method for network management. By decoupling the control plane from the data plane, SDN provides a centralized view and more flexibility, scalability, and global knowledge of the entire network. In a previous paper, the authors presented ROAMER, a routing protocol that exploits Roadside Units (RSUs) in order to route messages within Vehicular Ad hoc Networks (VANETs). ROAMER combines two famous routing methods that have been extensively used in VANETs, which are geographical and carry-and-forward routing paradigms. In this paper, we upgrade ROAMER by shifting the routing operations into the SDN. Hence, we present SURFER, a routing protocol for Internet of Vehicles (IoV) that makes use of a distributed SDN architecture within the RSU network in order to route packets efficiently. We describe the extensive simulations that we performed to test SURFER and compare it to two very recent routing protocols for IoV. The simulation results illustrated the high efficiency of SURFER in terms of packet delivery, latency, and network overhead.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Assessing modelling readiness in a games environment
Potential university students have to prove readiness to acquire modeling competence if they get enrolled in an Information Systems (IS) program. University admission is generally based on scores acquired in pre-university education and based on conventional assessment which puts the students in stress and panic where they cannot perform to their full potential. In this paper, games based assessment which can be considered a type of stealth assessment is proposed to assess the modeling readiness. A player in a game performs in a natural setting that helps proper evaluation. The paper presents conventional readiness assessment scenarios, maps them to a number of games scenarios which are then developed into a game. The game addresses readiness levels related to modeling as well as other competencies. Aspects and choices related to game design are presented. The game is intended to be part of a bigger platform for assessment and assignment of students to academic programs. The game has been developed in unity and the first version tested by some students who would potentially enroll in Alexandria University, Egypt.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Assessing modelling readiness in a games environment
Potential university students have to prove readiness to acquire modeling competence if they get enrolled in an Information Systems (IS) program. University admission is generally based on scores acquired in pre-university education and based on conventional assessment which puts the students in stress and panic where they cannot perform to their full potential. In this paper, games based assessment which can be considered a type of stealth assessment is proposed to assess the modeling readiness. A player in a game performs in a natural setting that helps proper evaluation. The paper presents conventional readiness assessment scenarios, maps them to a number of games scenarios which are then developed into a game. The game addresses readiness levels related to modeling as well as other competencies. Aspects and choices related to game design are presented. The game is intended to be part of a bigger platform for assessment and assignment of students to academic programs. The game has been developed in unity and the first version tested by some students who would potentially enroll in Alexandria University, Egypt.
- 1 November 2019
- Published by IATED Academy in ICERI Proceedings
- p. 6144-6153
A FRAMEWORK FOR SERIOUS GAMES BASED ASSESSMENT: TECHNICAL CHOICES
Information about the paper titled "A FRAMEWORK FOR SERIOUS GAMES BASED ASSESSMENT: TECHNICAL CHOICES" at IATED Digital Library
- 1 November 2019
- Published by IATED Academy in ICERI Proceedings
- p. 6144-6153
A FRAMEWORK FOR SERIOUS GAMES BASED ASSESSMENT: TECHNICAL CHOICES
Information about the paper titled "A FRAMEWORK FOR SERIOUS GAMES BASED ASSESSMENT: TECHNICAL CHOICES" at IATED Digital Library
- 1 November 2019
- Published by IATED Academy in ICERI Proceedings
- Vol. 1, 4845-4852
PERSONALIZATION IN SERIOUS GAMES FOR ASSESSMENT
Information about the paper titled "PERSONALIZATION IN SERIOUS GAMES FOR ASSESSMENT" at IATED Digital Library
- 1 November 2019
- Published by IATED Academy in ICERI Proceedings
- Vol. 1, 4845-4852
PERSONALIZATION IN SERIOUS GAMES FOR ASSESSMENT
Information about the paper titled "PERSONALIZATION IN SERIOUS GAMES FOR ASSESSMENT" at IATED Digital Library
- 1 November 2019
- Published by Springer Nature
- p. 407-416
A Framework for the Development of Serious Games for Assessment
- 1 November 2019
- Published by Springer Nature
- p. 407-416
A Framework for the Development of Serious Games for Assessment
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 163-166
Knowledge Engineering for Competence Assessment on Serious Games Based on Semantic Web
Recognizing the inadequacy of traditional knowledge-based assessment systems in higher education to discover Learner competencies, we rethink the design of traditional assessment, using approaches that can both respond to the corporate requirements of the twenty-first century and reflect learners' competencies. The serious game sector has gained prominence in the last decade and the need to assess players' competencies in terms of knowledge, skills, and attitudes has grown. The assessment typically involves analyzing the player's performance in the game environment. At the same time, ontologies have emerged as one of the most popular and widely accepted tools in technology-enhanced learning and assessment. This paper proposes a framework for Competence Assessment based on ontological models for the generation of Personalized Assessment Scenarios, Assessment Portfolios and Personalized Assessment Paths on Serious games. Assessment Portfolios are used to track and store learners' interactions with the games, which can then be used as proof of competence during the assessment process. The personalized assessment scenarios on serious games are formalized with First Order Logic rules that are able to reason over resources annotated with Semantic Web metadata, thus allowing the reusability and interoperability of data.
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 163-166
Knowledge Engineering for Competence Assessment on Serious Games Based on Semantic Web
Recognizing the inadequacy of traditional knowledge-based assessment systems in higher education to discover Learner competencies, we rethink the design of traditional assessment, using approaches that can both respond to the corporate requirements of the twenty-first century and reflect learners' competencies. The serious game sector has gained prominence in the last decade and the need to assess players' competencies in terms of knowledge, skills, and attitudes has grown. The assessment typically involves analyzing the player's performance in the game environment. At the same time, ontologies have emerged as one of the most popular and widely accepted tools in technology-enhanced learning and assessment. This paper proposes a framework for Competence Assessment based on ontological models for the generation of Personalized Assessment Scenarios, Assessment Portfolios and Personalized Assessment Paths on Serious games. Assessment Portfolios are used to track and store learners' interactions with the games, which can then be used as proof of competence during the assessment process. The personalized assessment scenarios on serious games are formalized with First Order Logic rules that are able to reason over resources annotated with Semantic Web metadata, thus allowing the reusability and interoperability of data.