Acceso abierto

Drama plot development law and its prediction model based on time series analysis

Ting Nie

Ting Nie

School of Xi’an Peihua UniversityXi’an, China
Buscar este autor en
Sciendo|Google Scholar
Nie, Ting
  
25 sept 2025
Drama plot development law and its prediction model based on time series analysis's Cover Image
Acerca de este artículo
Artículo anterior
Artículo siguiente
Cite
Descargar portada
Publicado en línea: 25 sept 2025
Recibido: 13 ene 2025
Aceptado: 08 may 2025
DOI: https://doi.org/10.2478/amns-2025-1010
Palabras clave
© 2025 Ting Nie, published by Sciendo.
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Flowchart of ARIMA model construction
Flowchart of ARIMA model construction

Figure 2.

LSTM neural network structure diagram
LSTM neural network structure diagram

Figure 3.

Flowchart of combined model prediction
Flowchart of combined model prediction

Figure 4.

AQI sequence diagram on training set
AQI sequence diagram on training set

Figure 5.

Model check Q-Q chart
Model check Q-Q chart

Figure 6.

Model check autocorrelation graph
Model check autocorrelation graph

Figure 7.

The prediction results of ARIMA model
The prediction results of ARIMA model

Figure 8.

DA-LSTM model prediction result
DA-LSTM model prediction result

Figure 9.

Prediction result of ARMI-LSTM
Prediction result of ARMI-LSTM

Figure 10.

Comparison between the true value and predicted value of Model1
Comparison between the true value and predicted value of Model1

Figure 11.

Comparison between the true value and predicted value of Model2
Comparison between the true value and predicted value of Model2

Figure 12.

Comparison between the true value and predicted value of Model3
Comparison between the true value and predicted value of Model3

Figure 13.

Comparison between the true value and predicted value of Model4
Comparison between the true value and predicted value of Model4

Figure 14.

Comparison between the true value and predicted value of Model5
Comparison between the true value and predicted value of Model5

Experimental result

Model MAE RMSE MAPE
Modell 0.002459 0.003268 0.002043
Model2 0.000735 0.000987 0.000614
Model3 0.000638 0.000906 0.000547
Model4 0.000624 0.000879 0.000521
Model5 0.000601 0.000852 0.000504
Idioma:
Inglés
Calendario de la edición:
1 veces al año
Temas de la revista:
Ciencias de la vida, Ciencias de la vida, otros, Matemáticas, Matemáticas aplicadas, Matemáticas generales, Física, Física, otros
RSS Feed de revista