Diverse Relevance Feedback for Time Series with Autoencoder Based Summarizations

Abstract

We present a relevance feedback based browsing methodology using different representations for time series data. The outperforming representation type, e.g., among dual-tree complex wavelet transformation, Fourier, symbolic aggregate approximation (SAX), is learned based on user annotations of the presented query results with representation feedback. We present the use of autoencoder type neural networks to summarize time series or its representations into sparse vectors, which serves as another representation learned from the data. Experiments on 85 real data sets confirm that diversity in the result set increases precision, representation feedback incorporates item diversity and helps to identify the appropriate representation. The results also illustrate that the autoencoders can enhance the base representations, and achieve comparably accurate results with reduced data sizes.

Analysis of Mechanical Fault Diagnosis Method According to Signal Deep Autoencoder

“…The automatic encoder is an unsupervised selflearning mode with three fully connected neural network structures, including the input layer, the hidden layer, and the output layer. The encoder can map the input data from the high-dimensional space into the code in the low-dimensional space, and the decoder reconstructs the output data in the feature layer into the original input data, and obtains the effective features of the input data from the hidden layer through the encoding process and decoding process [16]. In this research, the constructed automatic encoder structure is shown in figure 2.…”