arXiv subjects

Sergey Shevchik

Publications and source records attributed to Sergey Shevchik.

4 recordsLinked to original sources

arXiv2026

Drill-bit-inspired dynamic focal fields for augmented laser materials processing

Laser manufacturing has advanced through increasingly precise control of power, pulse duration, repetition rate and scan trajectory, yet the spatial intensity profile of the beam is still usually fixed during light-matter interaction. This constraint limits how energy can be delivered to matter, particularly in processes where melt flow, material removal and surface morphology evolve on comparable time and length scales. Here we introduce drill-bit-inspired laser beams that convert the focal intensity distribution from a passive, static spot into an active, programmable processing tool. By combining cylindrical vector beams with rotational vectorial polarization filtering, we create a near diffraction limited two lobe Hermite-Gaussian focus that continuously spins about the propagation axis and can be reconfigured on demand. We establish two operating regimes, dynamic beam spinning and instantaneous beam-profile shifting, and derive closed-form descriptions of the accumulated fluence and effective pulse number governed by the along-scan pitch l = u/f, where u is the scan speed and f is the spin frequency. Across continuous-wave and ultrashort-pulse regimes, this dynamic energy deposition enables low-power metal machining with drilling efficiencies about four times higher than static Gaussian, enhances convective melt flow, promotes pore resorption and reduces retained porosity in keyhole welding, as visualized by in situ X-ray imaging, and turns simple linear scans into programmable surface textures. These results show that dynamic focal-profile control can extend laser processing beyond static beam shaping, opening a broadly applicable route to programmable energy deposition in manufacturing.

physics.optics↗

arXiv2026

Chaotic Oscillator Networks for Classification Tasks

Chaotic oscillators have gained significant attention in the research community because of their ability to reproduce and investigate the complex dynamics of real-world phenomena. Recent advances in the design of chaotic oscillator ensembles have led to the development of efficient signal processing frameworks that surpass traditional approaches. However, scaling such systems remains challenging due to the significant increase of computational resources and issues with training convergence. This study advances the state of the art by addressing the problem of data processing with ensembles of nonlinear oscillators that can be scaled up. In our approach, the processing is achieved as an anticipated local resonance or echo in a group of coupled chaotic oscillators, driven by external data input. Local resonance is enabled by tuning the coupling terms between the oscillators, which are approximated using the traditional artificial neural network and adapted to match the input feature distributions. Training the framework entails training this neural network to capture the dynamics of the entire oscillator system. The framework is evaluated using synthetic data and demonstrates an accuracy in machine learning classification task, while patterns recognition and dynamic system identification are also presented here as an extension of the functionality that involves additional modifications. Additionally, the universality of this approach is demonstrated by tests with different connections configurations between the oscillators and their types. The main advantage of the proposed framework is that it avoids hand-crafting explicit coupling terms, which requires expert knowledge and does not scale for large problems. Leveraging standard machine learning components simplifies both training and deployment of oscillator networks, enabling gradient-based optimization.

nlin.CD↗

arXiv2025

AquaCast: Urban Water Dynamics Forecasting with Precipitation-Informed Multi-Input Transformer

This work addresses the challenge of forecasting urban water dynamics by developing a multi-input, multi-output deep learning model that incorporates both endogenous variables (e.g., water height or discharge) and exogenous factors (e.g., precipitation history and forecast reports). Unlike conventional forecasting, the proposed model, AquaCast, captures both inter-variable and temporal dependencies across all inputs, while focusing forecast solely on endogenous variables. Exogenous inputs are fused via an embedding layer, eliminating the need to forecast them and enabling the model to attend to their short-term influences more effectively. We evaluate our approach on the LausanneCity dataset, which includes measurements from four urban drainage sensors, and demonstrate state-of-the-art performance when using only endogenous variables. Performance also improves with the inclusion of exogenous variables and forecast reports. To assess generalization and scalability, we additionally test the model on three large-scale synthesized datasets, generated from MeteoSwiss records, the Lorenz Attractors model, and the Random Fields model, each representing a different level of temporal complexity across 100 nodes. The results confirm that our model consistently outperforms existing baselines and maintains a robust and accurate forecast across both real and synthetic datasets.

cs.LG↗

arXiv2017

Two-view 3D Reconstruction for Food Volume Estimation

The increasing prevalence of diet-related chronic diseases coupled with the ineffectiveness of traditional diet management methods have resulted in a need for novel tools to accurately and automatically assess meals. Recently, computer vision based systems that use meal images to assess their content have been proposed. Food portion estimation is the most difficult task for individuals assessing their meals and it is also the least studied area. The present paper proposes a three-stage system to calculate portion sizes using two images of a dish acquired by mobile devices. The first stage consists in understanding the configuration of the different views, after which a dense 3D model is built from the two images; finally, this 3D model serves to extract the volume of the different items. The system was extensively tested on 77 real dishes of known volume, and achieved an average error of less than 10% in 5.5 seconds per dish. The proposed pipeline is computationally tractable and requires no user input, making it a viable option for fully automated dietary assessment.

cs.CV↗