EMG BASED ARTIFICIAL PROSTHETIC HAND

Prosthetic hands are devices designed to help those with full or partial hand loss retain the function and appearance of a regular hand. Basic prosthetic hands are cosmetic replicas with only basic function. Whereas innovative electric prosthetic hands have a set of fully articulated fingers.

Project Title

EMG BASED ARTIFICIAL PROSTHETIC HAND

Project Area of Specialization

Artificial Intelligence

Project Summary

Prosthetic hands are devices designed to help those with full or partial hand loss retain the function and appearance of a regular hand. Basic prosthetic hands are cosmetic replicas with only basic function. Whereas innovative electric prosthetic hands have a set of fully articulated fingers.

Myoelectric Hand Prostheses:

Myoelectric hand prostheses come the closest to replacing a natural hand or arm. They do not require a harness and are controlled by nerves and electrical impulses from the wearer’s residual limb.

Losing a hand or an arm doesn’t mean losing independence. Thousands of people across the world have lost all or part of an upper limb due to accident, infection, cancer or diabetic neuropathy.

Prosthetic hands provide functionality, mobility, and confidence to amputees. With these devices, amputees can overcome trauma and lead rich, full lives.

At present, the process of EMG signals is the most common approach used for the control of active prosthetic hands.

A hand amputation is one of the most impairing injuries and it can dramatically affect the capabilities of a person.

We focus on the main challenges facing myoelectric control and on possible approaches to bridge the gap, by providing a prototype for the  control strategy of prosthetic hand.

Project Objectives

The objective of the research is to design low cost myoelectric hand which utilize Myo-electric control. Surface EMG signals had been acquired from the residual limb of the hand, perform pre-processing task and featured extraction on EMG signals. The final output of EMG signals applied through servo motor to the 3D Myo-electric hand.

The subject (amputee) can perform some particular gestures e.g. opening, closing, elbow flexion and hook grip with the help of his/her forearm muscle movements.

The aim of project is to provide a control method for prosthetic hand using natural muscle movements of forearm. The EMG signals are captured by non-invasive (without surgery) methods. To make a multigrasp 3D printed hand prosthesis prototype, and a surface EMG based multigrasp control interface for its control. The 3D model of hand must be light weight. To control the Myoelectric  prosthetic hand through the acquisition and processing of the electrical signal that is generated by muscle activity in human body.

Project Implementation Method

• Collecting data: A surface electromyography (sEMG) sensor to collect the EMG signal from the residual limb muscle and the output of the sensors was amplified and then entered to the computer 
• Processing The EMG signals are difficult to analyze due to their small amplitude (micro/millivolts). Consequently, these signals are easily affected by impure signals that come from different sources of noise. Several types of noise might occur as a result of inherent equipment noise, electromagnetic radiation, motion artifacts, or others. Therefore, processing is a must in order to acquire the raw EMG signal.

• Classification of EMG signals : This is the most challenging task. Once the filtered and amplified signals are available then features are extracted for specific movements of user’s arm. These feature may either time domain or frequency domain e.g  amplitude, wave length, slope sign change.   The signals are then categories by a classifier according to these features. The classifier takes the selected features of signal as inputs and gives a output which will fall in anyone class.

• Interface of control unit with 3D-printed hand : Once the signals are classified then control unit provide commands to the actuators(motors which are assembled in the hand )  to perform a specific movement accordingly.

• Deliverables: The final product will be a 3D printed prosthetic hand, which is controlled (perform specified tasks) by the subject.  The subject will control the hand using

Benefits of the Project

can help people with disabilities,with brain signals

to develop sensing system

it can be used in medical and educational sectors

it can be used to make brain controlled heavy duty lifts

Prosthetic hands provide functionality, mobility, and confidence to amputees

Technical Details of Final Deliverable

• Design and development of 3D-printed prosthetic hand
• Collecting data.
• Pre-Processing (digital filtering).
• Classification of EMG signals
•  Interface of control unit and 3D-printed hand
• using raspberry pi
• Python / Matlab
• library : Numpy
• library: Panda

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Medical

Other Industries

Health

Core Technology

Artificial Intelligence(AI)

Other Technologies

Robotics

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com