Page 85 - AJWEP-22-5

Hybrid optimization for LSTM DO prediction

application in optimization problem. Soft Comput. 29. Chicho BT, Sallow AB. A comprehensive survey of
2021;25:5277-5298. deep learning models based on keras framework. J Soft
doi: 10.1007/s00500-020-05527-x Comput Data Min. 2021;2(2):49-62.
25. Nguyen QV, Miller N, Arness D, Huang W, Huang ML, doi: 10.30880/jscdm.2021.02.02.005
Simoff S. Evaluation on interactive visualization data 30. Karim F, Majumdar S, Darabi H. Insights into lstm fully
with scatterplots. Vis Informatics. 2020;4(4):1-10. convolutional networks for time series classification.
doi: 10.1016/j.visinf.2020.09.004 IEEE Access. 2019;7:67718-67725.
26. Lu Z. Comparison of stock price prediction models for doi: 10.1109/ACCESS.2019.2916828
linear models, random forest and LSTM. Appl Comput 31. Liao L, Li H, Shang W, Ma L. An empirical study of the
Eng. 2024;54(1):226-233. impact of hyperparameter tuning and model optimization
doi: 10.54254/2755-2721/54/20241598 on the performance properties of deep neural networks.
27. Gürsoy Mİ, Alkan A. Investigation of diabetes data with ACM Trans Softw Eng Methodol. 2022;31(3):1-40.
permutation feature importance based deep learning doi: 10.1145/3506695
methods. Karadeniz Fen Bilim Derg. 2022;12(2):916-930. 32. Hodson TO, Over TM, Foks SS. Mean squared
doi: 10.31466/kfbd.1174591 error, deconstructed. J Adv Model Earth Syst.
28. De Smedt T, Daelemans W. Pattern for python. J Mach 2021;13(12):e2021MS002681.
Learn Res. 2012;13(1):2063-2067. doi: 10.1029/2021MS002681

Volume 22 Issue 5 (2025) 79 doi: 10.36922/AJWEP025210165