arXiv subjects

Ilya Makarov

Publications and source records attributed to Ilya Makarov.

43 records · Page 3Linked to original sources

arXiv2023

Interaction models for remaining useful life estimation

The paper deals with the problem of controlling the state of industrial devices according to the readings of their sensors. The current methods rely on one approach to feature extraction in which the prediction occurs. We proposed a technique to build a scalable model that combines multiple different feature extractor blocks. A new model based on sequential sensor space analysis achieves state-of-the-art results on the C-MAPSS benchmark for equipment remaining useful life estimation. The resulting model performance was validated including the prediction changes with scaling.

cs.LG↗

arXiv2022

Graph Neural Networks with Trainable Adjacency Matrices for Fault Diagnosis on Multivariate Sensor Data

Timely detected anomalies in the chemical technological processes, as well as the earliest detection of the cause of the fault, significantly reduce the production cost in the industrial factories. Data on the state of the technological process and the operation of production equipment are received by a large number of different sensors. To better predict the behavior of the process and equipment, it is necessary not only to consider the behavior of the signals in each sensor separately, but also to take into account their correlation and hidden relationships with each other. Graph-based data representation helps with this. The graph nodes can be represented as data from the different sensors, and the edges can display the influence of these data on each other. In this work, the possibility of applying graph neural networks to the problem of fault diagnosis in a chemical process is studied. It was proposed to construct a graph during the training of graph neural network. This allows to train models on data where the dependencies between the sensors are not known in advance. In this work, several methods for obtaining adjacency matrices were considered, as well as their quality was studied. It has also been proposed to use multiple adjacency matrices in one model. We showed state-of-the-art performance on the fault diagnosis task with the Tennessee Eastman Process dataset. The proposed graph neural networks outperformed the results of recurrent neural networks.

cs.AI↗

arXiv2022

Long-term hail risk assessment with deep neural networks

Hail risk assessment is necessary to estimate and reduce damage to crops, orchards, and infrastructure. Also, it helps to estimate and reduce consequent losses for businesses and, particularly, insurance companies. But hail forecasting is challenging. Data used for designing models for this purpose are tree-dimensional geospatial time series. Hail is a very local event with respect to the resolution of available datasets. Also, hail events are rare - only 1% of targets in observations are marked as "hail". Models for nowcasting and short-term hail forecasts are improving. Introducing machine learning models to the meteorology field is not new. There are also various climate models reflecting possible scenarios of climate change in the future. But there are no machine learning models for data-driven forecasting of changes in hail frequency for a given area. The first possible approach for the latter task is to ignore spatial and temporal structure and develop a model capable of classifying a given vertical profile of meteorological variables as favorable to hail formation or not. Although such an approach certainly neglects important information, it is very light weighted and easily scalable because it treats observations as independent from each other. The more advanced approach is to design a neural network capable to process geospatial data. Our idea here is to combine convolutional layers responsible for the processing of spatial data with recurrent neural network blocks capable to work with temporal structure. This study compares two approaches and introduces a model suitable for the task of forecasting changes in hail frequency for ongoing decades.

physics.ao-ph↗

arXiv2021

Temporal Graph Network Embedding with Causal Anonymous Walks Representations

Many tasks in graph machine learning, such as link prediction and node classification, are typically solved by using representation learning, in which each node or edge in the network is encoded via an embedding. Though there exists a lot of network embeddings for static graphs, the task becomes much more complicated when the dynamic (i.e. temporal) network is analyzed. In this paper, we propose a novel approach for dynamic network representation learning based on Temporal Graph Network by using a highly custom message generating function by extracting Causal Anonymous Walks. For evaluation, we provide a benchmark pipeline for the evaluation of temporal network embeddings. This work provides the first comprehensive comparison framework for temporal network representation learning in every available setting for graph machine learning problems involving node classification and link prediction. The proposed model outperforms state-of-the-art baseline models. The work also justifies the difference between them based on evaluation in various transductive/inductive edge/node classification tasks. In addition, we show the applicability and superior performance of our model in the real-world downstream graph machine learning task provided by one of the top European banks, involving credit scoring based on transaction data.

cs.LG↗

arXiv2021

Epidemic modelling of multiple virus strains: a case study of SARS-CoV-2 B.1.1.7 in Moscow

During a long-running pandemic a pathogen can mutate, producing new strains with different epidemiological parameters. Existing approaches to epidemic modelling only consider one virus strain. We have developed a modified SEIR model to simulate multiple virus strains within the same population. As a case study, we investigate the potential effects of SARS-CoV-2 strain B.1.1.7 on the city of Moscow. Our analysis indicates a high risk of a new wave of infections in September-October 2021 with up to 35 000 daily infections at peak. We open-source our code and data.

q-bio.PE↗

arXiv2021

Hotel Recognition via Latent Image Embedding

We approach the problem of hotel recognition with deep metric learning. We overview the existing approaches and propose a modification to Contrastive loss called Contrastive-Triplet loss. We construct a robust pipeline for benchmarking metric learning models and perform experiments on Hotels-50K and CUB200 datasets. Contrastive-Triplet loss is shown to achieve better retrieval on Hotels-50k. We open-source our code.

cs.CV↗

arXiv2018

Effect of CuO2 lattice strain on the electronic structure and properties of high-Tc cuprate family

Doping and strain dependences of the electronic structure of the CuO6-octahedra layer within LDA+GTB method in the frameworks of six-band p-d model are calculated. Band structure and Fermi surface of the quasiparticle excitations in the effective Hubbard model are characterized by inhomogeneous distribution of the k-dependent spectral weight. Doping results in reconstruction of the band structure, redistribution of the spectral weight over dispersion surface and reconstruction of Fermi surface from small hole pockets in the underdoped region to large hole contour in the overdoped region through two quantum phase transitions (QPT). Strain increasing leads to displacement of the valence and conductivity bands, bandwidths decreasing and shift of the concentrations corresponding to QPTs. Strain dependences of the antiferromagnetic exchange coupling and DOS at the Fermi level determining superconducting temperature Tc are obtained. Effective exchange coupling in the equation for Tc demonstrates monotonic strain dependence.

cond-mat.str-el↗