Sliding-Window Probabilistic Threshold Aggregate Queries on Uncertain Data Streams

With the increase of real-time stream data, knowledge discovery from stream data becomes more and more important, which requires an efficient data structure to store transactions and scan sliding windows once to discover frequent itemsets. We present a new method named Linking Compact Tree (LCTree). We designed an algorithm by using an improved data structure to create objective tree, which can find frequent itemsets with linear complexity. Secondly, we can merge items in sliding windows by one scan with Head Linking List data structure. Third, by implementing data structure of Tail Linking List, we can locate the obsolete nodes and remove them easily. Finally, LCTree is able to find all exact frequent items in data stream with reduced time and space complexity by using such a linear data structure. Experiments on datasets with different sizes and types were conducted to compare the proposed LCTree technique with well-known frequent item mining methods including Cantree, FP-tree, DSTree, CPSTree, and Gtree. The results of experiments show presented algorithm has better performance than other methods, and also confirm that it is a promising solution for detecting frequent item sets in real time applications.

show abstract

“…(2) Damped window model [26][27][28] and (3) Sliding window model [29][30][31][32]. e landmark is defined as a specific timestamp.…”

Section: Related Workmentioning

confidence: 99%

LCTree-Based Approach for Mining Frequent Items in Real-Time

Chen

Zhong

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

Efficient Query Method for Collaborative Sharing of Monitoring-Based Data Streams Based on a Distributed Platform

Feng

Liu

et al. 2023

2023 6th International Conference on Artificial Intelligence and Big Data (ICAIBD)

View full text Add to dashboard Cite

A Method for Processing Top-k Continuous Query on Uncertain Data Stream in Sliding Window Model

Wahab

Rum

Ibrahim

et al. 2021

Wseas Transactions on Systems and Control

View full text Add to dashboard Cite

The data stream is a series of data generated at sequential time from different sources. Processing such data is very important in many contemporary applications such as sensor networks, RFID technology, mobile computing and many more. The huge amount data generated and frequent changes in a short time makes the conventional processing methods insufficient. The Sliding Window Model (SWM) was introduced by Datar et. al to handle this problem. Avoiding multiple scans of the whole data sets, optimizing memory usage, and processing only the most recent tuple are the main challenges. The number of possible world instances grows exponentially in uncertain data and it is highly difficult to comprehend what it takes to meet Top-k query processing in the shortest amount of time. Following the generation of rules and the probability theory of this model, a framework was anticipated to sustain top-k processing algorithm over the SWM approach until the candidates expired. Based on the literature review study, none of the existing work have been made to tackle the issue arises from the top-k query processing of the possible world instance of the uncertain data streams within the SWM. The major issue resulted from these scenarios need to be addressed especially in the computation redundancy area that contributed to the increases of computational cost within the SWM. Therefore, the main objective of this research work is to propose the top-k query processing methods over uncertain data streams in SWM utilizing the score and the Possible World (PW) setting. In this study, a novel expiration and object indexing method is introduced to address the computational redundancy issues. We believed the proposed method can reduce computational costs and by managing insertion and exit policy on the right tuple candidates within a specified window frame. This research work will contribute to the area of computational query processing.

show abstract

Sliding-Window Probabilistic Threshold Aggregate Queries on Uncertain Data Streams

Cited by 4 publications

References 19 publications

LCTree-Based Approach for Mining Frequent Items in Real-Time

LCTree-Based Approach for Mining Frequent Items in Real-Time

Efficient Query Method for Collaborative Sharing of Monitoring-Based Data Streams Based on a Distributed Platform

A Method for Processing Top-k Continuous Query on Uncertain Data Stream in Sliding Window Model

Contact Info

Product

Resources

About