Academic Journal of Computing & Information Science, 2023, 6(13); doi: 10.25236/AJCIS.2023.061321.
Jianguo Deng1, Jiahang Liang1, Yi Wu2, Dan Wang1
1College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, 300222, China
2College of Information and Intelligence, Hunan Agricultural University, Hunan, Changsha, 410125, China
In this paper, the time series model and grey prediction model are established, and the stability of ARIMA model is tested by difference test, and the prediction is carried out. The prediction result is taken as the upper interval of the prediction interval, and the grey prediction result is taken as the lower interval of the prediction interval. The time series and grey prediction models are established respectively. Secondly, this paper establishes Pearson correlation coefficient model to analyze the relationship between lexical attributes and the percentage of difficulty pattern attempt scores. Three indicators are selected for the attributes of words: word complexity, letter frequency and the number of repeated letters, which are analyzed by taking the average number of attempts. It is found that these three indicators are significantly correlated with the number of attempts, the number of letter repetition and word complexity are positively correlated with the average number of attempts, and the letter frequency is negatively correlated with the average number of attempts.
Time series, Neural network module, Elbow rule, K-Means clustering, Euclidean distance
Jianguo Deng, Jiahang Liang, Yi Wu, Dan Wang. Research on Wordle Based on Time Series Model and Grey Prediction Model. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 13: 145-153. https://doi.org/10.25236/AJCIS.2023.061321.
[1] Xiaolong Z,Congjun R,Xinping X, et al. Prediction of demand for staple food and feed grain by a novel hybrid fractional discrete multivariate grey model[J]. Applied Mathematical Modelling, 2024, 125(PB).
[2] Junting Z,Haifei L,Wei B, et al. A hybrid approach of wavelet transform, ARIMA and LSTM model for the share price index futures forecasting[J]. North American Journal of Economics and Finance, 2024,69(PB).
[3] Rui S , Shu-Hua W , Dong-Lian G ,et al.Research of combined forecasting model based on time series model and gray model[J].Journal of Yanshan University, 2012.
[4] Babu M S V K,Pratyush C,Mayukha P . Planning of fast charging infrastructure for electric vehicles in a distribution system and prediction of dynamic price[J]. International Journal of Electrical Power and Energy Systems,2024,155(PA).
[5] Sareh G H,Abbasali V,Reza M S . Desertification simulation using wavelet and box-jenkins time series analysis based on TGSI and albedo remote sensing indices[J]. Journal of Arid Environments, 2023, 219.
[6] Bin M,Xing G,Penghui L . Adaptive energy management strategy based on a model predictive control with real-time tuning weight for hybrid energy storage system[J]. Energy,2023,283.
[7] Yangyang S,Yuhang X,Yingjie W, et al. Reconstruction of incomplete flow fields based on unsupervised learning[J]. Ocean Engineering,2023,288(P1).
[8] Şenol Halil,Çakır İlkay Türk,Bianco Francesco. Improved methane production from ultrasonically -pretreated secondary sedimentation tank sludge and new model proposal: Time series (ARIMA). [J]. Bioresource technology,2023.
[9] Pantelis L,Vasilis P,Theodor P, et al. CO2 concentration forecasting in smart cities using a hybrid ARIMA–TFT model on multivariate time series IoT data[J]. Scientific Reports,2023,13(1).
[10] Ke W,Changxi M,Xiaoting H . Research on traffic speed prediction based on wavelet transform and ARIMA-GRU hybrid model[J]. International Journal of Modern Physics C,2023,34(10).