@article{Li2017, 
author = {Peng Li and Hong Luo and Yan Sun},
title = {Similarity Search Algorithm over Data Supply Chain Based on Key Points},
year = {2017},
journal = {Tsinghua Science and Technology},
volume = {22},
number = {2},
pages = {174-184},
keywords = {data supply chain, similarity search, feature space, hierarchical clustering},
url = {https://www.sciopen.com/article/10.23919/TST.2017.7889639},
doi = {10.23919/TST.2017.7889639},
abstract = {In this paper, we target a similarity search among data supply chains, which plays an essential role in optimizing the supply chain and extending its value. This problem is very challenging for application-oriented data supply chains because the high complexity of the data supply chain makes the computation of similarity extremely complex and inefficient. In this paper, we propose a feature space representation model based on key points, which can extract the key features from the subsequences of the original data supply chain and simplify it into a feature vector form. Then, we formulate the similarity computation of the subsequences based on the multiscale features. Further, we propose an improved hierarchical clustering algorithm for a similarity search over the data supply chains. The main idea is to separate the subsequences into disjoint groups such that each group meets one specific clustering criteria; thus, the cluster containing the query object is the similarity search result. The experimental results show that the proposed approach is both effective and efficient for data supply chain retrieval.}
}