Extracts from the article: –
“Mind control may sound like it’s out of a sci-fi show, but like the tablet, the Universal Translator, or the virtual reality device, it’s actually a technology that’s made its entrance. in the real world. Although these devices often require advanced technology and expensive equipment to correctly interpret brainwaves, with the right machine learning system, it is possible to do things like this spirit controlled flamethrower on a much smaller budget. (Video, embedded below.)
[Nathaniel F] was already experimenting with the use of brain-computer interfaces and machine learning, and wanted to see if he could build something practical combining these two technologies. Instead of turning to an EEG machine to read brain patterns, he chose a much cheaper Mindflex and associated with a machine learning system run TensorFlow to compensate for some of its shortcomings. The processing is done by a Raspberry Pi 4, which sends commands to an Arduino to trigger the flamethrower when it detects the appropriate thought patterns. Also, don’t forget the flamethrower part of this build: it was completely designed and built by [Nathanial F] as well using gas and an arc lighter.
While the build took many hours of training to collect the right amount of data to build the neural network and works like the proof of concept it hoped for, [Nathaniel F] notes that it could be improved by replacing the obsolete Mindflex with a better EEG. “