A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Brain computer interface based robotic arm control
Brain computer interface (BCI) establishes a communication channel between a computer and a human brain which converts brain activity to control signals. With the advancement in research and technology, many BCI based rehabilitation devices have been developed to augment, support, and supplement human motion in a paralyzed or partially disabled person. This would help in developing a smart society where a disabled person will have the freedom to complete their day to day tasks. In the proposed experimental setup, brain signals are used to move the robotic arm and perform different tasks i.e., picking and placing. Electroencephalography (EEG) signals are recorded using a five-channel wearable headband. A total of five subjects voluntarily participated in the study, with an informed consent. The EEG data is recorded for a duration of twenty minutes for each participant, and eight different statistical features are extracted to detect clench and attention signals. Five different classifiers namely support vector machine, Naive Bayes, K-nearest neighbor, multilayer perceptron, and random forest are used. The results are compared in terms of accuracy and error parameters. The proposed method achieves significant results for smart robotic arm control.
Brain computer interface based robotic arm control
Brain computer interface (BCI) establishes a communication channel between a computer and a human brain which converts brain activity to control signals. With the advancement in research and technology, many BCI based rehabilitation devices have been developed to augment, support, and supplement human motion in a paralyzed or partially disabled person. This would help in developing a smart society where a disabled person will have the freedom to complete their day to day tasks. In the proposed experimental setup, brain signals are used to move the robotic arm and perform different tasks i.e., picking and placing. Electroencephalography (EEG) signals are recorded using a five-channel wearable headband. A total of five subjects voluntarily participated in the study, with an informed consent. The EEG data is recorded for a duration of twenty minutes for each participant, and eight different statistical features are extracted to detect clench and attention signals. Five different classifiers namely support vector machine, Naive Bayes, K-nearest neighbor, multilayer perceptron, and random forest are used. The results are compared in terms of accuracy and error parameters. The proposed method achieves significant results for smart robotic arm control.
Brain computer interface based robotic arm control
Latif, Muhammad Yasir (author) / Naeem, Laiba (author) / Hafeez, Tehmina (author) / Raheel, Aasim (author) / Saeed, Sanay Muhammad Umar (author) / Awais, Muhammad (author) / Alnowami, Majdi (author) / Anwar, Syed Muhammad (author)
2017-09-01
356631 byte
Conference paper
Electronic Resource
English
Review of Machine Learning Techniques for EEG Based Brain Computer Interface
| Online Contents | 2022
A new auditory brain-computer interface based on stream segregation utilizing ASSR
| TIBKAT | 2024