Mariem Jelassi
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
Mariem Jelassi has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Jacques Demongeot
University Grenoble Alpes
8 shared publications - Houssem Ben Khalfallah
Laboratoire AGEIS, Faculté de Médecine, Université Grenoble Alpes, France
3 shared publications - Carla Taramasco
Instituto de Tecnología para la Innovación en Salud y Bienestar, Facultad de Ingeniería, Universidad Andrés Bello, Viña del Mar 2520000, Chile
2 shared publications - Clément Baraille
Orange Laboratorys, 38229 Meylan, France
2 shared publications - Hajar Rissaoui
Laboratory AGEIS EA 7407, Team Tools for e-Gnosis Medical & Labcom CNRS/UGA/OrangeLabs Telecom4Health, Faculty of Medicine, University Grenoble Alpes (UGA), 38700 La Tronche, France
2 shared publications - Joël Gardes
Orange Labs, 38229 Meylan, France
2 shared publications
Latest Publications
- 2 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Modélisation, simulation et analyse multi-échelle de réseaux sociaux complexes : Application à l'aide à la prévention des maladies contagieuses
La présente thèse porte sur la mise en place d'un cadre théorique (conceptualisation et formalisation), visant à décrire la propagation de l'obésité au sein d'un réseau d'individus, pour parvenir à mettre en place les bonnes politiques de prévention, afin de limiter la diffusion de cette épidémie, dont la contamination est à caractère social. Pour ce faire, j’ai commencé d'abord à mettre en place une analyse approfondie des différents déterminants de l'obésité. Une fois cette étape achevée, j’ai développé un modèle de réseau, dans lequel les relations entre les individus (représentés par les nœuds du réseau) sont régies par des règles permettant d'évaluer la présence/absence de liens selon certaines valeurs d'influence, fonction de la tranche d'âge des nœuds en question et de leur caractère homophilique. Ce modèle, fondé sur la structuration en âges et la démographie, comporte deux processus; le premier permet de décrire l'obésité au niveau individuel, sous forme de compartiments épidémiologiques. Le deuxième, quant à lui, représente le niveau inter-individuel, sous forme de réseau individu-centré. Par la suite, une fois analysé le comportement asymptotique du modèle, j'ai étudié la structure sociale obtenue, pour y repérer les individus les plus influents. Ces derniers seront ceux à cibler dans la politique de prévention. Enfin, pour valider le modèle par des données de terrain, j'ai réalisé une enquête au sein d'un collège tunisien, et j'ai comparé les résultats obtenus par cette dernière avec ceux d'une enquête réalisée dans un collège français.
- 2 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Modélisation, simulation et analyse multi-échelle de réseaux sociaux complexes : Application à l'aide à la prévention des maladies contagieuses
La présente thèse porte sur la mise en place d'un cadre théorique (conceptualisation et formalisation), visant à décrire la propagation de l'obésité au sein d'un réseau d'individus, pour parvenir à mettre en place les bonnes politiques de prévention, afin de limiter la diffusion de cette épidémie, dont la contamination est à caractère social. Pour ce faire, j’ai commencé d'abord à mettre en place une analyse approfondie des différents déterminants de l'obésité. Une fois cette étape achevée, j’ai développé un modèle de réseau, dans lequel les relations entre les individus (représentés par les nœuds du réseau) sont régies par des règles permettant d'évaluer la présence/absence de liens selon certaines valeurs d'influence, fonction de la tranche d'âge des nœuds en question et de leur caractère homophilique. Ce modèle, fondé sur la structuration en âges et la démographie, comporte deux processus; le premier permet de décrire l'obésité au niveau individuel, sous forme de compartiments épidémiologiques. Le deuxième, quant à lui, représente le niveau inter-individuel, sous forme de réseau individu-centré. Par la suite, une fois analysé le comportement asymptotique du modèle, j'ai étudié la structure sociale obtenue, pour y repérer les individus les plus influents. Ces derniers seront ceux à cibler dans la politique de prévention. Enfin, pour valider le modèle par des données de terrain, j'ai réalisé une enquête au sein d'un collège tunisien, et j'ai comparé les résultats obtenus par cette dernière avec ceux d'une enquête réalisée dans un collège français.
- Open Access
- 9 July 2024
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 25 (14) , 7521
Information Gradient among Nucleotide Sequences of Essential RNAs from an Evolutionary Perspective
We hypothesize that the first ancestral “protocell” molecular structures, i.e., the first RNAs and peptides that gradually transformed into real cells once the Earth had cooled sufficiently for organic molecules to appear, have left traces in the RNAs and the genes in present cells. We propose a circular RNA that could have been one of these ancestral structures whose vestigial pentameric subsequences would mark the evolution from this key moment when the protocells began to join with living organisms. In particular, we propose that, in present RNAs (ribosomal or messenger), which play an important role in the metabolism of current cells, we look for traces of the proposed primitive structure in the form of pentamers (or longer fragments) that belong to their nucleotide sequence. The result obtained can be summarized in the existence of a gradient of occurrence of such pentamers, with a high frequency for the most vital functions (protein synthesis, nucleic synthesis, cell respiration, etc.). This gradient is also visible between organisms, from the oldest (Archaea) to the most recent (Eukaryotes) in the evolution of species.
- 9 July 2024
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 25 (14) , 7521
Open AccessInformation Gradient among Nucleotide Sequences of Essential RNAs from an Evolutionary Perspective
We hypothesize that the first ancestral “protocell” molecular structures, i.e., the first RNAs and peptides that gradually transformed into real cells once the Earth had cooled sufficiently for organic molecules to appear, have left traces in the RNAs and the genes in present cells. We propose a circular RNA that could have been one of these ancestral structures whose vestigial pentameric subsequences would mark the evolution from this key moment when the protocells began to join with living organisms. In particular, we propose that, in present RNAs (ribosomal or messenger), which play an important role in the metabolism of current cells, we look for traces of the proposed primitive structure in the form of pentamers (or longer fragments) that belong to their nucleotide sequence. The result obtained can be summarized in the existence of a gradient of occurrence of such pentamers, with a high frequency for the most vital functions (protein synthesis, nucleic synthesis, cell respiration, etc.). This gradient is also visible between organisms, from the oldest (Archaea) to the most recent (Eukaryotes) in the evolution of species.
- Open Access
- 24 May 2024
- Published by MDPI AG in Preprints.org
Information Gradient among Nucleotide Sequences of Essential RNAs in an Evolutionary Perspective
We hypothesize that the first ancestral "ante-cell" molecular structures, i.e., first RNAs and peptides which gradually transformed into real cells once the Earth had cooled sufficiently for organic molecules to appear there, have leaved traces in RNAs and genes of present cells. We propose a circular RNA which could have been one of these ancestral structures whose vestigial pentameric subsequences would mark the evolution from this key moment when the ante-cells have begun to join the living organisms. In particular, we propose that in present RNAs (ribosomal or messenger) playing an important role in the metabolism of current cells, we look for traces of the proposed primitive structure in the form of pentamers (or longer fragments) belonging to their nucleotide sequence. The result obtained can be summarized in the existence of a gradient of occurrence of such pentamers, with a high frequency for the most vital functions (protein synthesis, nucleic synthesis, cell respiration, etc.). This gradient is also visible between organisms, from the oldest (Archaea) to the most recent (Eukaryotes) in evolution of species.
- 24 May 2024
- Published by MDPI AG in Preprints.org
Open AccessInformation Gradient among Nucleotide Sequences of Essential RNAs in an Evolutionary Perspective
We hypothesize that the first ancestral "ante-cell" molecular structures, i.e., first RNAs and peptides which gradually transformed into real cells once the Earth had cooled sufficiently for organic molecules to appear there, have leaved traces in RNAs and genes of present cells. We propose a circular RNA which could have been one of these ancestral structures whose vestigial pentameric subsequences would mark the evolution from this key moment when the ante-cells have begun to join the living organisms. In particular, we propose that in present RNAs (ribosomal or messenger) playing an important role in the metabolism of current cells, we look for traces of the proposed primitive structure in the form of pentamers (or longer fragments) belonging to their nucleotide sequence. The result obtained can be summarized in the existence of a gradient of occurrence of such pentamers, with a high frequency for the most vital functions (protein synthesis, nucleic synthesis, cell respiration, etc.). This gradient is also visible between organisms, from the oldest (Archaea) to the most recent (Eukaryotes) in evolution of species.
- Open Access
- 25 April 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (9) , 895
Revolutionizing Radiological Analysis: The Future of French Language Automatic Speech Recognition in Healthcare
This study introduces a specialized Automatic Speech Recognition (ASR) system, leveraging the Whisper Large-v2 model, specifically adapted for radiological applications in the French language. The methodology focused on adapting the model to accurately transcribe medical terminology and diverse accents within the French language context, achieving a notable Word Error Rate (WER) of 17.121%. This research involved extensive data collection and preprocessing, utilizing a wide range of French medical audio content. The results demonstrate the system’s effectiveness in transcribing complex radiological data, underscoring its potential to enhance medical documentation efficiency in French-speaking clinical settings. The discussion extends to the broader implications of this technology in healthcare, including its potential integration with electronic health records (EHRs) and its utility in medical education. This study also explores future research directions, such as tailoring ASR systems to specific medical specialties and languages. Overall, this research contributes significantly to the field of medical ASR systems, presenting a robust tool for radiological transcription in the French language and paving the way for advanced technology-enhanced healthcare solutions.
- 25 April 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (9) , 895
Open AccessRevolutionizing Radiological Analysis: The Future of French Language Automatic Speech Recognition in Healthcare
This study introduces a specialized Automatic Speech Recognition (ASR) system, leveraging the Whisper Large-v2 model, specifically adapted for radiological applications in the French language. The methodology focused on adapting the model to accurately transcribe medical terminology and diverse accents within the French language context, achieving a notable Word Error Rate (WER) of 17.121%. This research involved extensive data collection and preprocessing, utilizing a wide range of French medical audio content. The results demonstrate the system’s effectiveness in transcribing complex radiological data, underscoring its potential to enhance medical documentation efficiency in French-speaking clinical settings. The discussion extends to the broader implications of this technology in healthcare, including its potential integration with electronic health records (EHRs) and its utility in medical education. This study also explores future research directions, such as tailoring ASR systems to specific medical specialties and languages. Overall, this research contributes significantly to the field of medical ASR systems, presenting a robust tool for radiological transcription in the French language and paving the way for advanced technology-enhanced healthcare solutions.
- Open Access
- 11 March 2024
- Published by MDPI AG in Preprints.org
Revolutionizing Radiological Analysis: The Future of French Language Automatic Speech Recognition in Healthcare
This study introduces a specialized Automatic Speech Recognition (ASR) system, leveraging the Whisper Large-v2 model, specifically adapted for radiological applications in French language. Our methodology focused on adapting the model to accurately transcribe medical terminology and diverse accents within the French language context, achieving a notable Word Error Rate (WER) of 17.121%. The research involved extensive data collection and preprocessing, utilizing a wide range of French medical audio content. The results demonstrate the system's effectiveness in transcribing complex radiological data, underscoring its potential to enhance medical documentation efficiency in French-speaking clinical settings. The discussion extends to the broader implications of this technology in healthcare, including its potential integration with Electronic Health Records (EHRs) and its utility in medical education. The study also explores future research directions, such as tailoring ASR systems to specific medical specialties and languages. Overall, this research contributes significantly to the field of medical ASR systems, presenting a robust tool for radiological transcription in the French language and paving the way for advanced technology-enhanced healthcare solutions.
- 11 March 2024
- Published by MDPI AG in Preprints.org
Open AccessRevolutionizing Radiological Analysis: The Future of French Language Automatic Speech Recognition in Healthcare
This study introduces a specialized Automatic Speech Recognition (ASR) system, leveraging the Whisper Large-v2 model, specifically adapted for radiological applications in French language. Our methodology focused on adapting the model to accurately transcribe medical terminology and diverse accents within the French language context, achieving a notable Word Error Rate (WER) of 17.121%. The research involved extensive data collection and preprocessing, utilizing a wide range of French medical audio content. The results demonstrate the system's effectiveness in transcribing complex radiological data, underscoring its potential to enhance medical documentation efficiency in French-speaking clinical settings. The discussion extends to the broader implications of this technology in healthcare, including its potential integration with Electronic Health Records (EHRs) and its utility in medical education. The study also explores future research directions, such as tailoring ASR systems to specific medical specialties and languages. Overall, this research contributes significantly to the field of medical ASR systems, presenting a robust tool for radiological transcription in the French language and paving the way for advanced technology-enhanced healthcare solutions.
- Open Access
- 27 February 2024
- Published by MDPI AG in Preprints.org
Enhancing Mental Health Support through Artificial Intelligence: Advances in Speech and Text Analysis within Online Therapy Platforms
In the dynamic field of mental health care, the nuanced application of Artificial Intelligence (AI) through Natural Language Processing (NLP) and Automatic Speech Recognition (ASR) is a pivotal innovation in patient empowerment and service optimization. This study introduces a distinctive online therapy platform that capitalizes on the synergy of NLP and ASR to offer unprecedented levels of interactive and personalized therapeutic interventions. The architecture of our system is meticulously detailed, featuring an ASR component with an impressive Word Error Rate (WER) of 14% when trained on the diverse French subsets of the Mozilla Common Voice dataset, complemented by a high-precision NLP framework skilled in processing and responding to user inputs. The evaluation of our system highlights its efficacy in enhancing therapy sessions and user satisfaction, with an emphasis on the qualitative aspects of user feedback. The paper addresses challenges such as dataset representativeness and language model refinement and articulates the strategic solutions employed to overcome them. The paper concludes with forward-looking perspectives on AI's role in mental health services, advocating for the creation of sophisticated, language-specific datasets and models to satisfy the increasing demands of online therapy, reflecting a growing commitment of patients in the management of their therapy. This research underscores the transformative impact of AI in advancing mental health care into the digital age, representing a significant evolution over existing methodologies.
- 27 February 2024
- Published by MDPI AG in Preprints.org
Open AccessEnhancing Mental Health Support through Artificial Intelligence: Advances in Speech and Text Analysis within Online Therapy Platforms
In the dynamic field of mental health care, the nuanced application of Artificial Intelligence (AI) through Natural Language Processing (NLP) and Automatic Speech Recognition (ASR) is a pivotal innovation in patient empowerment and service optimization. This study introduces a distinctive online therapy platform that capitalizes on the synergy of NLP and ASR to offer unprecedented levels of interactive and personalized therapeutic interventions. The architecture of our system is meticulously detailed, featuring an ASR component with an impressive Word Error Rate (WER) of 14% when trained on the diverse French subsets of the Mozilla Common Voice dataset, complemented by a high-precision NLP framework skilled in processing and responding to user inputs. The evaluation of our system highlights its efficacy in enhancing therapy sessions and user satisfaction, with an emphasis on the qualitative aspects of user feedback. The paper addresses challenges such as dataset representativeness and language model refinement and articulates the strategic solutions employed to overcome them. The paper concludes with forward-looking perspectives on AI's role in mental health services, advocating for the creation of sophisticated, language-specific datasets and models to satisfy the increasing demands of online therapy, reflecting a growing commitment of patients in the management of their therapy. This research underscores the transformative impact of AI in advancing mental health care into the digital age, representing a significant evolution over existing methodologies.
- Open Access
Biological Networks Entropies: Examples in Neural Memory Networks, Genetic Regulation Networks and Social Epidemic Networks
Networks used in biological applications at different scales (molecule, cell and population) are of different types: neuronal, genetic, and social, but they share the same dynamical concepts, in their continuous differential versions (e.g., non-linear Wilson-Cowan system) as well as in their discrete Boolean versions (e.g., non-linear Hopfield system); in both cases, the notion of interaction graph G(J) associated to its Jacobian matrix J, and also the concepts of frustrated nodes, positive or negative circuits of G(J), kinetic energy, entropy, attractors, structural stability, etc., are relevant and useful for studying the dynamics and the robustness of these systems. We will give some general results available for both continuous and discrete biological networks, and then study some specific applications of three new notions of entropy: (i) attractor entropy, (ii) isochronal entropy and (iii) entropy centrality; in three domains: a neural network involved in the memory evocation, a genetic network responsible of the iron control and a social network accounting for the obesity spread in high school environment.
Open AccessBiological Networks Entropies: Examples in Neural Memory Networks, Genetic Regulation Networks and Social Epidemic Networks
Networks used in biological applications at different scales (molecule, cell and population) are of different types: neuronal, genetic, and social, but they share the same dynamical concepts, in their continuous differential versions (e.g., non-linear Wilson-Cowan system) as well as in their discrete Boolean versions (e.g., non-linear Hopfield system); in both cases, the notion of interaction graph G(J) associated to its Jacobian matrix J, and also the concepts of frustrated nodes, positive or negative circuits of G(J), kinetic energy, entropy, attractors, structural stability, etc., are relevant and useful for studying the dynamics and the robustness of these systems. We will give some general results available for both continuous and discrete biological networks, and then study some specific applications of three new notions of entropy: (i) attractor entropy, (ii) isochronal entropy and (iii) entropy centrality; in three domains: a neural network involved in the memory evocation, a genetic network responsible of the iron control and a social network accounting for the obesity spread in high school environment.
- 2 October 2017
- Published by Taylor & Francis in Mathematical Population Studies
- Vol. 24 (4) , 219-245
From susceptibility to frailty in social networks: The case of obesity
The obesity pandemic is represented by a discrete-time Hopfield Boolean network embedded in continuous-time population dynamics. The influence of the social environment passes through a system of differential equations, whereby obesity spreads by imitation of the most influential neighbors, those who have the highest centrality indices in the network. This property is called “homophily.” Susceptibility and frailty are redefined using network properties. Projections of the spread of obesity are validated on data collected in a French high school.
- 2 October 2017
- Published by Taylor & Francis in Mathematical Population Studies
- Vol. 24 (4) , 219-245
From susceptibility to frailty in social networks: The case of obesity
The obesity pandemic is represented by a discrete-time Hopfield Boolean network embedded in continuous-time population dynamics. The influence of the social environment passes through a system of differential equations, whereby obesity spreads by imitation of the most influential neighbors, those who have the highest centrality indices in the network. This property is called “homophily.” Susceptibility and frailty are redefined using network properties. Projections of the spread of obesity are validated on data collected in a French high school.
- Open Access
- 8 August 2016
- Published by MDPI AG in Information
- Vol. 7 (3) , 50
Smart Homes and Sensors for Surveillance and Preventive Education at Home: Example of Obesity
(1) Background: The aim of this paper is to show that e-health tools like smart homes allow the personalization of the surveillance and preventive education of chronic patients, such as obese persons, in order to maintain a comfortable and preventive lifestyle at home. (2) Technologies and methods: Several types of sensors allow coaching the patient at home, e.g., the sensors recording the activity and monitoring the physiology of the person. All of this information serves to personalize serious games dedicated to preventive education, for example in nutrition and vision. (3) Results: We built a system of personalized preventive education at home based on serious games, derived from the feedback information they provide through a monitoring system. Therefore, it is possible to define (after clustering and personalized calibration) from the at home surveillance of chronic patients different comfort zones where their behavior can be estimated as normal or abnormal and, then, to adapt both alarm levels for surveillance and education programs for prevention, the chosen example of application being obesity.
- 8 August 2016
- Published by MDPI AG in Information
- Vol. 7 (3) , 50
Open AccessSmart Homes and Sensors for Surveillance and Preventive Education at Home: Example of Obesity
(1) Background: The aim of this paper is to show that e-health tools like smart homes allow the personalization of the surveillance and preventive education of chronic patients, such as obese persons, in order to maintain a comfortable and preventive lifestyle at home. (2) Technologies and methods: Several types of sensors allow coaching the patient at home, e.g., the sensors recording the activity and monitoring the physiology of the person. All of this information serves to personalize serious games dedicated to preventive education, for example in nutrition and vision. (3) Results: We built a system of personalized preventive education at home based on serious games, derived from the feedback information they provide through a monitoring system. Therefore, it is possible to define (after clustering and personalized calibration) from the at home surveillance of chronic patients different comfort zones where their behavior can be estimated as normal or abnormal and, then, to adapt both alarm levels for surveillance and education programs for prevention, the chosen example of application being obesity.