Spatio-Temporal Feature Learning

semanticscholar(2018)

引用 0|浏览3
暂无评分
摘要
In modern medicine, patient vital sign information is often collected as 1 high-dimensional multi-channel time series data, which contains both spatial 2 and temporal information. In this paper, we propose a hybrid feature 3 learning model containing both spatial and temporal autoencoders to learn 4 deep feature representations of time series data. We use a publicly available 5 electroencephalograph (EEG) dataset to evaluate our model’s classification 6 performance and compare the results to: (i) using raw data as features, and (ii) 7 features learned from various combinations of spatial and temporal autoencoders. 8 Our findings highlight that the way in which we exploit spatial and temporal 9 correlations makes a significant difference and demonstrate the effectiveness of our 10 model in processing multivariate time series patient data. 11
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要