Source: atthree23 / AIX
Brain computer interface (BCI), Also known as the Brain Machine Interface (BMI), converts brain activity into output, allowing loss or impairment of functions such as movement and speech. BCI is used to assist people with severe paralysis or communication problems due to stroke, spinal cord injury, amyotrophic lateral sclerosis (ALS) (also known as Lugeric’s disease), and other conditions. I have come.Recently published new research Nature Led by researchers at Stanford University, using to show a new paradigm for brain-computer interfaces artificial intelligence (AI) Decodes brain activity into text in real time by considering handwritten movements.
The lead author of this study is Dr. Frank Willett, a research scientist at the Howard Hughes Medical Institute (HHMI) at Stanford University, and co-author is Krishnachenoy, an HHMI researcher and Professor Lee R at Stanford University. Includes a doctor. .. Donald T. Avansino, a senior lecturer in Hochberg, MD, PhD and neurology at Harvard Medical School, and a researcher at Stanford University. The research was funded by the National Institute of Health’s Advancing Innovative Neurotechnologies® (BRAIN) initiative, the National Institute of Neurological Disorders and Stroke (NINDS), and the National Institute on Deafness and other Communication Disorders (NIDCD).
Mental-Handwriting-to-Text: BCI’s new paradigm
“So far, the main focus of BCI research has been on the recovery of overall motor skills, such as reaching and grasping, and pointing and clicking with a computer cursor,” the researchers write. I am. “But a rapid sequence of very dexterous actions such as handwriting and touch typing may enable faster communication speeds. Here we develop an intracortical BCI that decodes attempted handwriting movements. Did. neural Converts to text in real time using activity in the motor cortex and a recurrent neural network decoding approach. “
In this study, a right-handed 65-year-old man was equipped with two 96 microelectrode cortical arrays for recording neural signals. Specifically, a Blackrock Microsystems NeuroPort ™ array with 1.5 mm electrodes was placed in the precentral gyrus region of the left hemisphere of the study participants’ brains. Participants had had a spinal cord injury nine years before study enrollment and had very limited voluntary limb movements.
Researchers used software developed through MATLAB and Simulink to manipulate recorded data and real-time decoding. Brain activity data was collected when participants were appointed to attempt handwritten text in the course of multiple sessions. The decoder was trained using session data.
AI Deep Learning: Recurrent Neural Networks (RNN)
In this study, we used a two-layer gated recurrent unit recurrent neural network (RNN) to convert participant brain activity into time-series character probabilities and trained the decoder using forced alignment labeling. RNNs have been trained to predict character probabilities from a one second time delay, taking into account system processing time.
Artificially Intelligence, Recurrent Neural Networks are a class of artificial neural networks that are often used when contextual data is needed to provide decisions based on natural language processing, speech recognition, and input data. Artificial neural networks are somewhat inspired by the biological brain, which has an architecture consisting of layers of interconnected nodes called artificial neurons. RNN’s deep learning algorithms can process sequences of inputs using internal states that work as follows: Memory, If the inputs are interrelated. Relationships are “remembered” while the recurrent neural network is training. RNNs are useful in scenarios where you need to model non-linear temporal or sequential relationships.
“This BCI has paralyzed our hands due to spinal cord injury, achieving typing speeds of 90 characters per minute online with 94.1% raw accuracy and over 99% offline with general-purpose AutoCorrect. We have achieved accuracy, “says the researchers. report. “As far as we know, these input speeds exceed those reported by other BCIs and are comparable to the typical smartphone input speeds (115 characters / minute) for individuals in the participant’s age group. “
Copyright © 2021 Cami Rosso All rights reserved.
"interface" - Google News
July 10, 2021 at 03:15PM
https://ift.tt/3k4cM12
AI Brain Computer Interface Turns Mental Handwriting into Text - Illinoisnewstoday.com
"interface" - Google News
https://ift.tt/2z6joXy
https://ift.tt/2KUD1V2
Bagikan Berita Ini
0 Response to "AI Brain Computer Interface Turns Mental Handwriting into Text - Illinoisnewstoday.com"
Post a Comment