PERAMALAN INDEKS ULTRAVIOLET DI KOTA BANDUNG MENGGUNAKAN METODE LONG SHORT-TERM MEMORY

Ida Bagus Wira Krishna Satyaputra; Herlina Napitupulu; Nurul Gusriani

doi:10.24198/jmi.v20.n2.58798.249-258

PERAMALAN INDEKS ULTRAVIOLET DI KOTA BANDUNG MENGGUNAKAN METODE LONG SHORT-TERM MEMORY

Ida Bagus Wira Krishna Satyaputra, Herlina Napitupulu, Nurul Gusriani

Abstract

Peramalan nilai indeks Ultraviolet (UV) memainkan peran penting dalam menjaga kesehatan masyarakat dan pengelolaan lingkungan. Penelitian ini bertujuan untuk menghasilkan nilai peramalan indeks UV di Kota Bandung pada tanggal 1–30 April 2024 menggunakan Metode Long Short-Term Memory (LSTM). Metode LSTM merupakan pengembangan dari metode Recurrent Neural Network (RNN). RNN diubah dengan menambahkan mekanisme gate untuk menyimpan informasi jangka panjang sehingga mengurangi resiko munculnya exploding gradients dan vanishing gradients. Model LSTM dalam penelitian ini dibangun menggunakan 1 input layer dengan 400 unit cell dan 1 output dense layer dengan fungsi update bobot adam optimizer, randomizer bobot glorot uniform distribution, dan 400 jumlah epoch. Performa model peramalan diuji menggunakan RMSE dan MAPE. Pada data training menghasilkan nilai RMSE sebesar 0,28 dan MAPE sebesar 11%. Untuk data testing menghasilkan nilai RMSE sebesar 0,48 dan MAPE sebesar 14%. Hasil peramalan indeks UV di Kota Bandung menunjukkan bahwa selama bulan April nilai rata-rata indeks UV adalah 2,27, hal ini mengartikan bahwa masyarakat Kota Bandung dapat beraktivitas diluar tanpa perlu mengkhawatirkan bahaya sinar UV.

Keywords

Peramalan; machine learning; long short term memory; indeks UV.

Full Text:

PDF

References

Vanicek, K., Frei, T., Litynska, Z., and Schmalwieser, A., “UV-Index for the Public COST-713 participating countries,” 1999.

Rehfuess E. Global solar UV index: a practical guide. World Health Organization; 2002.

Gers, F., Schmidhuber, J., and Cummins, F. “Learning to Forget: Continual Prediction with LSTM,” Neural Comput, vol. 12, pp. 2451–2471, Oct. 2000, doi: 10.1162/089976600300015015.

Van Houdt, G., Mosquera, C., and Nápoles, G. “A review on the long short-term memory model,” Artif Intell Rev, vol. 53, no. 8, pp. 5929–5955, Dec. 2020, doi: 10.1007/s10462-020-09838-1.

T. P. Lillicrap and A. Santoro, “Backpropagation through time and the brain,” Curr Opin Neurobiol, vol. 55, pp. 82–89, 2019, doi: https://doi.org/10.1016/j.conb.2019.01.011.

Chang, Z., Zhang, Y., and Chen, W. “Electricity price prediction based on hybrid model of adam optimized LSTM neural network and wavelet transform,” Energy, vol. 187, Nov. 2019, doi: 10.1016/j.energy.2019.07.134.

Wibowo, A., Wiryawan, P. W., and Nuqoyati, N. I. “Optimization of neural network for cancer microRNA biomarkers classification,” in Journal of Physics: Conference Series, Institute of Physics Publishing, Jun. 2019. doi: 10.1088/1742-6596/1217/1/012124.

Sharma, D. K., Chatterjee, M., Kaur, G., & Vavilala, S., “3 - Deep learning applications for disease diagnosis,” in Deep Learning for Medical Applications with Unique Data, pp. 31-51. Academic Press. Gupta, D. Kose, U., Khanna, A., and Balas, V.E. Eds., Academic Press, 2022, pp. 31–51. doi: https://doi.org/10.1016/B978-0-12-824145-5.00005-8.

de Myttenaere, A. Golden, B. Le Grand, and Rossi, F. “Mean Absolute Percentage Error for regression models,” Neurocomputing, vol. 192, pp. 38–48, 2016, doi: https://doi.org/10.1016/j.neucom.2015.12.114.

Lewis, C. D. Industrial and Business Forecasting Methods: A Practical Guide to Exponential Smoothing and Curve Fitting Butterworth scientific, Illustrated. Butterworth Scientific, 1982.

Kumar, S. L., “Predictive analytics of covid-19 pandemic: Statistical modelling perspective,” Walailak J Sci Technol, vol. 18, no. 16, Aug. 2021, doi: 10.48048/wjst.2021.15583.

DOI: https://doi.org/10.24198/jmi.v20.n2.58798.249-258