HSE Researchers Develop Python Library for Analysing Eye Movements
A research team at HSE University has developed EyeFeatures, a Python library for analysing and modelling eye movement data. This tool is designed to simplify the work of scientists and developers by enabling them to efficiently process complex data and create predictive models.
The project was implemented as part of the Strategic Project 'Human-Centred AI' (Priority 2030).
Modern research increasingly leverages machine learning and artificial intelligence to analyse vast amounts of eye movement data. However, despite significant advancements in this field, certain challenges continue to limit the effectiveness of these methods. One such challenge is the limited flexibility of existing software solutions, which often offer a narrow range of parameter settings, making it difficult to customize them for specific research tasks. Additionally, the integration of these tools with other specialised software remains a significant limitation.
The Python library EyeFeatures, developed by the Laboratory for Social and Cognitive Informatics at HSE Campus in St Petersburg, addresses these challenges by providing a versatile and user-friendly toolkit for working with eye movement data. It includes modules for processing and analysing data collected from eye trackers, devices that monitor eye movement during the performance of various tasks.
Processing eye movement data is a complex task that involves several stages. Since the eyes do not move smoothly but rather in a series of rapid, jerky motions, focusing on specific points, the first stage of data processing is identifying areas of fixation. In the second stage, metrics such as the average gaze fixation duration and the average distance between points are calculated, enabling the creation of initial, simple predictive or diagnostic models.
All stages of data processing can be carried out using the various modules of the EyeFeatures library. The flexible, modular approach makes it easy to integrate eye movement data processing into existing research and commercial projects, from raw data to a fully developed predictive or explanatory model. For example, using the library in marketing research allows for the evaluation of consumer reactions to advertisements. Eye movement analysis will reveal which elements capture the most attention from the audience.
According to Anton Surkov, Project Head, Junior Research Fellow at Laboratory for Social and Cognitive Informatics at HSE Campus in St Petersburg, 'The library can be valuable to researchers, as it enables them not simply to replicate existing functionality from other software but to implement new algorithms and create more advanced models for research in fields such as marketing, cognitive process diagnostics, user interface and neural interface development (where control and interaction with the program occur through eye movement), as well as combine components in innovative ways to achieve new results and enhance methodology.'
This solution streamlines data analysis and accelerates the creation of predictive models, which is particularly beneficial in medical diagnostics, marketing, and the study of cognitive processes. The library has already been applied in research conducted as part of the Strategic Project 'Human-Centred AI' and was presented at the ECEM 2024 international conference in Ireland.
See also:
Cerium Glows Yellow: Chemists Discover How to Control Luminescence of Rare Earth Elements
Researchers at HSE University and the Institute of Petrochemical Synthesis of the Russian Academy of Sciences have discovered a way to control both the colour and brightness of the glow emitted by rare earth elements. Their luminescence is generally predictable—for example, cerium typically emits light in the ultraviolet range. However, the scientists have demonstrated that this can be altered. They created a chemical environment in which a cerium ion began to emit a yellow glow. The findings could contribute to the development of new light sources, displays, and lasers. The study has been published in Optical Materials.
Genetic Prediction of Cancer Recurrence: Scientists Verify Reliability of Computer Models
In biomedical research, machine learning algorithms are often used to analyse data—for instance, to predict cancer recurrence. However, it is not always clear whether these algorithms are detecting meaningful patterns or merely fitting random noise in the data. Scientists from HSE University, IBCh RAS, and Moscow State University have developed a test that makes it possible to determine this distinction. It could become an important tool for verifying the reliability of algorithms in medicine and biology. The study has been published on arXiv.
Artificial Intelligence as a Catalyst for Sustainable Development
Artificial intelligence is transforming every aspect of life, expanding both our capabilities and our boundaries. At the same time, it presents new challenges for humanity, including concerns about safety, ethics, and environmental sustainability. Today, each neural network leaves a significant carbon footprint. However, with responsible management, AI has the potential to benefit the planet and become a cornerstone of a sustainable future economy. Panos Pardalos, Academic Supervisor of the Laboratory of Algorithms and Technologies for Network Analysis at the HSE Campus in Nizhny Novgorod, emphasised this point as he addressed the XXV Yasin (April) International Academic Conference on Economic and Social Development.
HSE Develops Its Own MLOps Platform
HSE researchers have developed an MLOps platform called SmartMLOps. It has been created for artificial intelligence researchers who wish to transform their invention into a fully-fledged service. In the future, the platform may host AI assistants to simplify educational processes, provide medical support, offer consultations, and solve a wide range of other tasks. Creators of AI technologies will be able to obtain a ready-to-use service within just a few hours. Utilising HSE’s supercomputer, the service can be launched in just a few clicks.
Habits Stem from Childhood: School Years Found to Shape Leisure Preferences in Adulthood
Moving to a big city does not necessarily lead to dramatic changes in daily habits. A study conducted at HSE University found that leisure preferences in adulthood are largely shaped during childhood and are influenced by where individuals spent their school years. This conclusion was drawn by Sergey Korotaev, Research Fellow at the HSE Faculty of Economic Sciences, from analysing the leisure habits of more than 5,000 Russians.
Russian Scientists Reconstruct Dynamics of Brain Neuron Model Using Neural Network
Researchers from HSE University in Nizhny Novgorod have shown that a neural network can reconstruct the dynamics of a brain neuron model using just a single set of measurements, such as recordings of its electrical activity. The developed neural network was trained to reconstruct the system's full dynamics and predict its behaviour under changing conditions. This method enables the investigation of complex biological processes, even when not all necessary measurements are available. The study has been published in Chaos, Solitons & Fractals.
Researchers Uncover Specific Aspects of Story Comprehension in Young Children
For the first time, psycholinguists from the HSE Centre for Language and Brain, in collaboration with colleagues from the USA and Germany, recorded eye movements during a test to assess narrative skills in young children and adults. The researchers found that story comprehension depends on plot structure, and that children aged five to six tend to struggle with questions about protagonists' internal states. The study findings have been published in the Journal of Experimental Child Psychology.
Scientists Propose Novel Theory on Origin of Genetic Code
Alan Herbert, Scientific Supervisor of the HSE International Laboratory of Bioinformatics, has put forward a new explanation for one of biology's enduring mysteries—the origin of the genetic code. According to his publication in Biology Letters, the contemporary genetic code may have originated from self-organising molecular complexes known as ‘tinkers.’ The author presents this novel hypothesis based on an analysis of secondary DNA structures using the AlphaFold 3 neural network.
See, Feel, and Understand: HSE Researchers to Explore Mechanisms of Movement Perception in Autism
Scientists at the HSE Cognitive Health and Intelligence Centre have won a grant from the Russian Science Foundation (RSF) to investigate the mechanisms of visual motion perception in autism. The researchers will design an experimental paradigm to explore the relationship between visual attention and motor skills in individuals with autism spectrum disorders. This will provide insight into the neurocognitive mechanisms underlying social interaction difficulties in autism and help identify strategies for compensating for them.
Scholars Disprove Existence of ‘Crisis of Trust’ in Science
An international team of researchers, including specialists from HSE University, has conducted a large-scale survey in 68 countries on the subject of trust in science. In most countries, people continue to highly value the work of scientists and want to see them take a more active role in public life. The results have been published in Nature Human Behaviour.