- Context-Aware Activity Recognition Systems
- Anomaly Detection Techniques and Applications
- Balance, Gait, and Falls Prevention
- Gait Recognition and Analysis
- IoT and Edge/Fog Computing
- IoT-based Smart Home Systems
- Muscle activation and electromyography studies
- Tactile and Sensory Interactions
- Human Pose and Action Recognition
- Agriculture and Rural Development Research
- Non-Invasive Vital Sign Monitoring
- Network Security and Intrusion Detection
- Video Surveillance and Tracking Methods
- Hand Gesture Recognition Systems
- Electric Motor Design and Analysis
- Time Series Analysis and Forecasting
- Advanced Sensor and Energy Harvesting Materials
- Indoor and Outdoor Localization Technologies
- Music and Audio Processing
- Mobile Health and mHealth Applications
- Security in Wireless Sensor Networks
- Speech and Audio Processing
- Technology Use by Older Adults
- Neural Networks and Applications
- Induction Heating and Inverter Technology
Université de Lille
2015-2025
IMT Nord Europe
2015-2025
Institut Mines-Télécom
2021-2025
Université Gustave Eiffel
2024
Centre de recherche Inria Lille - Nord Europe
2023
Railenium
2019
École des Mines de Douai
2009-2017
Pontifícia Universidade Católica de Goiás
2008-2017
Universidade Estadual de Goiás
2008-2017
Laboratoire Stress Oxydant et Pathologies Métaboliques
2014-2016
By 2050, about one third of the French population will be over 65. Our laboratory's current research focuses on monitoring elderly people at home, to detect a loss autonomy as early possible. aim is quantify criteria such international activities daily living (ADL) or Autonomie Gerontologie Groupes Iso-Ressources (AGGIR) scales, by automatically classifying different ADL performed subject during day. A Health Smart Home used for this. includes, in real flat, infrared presence sensors...
The Internet of Things (IoT) is a computing paradigm whereby everyday life objects are augmented with computational and wireless communication capabilities, typically through the incorporation resource-constrained devices including sensors actuators, which enable their connection to Internet.The IoT seen as key ingredient for development smart environments.Nevertheless, current ecosystem offers many alternative solutions diverse performance characteristics.This situation presents major...
Over the years, smartphones have become tools for scientific and clinical research. They can, instance, be used to assess range of motion joint angle measurement. In this paper, our aim was determine if are reliable accurate enough This work proposes an evaluation different smartphone sensors performance manufacturer algorithm performances with comparison gold standard, industrial robotic arm actual standard use inertial unit in measurement, Xsens product. Both dynamic static protocols were...
Automatic human Activity Recognition (AR) is an important process for the provision of context-aware services in smart spaces such as voice-controlled homes. This paper presents on-line Activities Daily Living (ADL) recognition method automatic identification within homes which m ultiple sensors, actuators and automation equipment coexist, including audio sensors. Three sequence-based models are presented compared: a Hidden Markov Model (HMM), Conditional Random Fields (CRF) sequential Logic...
Considering the important role of cervical joint position sense on control human posture and locomotion, accurate reliable evaluation neck proprioceptive abilities appears great importance. Although cervicocephalic relocation test (CRT) to neutral head (NHP) usually is used for both research clinical purposes, its test-retest reliability has not been clearly established yet. The purpose present experiment was 1) evaluate CRT NHP 2) determine number trial recordings required ensure...
This paper proposes an implementation of a Kalman filter, using inertial sensors smartphone, to estimate 3-D angulation the trunk. The developed system monitors trunk angular evolution during bipedal stance and helps user improve balance through configurable integrated auditory-biofeedback (ABF) loop. A proof-of-concept study was performed assess effectiveness this so-called iBalance-ABF--smartphone-based audio-biofeedback system--in improving standing. Results showed that young healthy...
One of the greatest challenges in Ambient Assisted Living is to design health smart homes that anticipate needs its inhabitant while maintaining their safety and comfort. It thus essential ease interaction with home through systems naturally react voice command using microphones rather than tactile interfaces. However, efficient audio analysis such noisy environment a challenging task. In this paper, real-time system, AuditHIS devoted presented. has been tested thought three experiments...
An online recognition system must analyze the changes in sensing data and at any significant detection; it has to decide if there is a change activity performed by person. Such can use previous sensor readings for decision-making (decide which performed), without need wait future ones. This paper proposes an approach of human on data. We present four methods used extract features from sequence events. Our experimental results public smart home show improvement effectiveness classification accuracy.
Improvements in medicine increase life expectancy the world and create a new bottleneck at entrance of specialized equipped institutions. To allow elderly people to stay home, researchers work on ways monitor them their own environment, with non-invasive sensors. meet this goal, smart homes, lots sensors, deliver information activities person can help detect distress situations. In paper, we present global speech sound recognition system that be set-up flat. We placed eight microphones...
Abstract Smart homes are equipped with several sensor networks to keep an eye on both residents and their environment, interpret the current situation react immediately. Handling large scale dataset of sensory events real time enable efficient interventions is challenging very difficult. To deal these data flows challenges, traditional streaming classification approaches can be boosted by use incremental learning. In this paper, we presented two new Incremental SVM methods improve...
One of the greatest challenges in Ambient Assisted Living is to design health smart homes that could be able anticipate needs its inhabitant while maintaining their comfort and safety with an adaptation house environment a facilitation connections outside world. The most likely benefit from these are people loss autonomy such as disabled or elderly cognitive deficiencies. But it becomes essential ease interactions home through dedicated interfaces, particular, thanks systems reactive vocal...
Over the last decade, Higher Education has focused more of its attention toward soft skills compared to traditional technical skills. Nevertheless, there are not many studies concerning relation between courses followed within an academic program and development This work presents a practical approach model effects on proficiency. Multiple Membership Ordinal Logistic Regression models trained with real data from students 2021, 2022, 2023 cohorts general engineering in French institution. The...
Communication Across the Curriculum (CXC) has been gaining theoretical sophistication in recent years, slowly moving beyond an exclusively skills orientation. Proponents of In Disciplines (CID) focus on teaching students specific disciplinary communication conventions as productive knowledge and identity. I claim this essay that CID specialized competencies is too narrow. The CXC project should instead emphasize liberal education, which a multifaceted citizenship. Liberal education can be...
By 2050, about a third of the French population will be over 65. To face this modification population, current studies our laboratory focus on monitoring elderly people at home. This aims detect, as early possible, loss autonomy by objectivizing criterions such international ADL or AGGIR scales implementing automatic classification different Activities Daily Living. A Health Smart Home is used to achieve goal. flat includes sensors. The data from various sensors were classify each temporal...