Related Experiment Video
Updated: Jan 30, 2026

Brain Morphology of Cannabis Users With or Without Psychosis: A Pilot MRI Study
Published on: August 18, 2020
User activity recognition system to improve the performance of environmental control interfaces: a pilot study with
Arturo Bertomeu-Motos1, Santiago Ezquerro2, Juan A Barios2
1Miguel Hernández University of Elche, Av. Universidad w/n, Ed. Innova, Elche, 03202, Spain. abertomeu@umh.es.
This study shows that the AIDE mode, using a prediction model, significantly reduced task time and complexity for users with motor impairments controlling their environment. This assistive technology enhances independence by predicting user intentions for environment control interface (ECI) use.
Area of Science:
- Rehabilitation Engineering
- Human-Computer Interaction
- Neuroscience
Background:
- Assistive technologies enhance quality of life and reduce care dependence for individuals with motor impairments.
- Brain-Computer Interfaces (BCI) and exoskeletons are advancing interaction capabilities for users with motor disabilities.
- The AIDE project developed a multimodal Environment Control Interface (ECI) analyzing user abilities and intentions.
Purpose of the Study:
- To evaluate the effectiveness of the AIDE project's Environment Control Interface (ECI).
- To assess the ECI's ability to analyze environmental information and user residual abilities.
- To determine if the ECI can identify user behaviors and intentions for improved environmental control.
Main Methods:
- The ECI was evaluated in a simulated home environment using a two-screen setup.
- Sensorimotor rhythms and oculoversion data from BCI2000 were used for online ECI control.
- Eight participants with neurological diseases or spinal cord injury performed simulated Activities of Daily Living (ADLs) in AIDE mode (with prediction) and Manual mode.
Main Results:
- The AIDE mode significantly reduced mean task completion time compared to Manual mode (p<0.001).
- Users performed more tasks in the AIDE mode within the same timeframe.
- ADLs required fewer abstraction levels in AIDE mode (1 step) versus Manual mode (≥3 steps).
- User intention prediction achieved approximately 87% accuracy using conditional random fields (CRF).
Conclusions:
- Analyzing environment and user behavior can predict intentions, creating a new paradigm for ECI design.
- The developed ECI, tested in simulation, is adaptable to real environments.
- This technology has the potential to significantly increase user independence at home.
More Related Videos
Related Concept Videos
Pilot and Numeric Relaying
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Protein-protein Interfaces
Protein-Protein Interfaces
Bioavailability Study Design: Healthy Subjects Versus Patients
Environmental Influences on Intelligence

