{"id":163852,"date":"2019-09-23T21:43:53","date_gmt":"2019-09-23T13:43:53","guid":{"rendered":"https:\/\/www.geek.com\/featured\/-1804877\/"},"modified":"2019-09-23T21:43:53","modified_gmt":"2019-09-23T13:43:53","slug":"control-a-wheelchair-with-this-wearable-brain-machine","status":"publish","type":"post","link":"https:\/\/itteacheritfreelance.hk\/test\/wordpress\/2019\/09\/23\/control-a-wheelchair-with-this-wearable-brain-machine\/","title":{"rendered":"Control a Wheelchair With This Wearable Brain Machine"},"content":{"rendered":"
\n\t\t\t\t\t<\/p>\n
Test subject has flexible wireless electronics conformed to the back of the neck, with dry hair electrodes under a fabric headband, and a membrane electrode on the mastoid, connected with thin-film cables (via Woon-Hong Yeo\/Georgia Institute of Technology)<\/div>\n<\/figure>\n

An international team of researchers has developed a fully portable wireless wheelchair control platform.<\/span><\/p>\n

The wearable brain-machine interface<\/a> (BMI) offers an improvement over conventional electroencephalography (EEG) tools for measuring signals in the human brain.<\/span><\/p>\n

BMI is an essential part of rehabilitation, allowing those with ALS, chronic stroke, or other severe motor disabilities to control prosthetic accessories.<\/span><\/p>\n

Scientists combined nanomembrane electrodes, flexible electronics, and a deep learning algorithm to help disabled people wirelessly control an electric wheelchair, computer, or small robotic vehicle.<\/span><\/p>\n

Rather than donning a bulky hair-electrode cap with a mess of tangled wires trailing behind, users can simply slip a headband with three elastomeric scalp electrodes, an ultrathin wireless electronics patch, and a printed electrode.<\/span><\/p>\n

Recorded EEG data from the brain is then processed in the flexible circuitry, when wirelessly delivered via Bluetooth to a tablet up to 50 feet away.<\/span><\/p>\n

“Deep learning methods, commonly used to class<\/a>ify pictures of everyday things such as cats and dogs, are used to analyze the EEG signals,” Chee Siang Ang, senior lecturer at the University of Kent, said in a statement.<\/span><\/p>\n

“Like pictures of a dog which can have a lot of variations, EEG signals have the same challenge of high variability,” he continued. “Deep learning methods have proven to work well with pictures, and we show that they work very well with EEG signals as well.”<\/span><\/p>\n

Researchers also used deep learning models to identify which electrodes are most useful for gathering information.<\/span><\/p>\n

“We found that the model is able to identify the relevant locations in the brain for BMI,” Ang added. “This reduces the number of sensors we need, cutting cost and improving portability.”<\/span><\/p>\n

The device has so far been tested only on six human subjects\u2014none of whom are disabled.<\/span><\/p>\n

“The primary innovation is in the development of a fully integrated package of high-resolution EEG monitoring systems and circuits within a miniaturized skin-conformal system,” according to Woon-Hong Yeo, an assistant professor at Georgia Tech.<\/span><\/p>\n

Moving forward, the group plans to improve its electrodes and make the system more useful for motor-impaired individuals.<\/span><\/p>\n

The full study<\/a>\u2014conducted by researchers from Georgia Tech, Wichita State University, and the University of Kent in England\u2014was published this month in the journal <\/span>Nature Machine Intelligence<\/span><\/i>.<\/span><\/p>\n

More on Geek.com:<\/span><\/i><\/p>\n