Optimization of schedule for distribution of dosimeter sets by the IAEA/WHO using  machine learning

Vedernikova, Anastasiia

Домівка
→
Students Research & Project Works | Роботи студентів
→
Факультет прикладних наук
→
Бакалаврська програма "Комп'ютерні науки"
→
2019
→
Перегляд матеріалів

dc.contributor.author	Vedernikova, Anastasiia
dc.date.accessioned	2024-02-14T17:02:27Z
dc.date.available	2024-02-14T17:02:27Z
dc.date.issued	2019
dc.identifier.citation	Vedernikova, Anastasiia. Optimization of schedule for distribution of dosimeter sets by the IAEA/WHO using machine learning / Vedernikova, Anastasiia; Supervisor: Yaroslav Pynda, Tomislav Bokulic; Ukrainian Catholic University, Department of Computer Sciences. – Lviv: 2019. – 64 p.	uk
dc.identifier.uri	https://er.ucu.edu.ua/handle/1/4486
dc.language.iso	en	uk
dc.title	Optimization of schedule for distribution of dosimeter sets by the IAEA/WHO using machine learning	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	IAEA dosimetry laboratory (DOL) uses almost the same schedule for sending RPLD sets to hospitals around the world each year. Hospitals irradiate sets and send them back to the DOL for further analysis. The workload intensity of laboratory mostly depends on number of sets it receives each month. The goal of this project is to cre- ate more balanced schedule of irradiation windows, by minimizing the difference between received number of sets each month. The project consists of three main steps: forecasting waiting time, forecasting number of sets and scheduling. As a re- sult, predictions for waiting time created by LSTM and ARIMA, together with pre- dictions for number of sets created by Exponential Smoothing were used to generate more balanced schedule of irradiation windows using Linear Programming. New schedule satisfies all constraints and can be used next year for IAEA/WHO postal dose quality audits.	uk