Breaking News
April 19, 2019 - New insights into how vitamin D affects immune system
April 19, 2019 - Pfizer Announces Presentation of Data from a Phase 2 Study of its 20-Valent Pneumococcal Conjugate Vaccine Candidate Being Investigated for the Prevention of Invasive Disease and Pneumonia in Adults Aged 18 Years and Older
April 19, 2019 - Exercise can improve non-motor symptoms of Parkinson’s disease
April 19, 2019 - KZFPs play a key role in the regulation of human genome
April 19, 2019 - Extracts of ginkgo seeds show antibacterial activity on pathogens that cause skin infections
April 19, 2019 - Exercises and swimming goggles may reduce adverse effects on eye during long spaceflights
April 19, 2019 - Review suggests a reciprocal relationship between obesity and self-control
April 19, 2019 - Study identifies how enterococci bacteria cause antibiotic-resistant bloodstream infections
April 19, 2019 - Triple negative breast cancer develop resistance to chemotherapy by turning on molecular pathway
April 19, 2019 - Researchers identify key clues to brain and pancreas development
April 19, 2019 - Metformin May Cut Risk for Prematurity, Miscarriage in PCOS
April 19, 2019 - Obese mouse mothers trigger heart problems in offspring
April 19, 2019 - Research sheds light on how leukemia cells become resistant to drugs
April 19, 2019 - Health Tip: Stopping Nosebleeds – Drugs.com MedNews
April 19, 2019 - Pediatric endocrinologist gives iconic ‘Mona Lisa’ a second medical opinion
April 19, 2019 - Tapping patients’ wisdom for C-section pain management
April 18, 2019 - Why have autism rates ‘exploded’ in New Jersey?
April 18, 2019 - Microbiome science may help doctors to improve treatment for children with IBS
April 18, 2019 - New gene therapy cures babies with fatal ‘Bubble Boy’ disease
April 18, 2019 - No female mice? Scientists may still approve NIH grant
April 18, 2019 - What needs to be said about mental health in medicine
April 18, 2019 - Hickenlooper Expanded Medicaid, Created State-Run Marketplace To Insure Nearly All Coloradans
April 18, 2019 - Cancer cells grown in tumor-mimicking environment can help predict the effect of experimental drugs
April 18, 2019 - Albireo Announces FDA Clearance of IND to Commence Phase 2 Trial of Elobixibat for the Treatment of NAFLD/NASH
April 18, 2019 - Adhesive gel bonds to eye surface, could repair injuries without surgery
April 18, 2019 - The future of genomics: A podcast featuring Stanford geneticists
April 18, 2019 - As Syphilis Invades Rural America, A Fraying Health Safety Net Is Failing To Stop It
April 18, 2019 - APOE gene impacts sleep depending on gender and severity of Alzheimer’s
April 18, 2019 - PCORI’s newly approved awards focus on cancer pain and opioid use disorders
April 18, 2019 - New tool provides a standard way to measure effects of caring for survivors of TBI
April 18, 2019 - Smartphone use risks eye examination misdiagnosis
April 18, 2019 - How drug-resistant bugs grow in CF patients’ lungs
April 18, 2019 - Gordana Vunjak-Novakovic Elected to American Academy of Arts & Sciences
April 18, 2019 - Podcast: KHN’s ‘What The Health?’ You Have Questions, We Have Answers
April 18, 2019 - Diabetic drug shows potential to be repurposed as heart disease treatment for non-diabetic patients
April 18, 2019 - New estimation method assesses natural variations in sex ratio at birth
April 18, 2019 - UTA scientist receives $1.17 million grant for cancer research
April 18, 2019 - Coagulation factor VIIa prevents bleeds in hemophilia animal models
April 18, 2019 - Researchers identify risk factors for severe infection after knee replacement
April 18, 2019 - Mass drug administration can offer community-level protection against malaria
April 18, 2019 - FDA’s added sugar label could have substantial health and cost-saving benefits
April 18, 2019 - Researchers identify cause of inherited metabolic disorder
April 18, 2019 - Single strip of white paint not sufficient to protect people who ride bikes
April 18, 2019 - Partner status influences link between sexual problems and self-efficacy in breast cancer survivors
April 18, 2019 - Colorectal Neoplasia Risk Up for Hodgkin Lymphoma Survivors
April 18, 2019 - Rigid spine muscular dystrophy – Genetics Home Reference
April 18, 2019 - Simple bile acid blood test could tell risk of stillbirth
April 18, 2019 - Center for Experimental Therapeutics aims to enable all steps of drug development | News Center
April 18, 2019 - Falling for telephone scams could be an early sign of dementia
April 18, 2019 - Researchers annotate key neuronal proteins in lamprey genome
April 18, 2019 - Study uncovers new biomarker for personalized cancer treatments
April 18, 2019 - Scientists enter research collaboration to find a cure for cancer
April 18, 2019 - Study to compare benefits of tai chi and mindfulness meditation on MS symptoms
April 18, 2019 - Gestational diabetes during pregnancy may increase risk of type 1 diabetes in children
April 18, 2019 - Maternal age has no effect on IVF success, conclude researchers
April 18, 2019 - Is a New Remedy for Body Odor on the Horizon?
April 18, 2019 - Orthostatic hypotension – Genetics Home Reference
April 18, 2019 - Healing the heartbreak of stillbirth and newborn death
April 18, 2019 - New study calls healthiness of eggs into question
April 18, 2019 - Conference to highlight advances in human immune monitoring, bioinformatics | News Center
April 18, 2019 - Bacteria use viruses for self-recognition, study reveals
April 18, 2019 - New adhesive patch could help reduce post-heart attack muscle damage
April 18, 2019 - Researchers analyze the effects of dark play in a serious video game
April 18, 2019 - Scientists revive pig brain cells four hours after death
April 18, 2019 - Filial cannibalism and offspring abandonment may be forms of parental care
April 18, 2019 - Two proteins act in concert to maintain a healthy heart in mice, shows study
April 18, 2019 - Scientists create a functioning 3D printed heart
April 18, 2019 - Non-invasive vagus nerve stimulation improves disease symptoms in patients with rheumatoid arthritis
April 18, 2019 - Majority of men struggle to understand diagnosis and treatment of prostate cancer
April 18, 2019 - Researchers create new small molecules that may combat equine encephalitis viruses
April 18, 2019 - Animal-assisted therapy improves social behavior in patients with brain injuries
April 18, 2019 - Some viruses help protect harmful bacteria in CF patients | News Center
April 18, 2019 - Outpatient healthcare providers inappropriately prescribe antibiotics to 40% of patients
April 18, 2019 - Men who have a resting heart rate of 75 bpm are twice as likely to die early
April 18, 2019 - Novel serum biomarkers to detect NAFLD-related fibrosis
April 18, 2019 - New study delves deeper into individual genomic differences than ever before
April 18, 2019 - Gilead and Galapagos Announce Filgotinib Meets Primary Endpoint in the Phase 3 FINCH 3 Study in Methotrexate-Naïve Rheumatoid Arthritis Patients
April 18, 2019 - Emotional mirror neurons found in rats
April 18, 2019 - Sylvia Plevritis appointed chair of biomedical data science | News Center
April 18, 2019 - Cervical cancer subtype increasing in several subpopulations of women
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