Paper in Progress

Topic:
Exploring Behavioral and Motor Differences Between ADHD and Non-ADHD Individuals Using Raspberry Pi and SenseHAT

Objective:
This research investigates whether motor patterns during learning tasks—captured via a sensor-equipped smart pen—can reveal distinguishable differences between individuals with ADHD and those without. Specifically, the study aims to identify whether people with ADHD exhibit higher frequency or amplitude of fidgeting compared to neurotypical individuals.

十月是注意力缺陷多动症宣传月。注意缺陷多动障碍。在美国庆祝一年一度的节日。保健概

🔍 Core Research Question

Can motor pattern data—such as movement frequency, intensity, and irregularity—collected by a smart pen be used to objectively distinguish between individuals with ADHD and neurotypical individuals? Furthermore, how are these motor features associated with core ADHD symptoms such as inattention and hyperactivity?

⚙️ Research Tools and Progress

Hardware Setup:
A prototype smart pen has been built using a Raspberry Pi development board equipped with a SenseHAT extension module. The device captures real-time hand movement data during writing or learning tasks via the built-in 3-axis accelerometer.

Data Acquisition Capabilities:
The smart pen is capable of collecting:

Three-axis linear acceleration (X/Y/Z)
Three-dimensional orientation angles (Roll, Pitch, Yaw)
These measurements form a multidimensional dataset of motor features.

Current Progress:

Hardware prototyping and data collection scripts have been completed.The system can now stream and record real-time motion data, which is stored in CSV format.

📈 Next Steps

The project is currently in the data collection phase. Around 30 participants will be recruited—15 diagnosed with ADHD and 15 neurotypical controls. During the study, each participant will complete designated learning tasks using the smart pen, generating a rich dataset of motion patterns.

Subsequent steps will include:

Feature extraction from raw sensor data
Training machine learning classification models
Evaluating whether the extracted motor patterns can reliably distinguish ADHD individuals from non-ADHD participants.

Paper in progress

Hardware Setup: A prototype smart pen has been built using a Raspberry Pi development board equipped with a SenseHAT extension module. The device captures real-time hand movement data during writing or learning tasks via the built-in 3-axis accelerometer.

​​The project is currently in the data collection phase. Around 30 participants will be recruited—15 diagnosed with ADHD and 15 neurotypical controls. During the study, each participant will complete designated learning tasks using the smart pen, generating a rich dataset of motion patterns.

Hardware Setup:
A prototype smart pen has been built using a Raspberry Pi development board equipped with a SenseHAT extension module. The device captures real-time hand movement data during writing or learning tasks via the built-in 3-axis accelerometer.

The project is currently in the data collection phase. Around 30 participants will be recruited—15 diagnosed with ADHD and 15 neurotypical controls. During the study, each participant will complete designated learning tasks using the smart pen, generating a rich dataset of motion patterns.