Description:FIG.1 demonstrates a complete idea of the proposed anti-tremor band. To start the device, we used the switch. The Nano 33 BLE has a 9-axis Inertial Measurement Unit (IMU), which includes an accelerometer, gyroscope, and magnetometer with 3-axis resolution each. The input voltage is 3.7 volt which is used to start the motor.
After wearing the band, the built-in accelerometer can sense the hand's motion and then start rotating the vibration motor to stabilize the handshaking. When the inbuilt accelerometer sensor detects the motion of the hand through radial and median nerve, machine learning algorithms can analyze the data and predict whether the tremor is in the primary, intermediate, or crucial stage. Then, the patient can level up or level down the intensity of that vibration motor accordingly through a mobile phone. The vibration works on the radial and median nerve to stabilize the tremor. After predicting the stage, the data is sent to the mobile phone, and the patient can quickly control the intensity of the vibration. The inbuilt Bluetooth in Arduino nano board helps the data transmission between the phone and the anti-tremor band. , Claims:We Claim:
1. This device claims a technique for reducing tremors in a patient entails positioning a median effector in one location concerning a median nerve and radial nerve in another; administering the first stimulus to the median nerve through the median effector and the radial nerve through the radial effector, and reducing the tremor amplitude by altering the stage of patient's neural network.
2. This device claims that the mechanism of machine learning helps to detect the stage of the tremor. The dataset of different types of tremor patients has been trained to the model, and according to the hand motion, the model trains to detect the level of tremor.