(n, m)-Layer MC-MHLF: Deep Neural Network for Classifying Time Series

Time series is now ubiquitous and time series classification has applications in many different areas; therefore, improving the accuracy of time series classification is one of the most interesting research topics. Fully convolutional neural network (FCN) and long short term memory fully convolutional network (LSTM-FCN) are leading techniques for deep-learning-based classification models. In our previous work, we proposed a new LSTM-FCN-based model, which is called multi-channel MACD histogram LSTM-FCN (MC-MHLF). The experimental results showed the MC-MHLF model had a good classification performance. To enhance the ability of the model, we propose a new deep neural model, which is called (n, m)-Layer MC-MHLF. The (n, m)-Layer MC-MHLF model is based on the MC-MHLF model and it is composed of n LSTM layers and m convolution layers. To evaluate the (n, m)-Layer MC-MHLF model, we compared the classification performance of it with that of conventional models. The experimental results showed that the (n, m)-Layer MC-MHLF model has good performance for classifying time series.