Dmitrii I Kaplun | Saint Petersburg State Electrotechnical University "LETI" (ETU) (original) (raw)

Papers by Dmitrii I Kaplun

Studies in big data, 2023

Frontiers in Environmental Science, Jun 8, 2023

observations and predictions, indicating the capability of risk assessment that could be further ... more observations and predictions, indicating the capability of risk assessment that could be further employed for an informed forest management.

In a changing climate, forest ecosystems become increasingly vulnerable to the continuously exace... more In a changing climate, forest ecosystems become increasingly vulnerable to the continuously exacerbating heat and drought stress conditions. Climate stress resilience is governed by a complex interplay of global, regional and local factors, with hydrological conditions among the key roles. Using a modified detrended partial cross-correlation analysis (DPCCA), we analyse the interconnections between long-term tree-ring width (TRW) data and regional climate variations at various scales and time lags. By comparing dendrochronological series of Scots pine trees near the southern edge of the boreal ecotone, we investigate how local hydrological conditions affect heat- and drought stress resilience of the forest ecosystem. While TRW are negatively correlated with spring and summer temperatures and positively cor-related with the Palmer drought severety index (PDSI) in the same year indicating that heatwaves and droughts represent the limiting factors, at interannual scales remarkable cont...

PLOS ONE

We have recently been witnessing that our society is starting to heal from the impacts of COVID-1... more We have recently been witnessing that our society is starting to heal from the impacts of COVID-19. The economic, social and cultural impacts of a pandemic cannot be ignored and we should be properly equipped to deal with similar situations in future. Recently, Monkeypox has been concerning the international health community with its lethal impacts for a probable pandemic. In such situations, having appropriate protocols and methodologies to deal with the outbreak efficiently is of paramount interest to the world. Early diagnosis and treatment stand as the only viable option to tackle such problems. To this end, in this paper, we propose an ensemble learning-based framework to detect the presence of the Monkeypox virus from skin lesion images. We first consider three pre-trained base learners, namely Inception V3, Xception and DenseNet169 to fine-tune on a target Monkeypox dataset. Further, we extract probabilities from these deep models to feed into the ensemble framework. To combi...

Social Science Research Network, 2023

Biomedical Signal Processing and Control

2020 9th Mediterranean Conference on Embedded Computing (MECO), 2020

The paper proposes a system for determining malignant skin neoplasms. The use of convolutional ne... more The paper proposes a system for determining malignant skin neoplasms. The use of convolutional neural networks for determining skin tumors from images is considered. A convolutional neural network of deep learning has been developed and modeled, which allows you to determine and classify pigmented skin lesions by examining photographs. The article proposes a system for determining malignant skin neoplasms. The proposed neural network has the basic parameters of the VGG-A architecture with a maximum number of epoch training of 10. The accuracy of the determination of the proposed model of the convolutional neural network is at least 77%. The minimum learning loss function was 0.5577. As a result of the work, a database of training photos of real pigmented skin formations taken from the international open archive ISIC Melanoma Project was used, which is a database of digital images of various types of skin lesions, was formed. Using the proposed model can be of great help in determining and diagnosing malignant skin lesions by dermatologists.

Diagnostics, May 21, 2022

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

2022 11th Mediterranean Conference on Embedded Computing (MECO)

Mathematics and its Applications in New Computer Systems

IEEE Access, 2019

In the last two decades, both Empirical Mode Decomposition (EMD) and Intrinsic TimeScale Decompos... more In the last two decades, both Empirical Mode Decomposition (EMD) and Intrinsic TimeScale Decomposition (ITD) algorithms deserved a variety of applications in various fields of science and engineering due to their obvious advantages compared to conventional (e.g. correlation-or spectral-based analysis) approaches like the ability of their direct application to non-stationary signal analysis. However, high computational complexity remains a common drawback of these otherwise universal and powerful algorithms. Here we compare similarly designed signal analysis algorithms utilizing either EMD or ITD as their core functions. Based on extensive computer simulations, we show explicitly that the replacement of EMD by ITD in several otherwise similar signal analysis scenarios leads to the increased noise robustness with simultaneous considerable reduction of the processing time. We also demonstrate that the proposed algorithms modifications could be successfully utilized in a series of emerging applications for processing of non-stationary signals. INDEX TERMS Adaptive filter bank, denoising algorithms, empirical mode decomposition, Fourier transform, Hilbert-Huang transform, internal oscillations, intrinsic timescale decomposition, spectral analysis, wavelet transform.

2022 Conference of Russian Young Researchers in Electrical and Electronic Engineering (ElConRus)

According to the international classification of sleep disorders ICSD-3, sleep disorders are grou... more According to the international classification of sleep disorders ICSD-3, sleep disorders are grouped into 7 different groups, one of which is "Obstructive Sleep Apnea" (OSA). In order to improve the quality of sleep, a mobile application "Apnea" was developed. It helps users in self-diagnosis and treatment of snoring and OSA. This will have a positive effect on many areas of life in the future: the number of accidents due to falling asleep while driving will decrease; the working capacity of the population will increase due to the improvement of people, since inadequate sleep increases the risk of many diseases, including sudden death. The software complex analyzes many patient data: name, age, gender, height and weight of the user, neck circumference, waist circumference, patient complaints, recording of the sound phenomenon of the client's snoring, processing of user's photographs to construction of a 3D model and determine the pathology of the dentition, heart rate data processing and activity results during the day. Based on the results of the assessment, users are offered various recommendations compiled by a team of doctors to improve the quality of sleep (smart alarm clock, soothing music, breathing techniques, myofunctional exercises, recommendations for diet therapy, sleep hygiene, etc.).

2021 10th Mediterranean Conference on Embedded Computing (MECO)

The development of modern computer technologies makes an urgent task of improving methods of stor... more The development of modern computer technologies makes an urgent task of improving methods of storing, transferring and processing information. One of these methods is the Residue Number System (RNS), based on parallel computing of arithmetic operations [1]–[2].in This Paper, the Analysis of Three-Module Rns Was Carried Out Using a Measure of Rns Balance, the Crtf Constants for Rns 2n,2n−1,2n−1−1\{2^{n},2^{n}-1,2^{n-1}-1\}2n,2n−1,2n−1−1 Were Calculated, a Device Was Proposed that Implements the Reverse Conversion for Rns 2n,2n−1,2n−1−1\{2^{n},2^{n}-1,2^{n-1}-1\}2n,2n−1,2n−1−1, the Simulation Was Carried Out on Fpga, Which Confirmed the Quality of the Proposed Reverse Conversion. the Simulation Results Have Confirmed that the Proposed Reverse Conversion Takes Fewer Hardware Costs By 10-15%and Higher Speed By 2-25%.

PRZEGL�D ELEKTROTECHNICZNY, 2015

The paper discusses digital filter bank implementation using the weighted overlap-add (WOLA) algo... more The paper discusses digital filter bank implementation using the weighted overlap-add (WOLA) algorithm modification introduced in the context of multichannel signal processing. The suggested modification is applied to hydroacoustic monitoring tasks. High-performance softwarehardware implementations on the basis of CPU (Central Processing Unit) and CUDA (Compute Unified Device Architecture) are compared and CUDA is shown to provide advantages for the filter banks studied. Streszczenie. W artykule przedstawiono implementację banku filtrów cyfrowych opartych na algorytmie Weighted Overlap-Add (WOLA), zmodyfikowanego w kontekście przetwarzania sygnału wielokanałowego. Zaproponowane modyfikacje zostały zastosowane w hydroakustycznych zadaniach monitorowania. Dokonano porównania wysokowydajnych programowo-sprzętowych implementacji opartych na CPU (Central Processing Unit) oraz CUDA (Compute i Unified Device Architecture). Badania wykonane dla zdefiniowanego banku filtrów pokazały, że najbardziej korzystne jest zastosowanie CUDA. (Implementacja banku filtrów w hydroakustycznych zadaniach monitorowania).

ABSTRACT The present paper discusses digital filter banks in the context of wideband radio monito... more ABSTRACT The present paper discusses digital filter banks in the context of wideband radio monitoring tasks including DFT-modulated filter banks and the weighted overlap-add (WOLA) algorithm. Filter bank software-hardware implementations are considered on the basis of Central Processing Unit (CPU) and Compute Unified Device Architecture (CUDA) with the use of Graphics Processing Unit (GPU). The main filter bank forms are studied and compared by their execution time in MATLAB. It is shown that CUDA technology is efficient for processing large datasets and outperforms computation results on CPU.

Pattern Recognition and Image Analysis, 2017

The paper discusses an algorithm for spectral density estimation in the frequency domain using wa... more The paper discusses an algorithm for spectral density estimation in the frequency domain using wavelet-based smoothing by wavelet thresholding techniques. The suggested algorithm can be applied to vibrational and hydroacoustic signal processing in order to estimate signal parameters in the frequency domain. The algorithm can be applied to the Fourier periodogram without using signal samples in the time domain. We also propose a technique aimed at working with signals of arbitrary length by applying the maximal overlap discrete wavelet transform. We also study software-hardware implementation of the developed algorithms.

2016 IEEE NW Russia Young Researchers in Electrical and Electronic Engineering Conference (EIConRusNW), 2016

We consider software-hardware implementation of a digital filter (FIR-filter) using the residue n... more We consider software-hardware implementation of a digital filter (FIR-filter) using the residue number system and scaling of output samples of each filter channel. It is shown that scaling leads to a significant reduction in instrumental and temporal costs.