Prediksi Indeks Standar Pencemar Udara Menggunakan Metode Long Short-term Memory Berbasis Web (studi Kasus Pada Kota Jakarta)
DOI:
https://doi.org/10.34818/eoe.v9i3.18092Abstract
Abstrak Penggunaan long short-term memory karena metode tersebut menghasilkan prediksi angka sangat baik untuk data time series. prediksi yang telah dilakukan lalu diimplementasikan ke dalam website menggunakan kerangka flask. Penelitian menggunakan 5 parameter zat yang terdapat dalam ISPU sehingga mendapatkan hasil pengujian berbeda di setiap parameter zat. Hasil pengujian partisi data tiap zat adalah PM10 80% data latih 20% data uji, SO2 50% data latih 50% data uji, CO 80% data latih 20% data uji, O3 80% data latih 20% data uji, dan NO2 50% data latih 50% data uji. Dari hasil pengujian partisi data ditemukan pemodelan terbaik dari PM10 dengan epoch = 100, hidden layer = 1, neuron = 128, optimizer = Rmsprop, RMSE sebesar 0.007237, SO2 dengan epoch = 50, hidden layer = 1, neuron = 64, optimizer = Adamax, RMSE sebesar 0.05841, CO dengan epoch = 100, hidden layer = 1, neuron = 64, optimizer = Adamax, RMSE sebesar 0.05474, O3 dengan epoch = 50, hidden layer = 1, neuron = 64, optimizer = Adam, RMSE sebesar 0.04465, dan NO2 dengan epoch = 50, hidden layer = 1, neuron = 64, optimizer = Adam, RMSE sebesar 0.0431. berdasarkan usability testing yang telah dilakukan, website yang dirancang dapat membantu dalam memprediksikan ISPU dengan presentase nilai 80.7%. Kata Kunci: udara, long short-term memory, ISPU, DKI Jakarta, websiteReferences
[1] K. S. Rao, G. L. Devi, and N. Ramesh, “Air Quality Prediction in Visakhapatnam with LSTM based Recurrent Neural Networks,” Int. J. Intell. Syst. Appl., vol. 11, no. 2, pp. 18–24, 2019, doi: 10.5815/ijisa.2019.02.03.
[2] A. N. Irfansyah, “Prediksi polusi udara perkotaan di surabaya menggunakan,” vol. 18, pp. 102–114, 2020.
[3] R. Navares and J. L. Aznarte, “Predicting air quality with deep learning LSTM: Towards comprehensive models,” Ecol. Inform., vol. 55, p. 101019, 2020, doi: 10.1016/j.ecoinf.2019.101019.
[4] A. L. Samuel, “Some Studies in Machine Learning.”
[5] A. S. and S. V. N. Vishwanathan, “Introduction to machine learning,” Methods Mol. Biol., vol. 1107, pp. 105–128, 2014, doi: 10.1007/978-1-62703-748-8_7.
[6] Herdianto, “Prediksi Kerusakan Motor Induksi Menggunakan Tesis Oleh Herdianto Fakultas Teknik,” 2013.
[7] V. Dhar, “Data Science and Prediction Vasant Dhar Professor, Stern School of Business Director, Center for Digital Economy Research,” Commun. ACM, no. May, pp. 64–73, 2012, [Online]. Available: http://archive.nyu.edu/bitstream/2451/31553/2/Dhar-DataScience.pdf.
[8] M. Z. Alom et al., “A state-of-the-art survey on deep learning theory and architectures,” Electron., vol. 8, no. 3, 2019, doi: 10.3390/electronics8030292.
[9] J. Schmidhuber, “Deep Learning in neural networks: An overview,” Neural Networks, vol. 61, pp. 85–117, 2015, doi: 10.1016/j.neunet.2014.09.003.
[10] Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015, doi: 10.1038/nature14539.
[11] M. Monteleone, “NooJ local grammars and formal semantics: Past participles vs. adjectives in Italian,” Commun. Comput. Inf. Sci., vol. 607, no. 8, pp. 83–95, 2016, doi: 10.1007/978-3-319-42471-2_8.
[12] X. Zhang, M. H. Chen, and Y. Qin, “NLP-QA framework based on LSTM-RNN,” 2018 2nd Int. Conf. Data Sci. Bus. Anal., pp. 307–311, 2018, doi: 10.1109/ICDSBA.2018.00065.
[13] S. Abujar, A. K. M. Masum, S. M. M. H. Chowdhury, M. Hasan, and S. A. Hossain, “Bengali Text generation Using Bi-directional RNN,” 2019 10th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2019, pp. 1–5, 2019, doi: 10.1109/ICCCNT45670.2019.8944784.
[14] L. Guo, T. Ge, and J. S. Chang, “A 101 dB PSRR, 0.0027% THD + N and 94% power-efficiency filterless class D amplifier,” IEEE J. Solid-State Circuits, vol. 49, no. 11, pp. 2608–2617, 2014, doi: 10.1109/JSSC.2014.2359913.
[15] A. Xiao, J. Liu, Y. Li, Q. Song, and N. Ge, “Two-phase rate adaptation strategy for improving real-time video QoE in mobile networks,” China Commun., vol. 15, no. 10, pp. 12–24, 2018, doi: 10.1109/CC.2018.8485465.
[16] F. A. Gers, J. Schmidhuber, and F. Cummins, “Learning to Forget: Continual Prediction with LSTM,” Neural Comput., vol. 12, no. 10, pp. 2451–2471, Oct. 2000, doi: 10.1162/089976600300015015.
[17] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.
[18] V. Turchenko et al., “Stanford CS224d: Deep Learning for NLP Lecture 4,” Sigir, pp. 655–665, 2015, [Online]. Available: http://dx.doi.org/10.3115/v1/w15-1509%0Ahttp://disi.unitn.it/~severyn/papers/sigir-2015-long.pdf%0Ahttp://emnlp2014.org/papers/pdf/EMNLP2014181.pdf%0Ahttp://goo.gl/EsQCuC%0Ahttp://arxiv.org/abs/1512.01596.
[19] S. Sharma, S. Sharma, and A. Athaiya, “Activation Functions in Neural Networks,” Int. J. Eng. Appl. Sci. Technol., vol. 04, no. 12, pp. 310–316, 2020, doi: 10.33564/ijeast.2020.v04i12.054.
[20] U. Ugurlu, I. Oksuz, and O. Tas, “Electricity price forecasting using recurrent neural networks,” Energies, vol. 11, no. 5, pp. 1–23, 2018, doi: 10.3390/en11051255.
[21] S. Chaudhury and T. Yamasaki, “Robustness of Adaptive Neural Network Optimization Under Training Noise,” IEEE Access, vol. 9, pp. 37039–37053, 2021.
[22] R. A. Holzworth, G.C. & Cormick, “Air Pollution third edition. Academy Press,” Third., new york: In A.C Stren (Eds), 1976.
[23] J. Feng, X. He, Q. Teng, C. Ren, H. Chen, and Y. Li, “Reconstruction of porous media from extremely limited information using conditional generative adversarial networks,” Phys. Rev. E, vol. 100, no. 3, p. 33308, 2019, doi: 10.1103/PhysRevE.100.033308.
