IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Statistics and Data Sciences
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Statistics and Data Sciences
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Kajian Penerapan Model GSTAR dan MIMO-LSTM dalam Peramalan Pasien Rawat Rumah Sakit Dinkes Kota Administrasi DKI Jakarta

      Thumbnail
      View/Open
      Cover (379.4Kb)
      Fulltext (8.356Mb)
      Lampiran (1.571Mb)
      Date
      2026
      Author
      Saputra, Ghonniyu Hiban
      Sumertajaya, I Made
      Firdawanti, Aulia Rizki
      Metadata
      Show full item record
      Abstract
      Peningkatan kebutuhan layanan kesehatan memerlukan informasi prediksi jumlah pasien untuk mendukung pengelolaan sumber daya rumah sakit secara efektif. Penelitian ini bertujuan menentukan model terbaik antara generalized space time autoregressive (GSTAR) dan multiple input multiple output long short-term memory (MIMO-LSTM) dalam memodelkan serta meramalkan jumlah pasien rawat rumah sakit pada lima Kota Administrasi DKI Jakarta. Data yang digunakan berupa data mingguan jumlah pasien periode Januari 2021 hingga Januari 2026. Pemodelan GSTAR dilakukan menggunakan pembobot queen contiguity dan inverse distance weighting, sedangkan MIMO-LSTM dibangun menggunakan optimasi hyperparameter melalui grid search dan time series cross validation dengan skema expanding window. Hasil penelitian menunjukkan bahwa model GSTAR(1;1) dengan pembobot queen contiguity memberikan performa terbaik dibandingkan MIMO-LSTM. Model GSTAR menghasilkan nilai MAPE dan RMSE pada data testing masing-masing sebesar 2,478% dan 15,626, sedangkan MIMO-LSTM menghasilkan nilai MAPE 11,522% dan RMSE 79,759. Hasil peramalan delapan periode menunjukkan pola jumlah pasien yang relatif stabil dengan rataan keseluruhan wilayah menghasilkan nilai MAPE 12,708%. Temuan ini menunjukkan bahwa model GSTAR mampu menjadi pendukung pengambilan keputusan dan perencanaan layanan kesehatan jangka pendek.
       
      The increasing demand for healthcare services requires patient forecasting information to support effective hospital resource management. This study aimed to determine the best model between generalized space time autoregressive (GSTAR) and multiple input multiple output long short-term memory (MIMO-LSTM) for modeling and forecasting the number of hospital inpatients across five administrative cities of DKI Jakarta. The study used weekly inpatient data from January 2021 to January 2026. The GSTAR model was developed using queen contiguity and inverse distance weighting schemes, while the MIMO-LSTM model was optimized through hyperparameter tuning using grid search and time series cross validation with an expanding window approach. The results showed that the GSTAR(1;1) model with queen contiguity weighting outperformed the MIMO-LSTM model. GSTAR achieved testing MAPE and RMSE values of 2,478% and 15,626 respectively, while MIMO-LSTM produced MAPE and RMSE values of 11,522% and 79,759. Forecasting results for the next eight periods indicated a relatively stable pattern in patient numbers, with an overall mean MAPE of 12.708% across all administrative cities. These findings suggest that the GSTAR model can support short-term healthcare planning and decision making.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/173646
      Collections
      • UF - Statistics and Data Sciences [103]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository