Лариса Коряшкіна

Лариса Коряшкіна

Auto-generated profile, based on publicly available information

Лариса Коряшкіна

Національний технічний університет «Дніпровська політехніка

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 April 2022 in Journal of Computer Science and Technology
Verified
Journal Article
Open access
PDF file
KKKostiantyn Khabarlak
Kostiantyn Khabarlak
LKLarysa Koriashkina
Larysa Koriashkina
Dense facial landmark detection is a key element of face processing pipeline. In this paper we survey and analyze modern neural-network-based facial landmark detection algorithms, focus on approaches that have led to a significant increase in quality over the past few years on datasets with large pose and emotion variability, significant face occlusion, all of which are typical in real-world scenarios. We summarize the improvements into categories, provide quality comparison on difficult and modern in-the-wild datasets: 300 Faces in-the-wild (300W), Annotated Facial Landmarks in-the-wild (AFLW), Wider Facial Landmarks in-the-wild (WFLW), Caltech Occluded Faces in-the-wild (COFW). Additionally, we compare algorithm speed on desktop central and graphical processors, mobile devices. For completeness, we also briefly touch on established methods with open implementations available. Besides, we cover applications and vulnerabilities of the landmark detection algorithms. We hope that generalizations that we make will lead to further algorithm improvements.

23 November 2022 in Heliyon
Verified
Journal Article
Open access
OBOleg Bazaluk
Oleg Bazaluk
LKLarysa Koriashkina
Larysa Koriashkina
SCSerhii Cheberiachko
Serhii Cheberiachko
ODOleg Deryugin
Oleg Deryugin
MOMykola Odnovol
Mykola Odnovol
ONOlha Nesterova
Olha Nesterova
Safety of passenger road transportation (PRT) is a global problem considered by scientists. The present study is aimed at PRT safety improvement by developing its advanced model with accident risk minimization. Functional Resonance Analysis Method is used to identify factors influencing PRT safety. Accident risk assessment of the combined action of several factors in PRT is based on a phenomenological model. Possible good and bad PRT scenarios were considered differing in the staff professional experience, work shift duration, speed, vehicle service lifetime, and driver's stress load. Method for quantitative assessment of five main functions in PRT with their variability caused by parameters changes was designed. The proposed criteria were used to assess the parameter's deviations from their normative values and determine the major characteristics of each function. The recommendations for monitoring the driver's psychophysiological state at all transportation stages were developed and the relationship of transportation functions characteristics and criteria affecting passenger safety was established. This methodology enables assessing the PRT reliability level at a certain time. The approach allows evaluating the criteria affecting traffic safety, identifying their potential functionally resonant effect for abnormal PRT due to conditional changes; developing mechanisms to reduce accident risks by improving technical and organizational management.


12 October 2015 in Computational and Mathematical Methods in Medicine
Verified
Journal Article
Open access
PDF file
OBOleg Blyuss
Oleg Blyuss
LKLarysa Koriashkina
Larysa Koriashkina
EKElena Kiseleva
Elena Kiseleva
RMRobert Molchanov
Robert Molchanov
This paper proposes and analyses a mathematical model for the problem of distribution of a finite number of irradiation sources during radiotherapy in continuous environments to maximize the minimal cumulative effects. A new algorithm based on nondifferentiable optimization techniques has been developed to solve this problem. This paper proposes and analyses a mathematical model for the problem of distribution of a finite number of irradiation sources during radiotherapy in continuous environments to maximize the minimal cumulative effects. A new algorithm based on nondifferentiable optimization techniques has been developed to solve this problem.


29 February 2024 in Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu
Verified
Journal Article
Closed access
LKL. S Koriashkina
L. S Koriashkina
SDS. V Dziuba
S. V Dziuba
SUS. A Us
S. A Us
OSO. D Stanina
O. D Stanina
MOM. M Odnovol
M. M Odnovol
New+Information Technologies, Systems Analysis and Administration +https://doi.org/10.33271/nvngu/2024-1 +/jdownloads/pdf/2024/1/01_2024_contents-en-GB.pdf