Attention deficit hyperactivity disorder (ADHD) is a common neurobehavioral disorder in childhood. Due to the long-term negative effects on quality of life and the difficulty of spontaneous remission, early diagnosis and treatment are particularly important. The current assessment tools mainly include scales and neuropsychological tests. Scales are subjective and are not easy to quantify children's behaviors. Neuropsychological tests are usually performed by computers. There are still problems of ecological validity. Therefore, the diagnosis or evaluation of ADHD still faces many challenges. This study integrates VR technology with wearable neurobehavioral sensing technology, including brain waves, eye trajectory tracking, head rotation and limb movements, to develop an attention assessment system. Based on the Taiwanese children's classroom, a virtual classroom is developed. Tasks, in regard to selective attention, continuous attention, and executive function, are embedded into the virtual classroom. Machine learning methods are used to perform multi-modal analysis on the data of task performance (missing error rate, alternative error rate, response time), neural behavior (brain wave, eye trajectory tracking, head rotation, limb movement) and assessment scales (CONNERS, SNAP-IV, Weiss's) in order to establish an automated assessment/ diagnostic model for attention deficit and hyperactivity disorder. In addition, we will further explore the impact of a variety of distractions, including visual interference, auditory interference, smell interference, on the distraction of children's attention.
|Effective start/end date
|1/08/20 → 31/07/21
UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):
- Virtual Reality
- Artificial Intelligence
- Neuro Behavior
- Wearable Sensing
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.