This form is a web page which was created in MS WORD and therefore can be easily edited that way

Entry Name: NICTA-Zhou-MC1

VAST Challenge 2015
Mini-Challenge 1

Team Members:

Jianlong Zhou, National ICT Australia (NICTA), Sydney, Australia, jianlong.zhou@nicta.com.au PRIMARY

Jinjun Sun, Red Planet of Qantas Loyalty, Sydney, Australia, jsunster@gmail.com PRIMARY

Student Team:

Did you use data from both mini-challenges?

Analytic Tools Used:

Python

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

30 hours.

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

YES

Video Download

Video:

http://rp-www.cs.usyd.edu.au/~zhou/images/nicta-zhou-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.

Safety-Oriented Visual Analytics of People Movement

We characterized the attendance at the park based on the following scenario:

There are five categories of check-in sites all together except the entry & exit gates and unlabeled check in sites: thrill rides (TR), kiddie rides (KR), rides for everyone (RE), shows & entertainment (SE), and information & assistance (IA). On each site category, people’s duration time on that site is compared with the average duration time of people on that site. If a person’s duration time is equal or longer than the average duration time on a site, it means that this person is very interested in this site category. Otherwise, this person is not interested in this site category and left the site after a short view. We assume that a valid visit for a site should longer than 5 minutes and filtered out check-ins which last less than 5 minutes in order to remove noise.

Safety is the core of the management of the park. And the kids are the people who are the easiest one to get affected by any accidents. We assume that people who visited Kiddie Rides (KR) had different safety requirements from people who did not visit KR. Therefore, kids are the core for the setup of management strategy in this analysis. Based on this viewpoint, people are firstly categorized into groups who visited KR and who did not visit KR. For four categories of check-in sites except IA, we define their safeties as follows:

· Level 1: KR is the safest site;

· Level 2: RE is the safer site;

· Level 3: TR is not safe as KR or RE;

· Special care: SE.

IA is not considered in the safety oriented grouping because it is not related to the safety.

Based on this scenario, attendance of people on Friday is grouped into nine groups as in Table 1. In this table, the attendance number in each group is the number of people who visited the indicated sites and whose duration time on that site was longer than the average duration time on that site in order to show that the person was really interested in that site than average.

Table 1. Nine groups based on safety and KR visiting on Friday (1: people visited this site, 0: people did not visit this site).

Group #	SE	TR	RE	KR	Attendance
1	1	1	1	1	1309
2	NO KR				958
3	0	1	1	1	598
4	1	1	0	1	270
5	1	0	1	1	180
6	0	1	0	1	93
7	0	0	1	1	75
8	1	0	0	1	45
9	0	0	0	1	29

The details of 9 groups are as follows:

Group 1: Figure 1 shows the average density of people and duration time of this group on sites on Friday. Both color and dot size are used to encode density or duration time, where color is used to encode different quantile of density or duration time (e.g. black means that the density or duration time is longer than 90% of other sites. It is same for other figures of other groups.), and the larger the size of the dot, the higher density or longer time people spent on the site. a) The size of this group is 1309. b) This group visited all four safety related site categories of SE, TR, RE, and KR. c) This is the largest group. d) From this figure, we can see that this group of people spent the most time on SE at Grinosaurus Stage (site 63), and more people of this group spent short time on thrills such as Atmosfear (site 8). e) We infer that this group liked to try every kind of sites, but they mostly liked shows and entertainment, and they were also afraid of playing some extreme thrills such as Atmosfear. f) Based on this group information, the park should improve the access to sites of TR such as Wrightiraptor Mountain. The park should also improve the environment of SE such as Grinosaurus Stage in order to improve the safety.

Figure 1. Average people density and duration time of this group on sites on Friday for group 1.

Group 2: Figure 2 shows the average density of people and duration time of this group on sites on Friday. a) The size of this group is 958. b) This group liked to go to sites of TR such as Wrightiraptor Mountain. c) This is the second largest group. This group did not visit any KR sites. d) From this figure, we can see that this group spent the most time on SE at Grinosaurus Stage (site 63), and spent very short time on thrills such as Atmosfear (site 8). e) We infer that this group did not include kids and was not the family group. f) Based on this group information, the park should improve the access to TR sites such as Wrightiraptor Mountain and access to SE sites such as Grinosaurus Stage and also increase the size of those sites in order to improve the safety.

Figure 2. Average people density and duration time of this group on sites on Friday for group 2.

Group 3: Figure 3 shows the average people density and duration time of this group on sites on Friday. a) The size of this group is 598. b) This group liked to go to TR sites such as TerrorSaur. c) This is the third largest group. This group did not visit any KR sites. d) From this figure, we can see that this group spent the most time on TerrorSaur (site 4) with a large number of people. e) We infer that this group did like TR site of TerrorSaur very much. f) Based on this group information, the park should improve the access to TerrorSaur in order to improve the safety because most of people spent the most time on that site.

Figure 3. Average people density and duration time of this group on sites on Friday for group 3.

Group 4: Figure 4 shows the average people density and duration time of this group on sites on Friday. a) The size of this group is 270. b) This group liked to go to TR sites such as TerrorSaur and SE sites such as Grinosaurus Stage. c) This is the forth largest group. This group did not like RE sites too much. d) From this figure, we can see that this group spent long time with a big number of people on sites of SabreTooth Threatre (site 64), Grinosaurus Stage (site 63) and TerrorSaur. e) We infer that this group did like shows and entertainment as well as thrill rides very much. f) Based on this group information, the park should improve the access to SabreTooth Threatre (site 64), Grinosaurus Stage (site 63) and TerrorSaur in order to improve the safety because a large number of people spent long time on that site.

Figure 4. Average people density and duration time of this group on sites on Friday for group 4.

Group 5: Figure 5 shows the average people density and duration time of this group on sites on Friday. a) The size of this group is 180. b) This group liked to go to SE sites such as SabreTooth Threatre (site 64). c) This is the fifth largest group. This group did not like TR sites too much. d) From this figure, we can see that this group spent long time with a big number of people on sites of SabreTooth Threatre (site 64) and Grinosaurus Stage (site 63). e) We infer that this group did like shows and entertainment. f) Based on this group information, the park should improve the access to SabreTooth Threatre (site 64) and Grinosaurus Stage (site 63) in order to improve the safety.

Figure 5. Average people density and duration time of this group on sites on Friday for group 5.

Group 6: Figure 6 shows the average people density and duration time of this group on sites on Friday. a) The size of this group is 93. b) This group liked to go to TR sites such as TerrorSaur (site 4). c) This is the sixth largest group. This group did not like SE sites and RE sites too much. d) From this figure, we can see that despite large number of people visiting TR sites of Wrightiraptor Mountain, Galactosaurus Rage, and Auvilotops Express, they spent a very short time on those sites. e) We infer that this group did like SE sites and RE sites. This group was also afraid of some TR sites, such as Wrightiraptor Mountain. f) Based on this group information, the park should improve the access to TerrorSaur in order to improve the safety.

Figure 6. Average people density and duration time of this group on sites on Friday for group 6.

Group 7: Figure 7 shows the average people density and duration time of this group on sites on Friday. a) The size of this group is 75. b) This group liked to go to RE sites such as Maiasaur Madness (site 25). c) This group did not like SE sites too much. d) From this figure, we can also see that this group did not like TR sites too much. e) We infer that this group did not like to have adventure activities, they also did not like show and entertainment. f) Based on this group information, the park should improve the access to RE sites such as Maiasaur Madness (site 25) in order to improve the safety.

Figure 7. Average people density and duration time of this group on sites on Friday for group 7.

Group 8: Figure 8 shows the average people density and duration time of this group on sites on Friday. a) The size of this group is 45. b) This group liked to go to SE sites such as SabreTooth Threatre (site 64) which has the high people density and large duration time. c) This group did not like TR sites too much. d) From this figure, we can also see that this group did not like RE sites too much. e) We infer that this group only liked show and entertainment. f) Based on this group information, the park should improve the access to SE sites such as SabreTooth Threatre (site 64) in order to improve the safety.

Figure 8. Average people density and duration time of this group on sites on Friday for group 8.

Group 9: Figure 9 shows the average people density and duration time of this group on sites on Friday. a) The size of this group is 29. b) This group only liked to go to KR sites. c) This group did not like SE, TR, and RE sites too much. d) From this figure, we can also see that this group spent the longest time beside the wetland maybe for having a rest. e) We infer that this group had very young kids and was not appropriate for other activities. f) Based on this group information, the park should improve the access to KR sites in order to improve the safety and attract kids.

Figure 9. Average people density and duration time of this group on sites on Friday for group 9.

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 are notable differences in the patterns of activity in the park across the three days. Figure 10 shows the comparison of people count on different site categories across the three days. As we can see from this figure, there were more people visiting different sites on Saturday than on the other two days. More interestingly, the most people entered the park on Sunday, while the least people entered the park on Friday.

Figure 10. Comparison of people count on different site categories across the three days.

Figure 11 shows the comparison of average duration time on different site categories across the three days. As we can see from this figure, people stayed the longest time on SE sites on Sunday than on other two days. People spent more time on TR sites both on Saturday and Sunday than on Friday. However, people spent similar time on sites of IA, RE, KR, and outdoor rest across three days. This is very interesting.

Figure 11. Comparison of average duration time on different site categories across the three days.

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.

Figure 12. The travel route of some person with different id in the park.

Some anomaly examples are:

1) Some people (e.g. a person with Id = 1412235) entered into the park, but did not visit any sites, walked through the park and then exited as shown in Figure 12. These person maybe were relevant to some kind of crime because they have no interest in any activities.