Breaking News
November 21, 2018 - FDA Alert: Gilenya (fingolimod): Drug Safety Communication
November 21, 2018 - Uric Acid Test: MedlinePlus Lab Test Information
November 21, 2018 - Researchers use genetics to predict response to antipsychotic medications
November 21, 2018 - Proposal to include the price of drugs in television ads is flawed, Stanford scholar writes
November 21, 2018 - Disrupting reproduction strategy of disease-causing parasites could help fight malaria
November 20, 2018 - ACAAI: Almost 2 Percent of Children Have Milk Allergy
November 20, 2018 - Congenital anomalies of kidney and urinary tract – Genetics Home Reference
November 20, 2018 - Can video games improve the health of older adults with schizophrenia?
November 20, 2018 - Can flicking a molecular switch restore the aging immune system’s competence?
November 20, 2018 - Restek launches new Oregon cannabis pesticide standards
November 20, 2018 - Health sector coalition urges Government to safeguard patients in future UK-EU relationship
November 20, 2018 - Study evaluates second-hand marijuana smoke exposure among children
November 20, 2018 - Scientists identify three genes responsible for recurrent molar pregnancies
November 20, 2018 - Researchers identify multisystem disorder caused by bi-allelic variants in CCDC47 gene
November 20, 2018 - Dining Out With Allergies Is Tough, But These Steps Can Help
November 20, 2018 - Breastfeeding protects infants from antibiotic-resistant bacteria
November 20, 2018 - AI matched, outperformed radiologists in screening X-rays for certain diseases | News Center
November 20, 2018 - Adolescents increasingly choose marijuana over cigarettes, alcohol
November 20, 2018 - World’s first medical imaging scanner produces diagnostic scan of the whole human body
November 20, 2018 - Cytocybernetics receives NIMH award to move into neuronal drug development
November 20, 2018 - ‘Unknown’ enzyme may be key to new treatment for inflammatory diseases
November 20, 2018 - Recreational drug may help people regain trust in others
November 20, 2018 - Researchers identify gene vital for post-stroke recovery
November 20, 2018 - Scientists identify novel target for neuron regeneration, functional recovery in spinal cord injury
November 20, 2018 - Potential new therapeutic approach developed for synovial sarcoma
November 20, 2018 - Skeletal imitation reveals how bones grow atom-by-atom
November 20, 2018 - Autism behaviors show unique brain network fingerprints in infants
November 20, 2018 - Location matters for inflammation clearance
November 20, 2018 - Towards finding a druggable cancer target
November 20, 2018 - Ultragenyx Announces Intent to Submit New Drug Application to U.S. FDA for UX007 for the Treatment of Long-chain Fatty Acid Oxidation Disorders in Mid-2019
November 20, 2018 - Cooling ‘brains on fire’ to treat Parkinson’s
November 20, 2018 - Less pollution could increase the average lifespan of Copenhageners by an entire year in 2040
November 20, 2018 - Abramson Cancer Center becomes the 28th member institution of National Comprehensive Cancer Network
November 20, 2018 - The plug and play time-resolved spectrometer from PicoQuant
November 20, 2018 - Breakthrough technology offers new hope to people with glaucoma, retinitis and macular degeneration
November 20, 2018 - New report highlights key focus areas to help cancer screening realize its full potential
November 20, 2018 - International experts to discuss strategies to maintain spatial orientation in old age
November 20, 2018 - Low-protein, high-carb diet may promote healthy brain ageing
November 20, 2018 - Scientists discover new inhibitor that decreases lung inflammation
November 20, 2018 - Participation project calls for relaxing research ban on germline interventions
November 20, 2018 - Karyopharm’s Selinexor Receives Fast Track Designation from FDA for the Treatment of Patients with Relapsed or Refractory Diffuse Large B-cell Lymphoma
November 20, 2018 - Arthritis by the Numbers: Book of Trusted Facts & Figures
November 20, 2018 - Drug homing method helps rethink Parkinson’s
November 20, 2018 - AHF commends the passage of global AIDS funding in the House, calls for swift approval
November 20, 2018 - The search for new psychiatric disorder treatments
November 20, 2018 - New research offers hope for simpler way to diagnose and treat cancer
November 20, 2018 - Study sheds light on the infection mechanism of influenza virus
November 20, 2018 - Storage failures of eggs and embryos gain a new perspective
November 20, 2018 - Buyers of short-term health plans: Wise or shortsighted?
November 20, 2018 - Study indicates that frogs in virus-exposed groups breed at young age
November 20, 2018 - FDA Alerts Health Care Professionals and Patients Not To Use Sterile Drug Products from Pharm D Solutions
November 20, 2018 - Asthma may contribute to childhood obesity epidemic
November 20, 2018 - Live probiotics can change existing gut flora and alter immune response
November 20, 2018 - Researchers to explore the enigmatic role of unstructured protein in regulating circadian function
November 20, 2018 - Many patients with adenomas do not receive colonoscopy within recommended time frame
November 20, 2018 - Drug used to treat PTSD does not reduce suicidal thinking, may worsen nightmares and insomnia
November 20, 2018 - In-person social contact may offer protection against depression and PTSD symptoms
November 20, 2018 - Routine HCV testing in correctional facilities can best identify and treat disease, say researchers
November 20, 2018 - Molecular DNA analysis could facilitate more accurate prognosis, treatment of aggressive brain tumors
November 20, 2018 - Breast Cancer Recurrence Rate Not Up With Autologous Fat Transfer
November 20, 2018 - Beta 2 Microglobulin (B2M) Tumor Marker Test: MedlinePlus Lab Test Information
November 20, 2018 - Could bariatric surgery make men more virile?
November 20, 2018 - Urine test to check if patients take their medications will save the NHS money, say researchers
November 20, 2018 - Study reveals impact of residual inflammatory risk on clinical outcomes after PCI
November 20, 2018 - RNAi therapy shown to alleviate preeclampsia
November 20, 2018 - Replacement of dysfunctional microglia has therapeutic potential for neurodegenerative diseases
November 20, 2018 - Forming 3D Neuronal Models of the Brain
November 20, 2018 - Shoulder ultrasounds could be used to predict diabetes
November 20, 2018 - SGLT2 Inhibitors for Diabetes Linked to Increased Risk for Amputation
November 20, 2018 - Stem cell transplant cements Arizona men’s father-son bond
November 20, 2018 - Scientists try to develop portable systems that can quickly produce biologics on demand
November 20, 2018 - Automating Data Capture and Image Analysis in Continuous Experiments
November 20, 2018 - New drug shows promise for treating people with peanut allergy
November 20, 2018 - Researchers develop novel mouse model to study immunomodulatory therapies
November 20, 2018 - “Britain must not go backward on antibiotic controls to appease US trade deals” – Jim Moseley, CEO of Red Tractor
November 20, 2018 - Widespread errors in ‘proofreading’ cause inherited blindness
November 20, 2018 - Reaping the benefits of living longer
November 20, 2018 - New Program Hopes to Make Early Detection and Treatment of ALS a Reality
November 19, 2018 - Artificial bone-like substance mimics the way real bone grows at atomic level
November 19, 2018 - FDA Grants Orphan Drug Designation To RGX-181 Gene Therapy For The Treatment Of CLN2 Form Of Batten Disease
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