Entry Name: VRVis-Matkovic-MC1

VAST Challenge 2015
Mini-Challenge 1

Team Members:

Krešimir Matković, VRVis Research Center, Austria, matkovic@vrvis.at PRIMARY

Denis Gračanin, Virginia Tech, USA, gracanin@vt.edu

Rainer Splechtna, VRVis Research Center, Austria, splechtna@vrvis.at

Alexandra Diehl, University of Buenos Aires, Argentina, ale.diehl@gmail.com

Mai Elshehaly, Virginia Tech, USA, maya70@vt.edu

Claudio Delrieux, Universidad Nacional del Sur, Bahía Blanca, Argentina, cad@uns.edu.ar

Student Team: YES

Did you use data from both mini-challenges? NO

Analytic Tools Used:

ComVis – a coordinated multiple view system developed by the VRVis Research Center and adapted for the challenge (extended data model, Trajectories and HeatMap views).

Python scripts for data processing

Excel

Approximately how many hours were spent working on this submission in total?

300

May we post your submission in the Visual Analytics Benchmark Repository after VAST Challenge 2015 is complete? YES

Video Download

Video:

http://www.cs.vt.edu/~gracanin/vrvis-matkovic-mc1-video.wmv

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Questions

MC1.1 – Characterize the attendance at DinoFun World on this weekend. Describe up to twelve different types of groups at the park on this weekend.

a. How big is this type of group?

b. Where does this type of group like to go in the park?

c. How common is this type of group?

d. What are your other observations about this type of group?

e. What can you infer about this type of group?

f. If you were to make one improvement to the park to better meet this group’s needs, what would it be?

Limit your response to no more than 12 images and 1000 words.

The curve view provides an overview of all the movements and serves as a starting point for group classification. The curves (user trajectories) are constructed and then the specialized Trajectories and Events view.

1. One-day groups

Individuals who visited only one day, Friday (orange), Saturday (green) and Sunday (blue). Most of them enter shortly after the opening (08:00-10:00), some of them at mid-day (13:00-15:00) and others late afternoon (17:00-18:00). There are very few late entries. The visitors on Friday traverse longer distances. This due to the smaller number visitors.

2. Two-day groups

Individuals who visited two days in a row, Friday-Saturday (orange) and Saturday-Sunday (green). Most of them enter shortly after the opening. There are very few later entries (mid-day, late afternoon, evening) and Sunday has the smallest number. No one has visited on Friday and Sunday. However, there are many visitors who visited on Friday, Saturday and Sunday.

3. Day and a Half Group

Individuals who stayed two days but left early the second day (only Friday-Saturday). There are only two such groups (4 an 1 individuals, respectively).

4. Late Visitor Group

Individuals who enter in the afternoon, either mid-day (13:00-15:00) or late afternoon (17:00-18:00). At least 50% of them are attending the show.

5. No Rides Group

Individuals who did not attend any ride or show (entering the park was the only check-in). Most of the groups (8-10 each day) consist of 3-4 individuals who are going shopping or eating. There are two groups of curves (7 and 1, respectively), however that all constitute a single group doing this twice a day Friday and Saturday and once on Sunday. The difference is due to the coarse sampling. Individual (ID 1787551) has only 954 movements and other have around 1900.

6. Fast Group

Individuals who moved very fast. There are five groups (between 1 and 4 individuals). We computed the first derivative of the movement to determine speed. We the brushed the maximum derivations. Some visitors have very high velocities. That could indicate some technical problems. There was also one corrupted record on Sunday.

MC1.2 – Are there notable differences in the patterns of activity on in the park across the three days? Please describe the notable difference you see.

Limit your response to no more than 3 images and 300 words.

There were 3557 visitors on Friday, 6411 on Saturday and 7569. For each day there are three distinctive periods of entrance, early morning from 08:00 to 10:00, mid-day from 13:00 to 15:00 and late afternoon from 17:00 to 18:00. The mid-day and late-afternoon are around 50% due to the two shows that appear to start at 15:00 and 18:00.

· Friday: 3557 total entries, 68 mid-day and 23 late afternoon.

· Saturday: 6411 total entries, 116 mid-day and 49 late afternoon.

· Sunday: 7569 total entries, 69 mid-day and 33 late afternoon.

Sunday has the largest number of total visits but proportionally the smallest number of mid-day and afternoon visits. This drop in visits is likely caused by the partial closure of the park and cancellation of the shows.

The curve view shows all individuals visiting the park. The x-axis is time in seconds and the y-axis is the distance walked. Time 0 corresponds to Friday at 08:00:00, time 86400 to Saturday at 08:00:00 and time 172800 to Sunday at 08:00:00. The drop in the

mid-day and afternoon visits on Sunday is indicated by less dense trajectories in the lower right corner.

MC1.3 – What anomalies or unusual patterns do you see? Describe no more than 10 anomalies, and prioritize those unusual patterns that you think are most likely to be relevant to the crime.

Limit your response to no more than 10 images and 500 words.

1. Repetitive Visits

A total of 8 individuals (521750, 644885, 1080969, 1600469, 1629516, 1781070, 1787551, 1935406) visited the park twice on Friday and Saturday (morning and afternoon) and once on Sunday (morning). The morning visits were all approximately from 08:45 to 12:15. The afternoon visits were all approximately from 13:45 to 17:15.

They always took the same path passing behind the Creighton Pavilion (32) where “the awards, trophies, and the Olympic Gold medal accumulated by our Hometown Hero through the years” were exhibited.

Our hypothesis is that after rehearsing for two days (Friday and Saturday), on Sunday morning they “vandalized a pavilion exhibiting Jones’s memorabilia and made off with an Olympic medal and possibly other irreplaceable items” before the first Sunday show started. Based on the times of their visits, the visits are timed with the start of the shows at 15:00 and 18:00. That would give them enough time to leave the park before the theft was discovered. Since they never entered Creighton Pavilion and just walked in the vicinity, it is plausible that they had someone on the inside who stole the items and handed them over during their walk.

2. Drunk Individual

An individual (ID 657863) entered the park on Friday at 16:11:36 and left it on Saturday at 08:10:03. The individual stayed over night. On Friday the individual just walked without taking a ride or visiting a show.

The individual walked directly to the Alvarez Beer Gradens (33), entered it at 17:04:28 and stayed there until 21:50:50. It is very likely that after drinking beer for over 4 hours, the individual was more or less drunk.

After leaving Alvarez Beer Garden at 21:50:50 and checking in to Sholtz Express ride (20) at 21:53:11, the individual did not move until 08:00:27 the next day (Saturday). It is plausible that the individual was drunk and found a place in the ride area to sleep.

The individual moved again on Saturday morning at 08:00:27, probably awaken from the noise of the park opening at 08:00:00. The individual then quickly exited the park at 08:10:03 on Saturday.