-
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
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
Written by Nagashi
EditorWang Duoyu
TypesettingWater writing
life.
According to statistics, more than 75 million people around the world need wheelchairs to travel, especially for those who are paralyzed by neuromuscular or spinal cord injuries.
If we could create a wheelchair that could read the user's thoughts and carry out commands, would it help paralyzed people live freer lives?
On November 18, 2022, José del R.
Millán et al.
of the University of Texas at Austin published a title: Learning in the Cell sub-journal iScience to control a BMI-driven wheelchair for people with severe tetraplegia
.
The study shows that quadriplegics can control wheelchairs
through their minds in natural or chaotic spatial environments after prolonged training.
It is worth mentioning that this longitudinal study is the first to evaluate the clinical translation of non-invasive brain-computer interface (BCI) technology in patients with complete paralysis.
For the study, Professor Gerwin Schalk, Director of the TCCI Frontiers Laboratory of Applied Neurotechnology at the Tianqiao Institute of Brain Science, said that Professor Millán, the leader of the study, is a former president
of the International Brain-Computer Interface Association.
He is well-known in the field and is respected
.
The study showed that three people with spinal cord injuries were able to control wheelchairs
simply by using their brain signals.
This possibility is very encouraging, as we may be able to offer more possibilities for mobility in the future by using new brain-based technologies for people with disabilities such as spinal cord injuries
.
Professor Gerwin Schalk, Director of TCCI's Frontiers Laboratory of Applied Neurotechnology
The mind-controlled wheelchair is an assisted mobility solution based on brain-computer interface technology, especially for people
with complete paralysis.
However, despite the astonishing progress made in brain-computer interface technology in recent years, its clinical translation remains elusive and difficult for most users to manipulate
.
It's worth noting that brain-computer interface technology is human-machine interaction, but most research focuses entirely on humans and ignores machine components, relegating machines to simple devices
that execute user commands.
With the development of artificial intelligence, machine components have stronger "intelligence", and how to couple users and artificial intelligence has become the key to
achieve efficient human-machine interaction.
In this latest study, the research team recruited 3 quadriplegics for a longitudinal study, with each participant receiving training 3 times a week for 2 to 5 months
.
Participants wore non-invasive "brain-computer caps" that detected their brain activity by electroencephalogram (EEG) and converted into mechanical instructions
for wheelchairs through brain-computer interface devices.
Participants were asked to control the direction of the wheelchair by thinking about moving body parts, specifically, they needed to think about moving their hands to the left and their feet to
the right.
Mind Control Wheelchair
In the first training, when the device's response was in line with the user's thoughts, the 3 participants had similar accuracy rates of about 43 to 55 percent
.
During the training, the research team found that participant No.
1's accuracy improved significantly, reaching more than
95% accuracy at the end of the training.
In addition, the researchers observed that the accuracy of participant No.
3 increased to 98% halfway through training, but after updating the device's algorithm, its accuracy dropped significantly, and only improved again after a period of training
.
This shows the importance of
mutual learning and adaptation between users and machines.
Evolution
of each participant's brain-computer interface training: The improved accuracy of participants No.
1 and No.
3 correlated with improvements in feature discrimination ability, the ability of the algorithm to distinguish between "walking left" and "walking right" patterns of brain activity
。 The research team found that better feature discrimination is not only the result of machine learning, but also the result of
brain learning in the participants.
EEGs from participants 1 and 3 showed significant changes
in their brainwave patterns as they improved the accuracy of their mind control devices.
This means that during the long training process, the brains of participants 1 and 3 underwent cortical reorganization, consolidating the skills to regulate different parts of the brain to generate different patterns
of "walking left" and "walking right.
"
Schematic
diagram of participants operating a mind-controlled wheelchair Compared to participants 1 and 3, participant 2 only slightly improved accuracy in the first few training sessions, but remained stable
in subsequent trainings.
Correspondingly, the EEG of participant number 2 showed no significant change
in his brain activity patterns throughout the training process.
This suggests that machine learning alone is not enough to successfully manipulate such a mind-controlling device, and that changes in participants' brain activity patterns are also important
.
At the end
of the training, all 3 participants were asked to drive wheelchairs through the messy wards
.
They must bypass obstacles such as room dividers and hospital beds, which are set up to simulate real-world environments
.
Of these, participants 1 and 3 completed their tasks, and participant 2 did not
.
José del R.
Millán is Professor
José, corresponding author of the paper Professor del R.
Millán said that for a person to gain good control of brain-computer interfaces to enable them to perform relatively complex daily activities, such as driving a wheelchair in a natural environment, this requires some neuroplastic restructuring
in the cerebral cortex.
Not only that, but the success rate
of 3 participants at each pathpoint in the final test was not only that, the study also highlighted the role
of long-term training for users.
For example, although participant number 1 performed exceptionally well in the final test, he also struggled
in the first few training sessions.
Next, the research team wanted to figure out why participant No.
2 did not experience the learning effect
.
They hope to conduct a more detailed analysis of brain signals from all participants to understand their differences and provide possible interventions
for future people who experience difficulties in the learning process.
In summary, this study suggests that mutual learning and shared control may be two cornerstones for the development of powerful and effective brain-driven neuroprostheses, that mutual learning of both users and brain-computer interface algorithms is important for users to successfully operate mind-controlled wheelchairs, and highlights potential pathways to improve the clinical translation of non-invasive brain-computer interface technologies
。
Professor Gerwin Schalk, Director of the TCCI Frontiers Laboratory of Applied Neurotechnology at the Tianqiao Institute of Brain Science, said that we are at the beginning of an exciting development and hope that neurotechnologies that will be able to be developed will not only demonstrate their potential in the laboratory or clinic, but also be applicable to the general public
.
There are already many technologies that bring us closer to our own bodies (such as smartwatches that measure heart rate, exercise, etc.
).
In the future, neurotechnology will also bring us closer to our own brains
.
These devices will be suitable for patients and ordinary people, telling us about the health of the brain and providing new opportunities
to improve the brain.
At the TCCI Applied Neurotechnology Frontiers Lab, which I lead, we have been focused on making this dream a reality
.
Paper link:
https://doi.
org/10.
1016/j.
isci.
2022.
105418
Open reprint, welcome to forward to Moments and WeChat groups
