Blar i forfatter "Shvetsov, Nikita"
-
Exploring auction based energy trade with the support of MAS and blockchain technology
Shvetsov, Nikita (Master thesis; Mastergradsoppgave, 2017-06-13)This document describes a simulation of the local energy market with support of multi-agent approach and blockchain technology. The investigated points include blockchain technology and its applications, Ethereum platform and smart contracts as a tool for storing data of operations and creating assets, multi-agent approach to model the local energy market. The document explores building a solution ... -
Lessons Learned Developing and Using a Machine Learning Model to Automatically Transcribe 2.3 Million Handwritten Occupation Codes
Pedersen, Bjørn-Richard; Holsbø, Einar; Andersen, Trygve; Shvetsov, Nikita; Ravn, Johan; Sommerseth, Hilde Leikny; Bongo, Lars Ailo (Journal article; Tidsskriftartikkel; Peer reviewed, 2022-01-06)Machine learning approaches achieve high accuracy for text recognition and are therefore increasingly used for the transcription of handwritten historical sources. However, using machine learning in production requires a streamlined end-to-end pipeline that scales to the dataset size and a model that achieves high accuracy with few manual transcriptions. The correctness of the model results must ... -
A Pragmatic Machine Learning Approach to Quantify Tumor-Infiltrating Lymphocytes in Whole Slide Images
Shvetsov, Nikita; Grønnesby, Morten; Pedersen, Edvard; Møllersen, Kajsa; Rasmussen Busund, Lill-Tove; Schwienbacher, Ruth; Bongo, Lars Ailo; Kilvær, Thomas Karsten (Journal article; Tidsskriftartikkel; Peer reviewed, 2022-06-16)Increased levels of tumor-infiltrating lymphocytes (TILs) indicate favorable outcomes in many types of cancer. The manual quantification of immune cells is inaccurate and time-consuming for pathologists. Our aim is to leverage a computational solution to automatically quantify TILs in standard diagnostic hematoxylin and eosin-stained sections (H&E slides) from lung cancer patients. Our approach ...