Skyline queries over incomplete data streams

摘要: Nowadays, efficient and effective processing over massive stream data has attracted much attention from the database community, which are useful in many real applications such as sensor monitoring, network intrusion detection, so on. In practice, due to malfunction of sensing devices or imperfect collection techniques, real-world may often contain missing incomplete attributes. this paper, we will formalize tackle a novel important problem, named skyline query (Sky-iDS), retrieves objects (in presence attributes) with high confidences stream. order Sky-iDS design approaches impute attributes via differential dependency (DD) rules. We propose pruning strategies reduce search space devise cost-model-based index structures facilitate imputation computation at same time, integrate our proposed techniques into an answering algorithm. Extensive experiments have been conducted confirm efficiency effectiveness approach both synthetic sets.