Tag «research projects»

Researchers from HSE University in Nizhny Novgorod, MISIS and the Artificial Intelligence Research Institute (AIRI) have developed an algorithm that selects the best available neural network for facial recognition, taking into account the features of a mobile device. This new approach accelerates the selection of the most suitable neural network and allows the identification of people with an accuracy rate of up to 99%. The study was published in the IEEE Access journal. The source code is available on GitHub.

Social integration has different effects on the academic achievement of women and men. Researchers from HSE University’s Institute of Education studied the connections between academic performance and social integration among 4,500 young Russians. It turned out that this connection is much stronger than it might seem at first glance, and that it is more important for women. The results of the work were published in the Journal of Social and Personal Relationships.

Chemists at HSE University, Kurnakov Institute of General and Inorganic Chemistry, and the University of Science and Technology of China have developed membranes with enhanced properties. The researchers experimentally revealed the impact of various factors on the desalination process and on the selectivity of ion separation. According to the study authors, their research will enable a more precise prediction of the properties of new ion-exchange membranes used in water treatment and desalination. The study findings have been published in Desalination.

Specialists at HSE Campus in Perm and clinicians at Perm City Clinical Hospital No. 4, have been collaborating to develop a neural network capable of determining the root cause of a stroke. This marks the world's first attempt to create such a system, the developers note.

Scientists at HSE MIEM have induced a superconducting current using 'liquid light,' or excitonic polaritons, which are hybrid particles formed by interaction between light and matter and possess the properties of both light and material particles. The ability to manipulate an electrical system through an optical one can be valuable in the development of technologies such as quantum computers. The study has been published in Physical Review B.

Physicists from HSE MIEM in collaboration with colleagues from MIPT and other universities have formulated a theory capable of explaining the transition between different superconductivity types, revealing an intertype regime characterised by exotic magnetic properties. This discovery can serve as the foundation for the development of sensors with enhanced sensitivity and accuracy, capable of functioning in conditions where traditional sensors are less effective. The study has been published in Communications Physics.

Researchers at HSE University and the Pirogov National Medical and Surgical Centre have examined alterations induced by epilepsy in the language-related neural network within the brain. Using graph-based analysis, the researchers studied fMRI data from 28 patients and found that in epilepsy, both hemispheres of the brain become activated during language processing and short connections form between the hemispheres, while long connections within one hemisphere are disrupted. The study has been published in Epilepsy&Behavior.

HSE scientists have developed a software tool for assessing the presence and degree of dyslexia in school students based on their gender, age, school grade, and eye-tracking data. The application is expected to be introduced into clinical practice in 2024. The underlying studies were conducted by specialists in machine learning and neurolinguistics at the HSE AI Research Centre.