Arda, Prafimana (2021) Optimasi Penjadwalan Perawat Dengan Menggunakan Metode Algoritma Reinforcement Learning Hyper-Heuristic (Studi Kasus: Rumah Sakit Anwar Medika di Sidoarjo). Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
Text
05211440000194-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) | Request a copy |
Abstract
Penjadwalan perawat memerankan peran penting pada pelayanan kesehatan di rumah sakit yang harus tetap beroperasi selama 24 jam, oleh karena itu penjadwalan perawat harus dibuat seoptimal mungkin. Akan tetapi sering kali dijumpai kendala dalam penjadwalan perawat, yaitu sulitnya untuk memenuhi setiap batasan yang ada. Batasan-batasan yang dimaksud bisa berupa regulasi rumah sakit, aturan-aturan dalam menyusun jadwal perawat, serta faktor pribadi dari masing-masing perawat. Pada studi kali ini metode algoritma Reinforcement Learning
HyperHeuristic digunakan untuk menyelesaikan permasalahan penjadwalan perawat di rumah sakit. Dimana algoritma
Reinforcement Learning Hyper Heuristic digunakan untuk memilih low-level heuristic yang menghasilkan solusi terbaik. Low-level heuristic yang digunakan adalah Move dan Swap. Sedangkan untuk mengetahui apakah hasil pengoptimasian sudah optimal akan diukur menggunakan nilai Jain Fairness Indeks (JFI) dengan rentang nilai 0-1 dari tiap unit yang ada di rumah sakit. Dimana jika nilai JFI semakin mendekati 1 maka jadwal semakin optimal. Setelah dilakukan optimasi dengan algoritma Reinforcement Learning, nilai JFI dari ketujuh unit yang beroperasi di rumah sakit mengalami peningkatan dengan rata-rata sebesar 6,66%.
=====================================================================================================
Nurse scheduling plays an important role on health services in hospital that must be open for 24 hours a day. Therefore, the scheduling should be optimized. However, it is hard to satisfy every constraint such as scheduling rules, nurse’s preference, etc. In this study, Reinforcement Learning hyper heuristic algorithm was used to optimize the nurse scheduling at Anwar Medika Hospital. The algorithm was used to choose one of low-level heuristic that offer the best solution. The low-level heuristics that were used in this study were move and swap. The value of Jain Fairness Index (JFI) of each unit was calculated to measure the optimization of the schedule. JFI value ranges from 0 - 1, the more optimum the schedule the bigger the value. The result shows that Reinforcement Learning hyper heuristic algorithm can optimize the nurse’s scheduling. After being optimized, the JFI values of all departments has increased by 6.66% on average.
Item Type: | Thesis (Undergraduate) |
---|---|
Uncontrolled Keywords: | Nurse Rostering Problem, Optimasi, Hyper Heuristic, Reinforcement Learning, Optimization. |
Subjects: | T Technology > T Technology (General) > T57.84 Heuristic algorithms. |
Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis |
Depositing User: | Prafimana Arda |
Date Deposited: | 23 Aug 2021 11:47 |
Last Modified: | 23 Aug 2021 11:47 |
URI: | http://repository.its.ac.id/id/eprint/89666 |
Actions (login required)
View Item |