Samar Allouch - Profile on Academia.edu (original) (raw)
Papers by Samar Allouch
New Approach for Effective Twitter Sentiments Analysis
2023 Al-Sadiq International Conference on Communication and Information Technology (AICCIT)
With the need to develop an artificial organ replacing the human finger in the case of a deficit ... more With the need to develop an artificial organ replacing the human finger in the case of a deficit and the need to understand the functioning of this physiological system, an inverse physical model of the finger system, allowing to search for neuronal activations from motion, is necessary. Despite the large number of studies in human hand modeling, there is almost no inverse physical model of the major finger system that is interested in searching for neuronal activations. Almost all of the existing models have focused on muscle strength and activation. The aim of the thesis is to present a neuromuscular-skeletal model of the human major finger system, allowing the neuronal activation, muscular activation and muscular forces of all the muscles acting on the finger system to be obtained from the analysis of the movement. The purpose of this type of models is to represent the essential characteristics of the movement as realistically as possible. Our work consists in studying, modeling ...
Avec le besoin de developper un organe artificiel remplacant le doigt humain dans le cas d'un... more Avec le besoin de developper un organe artificiel remplacant le doigt humain dans le cas d'un deficit et la necessite de comprendre le fonctionnement de ce systeme physiologique, un modele physique inverse du systeme doigt, permettant de chercher les activations neuronales a partir du mouvement, est necessaire. Malgre le grand nombre d'etudes dans la modelisation de la main humaine, presque il n'existe aucun modele physique inverse du systeme doigt majeur qui s'interesse a chercher les activations neuronales. Presque tous les modeles existants se sont interesses a la recherche des forces et des activations musculaires. L'objectif de la these est de presenter un modele neuromusculo-squelettique du systeme doigt majeur humain permettant d'obtenir les activations neuronales, les activations musculaires et les forces musculaires des tous les muscles agissants sur le systeme doigt d'apres l'analyse du mouvement. Le but de ce type des modeles est de represe...
2017 Fourth International Conference on Advances in Biomedical Engineering (ICABME), 2017
The main objective of the presented work is to do a preliminary sensitivity analysis of the simpl... more The main objective of the presented work is to do a preliminary sensitivity analysis of the simplified neuromusculoskeletal model of the human middle finger that we have already developed [1], [2]. The importance of this study is to improve the model by well estimating internal parameters, which are the most affecting the model output, and by adapting it to each individual. The sensitivity analysis presented in this study is preliminary; it is based on the computing of the elementary effect (EE) of the 3 signal features of the muscular force. We get significant results to indicate the most important parameters among those chosen; these are the most influential parameters on system output, and good estimation of them leads to a more realistic model. These results encourage us to do a deeper sensitivity analysis for the most complex model where the sensitivity analysis will be on all internal parameters of the model in order to improve it.
On the benefits of using HD-sEMG technique for estimating muscle force
Computer methods in biomechanics and biomedical engineering, 2015
In biomechanics modeling applications, muscle force estimators, using Hill-type model are classic... more In biomechanics modeling applications, muscle force estimators, using Hill-type model are classically fed using sEMG signals recorded from one lead per muscle. The major limitation of this methodology is the lack of muscle activation representativeness of this lead. Recently, it has emerged as an instrumental technique, based on multi-channel recordings. This technique, namely, the High-Density sEMG (HD-sEMG) technique allows us the access, at the same time, to up to 128 recording sites over a muscle. In this study, we propose to demonstrate the benefits of using such techniques in estimating more accurately the muscle force. For this purpose and using simulation, we will compare estimated force profiles using classical single bipolar and HD-sEMG techniques. Thus, we simulate HD-sEMG and bipolar signals using a recent generation model and the associated force as in Allouch et al. (2013). In fact, the simulation allows us the access to the intrinsic muscle force which is unrealizable in experiment. Next, the obtained results are discussed focusing on the benefits of using HD-sEMG for muscle force estimation.
Computers in Biology and Medicine, 2015
Purpose: The purpose of this study Q3 is to develop an inverse dynamic model of the human middle ... more Purpose: The purpose of this study Q3 is to develop an inverse dynamic model of the human middle finger in order to identify the muscle activation, muscle force, and neural activation of the muscles involved during motion. Its originality comes from the coupling of biomechanical and physiological models and the proposition of a dedicated optimization procedure and cost function for identifying the model unknowns. Methods: Three sub-models work in interaction: the first is the biomechanical model, primarily consisting of the dynamic equations of the middle finger system; the second is the muscle model, which helps to identify the muscle force from muscle activation and dynamic deformation for six involved muscles. The third model allows one to link muscle activation to neural intent from the Central Nervous System (CNS). This modeling procedure leads to a complex analytical nonlinear system identified using multi-step energy minimization procedure and a specific cost function. Results: Numerical simulations with different articulation velocities are presented and discussed. Then, experimental evaluation of the proposed model is performed following a protocol combining electromyography and motion capture during a hand opening-closing paradigm. After comparison, several results from the simulation and experiments were found to be in accordance. The difficulty in evaluating such complex dynamic models is also demonstrated. Conclusions: Despite the model simplifications, the obtained preliminary results are promising. Indeed, the proposed model, once correctly validated in future works, should be a relevant tool to simulate and predict deficiencies of the middle finger system for rehabilitation purposes.
Muscle force estimation using data fusion from high-density SEMG grid
2013 2nd International Conference on Advances in Biomedical Engineering, 2013
Physiological and Biomechanical Approach for Human Finger Movement: Modeling, Simulation and Experimental Validation
Journal of Mechanics in Medicine and Biology, 2014
The work presented in this paper deals with the description of an analytic modeling of the neurom... more The work presented in this paper deals with the description of an analytic modeling of the neuromusculoskeletal system responsible for the finger movement. This simulation task is complex due to the interacting processes (physiological and biomechanical) represented by muscles, joints and bones. In this study, we focused on the presentation of a complete model for the finger motion decomposed in quasi-static positions. In fact, this model can be considered as a preliminary step before dynamic modeling. The proposed model is composed of several compartments: biomechanical finger model, mechanical muscle model and muscle/neural activation model. The main objective of this study is to estimate, by inverse procedure, the muscle forces, muscle activations and neural activations that are responsible for generating a given finger movement decomposed in successive quasi-static positions. The anatomical model contains six muscles which control the decomposed movement of the three joints of t...
New Approach for Effective Twitter Sentiments Analysis
2023 Al-Sadiq International Conference on Communication and Information Technology (AICCIT)
With the need to develop an artificial organ replacing the human finger in the case of a deficit ... more With the need to develop an artificial organ replacing the human finger in the case of a deficit and the need to understand the functioning of this physiological system, an inverse physical model of the finger system, allowing to search for neuronal activations from motion, is necessary. Despite the large number of studies in human hand modeling, there is almost no inverse physical model of the major finger system that is interested in searching for neuronal activations. Almost all of the existing models have focused on muscle strength and activation. The aim of the thesis is to present a neuromuscular-skeletal model of the human major finger system, allowing the neuronal activation, muscular activation and muscular forces of all the muscles acting on the finger system to be obtained from the analysis of the movement. The purpose of this type of models is to represent the essential characteristics of the movement as realistically as possible. Our work consists in studying, modeling ...
Avec le besoin de developper un organe artificiel remplacant le doigt humain dans le cas d'un... more Avec le besoin de developper un organe artificiel remplacant le doigt humain dans le cas d'un deficit et la necessite de comprendre le fonctionnement de ce systeme physiologique, un modele physique inverse du systeme doigt, permettant de chercher les activations neuronales a partir du mouvement, est necessaire. Malgre le grand nombre d'etudes dans la modelisation de la main humaine, presque il n'existe aucun modele physique inverse du systeme doigt majeur qui s'interesse a chercher les activations neuronales. Presque tous les modeles existants se sont interesses a la recherche des forces et des activations musculaires. L'objectif de la these est de presenter un modele neuromusculo-squelettique du systeme doigt majeur humain permettant d'obtenir les activations neuronales, les activations musculaires et les forces musculaires des tous les muscles agissants sur le systeme doigt d'apres l'analyse du mouvement. Le but de ce type des modeles est de represe...
2017 Fourth International Conference on Advances in Biomedical Engineering (ICABME), 2017
The main objective of the presented work is to do a preliminary sensitivity analysis of the simpl... more The main objective of the presented work is to do a preliminary sensitivity analysis of the simplified neuromusculoskeletal model of the human middle finger that we have already developed [1], [2]. The importance of this study is to improve the model by well estimating internal parameters, which are the most affecting the model output, and by adapting it to each individual. The sensitivity analysis presented in this study is preliminary; it is based on the computing of the elementary effect (EE) of the 3 signal features of the muscular force. We get significant results to indicate the most important parameters among those chosen; these are the most influential parameters on system output, and good estimation of them leads to a more realistic model. These results encourage us to do a deeper sensitivity analysis for the most complex model where the sensitivity analysis will be on all internal parameters of the model in order to improve it.
On the benefits of using HD-sEMG technique for estimating muscle force
Computer methods in biomechanics and biomedical engineering, 2015
In biomechanics modeling applications, muscle force estimators, using Hill-type model are classic... more In biomechanics modeling applications, muscle force estimators, using Hill-type model are classically fed using sEMG signals recorded from one lead per muscle. The major limitation of this methodology is the lack of muscle activation representativeness of this lead. Recently, it has emerged as an instrumental technique, based on multi-channel recordings. This technique, namely, the High-Density sEMG (HD-sEMG) technique allows us the access, at the same time, to up to 128 recording sites over a muscle. In this study, we propose to demonstrate the benefits of using such techniques in estimating more accurately the muscle force. For this purpose and using simulation, we will compare estimated force profiles using classical single bipolar and HD-sEMG techniques. Thus, we simulate HD-sEMG and bipolar signals using a recent generation model and the associated force as in Allouch et al. (2013). In fact, the simulation allows us the access to the intrinsic muscle force which is unrealizable in experiment. Next, the obtained results are discussed focusing on the benefits of using HD-sEMG for muscle force estimation.
Computers in Biology and Medicine, 2015
Purpose: The purpose of this study Q3 is to develop an inverse dynamic model of the human middle ... more Purpose: The purpose of this study Q3 is to develop an inverse dynamic model of the human middle finger in order to identify the muscle activation, muscle force, and neural activation of the muscles involved during motion. Its originality comes from the coupling of biomechanical and physiological models and the proposition of a dedicated optimization procedure and cost function for identifying the model unknowns. Methods: Three sub-models work in interaction: the first is the biomechanical model, primarily consisting of the dynamic equations of the middle finger system; the second is the muscle model, which helps to identify the muscle force from muscle activation and dynamic deformation for six involved muscles. The third model allows one to link muscle activation to neural intent from the Central Nervous System (CNS). This modeling procedure leads to a complex analytical nonlinear system identified using multi-step energy minimization procedure and a specific cost function. Results: Numerical simulations with different articulation velocities are presented and discussed. Then, experimental evaluation of the proposed model is performed following a protocol combining electromyography and motion capture during a hand opening-closing paradigm. After comparison, several results from the simulation and experiments were found to be in accordance. The difficulty in evaluating such complex dynamic models is also demonstrated. Conclusions: Despite the model simplifications, the obtained preliminary results are promising. Indeed, the proposed model, once correctly validated in future works, should be a relevant tool to simulate and predict deficiencies of the middle finger system for rehabilitation purposes.
Muscle force estimation using data fusion from high-density SEMG grid
2013 2nd International Conference on Advances in Biomedical Engineering, 2013
Physiological and Biomechanical Approach for Human Finger Movement: Modeling, Simulation and Experimental Validation
Journal of Mechanics in Medicine and Biology, 2014
The work presented in this paper deals with the description of an analytic modeling of the neurom... more The work presented in this paper deals with the description of an analytic modeling of the neuromusculoskeletal system responsible for the finger movement. This simulation task is complex due to the interacting processes (physiological and biomechanical) represented by muscles, joints and bones. In this study, we focused on the presentation of a complete model for the finger motion decomposed in quasi-static positions. In fact, this model can be considered as a preliminary step before dynamic modeling. The proposed model is composed of several compartments: biomechanical finger model, mechanical muscle model and muscle/neural activation model. The main objective of this study is to estimate, by inverse procedure, the muscle forces, muscle activations and neural activations that are responsible for generating a given finger movement decomposed in successive quasi-static positions. The anatomical model contains six muscles which control the decomposed movement of the three joints of t...