Dan Istrate | Compiegne Technology University (original) (raw)
Papers by Dan Istrate
HAL (Le Centre pour la Communication Scientifique Directe), May 31, 2017
HAL (Le Centre pour la Communication Scientifique Directe), May 15, 2008
This presentation deals with different research axis followed by the Televigilance activity in Te... more This presentation deals with different research axis followed by the Televigilance activity in Telecom Sudparis : a) Multi-sensors Ambulatory Terminal on Patient: Automatic Fall detector and noise-robust vital signal extraction, Alarm automatisation and context identification based on Data Fusion, Physiological and actimetric data (cardiac frequency, movements,...) Fall, posture or activity recognition, Contextual information (sounds, localisation, activity) ANASON with ESIGETEL (D. Istrate) b) Cardiac pathology detection (R. Andreao): ECG signal segmentation based on sub-beat Hidden-Markov Models, Ischemias and Arrythmias events classification, Voice-controlled man-machine interface for Elderly persons to the smart home environment with TelecomParisTech (G. Chollet, P. Milhorat) c) Activity monitoring in care-houses in collaboration with LEGRAND company (P.Dore, T. Guettari) It also enlarges the scope to other teams within the Institut Mines-Telecom group, such as the QoL (Quality ...
Annals of the University of Craiova, Series: …
Abstract: The advent of modern communications and the low cost of some kinds of devices have resu... more Abstract: The advent of modern communications and the low cost of some kinds of devices have resulted in a desire to equip elderly peoples' homes with sensors to monitor their activities and be forewarned of abnormal situations. In such an environment, sound may ...
Sensors
Stress is an increasingly prevalent mental health condition across the world. In Europe, for exam... more Stress is an increasingly prevalent mental health condition across the world. In Europe, for example, stress is considered one of the most common health problems, and over USD 300 billion are spent on stress treatments annually. Therefore, monitoring, identification and prevention of stress are of the utmost importance. While most stress monitoring is carried out through self-reporting, there are now several studies on stress detection from physiological signals using Artificial Intelligence algorithms. However, the generalizability of these models is only rarely discussed. The main goal of this work is to provide a monitoring proof-of-concept tool exploring the generalization capabilities of Heart Rate Variability-based machine learning models. To this end, two Machine Learning models are used, Logistic Regression and Random Forest to analyze and classify stress in two datasets differing in terms of protocol, stressors and recording devices. First, the models are evaluated using le...
HAL (Le Centre pour la Communication Scientifique Directe), Feb 1, 2022
HAL (Le Centre pour la Communication Scientifique Directe), Jul 8, 2018
2018 13th Annual Conference on System of Systems Engineering (SoSE), 2018
The research purpose is to study the impact’s use of connected devices on cardiovascular diseases... more The research purpose is to study the impact’s use of connected devices on cardiovascular diseases. In this paper, we will explain our experimental methodology as well as the first outcomes. Three connected objects are being used for this experiment: a heart rate monitor belt, a tensiometer and a smartwatch. This communication intends to explain the methodology and the procedure that are being used to conduct this project. Our main objective is to monitor participants during their daily routine life, to record and to collect data continuously. This health care monitoring is a case of study of system of systems engineering within it we manage interactions between three aspects: humans, environment and sensors. The idea, then, is to study the different relations and correlations existing between variables coming from those aspects. An important part, of this work, takes into consideration the participant’s emotional aspect (stress, happiness, sadness, among) and analyse that using the appropriate artificial intelligence tools. Being able to detect participant’s emotion, categorize it and analyse its impact on cardiovascular disease, is the main goal of this work.
Cet article decrit les travaux de recherche d'une equipe pluridisciplinaire regroupee autour ... more Cet article decrit les travaux de recherche d'une equipe pluridisciplinaire regroupee autour du theme de la televigilance medicale. Il recense les resultats d'une collaboration de nombreuses annees qui a abouti au developpement et a la mise en place d'une plateforme multimodale pour la televigilance medicale. Cette plateforme est composee de trois systemes heterogenes mais complementaires concus pour assurer le maintient a domicile de personnes âgees en toute securite. Dans cet article, nous presentons une description detaillee des multiples capteurs que nous utilisons pour surveiller a distance l'etat de sante d'une personne âgee et/ou d'un patient a domicile. Il s'agit precisement d'un ensemble de microphones places convenablement dans la maison, d'un dispositif portable qui mesure des signaux physiologiques et detecte la chute et d'un ensemble de capteurs infrarouges. Cette plateforme geree et commandee a distance est utilisee par le person...
This work propose a remote healthcare monitoring system designed to derive elderly’s activities o... more This work propose a remote healthcare monitoring system designed to derive elderly’s activities of daily living and distress situation in Nursing Home environments through a set of pyroelectric infrared sensor placed in the rooms. We aim to infer from the nursing home environment information as the exits and entries in the room, presence of caregivers and activities as night rounds, sleeping, eating, care-giver intervention. Thank to the sensors emplacement in the present case is possible to extract patterns regarding paths performed inside the room. Based on these patterns, we propose in a first step, a finite state model that represents the behavior of only one person moving inside the room. Through accomplishing of this model, we can derive some information as resident tracking, presence of care-givers, entries and exits. In previous work we have used the Dempster-Shafer theory (DST) based on static and dynamic model called Evidential Networks [11] in order to take into account t...
In the frame of CompanionAble European project, we have utilized many ambient sensors in order to... more In the frame of CompanionAble European project, we have utilized many ambient sensors in order to implement multimodal fusion application aiming to detect abnormal status of the care receiver CR. We have exploited actimetry and sound signal to track and localize the person in his living place. In order to increase localization accuracy and to improve performance of the tracking system, ultimodal fusion methods can be used to exploit several modalities. Among these techniques, we are nterested by those based on finite states model with a random variable that changes along the time. Relying on N-dimensional states transition matrix, we propose a fusion model of heterogonous data generated from multiple ambient sensors. To detect abnormal situations of the observed person, we would use a personalized matrix estimated by applying a Polya model.
The research purpose is to study the impact’s use of connected devices on cardiovascular diseases... more The research purpose is to study the impact’s use of connected devices on cardiovascular diseases. One of our objective is stress recognition during daily routine life. To achieve that a long term experimentation have been conducted. This longitudinal empirical research study aided by connected devices enabling psycho-physiological monitoring to study the correlation between emotional states including stress levels and prognosis of cardiovascular disease. In this paper, we will present the main participant’s feedback concerning the conducted experimentation using wearables sensors. This manuscript explains participant selection. It will not treat data conducted from this experiment or show numerical results. It is a statistical feedback concerning the experimentation protocol. We will clarify the protocol strengths and weaknesses. Our main motivation is to give an opinion to other research and to inspire them if they want to conduct a similar experimentation.
Applied Medical Informatics, 2013
Our study has assessed the benefits that electronics health records can bring to small health car... more Our study has assessed the benefits that electronics health records can bring to small health care facilities by qualitatively and quantitatively analyzing a limited number of open source software suites in the area of medical informatics. We have investigated the way in which these benefits may be achieved by implementing the presented software solutions, taking care to highlight the peculiarities of the open source model of development that prove to be differentiating factors against equivalent closed source commercial solutions. Not taking into account the financial aspect (free software solutions have no licensing costs), we have tried to discern the intrinsic advantages of the model of free software development and its particularities in this specific area of investigation: health informatics.
The BV2 project aims to propose a monitoring system for wellbeing but also well-aging working on ... more The BV2 project aims to propose a monitoring system for wellbeing but also well-aging working on the prevention, detection and monitoring using a System of the Systems (SoS) approach. The project partner already uses the IoT technologies and the BV2 platform will combine the different developed systems. The main originality of the project consist s in the development of a virtual platform by combining the existing systems
Applied Medical Informatics, 2013
We developed an instrument which can ensure a quick and easy dialogue between the physicians of t... more We developed an instrument which can ensure a quick and easy dialogue between the physicians of the Oncology Institute and family physicians. The platform we chose was Simple Machines Forum (abbreviated as SMF), a free Internet forum (BBS - Bulletin Board System) application. The purpose of this article is not to detail the software platform, but to emphasize the facilities and advantages of using this solution in the medical community.
Cet article presente un systeme de localisation basee sur la combinaison de deux modules : SHPT (... more Cet article presente un systeme de localisation basee sur la combinaison de deux modules : SHPT (Smart Home Person Tracking), compose par un reseau de capteurs infrarouge, et APT (AudioPerson Tracking), qui utilisent des microphones capables d'estimer la direction (azimut) de la source sonore. Cette combinaison augment la precision de localisation par rapport a l'utilisation de chaque systeme separement. Le logiciel de localisation (LA Module) est un outil important qui nous permet d'integrer les deux systemes, de visualiser les positions en temps reel, d'enregistrer les donnees, d'evaluer les profils de deplacement et de detecter certaines situations de detresse de la personne (certains types de chutes). Les resultats de mise en oeuvre montrent une bonne adaptation aux environnements de type Smart Home et une robustesse de detection
Aujourd'hui les technologies au service des espaces intelligents ne cessent de se developper ... more Aujourd'hui les technologies au service des espaces intelligents ne cessent de se developper et sont en interaction avec les objets de la vie courante. Ils exploitent des signaux video, des signaux audio et des donnees environnementales afin de permettre la localisation des personnes, la reconnaissance des gestes, etc. Le projet FUICoCAPs entre dans cette categorie de technologies, il se base sur le developpement des capteurs a faible cout fournissant des informations enrichies sur le comportement des personnes dont le but est d'automatiser et de reduire la consommation de l'eclairage, de la ventilation, du chauffage, etc
The musculoskeletal system is a complex arrangement of muscles, tendons and bones. This system is... more The musculoskeletal system is a complex arrangement of muscles, tendons and bones. This system is affected by many factors, and presents unique features for each individual. There is constant risk that the normal behavior of this system might be altered due to transport accidents or aging effects. Usually, physical therapy sessions are practiced at the clinics to recover the patient’s functionalities. Recently, tele-rehabilitation has been investigated to improve the clinical outcomes. In this paper, we introduced a novel tele-rehabilitation solution based on serious gaming technologies. Different components of the system were designed and described. Two serious game scenarios were created. A multi-sensor fusion approach was developed to improve the kinematic accuracy of the rehabilitation movement. A preliminary evaluation showed great potential for our system to be applied in a home-based rehabilitation setting.
Technologies biomédicales, 2015
La detection automatique de la detresse (chute, malaise, etc.) des personnes âgees a domicile ou ... more La detection automatique de la detresse (chute, malaise, etc.) des personnes âgees a domicile ou en institution (EHPAD, maison de retraite, foyers logements, etc.) est une problematique importante. Cela passe par differents types de capteurs portes ou non, des systemes de fusion de l'information et d'analyse des donnees. Une premiere analyse concerne la demarche permettant de detecter une qualite de l'equilibre, facteur de risque de chute futur. Une deuxieme analyse presentee dans cet article concerne l'evaluation de differents capteurs de chute existants sur le marche a travers la methodologie BiVACS (Bien Vivre son Autonomie Chez Soi). Enfin, un capteur de detection de detresse qui utilise l'analyse de l'environnement sonore a travers les sons de la vie courante est presente.
Advances in Science, Technology and Engineering Systems Journal, 2019
HAL (Le Centre pour la Communication Scientifique Directe), May 31, 2017
HAL (Le Centre pour la Communication Scientifique Directe), May 15, 2008
This presentation deals with different research axis followed by the Televigilance activity in Te... more This presentation deals with different research axis followed by the Televigilance activity in Telecom Sudparis : a) Multi-sensors Ambulatory Terminal on Patient: Automatic Fall detector and noise-robust vital signal extraction, Alarm automatisation and context identification based on Data Fusion, Physiological and actimetric data (cardiac frequency, movements,...) Fall, posture or activity recognition, Contextual information (sounds, localisation, activity) ANASON with ESIGETEL (D. Istrate) b) Cardiac pathology detection (R. Andreao): ECG signal segmentation based on sub-beat Hidden-Markov Models, Ischemias and Arrythmias events classification, Voice-controlled man-machine interface for Elderly persons to the smart home environment with TelecomParisTech (G. Chollet, P. Milhorat) c) Activity monitoring in care-houses in collaboration with LEGRAND company (P.Dore, T. Guettari) It also enlarges the scope to other teams within the Institut Mines-Telecom group, such as the QoL (Quality ...
Annals of the University of Craiova, Series: …
Abstract: The advent of modern communications and the low cost of some kinds of devices have resu... more Abstract: The advent of modern communications and the low cost of some kinds of devices have resulted in a desire to equip elderly peoples' homes with sensors to monitor their activities and be forewarned of abnormal situations. In such an environment, sound may ...
Sensors
Stress is an increasingly prevalent mental health condition across the world. In Europe, for exam... more Stress is an increasingly prevalent mental health condition across the world. In Europe, for example, stress is considered one of the most common health problems, and over USD 300 billion are spent on stress treatments annually. Therefore, monitoring, identification and prevention of stress are of the utmost importance. While most stress monitoring is carried out through self-reporting, there are now several studies on stress detection from physiological signals using Artificial Intelligence algorithms. However, the generalizability of these models is only rarely discussed. The main goal of this work is to provide a monitoring proof-of-concept tool exploring the generalization capabilities of Heart Rate Variability-based machine learning models. To this end, two Machine Learning models are used, Logistic Regression and Random Forest to analyze and classify stress in two datasets differing in terms of protocol, stressors and recording devices. First, the models are evaluated using le...
HAL (Le Centre pour la Communication Scientifique Directe), Feb 1, 2022
HAL (Le Centre pour la Communication Scientifique Directe), Jul 8, 2018
2018 13th Annual Conference on System of Systems Engineering (SoSE), 2018
The research purpose is to study the impact’s use of connected devices on cardiovascular diseases... more The research purpose is to study the impact’s use of connected devices on cardiovascular diseases. In this paper, we will explain our experimental methodology as well as the first outcomes. Three connected objects are being used for this experiment: a heart rate monitor belt, a tensiometer and a smartwatch. This communication intends to explain the methodology and the procedure that are being used to conduct this project. Our main objective is to monitor participants during their daily routine life, to record and to collect data continuously. This health care monitoring is a case of study of system of systems engineering within it we manage interactions between three aspects: humans, environment and sensors. The idea, then, is to study the different relations and correlations existing between variables coming from those aspects. An important part, of this work, takes into consideration the participant’s emotional aspect (stress, happiness, sadness, among) and analyse that using the appropriate artificial intelligence tools. Being able to detect participant’s emotion, categorize it and analyse its impact on cardiovascular disease, is the main goal of this work.
Cet article decrit les travaux de recherche d'une equipe pluridisciplinaire regroupee autour ... more Cet article decrit les travaux de recherche d'une equipe pluridisciplinaire regroupee autour du theme de la televigilance medicale. Il recense les resultats d'une collaboration de nombreuses annees qui a abouti au developpement et a la mise en place d'une plateforme multimodale pour la televigilance medicale. Cette plateforme est composee de trois systemes heterogenes mais complementaires concus pour assurer le maintient a domicile de personnes âgees en toute securite. Dans cet article, nous presentons une description detaillee des multiples capteurs que nous utilisons pour surveiller a distance l'etat de sante d'une personne âgee et/ou d'un patient a domicile. Il s'agit precisement d'un ensemble de microphones places convenablement dans la maison, d'un dispositif portable qui mesure des signaux physiologiques et detecte la chute et d'un ensemble de capteurs infrarouges. Cette plateforme geree et commandee a distance est utilisee par le person...
This work propose a remote healthcare monitoring system designed to derive elderly’s activities o... more This work propose a remote healthcare monitoring system designed to derive elderly’s activities of daily living and distress situation in Nursing Home environments through a set of pyroelectric infrared sensor placed in the rooms. We aim to infer from the nursing home environment information as the exits and entries in the room, presence of caregivers and activities as night rounds, sleeping, eating, care-giver intervention. Thank to the sensors emplacement in the present case is possible to extract patterns regarding paths performed inside the room. Based on these patterns, we propose in a first step, a finite state model that represents the behavior of only one person moving inside the room. Through accomplishing of this model, we can derive some information as resident tracking, presence of care-givers, entries and exits. In previous work we have used the Dempster-Shafer theory (DST) based on static and dynamic model called Evidential Networks [11] in order to take into account t...
In the frame of CompanionAble European project, we have utilized many ambient sensors in order to... more In the frame of CompanionAble European project, we have utilized many ambient sensors in order to implement multimodal fusion application aiming to detect abnormal status of the care receiver CR. We have exploited actimetry and sound signal to track and localize the person in his living place. In order to increase localization accuracy and to improve performance of the tracking system, ultimodal fusion methods can be used to exploit several modalities. Among these techniques, we are nterested by those based on finite states model with a random variable that changes along the time. Relying on N-dimensional states transition matrix, we propose a fusion model of heterogonous data generated from multiple ambient sensors. To detect abnormal situations of the observed person, we would use a personalized matrix estimated by applying a Polya model.
The research purpose is to study the impact’s use of connected devices on cardiovascular diseases... more The research purpose is to study the impact’s use of connected devices on cardiovascular diseases. One of our objective is stress recognition during daily routine life. To achieve that a long term experimentation have been conducted. This longitudinal empirical research study aided by connected devices enabling psycho-physiological monitoring to study the correlation between emotional states including stress levels and prognosis of cardiovascular disease. In this paper, we will present the main participant’s feedback concerning the conducted experimentation using wearables sensors. This manuscript explains participant selection. It will not treat data conducted from this experiment or show numerical results. It is a statistical feedback concerning the experimentation protocol. We will clarify the protocol strengths and weaknesses. Our main motivation is to give an opinion to other research and to inspire them if they want to conduct a similar experimentation.
Applied Medical Informatics, 2013
Our study has assessed the benefits that electronics health records can bring to small health car... more Our study has assessed the benefits that electronics health records can bring to small health care facilities by qualitatively and quantitatively analyzing a limited number of open source software suites in the area of medical informatics. We have investigated the way in which these benefits may be achieved by implementing the presented software solutions, taking care to highlight the peculiarities of the open source model of development that prove to be differentiating factors against equivalent closed source commercial solutions. Not taking into account the financial aspect (free software solutions have no licensing costs), we have tried to discern the intrinsic advantages of the model of free software development and its particularities in this specific area of investigation: health informatics.
The BV2 project aims to propose a monitoring system for wellbeing but also well-aging working on ... more The BV2 project aims to propose a monitoring system for wellbeing but also well-aging working on the prevention, detection and monitoring using a System of the Systems (SoS) approach. The project partner already uses the IoT technologies and the BV2 platform will combine the different developed systems. The main originality of the project consist s in the development of a virtual platform by combining the existing systems
Applied Medical Informatics, 2013
We developed an instrument which can ensure a quick and easy dialogue between the physicians of t... more We developed an instrument which can ensure a quick and easy dialogue between the physicians of the Oncology Institute and family physicians. The platform we chose was Simple Machines Forum (abbreviated as SMF), a free Internet forum (BBS - Bulletin Board System) application. The purpose of this article is not to detail the software platform, but to emphasize the facilities and advantages of using this solution in the medical community.
Cet article presente un systeme de localisation basee sur la combinaison de deux modules : SHPT (... more Cet article presente un systeme de localisation basee sur la combinaison de deux modules : SHPT (Smart Home Person Tracking), compose par un reseau de capteurs infrarouge, et APT (AudioPerson Tracking), qui utilisent des microphones capables d'estimer la direction (azimut) de la source sonore. Cette combinaison augment la precision de localisation par rapport a l'utilisation de chaque systeme separement. Le logiciel de localisation (LA Module) est un outil important qui nous permet d'integrer les deux systemes, de visualiser les positions en temps reel, d'enregistrer les donnees, d'evaluer les profils de deplacement et de detecter certaines situations de detresse de la personne (certains types de chutes). Les resultats de mise en oeuvre montrent une bonne adaptation aux environnements de type Smart Home et une robustesse de detection
Aujourd'hui les technologies au service des espaces intelligents ne cessent de se developper ... more Aujourd'hui les technologies au service des espaces intelligents ne cessent de se developper et sont en interaction avec les objets de la vie courante. Ils exploitent des signaux video, des signaux audio et des donnees environnementales afin de permettre la localisation des personnes, la reconnaissance des gestes, etc. Le projet FUICoCAPs entre dans cette categorie de technologies, il se base sur le developpement des capteurs a faible cout fournissant des informations enrichies sur le comportement des personnes dont le but est d'automatiser et de reduire la consommation de l'eclairage, de la ventilation, du chauffage, etc
The musculoskeletal system is a complex arrangement of muscles, tendons and bones. This system is... more The musculoskeletal system is a complex arrangement of muscles, tendons and bones. This system is affected by many factors, and presents unique features for each individual. There is constant risk that the normal behavior of this system might be altered due to transport accidents or aging effects. Usually, physical therapy sessions are practiced at the clinics to recover the patient’s functionalities. Recently, tele-rehabilitation has been investigated to improve the clinical outcomes. In this paper, we introduced a novel tele-rehabilitation solution based on serious gaming technologies. Different components of the system were designed and described. Two serious game scenarios were created. A multi-sensor fusion approach was developed to improve the kinematic accuracy of the rehabilitation movement. A preliminary evaluation showed great potential for our system to be applied in a home-based rehabilitation setting.
Technologies biomédicales, 2015
La detection automatique de la detresse (chute, malaise, etc.) des personnes âgees a domicile ou ... more La detection automatique de la detresse (chute, malaise, etc.) des personnes âgees a domicile ou en institution (EHPAD, maison de retraite, foyers logements, etc.) est une problematique importante. Cela passe par differents types de capteurs portes ou non, des systemes de fusion de l'information et d'analyse des donnees. Une premiere analyse concerne la demarche permettant de detecter une qualite de l'equilibre, facteur de risque de chute futur. Une deuxieme analyse presentee dans cet article concerne l'evaluation de differents capteurs de chute existants sur le marche a travers la methodologie BiVACS (Bien Vivre son Autonomie Chez Soi). Enfin, un capteur de detection de detresse qui utilise l'analyse de l'environnement sonore a travers les sons de la vie courante est presente.
Advances in Science, Technology and Engineering Systems Journal, 2019