2023/11/05 · We propose a novel subsequence classification method that represents each subsequence as an ego-network, providing crucial nearest neighbor information to the ...
The ego-networks of all subsequences collectively form a time series subsequence graph, and we introduce an algorithm to efficiently construct this graph.
The ego-networks of all subsequences collectively form a time series subsequence graph, and we introduce an algorithm to efficiently construct this graph.
Co-authors ; Ego-network transformer for subsequence classification in time series data. CCM Yeh, H Chen, Y Fan, X Dai, Y Zheng, V Lai, J Wang, Z Zhuang, ...
My research interest includes, but not limit to: time series analysis, data mining, machine learning, and information retrieval. ... Ego-Network ...
The ego-networks of all subsequences collectively form a time series subsequence graph, and we introduce an algorithm to efficiently construct this graph. Time ...
Ego-Network Transformer for Subsequence Classification in Time Series Data · Conference Paper. December 2023. ·. 5 Reads. ·. 1 Citation. Chin-Chia Michael Yeh.
The ego-networks of all subsequences collectively form a time series subsequence graph, and we introduce an algorithm to efficiently construct this graph. Time ...
The ego-networks of all subsequences collectively form a time series subsequence graph, and we introduce an algorithm to efficiently construct this graph.
2023/10/21 · In this paper, we aim to develop an effective time series foundation model by leveraging unlabeled samples from multiple domains.