arXiv subjects

Sergey Gerasimov

Publications and source records attributed to Sergey Gerasimov.

5 recordsLinked to original sources

arXiv2026

Smart routes: a system for development and comparison of algorithms for solving vehicle routing problems with realistic constraints

The problem of route optimization with realistic constraints is becoming extremely relevant in the face of global urban population growth. While we are aware of approaches that theoretically provide an exact optimal solution, their application becomes challenging as the problem size increases because of exponential complexity. We investigate the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) and compare solutions obtaining by exact solver SCIP with heuristic algorithms such as LKH, 2-OPT, 3-OPT, the ORTools framework, and the deep learning model JAMPR. We demonstrate that for problem of size 50 deep learning and classical heuristic solutions became close to SCIP exact solution but requires less time. Additionally for problems with size 100, SCIP exact methods around 13 times slower that neural and classical heuristics with the same route cost and on around 50% worse for the first feasible solution on the same time. To conduct experiments, we developed the Smart Routes platform for solving route optimization problems, which includes exact, heuristic, and deep learning models, and facilitates convenient integration of custom algorithms and datasets.

cs.LG↗

arXiv2026

Deep Reinforcement Learning solution for pickup and delivery routing problems with time window and capacity constraints

The task of constructing vehicles optimal routes for pickup and delivery of goods is one of most promising tasks in the context of global urban population growth. Although this kind of problems with small size can be solved by various classical approaches, a fast (or realtime) route optimizer under the constraints of the real world (such as capacity and time windows constraints) for medium-large size problems still remains a highly challenging task. In this work we, for the first time, successfully applied a deep Reinforcing Learning approach (modified JAMPR model) to solve Pickup and Delivery problem with Capacity and Time Window constraints (CPDPTW). We obtained a robust model that gives a fast optimal solution for problems of small and medium size, and gives fast suboptimal solution for problems of larger (> 200) size.

cs.LG↗

arXiv2021

Probabilistic photo-z machine learning models for X-ray sky surveys

Accurate photo-z measurements are important to construct a large-scale structure map of X-ray Universe in the ongoing SRG/eROSITA All-Sky Survey. We present machine learning Random Forest-based models for probabilistic photo-z predictions based on information from 4 large photometric surveys (SDSS, Pan-STARRS, DESI Legacy Imaging Survey, and WISE). Our models are trained on the large sample of $\approx$580000 quasars and galaxies selected from the SDSS DR14 spectral catalog and take into account Galactic extinction and uncertainties in photometric measurements for target objects. On the Stripe82X test sample we obtained photo-z accuracy for X-ray sources: $NMAD=0.034$ (normalized median absolute deviation) and $n_{>0.15}=0.088$ (catastrophic outliers fraction), which is almost $\sim2$ times better than best photo-z results available in the literature.

astro-ph.IM↗

arXiv2021

Morphological classification of astronomical images with limited labelling

The task of morphological classification is complex for simple parameterization, but important for research in the galaxy evolution field. Future galaxy surveys (e.g. EUCLID) will collect data about more than a $10^9$ galaxies. To obtain morphological information one needs to involve people to mark up galaxy images, which requires either a considerable amount of money or a huge number of volunteers. We propose an effective semi-supervised approach for galaxy morphology classification task, based on active learning of adversarial autoencoder (AAE) model. For a binary classification problem (top level question of Galaxy Zoo 2 decision tree) we achieved accuracy 93.1% on the test part with only 0.86 millions markup actions, this model can easily scale up on any number of images. Our best model with additional markup achieves accuracy of 95.5%. To the best of our knowledge it is a first time AAE semi-supervised learning model used in astronomy.

cs.CV↗

arXiv2017

Architecture of processing and analysis system for big astronomical data

This work explores the use of big data technologies deployed in the cloud for processing of astronomical data. We have applied Hadoop and Spark to the task of co-adding astronomical images. We compared the overhead and execution time of these frameworks. We conclude that performance of both frameworks is generally on par. The Spark API is more flexible, which allows one to easily construct astronomical data processing pipelines.

astro-ph.IM↗