Speed-related traffic accident analysis using GIS-based DBSCAN and NNH clustering
This is a modal window.
The media could not be loaded, either because the server or network failed or because the format is not supported.
Formal Metadata
Title |
| |
Title of Series | ||
Number of Parts | 351 | |
Author | ||
Contributors | ||
License | CC Attribution 3.0 Unported: You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor. | |
Identifiers | 10.5446/68917 (DOI) | |
Publisher | ||
Release Date | ||
Language | ||
Production Year | 2022 |
Content Metadata
Subject Area | ||
Genre | ||
Abstract |
| |
Keywords |
FOSS4G Firenze 2022325 / 351
1
7
13
22
25
31
33
36
39
41
43
44
46
52
53
55
58
59
60
76
80
93
98
104
108
127
128
133
135
141
142
143
150
151
168
173
176
178
190
196
200
201
202
204
211
219
225
226
236
242
251
258
263
270
284
285
292
00:00
Student's t-testGoodness of fitCivil engineeringAuthorizationParabolaDegree (graph theory)Mathematical analysisObservational studyMIDIPort scannerComputer animation
00:30
Object (grammar)FrequencyObject (grammar)Type theoryPerturbation theoryMobile WebCondition numberFrequencyCollisionMereologyComputer animation
01:10
MetreComputer fontGame controllerObservational studyProcess (computing)Bit rateFrequencyPerformance appraisalPoint (geometry)Visualization (computer graphics)MetreComputer programmingShared memoryMultiplication signParameter (computer programming)Gene clusterEllipsoidConvex setLogicMathematical analysisDifferent (Kate Ryan album)ResultantAdditionDirectory serviceRing (mathematics)Term (mathematics)DialectAreaGeometryShape (magazine)Computer animation
02:24
Common Information Model (computing)Gene clusterObservational studyMereologyType theoryPoint (geometry)Frequency1 (number)Covering spaceNumberData miningAreaFigurate numberScaling (geometry)DialectDeterminantMeasurementMultiplication signShape (magazine)Local ringComputer animation
03:50
Computer animation
Transcript: English(auto-generated)
00:00
Good afternoon everyone. I'd like to quickly introduce myself. I'm Valento Cevolu and I'm a graduate student at the Middle East Technical University in Metu and a nursing degree as a GIS specialist in parabolic. Another author is Tobamim Cevolu-Michael who is a postdoctoral researcher at Metu and Yezhi Deshaman is a professor in the civil engineering department at Metu. Today I'm going to introduce to you our study which is speed related
00:25
traffic accident analysis using gis-based dvscan and nnh classroom. I would like to start with the region and data. Middle southern part of Turkey including Mersin, Adana and other five cities was selected as a scene. The traffic accident data between the years 2014 and 2021
00:47
were geographically different. The types rollover run-on-throat crashing into a stationary vehicle and collision with the object are classified as speed related accidents. Speed related accident data were divided into two year periods and the last period which is 2020 and 2021
01:05
were considered as the years with mobility restrictions due to pandemic conditions. After organizing the data hot spots were identified using nnh and dvscan methods as mentioned. For nnh classrooms crime style 3 program was used and qjs was used in dvscan
01:23
analysis visualization and evaluation processes. This is the logic behind nnh tends to create convex or ellipsoidal clusters whereas dvscan clusters are more randomly shaped. Obtained results are evaluated in terms of years the differences in the cluster ring of traffic
01:45
accidents between two selected methods are revealed by the analysis results. These evaluations were also examined using road geometry and different cluster areas were examined more locally. When it is considered that the general directory of highways in Turkey uses
02:01
nnh methods with five accidents and 100 meters parameters in one year and taken to regions overlapping in last three years into consideration in addition to their rate quality control methods 100 meters and 10 point parameters were used in nnh and dvscan for
02:21
two year periods in this study. Due to time restriction i'd like to briefly share two cluster examples stated by both dvscan and nnh methods. Here in the figures convex shapes represent nnh clusters and they are labeled with letters and dvscan clusters are labeled with numbers and represented with colored points. Cluster 3b belongs to 2016 and 2017 period
02:43
and cluster 1 is detected in 2020 and 2021 period. It is seen that the accidents occurring in the last two years are farther to the road than the ones in the other period. This may imply that the country measures were inadequate to prevent speed related accidents and the type of
03:03
the accidents are more likely to be run off road in last years. In the last example from adana and marcin clusters were detected in last two year periods especially in adana on the left hand side accidents were clustered as you can see same part of the rotary intersection
03:20
and also in marcin in the other figure the area of the cluster decreases as the time passes although both clusters including same number of points. This study in conclusion can constitute a base for studies of the same type and also can help the determination
03:41
of accident hotspots on local and regional scale and finally can guide in determining repeated clustered regions. And thanks for your attention and if you have any questions i appreciate the answer