HITS: Binarizing physiological time series with deep hashing neural network

Abstract

• A deep neural network architecture is proposed to learn binary hash codes from physiological time series. • High utility, similarity preserving and temporal relationship are jointly learned with multiple designed objectives. • Experiments on ECG and EEG datasets show the effectiveness of the proposed method. In this paper, we aim to transform numerical physiological time series into binary hash codes, that can be further used for indexing large-scale dataset, or accelerating downstream tasks such as instance-based classification . We propose HITS to learn binary H ash codes from phys I ological T ime S eries. HITS first builds a very deep one-dimensional convolutional neural network to learn lower-dimensional representations from raw physiological time series. Then, HITS jointly learns high utility, similarity preserving, and temporal related compact binary codes by corresponding objectives with imposed. Finally, given a new physiological time series, HITS can encode it to a binary hash code. Experiments are performed on two real-world Electrocardiogram and Electroencephalogram datasets. The accuracy of a k-nearest classifier is used to evaluate the quality of codes. HITS outperforms the second-best baseline 7.42% on average of k = { 1 , 2 , 4 , 8 , 16 , 32 } with code length c = 48 , while reducing 45.51% searching time than the same length numerical vectors on average of c = { 16 , 24 , 32 , 48 , 64 } . HITS consistently achieve higher classification accuracy than compared methods using k-nearest classifier varying different k and code length. Thus, HITS learns better binary hash codes than compared methods.