UGMINE: utility-based graph mining

Q-VIPER: Quantitative Vertical Bitwise Algorithm to Mine Frequent Patterns

Although urbanization benefits modern society and residents of urban cities, limited public resources—such as parking facilities—remain a problem. Parking pricing acts as a tool to adjust the available resources. How should parking pricing be used to maximize parking resource utilization while optimizing the parking revenue for parking management? In this paper, we present a system that utilizes available public resources while optimizing revenue with predefined restrictions, especially in the parking management field. More specifically, we design a data-driven time-series based prediction system, which can support dynamic pricing. Evaluation results show the effectiveness and practicality of our parking data analytics system for supporting parking facility management and dynamic pricing for parking applications. 

Data Analytics for Parking Facility Management

Frequent pattern mining is a popular technique in big data mining and analytics. It discovers frequently occurring sets of items (e.g., popular merchandise items, frequently co-occurring events) from big data found in numerous database engineered applications. These frequent patterns can be discovered horizontally by transaction-centric mining algorithms or vertically by item-centric mining algorithms. Regardless of their mining direction (horizontal or vertical), traditional frequent pattern mining algorithms aim to discover Boolean frequent patterns in the sense that patterns capture the presence (or absence) of items within the discovered patterns. However, there are many real-life situations, in which quantities of items within the patterns are important. For example, the quantity of items may also affect profits of selling the items within the discovered patterns. Hence, in this paper, we present an algorithm for vertical mining of interesting quantitative frequent patterns. This Q-Eclat algorithm first represents the big data as a collection of equivalence classes according to their prefix item labels. Each domain item is represented by one of these classes. Their corresponding item-centric sets capture (a) IDs of transactions containing the item, as well as (b) the quantity of that item in each transaction. With this representation, our algorithm then vertically mines quantitative frequent patterns. When compared the existing MQA-M algorithm (which was built for quantitative horizontal frequent pattern mining), evaluation results show that our quantitative vertical Q-Eclat algorithm takes shorter runtime to mine quantitative frequent patterns.

Q-Eclat: Vertical Mining of Interesting Quantitative Patterns

In the current data-driven era, large volumes of data of different dimensions are generated and collected at a rapid rate. Examples of these big data include transportation data (e.g., traffic accident data). Integration of different transportation data, as well as reuse of past knowledge and information on public transit, can be for social good (e.g., can help road users avoid traffic accidents). Multi-dimensional data analysis and mining helps reveal factors associating with, or contributing to, traffic accidents. To manage this type of human-made disaster, we present in this paper a data science solution for multi-dimensional analysis of traffic accident data. It integrates heterogeneous data regarding vehicles, accidents and causality. It reuses past knowledge and information discovered from historical data for handling future situations. Evaluation on real-life accident data from the UK reveals some common conditions leading to serious and/or fatal accidents. It demonstrates the practicality of our solution in multi-dimensional analysis of traffic accident data, as well as the benefits of data integration and information (and knowledge) reuse, for disaster management in smart cities. Moreover, it is important to note that, although we illustrate our solution on UK accident data, our solution is expected to be reusable for the analysis of traffic accidents, support of disaster management, and building of smart cities at other locations.

Analysis of Multi-Dimensional Road Accident Data for Disaster Management in Smart Cities

Nowadays graphical datasets are having a vast amount of applications. As a result, graph mining—mining graph datasets to extract frequent subgraphs—has proven to be crucial in numerous aspects. It ...

ChowdhuryMohammad Ehsan Shahmi

Papers

A New Approach for Mining Correlated Frequent Subgraphs