PREDIKSI PERMINTAAN KANTONG DARAH DI UTD PMI KOTA SURABAYA MENGGUNAKAN METODE ARIMA-ANFIS DENGAN OPTIMASI ARTIFICIAL BEE COLONY

Oktaviani, Sheny Eka (2025) PREDIKSI PERMINTAAN KANTONG DARAH DI UTD PMI KOTA SURABAYA MENGGUNAKAN METODE ARIMA-ANFIS DENGAN OPTIMASI ARTIFICIAL BEE COLONY. Undergraduate thesis, Universitas Pembangunan Nasional Veteran Jawa Timur.

	Text (Cover) 21083010037_Cover.pdf Download (1MB)
	Text (Bab 1) 21083010037_Bab 1.pdf Download (205kB)
	Text (Bab 2) 21083010037_Bab 2.pdf Restricted to Registered users only until 19 June 2028. Download (748kB)
	Text (Bab 3) 21083010037_Bab 3.pdf Restricted to Registered users only until 19 June 2028. Download (1MB)
	Text (Bab 4) 21083010037_Bab 4.pdf Restricted to Registered users only until 19 June 2028. Download (3MB)
	Text (Bab 5) 21083010037_Bab 5.pdf Download (165kB)
	Text (Daftar Pustaka) 21083010037_Daftar Pustaka.pdf Download (174kB)
	Text (Lampiran) 21083010037_Lampiran.pdf Restricted to Registered users only until 19 June 2028. Download (948kB)

Abstract

The increasing demand for blood along with population growth is a challenge for the Blood Transfusion Unit (UTD). One of the main problems faced by UTD Surabaya City is the uncertainty of blood demand which causes an imbalance between stock and demand. This results in the risk of stock shortage or wastage due to expired blood. Thus, accurate prediction is essential for efficient blood stock management, avoiding shortages or overstocks, as well as ensuring blood availability for patients in need. The purpose of this study is to apply the ARIMA-ANFIS approach with Artificial Bee Colony (ABC) optimization to predict blood demand. ARIMA is used to capture the linear component, while ANFIS addresses the non-linear pattern of ARIMA residuals. The ABC algorithm plays a role in optimizing ANFIS parameters to improve prediction accuracy. This research has a novelty in the application of ARIMA-ANFIS with ABC optimization for blood demand prediction, which has not been widely explored before. The analysis shows that the ARIMA(1,0,1)-ANFIS model with ABC optimization is the best model, with the lowest MAPE of 6.19%. Predictions for the next six months (January-June 2025) show realistic fluctuations between 5716,45 to 6595,37 blood bags. In addition, the developed GUI makes it easier for users in the process of data visualization, modeling, and interpretation of results without requiring technical expertise in modeling. Keywords: Blood Transfusion, Indonesian Red Cross (PMI), ARIMA, ANFIS, Artificial Bee Colony (ABC)

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Trimono, Trimono	NIDN0008099501	trimono.stat@upnjatim.ac.id
Thesis advisor	Damaliana, Aviolla Terza	NIDN0002089402	aviolla.terza.sada@upnjatim.ac.id

Subjects:

H Social Sciences > HA Statistics
Q Science > QA Mathematics
Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Sheny Eka

Date Deposited:

20 Jun 2025 02:05

Last Modified:

20 Jun 2025 02:05

URI:

https://repository.upnjatim.ac.id/id/eprint/38618