Breaking News
September 22, 2018 - Vici syndrome – Genetics Home Reference
September 22, 2018 - Single-dose drug can shorten flu symptoms by about a day, studies suggest
September 22, 2018 - AMSBIO launches circulating tumor DNA Reference Standards
September 22, 2018 - Sandalwood mimicking odorant could stimulate hair growth in humans
September 22, 2018 - Overlooked immune cells could play a key role in cancer immunotherapy, claims new study
September 22, 2018 - Study reveals prevalence of diagnosed type 1 and type 2 diabetes among American adults
September 22, 2018 - Researchers develop fast detection strategy to know type of virus acquired by patients
September 22, 2018 - Global Prevalence of Insufficient Activity 27.5 Percent
September 22, 2018 - Strategies to protect bone health in hematologic stem cell transplant recipients
September 22, 2018 - Brigham Genomic Medicine program unravels 30 medical mysteries
September 22, 2018 - New system harnesses power of bubbles to destroy dangerous biofilms
September 22, 2018 - Inflammation plays crucial role in preventing heart attacks and strokes, study reveals
September 22, 2018 - Calorie dense, nutrient deficient meals common across the world
September 22, 2018 - Researchers develop technology to study behavior of implants without animal testing
September 22, 2018 - First gut bacteria in newborns may have lasting effect on ability to ward off chronic diseases
September 22, 2018 - Detection of BFD virus in parrots in 8 new countries raises concerns for threatened species
September 22, 2018 - Insulin treatment shows great potential against chronic bowel inflammation
September 22, 2018 - ‘Liking Gap’ Might Stand in Way of New Friendships
September 22, 2018 - Simple factors that can avoid harmful side effects in type 2 diabetes
September 22, 2018 - ALSAM Foundation invests additional $2 million for drug discovery and development projects
September 22, 2018 - Study findings may advance discussion of how to effectively curb human-wildlife conflict
September 22, 2018 - Dopamine neurons may involve in conditions ranging from Parkinson’s disease to schizophrenia
September 22, 2018 - Protein C and Protein S Tests: MedlinePlus Lab Test Information
September 22, 2018 - Obesity and diabetes—two reasons why we should be worried about the plastics that surround us
September 22, 2018 - Concern over fussy eating prompts parents to use non-responsive feeding practices
September 22, 2018 - Novel mathematical approach uncovers existence of unsuspected biological cycles
September 22, 2018 - Cancer Research UK invests £14 million to transform London into cancer biotherapeutics hub
September 22, 2018 - Scientists predict how well the body will fight lung cancer by analyzing immune cell shapes
September 22, 2018 - New outbreak of rare eye disease identified in contact lens wearers
September 22, 2018 - Iterum Initiates SURE 2 and SURE 3 Phase 3 Clinical Trials of IV and Oral Sulopenem in Complicated Urinary Tract and Complicated Intra-abdominal Infections
September 22, 2018 - Research finds divide in dental health accessibility between city and regional areas
September 22, 2018 - Premature babies show better brain development when fed breast milk, finds study
September 22, 2018 - Novel system uses AI to detect abnormalities in fetal hearts
September 22, 2018 - UNC scientists reveal new approach to prevent obesity and diabetes
September 22, 2018 - CWRU receives NIH grant to learn how non-coding genes contribute to spread of colorectal cancer
September 22, 2018 - Scientists better understand influenza virus and how it spreads
September 22, 2018 - Scientists to focus on length of time when a person is alive and healthy
September 22, 2018 - Study shows positive financial impacts of Medicaid expansion for low-income Michigan residents
September 22, 2018 - Innovative approach for developing vaccine against most prevalent human malaria parasite
September 22, 2018 - Innovation Fund Denmark supports research project that aims to fight Clostridium difficile diarrhea
September 22, 2018 - Survey estimates caregiving costs for family members
September 22, 2018 - Inhibiting NF-kB improves heart function in a mouse model of Duchenne muscular dystrophy
September 22, 2018 - Introducing new EMR system may affect several aspects of clinic workflow
September 22, 2018 - Study finds why some human genes are more popular with biomedical researchers
September 22, 2018 - Finding epigenetic signature appears to predict inflammation risk in serious type of IBD
September 22, 2018 - Researchers develop light-based technique to measure very weak magnetic fields
September 22, 2018 - UAB researchers study dysfunction of the immune system associated with NSAID carprofen
September 22, 2018 - QIAGEN and DiaSorin launch automated, CE-marked workflow for high-throughput TB screening
September 22, 2018 - EFS checklist provides user-friendly tool for evaluating feeding skills in preterm infants
September 22, 2018 - Family history in blacks, Latinos associated with higher risk of AFib
September 22, 2018 - Researchers identify new genetic disorder in a human patient
September 22, 2018 - Cardiac MR With Contrast Feasible in Developing World
September 22, 2018 - Daily low-dose aspirin doesn’t reduce heart-attack risk in healthy people
September 21, 2018 - Children with asthma found to be disadvantaged in education and future occupation
September 21, 2018 - Interaction of chemical slurry and ancient shale in fracking wastewater causes radioactivity
September 21, 2018 - Scientists use mice to study transmission of Lyme disease bacteria by infected ticks
September 21, 2018 - Researchers find that sample size is key factor determining accuracy of study results
September 21, 2018 - Study shows how the drive to eat overpowers the brain’s signal to stop
September 21, 2018 - 30 Million Americans Now Have Diabetes
September 21, 2018 - Thousands of breast cancer gene variants engineered and analyzed
September 21, 2018 - The current fellowship interview process is cumbersome — Stanford researchers have a better idea
September 21, 2018 - Progenitor cells for human bone and cartilage have been identified
September 21, 2018 - Study reveals new therapeutic target for pediatric tumor-associated intractable epilepsy
September 21, 2018 - SLU’s College professor receives NIH grant to develop I-TEST project
September 21, 2018 - DermTech completes enrollment in clinical study to assess DNA damage and reversal
September 21, 2018 - Grieving patients treated with talk therapy have lower risk of suicide and psychiatric illness
September 21, 2018 - NIH and FDA call for eliminating involvement of RAC in human gene therapy experiments
September 21, 2018 - New system uses algorithm to convert 2D videos into 3D printed ‘motion sculptures’
September 21, 2018 - Sea squirt model reveals key molecules in dopaminergic neuron differentiation
September 21, 2018 - Effective management of neonatal abstinence syndrome requires coordinated ‘cascade of care’
September 21, 2018 - Refugees seek care for wounds of war
September 21, 2018 - Under the sea, in an octopus’ garden on ecstacy
September 21, 2018 - Eating foods with low nutritional quality ratings linked to cancer risk in large European cohort
September 21, 2018 - Giving kids honest information about water consumption may help them make healthy choices
September 21, 2018 - Horwitz Prize Awarded for Work on Hormones
September 21, 2018 - CHMP issues positive opinion supporting use of Trelegy Ellipta in broader group of COPD patients
September 21, 2018 - Scientists discover new molecules that work together to remove unwanted DNA
September 21, 2018 - Dr. Fenella France to deliver 2019 Plenary Lecture
September 21, 2018 - New research finds that MHC-II molecules have more influence on tumors than MHC-I
September 21, 2018 - Researchers study effects of cardiac cycle in simple learning task
Russian scientists develop model for predicting hand trajectories based on electrocorticograms

Russian scientists develop model for predicting hand trajectories based on electrocorticograms

image_pdfDownload PDFimage_print

Researchers from the Moscow Institute of Physics and Technology have developed a model for predicting hand movement trajectories based on cortical activity: Signals are measured directly from a human brain. The predictions rely on linear models. This offloads the processor, since it requires less memory and fewer computations in comparison with neural networks. As a result, the processor can be combined with a sensor and implanted in the cranium. By simplifying the model without degrading the predictions, it becomes possible to respond to the changing brain signals. This technology could drive exoskeletons that would allow patients with impaired mobility to regain movement. The paper was published in Expert Systems with Applications, the leading journal in the field of artificial intelligence.

Damage to the spinal cord prevents signals generated by the brain to control limb motion from reaching the muscles. As a result, the patients can no longer move freely. To restore motion, brain cortex signals are measured, decoded, and transmitted to an exoskeleton. Decoding means interpreting the signals as a prediction of the desired limb motion. To pick up high-quality signals, the sensor needs to be implanted directly in the braincase.

A surgical implantation of a sensor with electrodes onto the motor cortex, the area of the brain responsible for voluntary movements, has already been performed. Such a sensor is powered by a compact battery recharged wirelessly. The device comes with a processing unit, which handles the incoming signals, and a radio transmitter relaying the data to an external receiver. The processor heats up during operation, which becomes problematic since it is in contact with the brain. This puts a constraint on consumed power, which is crucial for decoding the signal.

Adequately measuring brain signals is only one part of the challenge. To use this data to control artificial limbs, movement trajectories need to be reconstructed from the electrocorticogram — a record of the electrical activity of the brain. This is the point of signal decoding. The research team led by Professor Vadim Strijov from MIPT works on models for predicting hand trajectories based on electrocorticograms. Such predictions are necessary to enable exoskeletons that patients with impaired motor function would control by imagining natural motions of their limbs.

“We turned to linear algebra for predicting limb motion trajectories. The advantage of the linear models over neural networks is that the optimization of model parameters requires much fewer operations. This means they are well-suited for a slow processor and a limited memory,” explains Strijov, the senior author of the paper.

“We solved the problem of building a model that would be simple, robust, and precise,” adds Strijov, who is a chief researcher at MIPT’s Machine Intelligence Laboratory. “By simple I mean there are relatively few parameters. Robustness refers to the ability to retain reasonable prediction quality under minor changes of parameters. Precision means that the predictions adequately approximate natural physical limb motions. To achieve this, we predict motion trajectories as a linear combination of the electrocorticogram feature descriptions.”

Each electrode outputs its own signal represented by a frequency and an amplitude. The frequencies are subdivided into bands. The feature description is a history of corticogram signal values for each electrode and each frequency band. This signal history is a time series, a vector in linear space. Each feature is therefore a vector. The prediction of hand motion trajectory is calculated as a linear combination of feature vectors, their weighted sum. To find the optimal weights for the linear model — that is, those resulting in an adequate prediction — a system of linear equations has to be solved.

However, the solution to the system mentioned above is unstable. This is a consequence of the sensors being located close to each other so that neighboring sensors output similar signals. As a result, the slightest change in the signals that are picked up causes a considerable change in the trajectory prediction. Therefore, the problem of feature space dimensionality reduction needs to be solved.

The authors of the paper introduce a feature selection method based on two criteria. First, the pairs of features have to be distinct, and second, their combinations have to approximate the target vector reasonably well. This approach allows the optimal feature set to be obtained even without calculating the model parameters. Taking into account the mutual positions of the sensors, the researchers came up with a simple, robust, and rather precise model, which is comparable to its analogs in terms of prediction quality.

In their future work, the team plans to address the problem of limb trajectory description in the case of a variable brain structure.

Strijov explains: “By moving around and getting a response from the environment, humans learn. The structure of the brain changes. New connections form, rendering the model obsolete. We need to propose a model that would adapt to the changes in the brain by changing its own structure. This task is far from simple, but we are working on it.”

Source:

https://mipt.ru/english/news/chip_controlling_exoskeleton_keeps_patients_brains_cool

Tagged with:

About author

Related Articles