Deconvolution-and-convolution Networks
This addresses the reliance on human pre-processing in existing CNN-based methods for 1D big data analysis, offering a more automated solution for tasks like classification and regression.
The paper tackles the problem of 1D pattern recognition for large datasets by proposing DCNet, a deep deconvolutional-convolutional network that converts 1D signals into 2D data without human pre-processing, achieving higher generalization performance across datasets with 50K to 11M training samples.
2D Convolutional neural network (CNN) has arguably become the de facto standard for computer vision tasks. Recent findings, however, suggest that CNN may not be the best option for 1D pattern recognition, especially for datasets with over 1 M training samples, e.g., existing CNN-based methods for 1D signals are highly reliant on human pre-processing. Common practices include utilizing discrete Fourier transform (DFT) to reconstruct 1D signal into 2D array. To add to extant knowledge, in this paper, a novel 1D data processing algorithm is proposed for 1D big data analysis through learning a deep deconvolutional-convolutional network. Rather than resorting to human-based techniques, we employed deconvolution layers to convert 1 D signals into 2D data. On top of the deconvolution model, the data was identified by a 2D CNN. Compared with the existing 1D signal processing algorithms, DCNet boasts the advantages of less human-made inference and higher generalization performance. Our experimental results from a varying number of training patterns (50 K to 11 M) from classification and regression demonstrate the desirability of our new approach.