Wibawa Aji Prasetya, Utama Agung Bella Putra, Elmunsyah Hakkun, Pujianto Utomo, Dwiyanto Felix Andika, Hernandez Leonel
Electrical Engineering Department, Universitas Negeri Malang, Malang, 65145 Indonesia.
Faculty of Engineering, ITSA Institución Universitaria, Cra 45 No. 48-31, Barranquilla, Colombia.
J Big Data. 2022;9(1):44. doi: 10.1186/s40537-022-00599-y. Epub 2022 Apr 26.
CNN originates from image processing and is not commonly known as a forecasting technique in time-series analysis which depends on the quality of input data. One of the methods to improve the quality is by smoothing the data. This study introduces a novel hybrid exponential smoothing using CNN called Smoothed-CNN (S-CNN). The method of combining tactics outperforms the majority of individual solutions in forecasting. The S-CNN was compared with the original CNN method and other forecasting methods such as Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM). The dataset is a year time-series of daily website visitors. Since there are no special rules for using the number of hidden layers, the Lucas number was used. The results show that S-CNN is better than MLP and LSTM, with the best MSE of 0.012147693 using 76 hidden layers at 80%:20% data composition.
卷积神经网络（CNN）起源于图像处理，在时间序列分析中通常不作为一种预测技术，时间序列分析依赖于输入数据的质量。提高数据质量的方法之一是对数据进行平滑处理。本研究引入了一种使用CNN的新型混合指数平滑方法，称为平滑卷积神经网络（S-CNN）。这种结合策略的方法在预测方面优于大多数单独的解决方案。将S-CNN与原始的CNN方法以及其他预测方法（如多层感知器（MLP）和长短期记忆网络（LSTM））进行了比较。数据集是一年的每日网站访问者时间序列。由于在使用隐藏层数量方面没有特殊规则，因此使用了卢卡斯数。结果表明，S-CNN优于MLP和LSTM，在80%:20%的数据构成下，使用76个隐藏层时，最佳均方误差为0.012147693。
