Improving Road Safety by Profiling Different Accident Type Te Team - - PowerPoint PPT Presentation

Improving Road Safety

by Profiling Different Accident Type

Te Team am 7 : 7 : An Ange gela, la, Ayl ylada, ada, Ce Celi lia, a, Dobby

• bby,

, Ma Mahs hsa

Profile certain accident types by identifying the factors that might be the cause of that accident. Accident types we are focusing on: FrontHit, SideHit, BackHit, PedCrossing, and Scratch

2

DATA MINING GOAL

To assist Transportation Department of Taipei City Government(Client) to improve the road safety in Taipei with more efficient way by learning the conditions that distinguished different type of accidents. To help the government decrease in number of certain accident types while wisely use the budgets. To have a safer road usage for Taipei citizens.

3

BUSINESS GOAL

Data set: Accident records in Taipei from Data Taipei

4

Time variables Environmental variables

DATA DESCRIPTION

5

2013 2013 - 39,577 39,577 rows 30 30 columns →17,991 17,991 rows 11 11 columns 2012 2012 - 39,062 39,062 rows 30 30 columns →17,843 17,843 rows 11 11 columns 2011 2011 - 41,082 41,082 rows 30 30 columns →18,963 18,963 rows 11 11 columns We combined the records of same case ID

• ne row: one record => one row: one accident case

We also deleted records that has accident on highway. (not our goal) To reduce dimensionalities, we have

• deleted some columns that are not significant in profiling accident types
• binned the categories that are similar

DATA DESCRIPTION (Cont.)

We found that our data is

imbalanced

To deal with this, we need to

• versample
• ur data.

6

DATA DESCRIPTION (Cont.)

Di Disc scri rimi minant Anal nant Analys ysis is (R (R) Decis ision ion Tr Tree e (R (R) Decis ision ion Tr Tree e (X (XLm Lmin iner) r) Ran andom dom Fo Fores rest t (R (R) Decis ision ion Tr Tree e (R (Rapi apidMi dMiner) ner)

7

METHODS

Method Chosen-Decision Tree (RapidMiner)

8

Data Preparation (and Oversampling)

Sub-process

Main process

Method Chosen-Decision Tree (RapidMiner)

Under most of the circumstances, all kinds

• f accidents could

happen.

10

Out utco come me Fa Factors ctors Fr Front

• ntHit

Hit 1.

• 1. At

At Cir ircl cle/ e/Pl Plaza, aza, Spee eed d li limi mit <= <= 65 65, , Fa Fast/ st/Slow low/Normal Normal La Lane ne Ba Back ckHit Hit 1.

• 1. Su

Sunny nny, , Sp Speed eed li limi mit > 65 > 65, , No Non-For Fork, k, No Non-Cross ross Road ad

• 2. Other Road Type, Speed limit <65, Non-Traffic Signal
• 3. Other Road Type, Speed limit <65, Motorcycle Lane
• 4. At Circle/Plaza, Motorcycle Lane

Sid ideH eHit it 1.

• 1. Spee

eed d li limi mit 65 65~7 ~75, 5, wh when en p pav avement ement is is We Wet, t, at at Cross ss Road ad Pe PedC dCrossin

• ssing
• 1. At Zebra Crossing

2.

• 2. At

At Cir ircl cle/ e/Pl Plaza, aza, Sid idew ewal alk, k, Ni Nigh ght Ti Time me, , Spee eed d li limi mit <= <= 75 75 Scr cratc atch

• 1. Speed limit >85
• 2. Speed limit <=85, Rainy, Weekend

Fa Factors ctors 1 Ac Acci cident dent Lo Location cation 2 Spee eed d Li Limi mit 3 Road ad Ty Type 4 Sig igna nal 5 We Weathe ather 6 We Weekday/ ekday/ We Weekend ekend

Results

However, there are circumstances where only certain accident type happens.

1.

• 1. Cr

Cross Vali ss Validatio dation n (w (wit ith 10 Va h 10 Vali lidati dations

• ns)

Ov Overal erall Ac l Accurac uracy: y: 22 22.7 .79% 9% Cl Clas ass o s of f In Inte tere rest st Accurac uracy: y: 27 27.3 .34% 4% 1.

• 1. Pur

Purit ity o y of f the the end end no nodes des We did identify some accident types that happens under certain circumstances

11

Those cannot be distinguished very well are predicted as SideHit Therefore lower the accuracy

Performance Evaluation

• 1. Build a br

brid idge ge or und under ergr groun

• und

d wa walk lkwa way for pedestrian at the circles/ plaza to increase their safety.

• 2. Install more signals at the circles/ plaza

to avoid front hit.

• 3. Install anti-slip textures and decrease

the speed limit before the cross roads to decrease the number of side hit and scratch.

• 4. Dynamic speed limit to avoid backhit.

(low speed limit in sunny days ?)

12

RECOMMENDATION

13