In this paper, we propose a novel algorithm called ShapeNet, which embeds shapelet candidates from different lengths into the unified space for shaplets selection. The network is trained using our cluster-wise triplet loss, which considers the distance between anchor and multiple positive (negative) samples and the distance among positive (negative) samples. Then, we compute representative and diversified final shapelets rather than directly using all the embeddings for model building to avoid a large fraction of computing non-discriminative shapelet candidates. A classical classifier (e.g., SVM) is then adopted.

The overview of ShapeNet


We implemented the proposed algorithms in Python. A well-known benchmark of time series classification datasets, UEA Time Series Classification Archive, has been tested.

Source code can be found in here.

The style of password is “xxxxxxxx”,
all the characters are with lower case of our method name.


Do one thing at a time, and do well. :)



Thanks the research community for supporting the datasets.

HKBU Database Group