Video | Business Headlines | Internet | Science | Scientific Ethics | Technology | Search

 

Machine Learning, Meet Human Emotions: How To Help A Computer Monitor Your Mental State

Researchers from Skoltech, INRIA, and the RIKEN Advanced Intelligence Project have considered several state-of-the-art machine learning algorithms for the challenging tasks of determining the mental workload and affective states of a human brain. Their software can help design smarter brain-computer interfaces for applications in medicine and beyond. The paper was published in the IEEE Systems, Man, and Cybernetics Magazine.

A brain-computer interface, or BCI, is a link between a human brain and a machine that can allow users to control various devices, such as robot arms or a wheelchair, by brain activity only (these are called active BCIs) or can monitor the mental state or emotions of a user and categorize them (these are passive BCIs). Brain signals in a BCI are usually measured by electroencephalography, a typically noninvasive method of recording the electrical activity of the brain.

But there is quite a long way from raw continuous EEG signals to digitally processed signals or patterns that would have the ability to correctly identify a user’s mental workload or affective states, something that passive BCIs need to be functional. Existing experiments have shown that the accuracy of these measurements, even for simple tasks of, say, discriminating low from high workload, is insufficient for reliable practical applications.

“The low accuracy is due to the extremely high complexity of a human brain. The brain is like a huge orchestra with thousands of musical instruments from which we wish to extract specific sounds of each individual instrument using a limited number of microphones or other sensors,” Andrzej Cichocki, professor at the Skoltech Center for Computational and Data-Intensive Science and Engineering (CDISE) and a co-author of the paper, notes.

Thus, more robust and accurate EEG classification and recognition of various brain patterns algorithms are badly needed. Cichocki and his colleagues looked at two groups of machine learning algorithms, Riemannian geometry-based classifiers (RGC) and convolutional neural networks (CNN), which have been doing quite well on the active side of BCIs. The researchers wondered whether these algorithms can work not just with so-called motor imaginary tasks, where a subject imagines some movements of limbs without any real movement, but for workload and affective states estimation.

They ran a competition of sorts among seven algorithms, two of which the scientists designed themselves by further improving well-performing Riemannian methods. The algorithms were tested in two studies, one with a typical arrangement for BCIs where algorithms were trained on data from a specific subject and later tested on that same subject, and one that was subject-independent — a much more challenging setup since our brain waves could be quite different. Real EEG data was taken from earlier experiments done by Fabien Lotte, a coauthor of the paper, and his colleagues, as well as from DEAP, an existing database for emotion analysis.

The scientists found, for instance, that an artificial deep neural network outperformed all its competitors quite significantly in the workload estimation task but did poorly in emotion classification. And the two modified Riemannian algorithms did quite well in both tasks. Overall, as the paper concludes, using passive BCIs for affective state classification is much harder than for workload estimation, and subject-independent calibration leads, at least for now, to much lower accuracies.

“In the next steps, we plan to use more sophisticated artificial intelligence (AI) methods, especially deep learning, which allow us to detect very tiny changes in brain signals or brain patterns. Deep neural networks can be trained on the basis of a large set of data for many subjects in different scenarios and under different conditions. AI is a real revolution and is also potentially useful for BCI and recognition of human emotions,” Cichocki said.

© Scoop Media

 
 
 
Business Headlines | Sci-Tech Headlines

 

Auckland Transport: Successful Bridge Repair Opens Two Additional Lanes To Traffic

The opening of two additional lanes on the Auckland Harbour Bridge this morning will help relieve some motorway congestion for motorists heading home to the North Shore tonight. More>>

ALSO:

Statistics New Zealand: COVID-19 Sees Record 12.2 Percent Fall In New Zealand’s Economy

Gross domestic product (GDP) fell by 12.2 percent in the June 2020 quarter, the largest quarterly fall recorded since the current series began in 1987, as the COVID-19 restrictions in place through the quarter impacted economic activity, Stats NZ said ... More>>

ALSO:

Climate: Scientists Release ‘Blueprint’ To Save Critical Ecosystems And Stabilize The Earth’s Climate

A group of scientists and experts produced the first comprehensive global-scale analysis of terrestrial areas essential for biodiversity and climate resilience, totaling 50.4% of the Earth's land. The report was published in Science Advances ... More>>

ALSO:

MPI: Independent Review Launched Into Assurances For Safe Transport Of Livestock By Sea

The Ministry for Primary Industries (MPI) has launched an independent review of the assurances it receives for the safe transport of livestock by sea. MPI Director-General Ray Smith says Mike Heron QC has been appointed to lead the review, which is expected ... More>>

ALSO:


Computers: New Zealand PC Market Grows Nearly 40% Due To Work From Home Demand

COVID-19 had large impacts on demand for PCs as businesses prepared for lockdowns by purchasing notebooks to mobilise their workforce. In the second quarter of 2020, New Zealand's Traditional PC market experienced a 39.7% year-on-year (YoY) growth ... More>>

ALSO:


University Of Auckland: Whale-Watching By Satellite – Follow Their Travels Online

Scientists have successfully attached satellite tracking tags to six New Zealand southern right whales, or tohorā, and are inviting the public to follow the whales’ travels online. Part of a major research project involving the University of Auckland ... More>>

Commerce Commission: Kiwibank Admits System Failures And Agrees To Pay Customers $5.2 Million

Kiwibank has entered into a settlement agreement with the Commerce Commission after reporting that it failed to have in place robust home loan variation disclosure policies, procedures and systems. In a settlement dated 27 August 2020, Kiwibank admitted that ... More>>

Ministry of Health: Public Transport Distancing Requirements Relaxed

Physical distancing requirements on public transport have been reviewed by the Ministry of Health to determine whether they are still required at Alert Level 2 (or below). The Ministry’s assessment is that mandatory face covering and individuals tracking ... More>>

ALSO:

NZHIA: New Zealand Hemp Industry Set To Generate $2 Billion Per Annum And Create 20,000 Jobs

A new report says a fully enabled hemp industry could generate $2 billion in income for New Zealand by 2030, while also creating thousands of new jobs. Written by industry strategist Dr Nick Marsh, the report has prompted calls from the New Zealand Hemp ... More>>

ALSO:

Stats NZ: One In 14 Employed People Report High Risk Of Losing Jobs

About one in 14 workers say they expect to lose their job or business by mid-2021, Stats NZ said today. A survey of employed people in the June 2020 quarter showed 7 percent felt there was a high or almost certain chance of losing their job or business ... More>>

ASB Quarterly Economic Forecast: NZ Economy Doing Better Than Expected, But Challenges Remain

August lockdown estimated to have shaved 8% off NZ’s weekly GDP, and 0.5% off annual GDP Economy now expected to shrink 5% (year-on-year) by end of 2020 Unemployment rate now expected to peak at 7.2% The latest ASB Quarterly Economic Forecast is less ... More>>

ALSO: