-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
-
Cosmetic Ingredient
- Water Treatment Chemical
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
▎Editor of WuXi AppTec's content team Today, a research progress on brain-computer interface (BCI) was published on the top academic journal "Nature".
Cooperated by scientists from research institutions such as Stanford University, Howard Hughes Medical Institute (HHMI), Brown University, etc.
, for the first time, the movement of handwritten letters is decoded from brain nerve signals, so that the writing movement in the mind of paralyzed people can be converted into screen in real time On the text.
Moreover, the finally realized typing speed is more than twice that of other brain-computer interfaces in the past, which is close to the typing speed on a smart phone! Brain-computer interface refers to the realization of information exchange between external devices and the brain by interpreting neural electrical activity signals.
This technology has progressed rapidly in recent years, so that those who have lost their ability to move or speak due to nerve damage are expected to resume communication with the outside world.
Restoring large motor functions such as grasping or grasping is a major research direction in this field.
People with paralysis can use brain-computer interfaces to achieve mental fetching.
However, it is still quite challenging to complete highly detailed movements, such as writing.
The previous brain-computer interface realized point-and-click typing by controlling the computer cursor, and the communication speed was very limited, with a maximum of about 40 characters per minute.
The new brain-computer interface method developed by this new research has greatly increased the communication speed.
▲A schematic diagram of a brain-computer interface for decoding mind writing (picture source: reference [1]) Dr.
Francis Willett is the first author and corresponding author of this study.
He and his colleagues asked a research subject who was paralyzed below the neck to imagine himself Holding a pen, "try" to write a sentence on the graph paper as if the hand is not paralyzed.
At the same time, an array of microelectrodes implanted in the brain recorded patterns of neuroelectric activity.
"We want to evaluate whether a person who has been paralyzed for many years can decode the fast and delicate writing movements.
As far as we know, no one has done this before.
" Dr.
Willett said, "What surprised us was that when the participants When trying to'write' a character, it evokes a strong and reproducible pattern of neural activity, which can encode pen motion.
" Next, the researchers developed an algorithm that uses machine learning methods such as recurrent neural networks (RNN) , To decipher the neural activity in the motor cortex when writing each letter, predict which letter the subject wants to write, and convert it into text on the screen in real time.
▲Imagine that when writing a letter or symbol, the sensor in the brain converts it into writing traces (video source: F.
Willett et al.
, HHMI).
Finally, the research subjects can use this brain-computer interface to write at a speed of 90 per minute.
Characters, the original accuracy rate is 94.
1%.
Using the computer's general automatic correction function, the content accuracy rate is further improved to more than 99%.
The research author said in the abstract of the paper: “As far as we know, this typing speed exceeds that reported by any other BCI, and can be comparable to the typing speed (115 characters per minute) of the average person of the same age group in the research subject’s smartphone.
.
"▲ real-time encoding type of the sentence example of FIG.
(source: reference [1]) based on the results of validation studies of this concept, the research team hopes that the new method of brain-computer interface can ultimately help paralyzed people communicate can not move.
The study authors also suggest that this method be extended to all sequence behaviors that cannot be directly observed, such as decoding the speech of people who cannot speak.
Because this brain-computer interface requires electrodes to be implanted in the patient's brain, the service life, safety and effect of this technology still need to be further verified before it is put into large-scale clinical application.
Another issue that attracts attention is that this research currently focuses on decoding the writing of the Latin alphabet, and how to extend this method to other languages.
A review article published by Nature at the same time stated that, "Although there is still a lot of work to be done, this research has broadened the horizons of BCI applications and is a milestone.
"References[1] Francis Willett et al, (2021) High-performance brain-to-text communication via handwriting.
Nature DOI: 10.
1038/s41586-021-03506-2[2] Pavithra Rajeswaran & Amy L.
Orsborn (2021) ) Neural interface translates thoughts into type.
Nature Doi: https://doi.
org/10.
1038/d41586-021-00776-8[3] A HIGH-PERFORMANCE HANDWRITING BCI – 1ST PLACE WINNER OF THE BCI AWARD 2020.
Retrieved May 12 , 2021 from
Cooperated by scientists from research institutions such as Stanford University, Howard Hughes Medical Institute (HHMI), Brown University, etc.
, for the first time, the movement of handwritten letters is decoded from brain nerve signals, so that the writing movement in the mind of paralyzed people can be converted into screen in real time On the text.
Moreover, the finally realized typing speed is more than twice that of other brain-computer interfaces in the past, which is close to the typing speed on a smart phone! Brain-computer interface refers to the realization of information exchange between external devices and the brain by interpreting neural electrical activity signals.
This technology has progressed rapidly in recent years, so that those who have lost their ability to move or speak due to nerve damage are expected to resume communication with the outside world.
Restoring large motor functions such as grasping or grasping is a major research direction in this field.
People with paralysis can use brain-computer interfaces to achieve mental fetching.
However, it is still quite challenging to complete highly detailed movements, such as writing.
The previous brain-computer interface realized point-and-click typing by controlling the computer cursor, and the communication speed was very limited, with a maximum of about 40 characters per minute.
The new brain-computer interface method developed by this new research has greatly increased the communication speed.
▲A schematic diagram of a brain-computer interface for decoding mind writing (picture source: reference [1]) Dr.
Francis Willett is the first author and corresponding author of this study.
He and his colleagues asked a research subject who was paralyzed below the neck to imagine himself Holding a pen, "try" to write a sentence on the graph paper as if the hand is not paralyzed.
At the same time, an array of microelectrodes implanted in the brain recorded patterns of neuroelectric activity.
"We want to evaluate whether a person who has been paralyzed for many years can decode the fast and delicate writing movements.
As far as we know, no one has done this before.
" Dr.
Willett said, "What surprised us was that when the participants When trying to'write' a character, it evokes a strong and reproducible pattern of neural activity, which can encode pen motion.
" Next, the researchers developed an algorithm that uses machine learning methods such as recurrent neural networks (RNN) , To decipher the neural activity in the motor cortex when writing each letter, predict which letter the subject wants to write, and convert it into text on the screen in real time.
▲Imagine that when writing a letter or symbol, the sensor in the brain converts it into writing traces (video source: F.
Willett et al.
, HHMI).
Finally, the research subjects can use this brain-computer interface to write at a speed of 90 per minute.
Characters, the original accuracy rate is 94.
1%.
Using the computer's general automatic correction function, the content accuracy rate is further improved to more than 99%.
The research author said in the abstract of the paper: “As far as we know, this typing speed exceeds that reported by any other BCI, and can be comparable to the typing speed (115 characters per minute) of the average person of the same age group in the research subject’s smartphone.
.
"▲ real-time encoding type of the sentence example of FIG.
(source: reference [1]) based on the results of validation studies of this concept, the research team hopes that the new method of brain-computer interface can ultimately help paralyzed people communicate can not move.
The study authors also suggest that this method be extended to all sequence behaviors that cannot be directly observed, such as decoding the speech of people who cannot speak.
Because this brain-computer interface requires electrodes to be implanted in the patient's brain, the service life, safety and effect of this technology still need to be further verified before it is put into large-scale clinical application.
Another issue that attracts attention is that this research currently focuses on decoding the writing of the Latin alphabet, and how to extend this method to other languages.
A review article published by Nature at the same time stated that, "Although there is still a lot of work to be done, this research has broadened the horizons of BCI applications and is a milestone.
"References[1] Francis Willett et al, (2021) High-performance brain-to-text communication via handwriting.
Nature DOI: 10.
1038/s41586-021-03506-2[2] Pavithra Rajeswaran & Amy L.
Orsborn (2021) ) Neural interface translates thoughts into type.
Nature Doi: https://doi.
org/10.
1038/d41586-021-00776-8[3] A HIGH-PERFORMANCE HANDWRITING BCI – 1ST PLACE WINNER OF THE BCI AWARD 2020.
Retrieved May 12 , 2021 from
