Search by tag «Algorithms» 39 results

• ITMO-Developed Analytics System Improves Search Systems and AI Assistants

  ITMO University researchers have released DocuMentor, a data processing library that can help analyze and extract the hierarchical structure of documents. Based on a vision-language model (VLM) for optical character recognition, the library identifies the location of elements in a PDF file with a 98% accuracy. The new tool can make documents machine-readable for subsequent integration into efficient corporate search systems and AI assistants. The Russian Ministry of Construction, Housing and Utilities will be using the tool to create a regulations database.

  05.05.2026

• ITMO Researchers Develop Affordable, Versatile Model for Tracking Potential Production Accidents

  A team of scientists from ITMO University has developed software that can automatically track potential human causes of industrial accidents, such as drinking or smoking in the workplace. Unlike its alternatives, the model is capable of detecting up to 10 events simultaneously, has the accuracy of 80% (higher than that of VideoMAE, the best open-source model trained on the same data), and requires less computational resources. The algorithm is already in use at a major production site in Perm Krai, where it has lowered the required number of in-person checkups by threefold.

  08.09.2025

• Maglev Trains, Smartphones, and Biochips: Biggest Breakthroughs in Quantum Mechanics

  Schrödinger's cat is one of the most famous metaphors in science, yet few people realize that there’d be no smartphones if it weren’t for this thought experiment. Although this and some other concepts of quantum physics may appear far from real life, they, in fact, underpin many commonly-used technologies. In honor of the field’s 100th anniversary, ITMO NEWS asked the university’s experts to share which breakthroughs paved the way for lasers, MRI, and the internet, how a single algorithm could spark a global quantum computer craze, and how the uncertainty principle allowed scientists to glimpse into the past of the universe.

  25.08.2025

• ITMO PhD Students Train Algorithms To Count Cells in Microalgae Images With Computer Vision

  Researchers from ITMO University have developed a new method for automated assessment of microalgae cell concentration in a solution based on microscope images. Unlike other popular neural networks, this method uses classic computer vision algorithms and doesn’t require training data. The new solution can be launched on a standard PC and can determine cell concentration in a sample in 30 seconds instead of the usual 30 minutes, with accuracy equal to manual calculation. This algorithm will facilitate environmental studies and improve their accuracy.

  11.08.2025

• ITMO PhD Student Triumphs at ALCOS 2025

  Nikita Mikhalkov, a PhD student at ITMO, won the 15th international Workshop on Adaptive and Learning Control Systems (ALCOS 2025) for inventing an algorithm that improves small drone navigation. The event was also attended by other ITMO researchers, who chaired six sections and presented 13 reports published in IFAC-PapersOnLine.

  21.07.2025

• ITMO’s New AI Model Analyzes Papers 90 Times Faster

  Researchers from ITMO University and Lomonosov Moscow State University have rolled out NanoMINER – a multi-agent system that automatically extracts and processes data from scientific papers on nanomaterials and nanozymes. The algorithm analyzes each text in one minute, whereas doing it manually takes an average of 90 minutes. NanoMINER shows an impressive accuracy rate of up to 98% and can accelerate research in materials science, bionanotechnologies, and other fields. The results of the study are published in npj Computational Materials.

  08.07.2025

• ITMO PhD Students Train Chess-Playing Algorithm to Design Robots

  Roboticists at ITMO have found a way to optimize the development of robotic systems with the help of the MCTS (Monte Carlo tree search) algorithm, commonly used for chess and renowned for its victories over numerous human grandmasters. The PhD students adapted the algorithm to generate designs for robots and deliver the optimal solution within hours – a process that usually takes more than a week. Results of the study were presented at the IROS (IEEE Intelligent Robots and Systems) conference.

  18.10.2024

• Improved Algorithm for Lung Cancer Diagnostics Suggested by ITMO Students

  Students from ITMO University have developed a machine learning-based algorithm for detecting lung tumors on computed tomography (CT) scans. Trained on over 10,000 public-domain images, the model proved to generate results in 0.38 seconds. As noted by the developers, the technology may assist in online medical consultations to facilitate diagnostics.

  31.07.2023

• ITMO Scientists Suggest New Method to Make More Adaptive and Autonomous Robots

  Scientists from ITMO have come up with a three-step algorithm for the development of manipulators and walking or wearable robots. Compared to the usual methods, the new approach results in lighter, more efficient, affordable, and compact mechanisms. Walking robots that can move without having a full map of their surroundings are just one example of the designs produced by the new method. Another is the jumping robot made by the researchers to demonstrate their new algorithm. Read on to discover more.

  31.05.2023

• ITMO Scientists Develop Algorithm to Predict Nanomaterials Toxicity

  Nanoparticles and nanomaterials are commonly used in diagnostics and drug delivery systems for oncological treatment. However, in order to be used safely, such materials have to be checked for toxicity. Students from ITMO University have developed an algorithm that can quickly predict a material’s toxicity, with fewer experiments needed to perform the task. Their study was published in Small.

  15.02.2023