Faculty of Computer Science, Najafabad Branch,
Guest Editors play a significant role in a special issue. They maintain the quality of published research and enhance the special issue’s impact. If you would like to be a Guest Editor or recommend a colleague as a Guest Editor of this special issue, please Click here to fulfill the Guest Editor application.
Recent progresses in sensor networks, cyber-physical systems, and the ubiquity of the internet of things have increased uncertain inherently as a result of noise, incompleteness, and irregularity. Mining of such data requires advanced analytical techniques for efficiently reviewing and/or predicting future progresses of action with high precision and advanced decision-making strategies. Therefore, uncertain data mining has gained wide attention from both academia and industry for understanding patterns in massive datasets. In comparison to traditional data techniques, artificial intelligence techniques (including machine learning, natural language processing, and computational intelligence) provide more accurate, faster, and scalable results in data analytics. Three types of uncertain data have been considered for mining frequent patterns : (1) Item set uncertain data, in which each item has a probability that shows the probability of its existence in the transaction; (2) Tuple uncertain data, in which each tuple consists a probability that shows the occurrence possibility of that tuple in the transaction; (3) Univariate Uncertain data, in which each attribute is associated with a quantitative interval and a possibility density function that shows the occurrence probability of each value in the interval. It is worth mentioning that the three mentioned categories are different. Mining frequent uncertain patterns is not as easy as mining frequent certain patterns. In addition, counting a patterns support in univariate uncertain data is more complex than in item set uncertain data for two reasons. First, the basic element that constitutes a pattern is not clear. Second, how to compute the support for patterns is still an open question. Most real-world applications generate univariate uncertain data, e.g. air quality reading systems, traffic control devices, and network monitoring systems. Therefore, uncertain data mining plays an essential role in data mining and machine learning. The aim of this special issue is to develop techniques to mine uncertain data for increasing the quality of data analysis.