scholarly journals Sequential Pattern Mining of Tourist Spatiotemporal Movement

2021 ◽  
Vol 9 (1) ◽  
pp. 69-78
Author(s):  
Maria Isabel Abucejo ◽  
◽  
Jovelyn Cuizon ◽  
Keyword(s):  
Pattern Mining ◽  
Sequential Pattern Mining ◽  
Sequential Pattern ◽  
Time Intervals ◽  
Heat Map ◽  
Software Application ◽  
Positive Indicators ◽  
Planning Experts ◽  
Flow Map ◽  
Activity Information

The study aimed to develop a software application to capture tourist activity information, extract movement patterns from the dataset through sequential pattern mining (SPM), and visualize spatiotemporal movement. Tourist activity information was captured through crowdsourced trajectory movements by scanning unique QR (Quick Response) codes for each visited tourist spots. The AprioriAll algorithm was used to find frequent trajectory patterns on tourist visits. The resulting maximal k-sequences and their subsequences represent the recommended trip itinerary. The spatial and temporal movements were visualized through a flow map and a heat map, respectively. The directed edges in the flow map show the recommended sequence of tourist sites to visit. The heat map shows the density of tourist visits in different areas at time intervals. The application was validated with selected tour planning experts to verify functional suitability, usability, and acceptability. Experimental results show positive indicators that the application met the users’ expectations.

Mining Time-Interval Sequential Patterns with High Utility from Transaction Databases

2016 ◽  
Vol 20 (6) ◽  
pp. 1018-1026 ◽  
Author(s):  
Wen-Yen Wang ◽  
◽  
Anna Y.-Q. Huang ◽  
Keyword(s):  
Pattern Mining ◽  
Sequential Pattern Mining ◽  
Business Practice ◽  
Sequential Pattern ◽  
Sequential Patterns ◽  
Time Interval ◽  
Business Managers ◽  
Time Intervals ◽  
High Utility ◽  
Product Sales

The purpose of time-interval sequential pattern mining is to help superstore business managers promote product sales. Sequential pattern mining discovers the time interval patterns for items: for example, if most customers purchase product item <span class="bold">A</span>, and then buy items <span class="bold">B</span> and <span class="bold">C</span> after <span class="bold">r</span> to <span class="bold">s</span> and <span class="bold">t</span> to <span class="bold">u</span> days respectively, the time interval between <span class="bold">r</span> to <span class="bold">s</span> and <span class="bold">t</span> to <span class="bold">u</span> days can be provided to business managers to facilitate informed marketing decisions. We treat these time intervals as patterns to be mined, to predict the purchasing time intervals between <span class="bold">A</span> and <span class="bold">B</span>, as well as <span class="bold">B</span> and <span class="bold">C</span>. Nevertheless, little work considers the significance of product items while mining these time-interval sequential patterns. This work extends previous work and retains high-utility time interval patterns during pattern mining. This type of mining is meant to more closely reflect actual business practice. Experimental results show the differences between three mining approaches when jointly considering item utility and time intervals for purchased items. In addition to yielding more accurate patterns than the other two methods, the proposed UTMining_A method shortens execution times by delaying join processing and removing unnecessary records.

Sign in / Sign up

Export Citation Format

Share Document