BRAIN-COMPUTER INTERFACE VIRTUAL KEYBOARD

Brain-Computer Interface (BCI) is a technology that translates the brain's electrical activity into a command for a device such as a robotic arm, a wheelchair, or a spelling device. BCIs have long been described as an assistive technology for severely disabled patients because they completely bypass

Project Title

BRAIN-COMPUTER INTERFACE VIRTUAL KEYBOARD

Project Area of Specialization

NeuroTech

Project Summary

Brain-Computer Interface (BCI) is a technology that translates the brain's electrical activity into a command for a device such as a robotic arm, a wheelchair, or a spelling device. BCIs have long been described as an assistive technology for severely disabled patients because they completely bypass the need for muscular activity. General computing skills continue to be an important workforce need, and the inability to use such a common instrument as the physical keyboard alienates certain individuals from a significant portion of the workforce, and society in general. To provide an accessibility option for those who are unable to use a physical keyboard (e.g., those with a motor disability), we will create a Brain-Computer Interface (BCI) Virtual Keyboard. We believe a large majority of the population that is unable to use a keyboard or mouse will be able to use a BCI in a meaningful way. We utilized the eMotiv EPOC neural headset (hereafter referred to as the eMotiv headset) as our physical input device for several reasons. The eMotiv headset is a consumer-ready and relatively inexpensive option for end-users. Use of consumer-ready systems has been suggested to provide a practically portable solution for recording EEG signals. In addition, if our virtual keyboard proves to be successful, Emotiv provides an application store for developers using the eMotiv headset that would enable us to easily distribute our software. The eMotiv headset detects sensorimotor signals, which are neurological signals related to motor control. This approach differs from many other implementations. For example, P300-based systems rely on a signal from the brain that is generated as a response to outside stimuli. Systems that rely on outside stimuli force the selection rate to be determined by the stimuli, as opposed to the user. The eMotiv headset does not rely on any outside stimuli, which we believe will give users a greater sense of control.

Project Objectives

The objectives of the projects are:

• To provide a virtual keyboard to assist people with motor disabilities.
• To provide a virtual keyboard that will be operated through the brain signals.
• To develop  a BCI virtual keyboard system for communication that could be used daily by patients without the help of a trained team of researchers
• To provide a viable alternative input device for those unable to use a physical keyboard.

Project Implementation Method

This project was developed in Java using Eclipse. Java was chosen because of our experience and the relative ease of designing a graphical user interface in Java. The eMotiv API is provided as a native C++ DLL. However, Emotiv provides a wrapper that utilizes the Java Native Access library to enable Java developers to utilize the eMotiv API. Additionally, the project uses the Java Robot class to send keyboard input from the virtual keyboard. The Robot class allows programmatic control of the mouse and keyboard (e.g., directing the mouse to a specific location of the screen or programmatically generating keyboard button events). The overall architecture of the design focuses on the implementation of the Model-View-Controller design pattern. In this implementation, the model is the Virtual Keyboard, the view is the Graphical Display, and the controller handles the mapping of headset inputs to functions we designed in the model. We believe this architecture allows for flexibility in our implementation. This flexibility can be realized by altering the controller to allow for different devices to utilize the same model and display. Additionally, the display could be tailored to various user expectations dependent on platform-specific or societal conventions.

First, we allowed the headset inputs to be mapped to functions based on an XML configuration file. The input mapping allows a user to choose the most appropriate inputs for his or her ability (e.g., left- or rightwink). Our system is designed to only require at least two distinct input signals. Each available input signal maps to one of the following actions that are ordered by an initial assessment of usefulness (most useful to least useful):

1. Select

2. Move Right

3. Move Out

4. Move Down

5. Move Left

6. Move Up

To realize this limited number of inputs, we created a model of the keyboard where the user navigates through the keys to make a selection. We needed to minimize the average number of movements required to navigate to each key. We accomplished this by utilizing a drill-down approach in which the user starts at a high-level and selects a set of keys and then navigates within this reduced set, selecting increasingly smaller sets until the current set contains only a single key The eMotiv headset provides several recognition suites: the Expressiv and Cognitiv suites. The Expressiv suite detects neural signals related to facial feature movements (e.g., a blink). The Cognitive suite allows the user to train the system to recognize custom neural states. The Expressive suite provides enough available input signals to satisfy the needs of our virtual keyboard. However, we recognized that not all users are capable of utilizing the full suite. The Cognitive suite provides the freedom to define inputs that are tailored to an individual. 

Benefits of the Project

The keyboard helps people with disabilities to write or type words. Taking into account the fact that it provides an unusual and interactive method of human-machine interaction, the virtual keyboard could also raise the interest of those who are passionate about futuristic technology.

This keyboard assists people with disabilities. Unfortunately, the patients who suffered a brain stroke, spinal cord injuries, or were diagnosed with Locked-In syndrome or amyotrophic lateral sclerosis, cope with severe speaking impairments and neuromotor diseases. Some significant examples could be the scientist Stephen Hawking and the journalist Jean Dominique Bauby. They lost their ability to communicate naturally (by spoken words or talking) and to interact with the outside environment via peripheral nerves and muscles, similar to the condition of healthy people.

Technical Details of Final Deliverable

In this project, we will build a virtual keyboard implemented using a Brain-Computer Interface (BCI) that interacts with the eMotiv EPOC Neural Headset as our physical input device for several reasons. The eMotiv headset detects sensorimotor signals, which are neurological signals related to motor control. The eMotiv headset is a consumer-ready and relatively inexpensive option for end-users. The use of consumer-ready systems has been suggested to provide a practically portable solution for recording EEG signals.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Health

Other Industries

IT , Medical

Core Technology

NeuroTech

Other Technologies

Others

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

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