Real-time brain computer interface (BCI) for robotic systems

• 主要作者: Seng, Deon Wee How
• 其他作者: Lam Siew Kei
• 格式: Final Year Project
• 語言: English
• 出版: 2017
• 主題: DRNTU::Engineering::Computer science and engineering
• 在線閱讀: http://hdl.handle.net/10356/72816
• 機構: Nanyang Technological University

Research and development in computer technology has been intense and successful since the early 20th century till today. It has allowed us to possess most of our prized possession today, such as our smartphones and computers. Today, technology is ubiquitous with an ever-growing demand for better technology. Not only does it improve and changes our daily life, computer technology has also contributed greatly to assist in medical operations. One of the trending research today is the Brain Computer Interface(BCI) with the purpose of assisting people with disabilities. BCI involves the capturing of electrical signals, such as ElectroEncephaloGram(EEG) from the user’s brain and processing the signals for further applications. Various biosensing hardware for BCI are available for purchase in the market. One such example is the Ganglion Board, developed by OpenBCI. It has 4 input channels to capture EEG signals at 4 different channel locations on the brain with reference to the International 10/20 system. Furthermore, OpenBCI’s bio-sensing boards are capable of capturing Electromyography(EMG), which is the measure of muscles and the nerve cells that control them. In this project, a Matlab-based BCI was developed to ease the process of interfacing the Ganglion Board with external devices. The Ganglion Board was used to sense the EEG signals from the subject’s brain and stream it to the computer through Bluetooth Low Energy (BLE) transfer protocol. As the server, the computer received the EEG signals and streamed them into Matlab through the Lab Streaming Layer(LSL) for analysis and processing. After which, the program classified an output label corresponding to the processed data to control the targeted robotic system. The BCI system can be broken into connection setup, signal acquisition, signal processing, training, neural network training, real-time testing and robotic control.