This document summarizes a traffic safety analysis project that aimed to identify risk factors in fatal collisions in Toronto. The analysis focused on extensive traffic collision data to gain insights. Key findings included that certain streets, vulnerable road users like pedestrians, and factors like speeding and aggressive driving were prominent in fatal incidents. The analysis also examined temporal patterns and characteristics of involved individuals. Machine learning models were able to accurately predict speeding incidents based on variables like traffic control type and road class with over 77% accuracy. The analysis identified opportunities to refine models and collaborate with stakeholders to use insights for preventing collisions.
Analyzed data set which contained list of possible factors that can explain the mortality rates. Ran regression models with various permutations and combinations of variables to arrive at a list of variables that can explain variances in mortality rates.
This is the presentation I made to our City\'s Transportation and Safety Commission, the Public Safety Commission, and various community organizations in favor of a red light camera system for out City.
Predictive analysis of traffic violationsDarshak Mehta
The paper produced results based on traffic violation data that was updated daily in Montgomery County in the USA. Using the data set, we analyzed the effect of a traffic violation on traffic accidents by using various big data analysis techniques. In particular, three modeling hypotheses have been developed based on initial data understanding and the performed 5 visualizations. The required data preprocessing has been performed to address these hypotheses using 3 models with different algorithms.
[Amended upload]
Presented by PhD student Segun Aluko at UTSG2014.
www.its.leeds.ac.uk/people/s.aluko
www.utsg.net/web/uploads/UTSG%202014%20Newcastle%20Programme.pdf
Analyzed data set which contained list of possible factors that can explain the mortality rates. Ran regression models with various permutations and combinations of variables to arrive at a list of variables that can explain variances in mortality rates.
This is the presentation I made to our City\'s Transportation and Safety Commission, the Public Safety Commission, and various community organizations in favor of a red light camera system for out City.
Predictive analysis of traffic violationsDarshak Mehta
The paper produced results based on traffic violation data that was updated daily in Montgomery County in the USA. Using the data set, we analyzed the effect of a traffic violation on traffic accidents by using various big data analysis techniques. In particular, three modeling hypotheses have been developed based on initial data understanding and the performed 5 visualizations. The required data preprocessing has been performed to address these hypotheses using 3 models with different algorithms.
[Amended upload]
Presented by PhD student Segun Aluko at UTSG2014.
www.its.leeds.ac.uk/people/s.aluko
www.utsg.net/web/uploads/UTSG%202014%20Newcastle%20Programme.pdf
Accident Analysis At The Black Spot: A Case Studyiosrjce
Humans prefer comfort in every form. The same reason has prompted him to lay the roads and invent
motor vehicles. This is the era we are seeing very huge number of vehicles on the roads. But to his dismay, with this
comfortless, there came the problem of accidents due to increase in traffic volume. The increased human misery and
serious economic loss caused by road accidents demand the attention of the society and call for the solution of this
problem. The causes for accidents are many. It may be either due to the fault of the driver or vehicular defect, tough
weather condition or due to improper road design and many more. Precisely, if accidents occur frequently at a
particular road stretch then, the location is coined as Black Spot. In the present work, an attempt has been made to
evaluate the effects of highway geometrics and speed parameters in increased accident rates at the black spot. The
black spot of our interest is Busthenahalli bypass (spot-A) on National Highway-48 between Bangalore and
Mangalore, Karnataka, India. The mixed traffic condition prevailing on the road and the inadequate geometric
conditions on field create the problem of increased accident rates. The regression equation for the condition
prevailing has been found for the location under consideration which represents the variation of accident rate with
age of the driver, rise and fall, pavement width, Stopping Sight Distance for operating speed and regulating speed and
Annual Daily Traffic(ADT).
Presentation by Jan-Dirk Schmöcker of of Kyoto University. Delivered at the Institute for Transport Studies (ITS), 27 November 2014.
http://trans.kuciv.kyoto-u.ac.jp/its/Schmoecker.html
Pedestrian Accident Scenario of Dhaka City and Development of a Prediction ModelRafidTahmid1
Conference: International Conference on Recent Innovation in Civil Engineering for Sustainable Development (IICSD).
Year: 2015.
Place: Department of Civil Engineering, DUET - Gazipur, Bangladesh.
Type: Conference Paper.
Paper ID: TE-049.
Authors: H. M. Ahsan (1); M. H. Rahman (2).
(1) Professor, Department of Civil Engineering, BUET.
Email: hmahsan@ce.buet.ac.bd
(2) Undergraduate Student, Department of Civil Engineering, BUET.
Email: md.hasibur.rahman.buet.ce@gmail.com
Study On Traffic Conlict At Unsignalized Intersection In Malaysia IOSR Journals
The research conducted is traffic conflict at unsignalized intersections . The purpose of this research
is to study accident data used as an identification of hazardous location leads to less accurate countermeasures.
It is because accidents are not always reported especially accident involving damage only and this situation can
reduce good comparative analysis. To overcome these lacks of accident data, many ways of employing nonaccident
data have been suggested. One of the ways using non-accident data is traffic conflicts, which is defined
as critical incidents not necessarily involving collisions. The traffic conflict technique was originally set up to
provide more reliable data and information of traffic problems at intersections which actually would replace the
unclear and incomplete recorded data accident. The conflict study was done at the selected unsignalized
intersection where types of traffic conflict can be identified and classified. Various road users involved in the
conflict at the unsignalized intersection were also observed. Then conflicts data captured were analyzed using
the computer program to observe for any conflicts at the intersections. The linear regression graph was used to
show the relationship between conflict and accident data where two different equations were derived from the
graph. This equation may be used to make a prediction for the relationship that might exist between those two
variables at another location.
Spatial Risk Diffusion: Predicting risk linked to human behaviorAccenture Insurance
To compete with digital disrupters, carriers must use new data sources, analytics methods to predict how customer behavior will affect risk across society.
An Exploration of Prosocial Aspects of Communication Cues between Automated V...Shadan Sadeghian
Road traffic is a social situation where participants heavily interact
with each other. Consequently, communication plays an important
role. Typically, the communication between pedestrians and drivers
is nonverbal and consists of a combination of gestures, eye contact,
and body movement. However, when vehicles become automated,
this will change. Previous work has investigated the design and
effectiveness of additional communication cues between pedestrians
and automated vehicles. It remains unclear, though, how this
impacts the perceptions of the quality of communication and impressions
of mindfulness and prosociality. In this paper, we report
an online experiment, where we evaluated the perception of communication
cues in the form of on-road light projections, across
different traffic scenarios and roles. Our results indicate that, while
the cues can improve communication, their effect is dependent on
traffic scenarios. These results provide preliminary implications
for the design of communication cues that consider their prosocial
aspects.
Portland Tames Speed for Safety, a Case Study for Vision Zero Citiesvisionzeronetwork
Portland, Oregon has a comprehensive approach to managing speed for safety. Their work provides a model for other Vision Zero cities to ensure action on this core value of Vision Zero.
Accident Analysis At The Black Spot: A Case Studyiosrjce
Humans prefer comfort in every form. The same reason has prompted him to lay the roads and invent
motor vehicles. This is the era we are seeing very huge number of vehicles on the roads. But to his dismay, with this
comfortless, there came the problem of accidents due to increase in traffic volume. The increased human misery and
serious economic loss caused by road accidents demand the attention of the society and call for the solution of this
problem. The causes for accidents are many. It may be either due to the fault of the driver or vehicular defect, tough
weather condition or due to improper road design and many more. Precisely, if accidents occur frequently at a
particular road stretch then, the location is coined as Black Spot. In the present work, an attempt has been made to
evaluate the effects of highway geometrics and speed parameters in increased accident rates at the black spot. The
black spot of our interest is Busthenahalli bypass (spot-A) on National Highway-48 between Bangalore and
Mangalore, Karnataka, India. The mixed traffic condition prevailing on the road and the inadequate geometric
conditions on field create the problem of increased accident rates. The regression equation for the condition
prevailing has been found for the location under consideration which represents the variation of accident rate with
age of the driver, rise and fall, pavement width, Stopping Sight Distance for operating speed and regulating speed and
Annual Daily Traffic(ADT).
Presentation by Jan-Dirk Schmöcker of of Kyoto University. Delivered at the Institute for Transport Studies (ITS), 27 November 2014.
http://trans.kuciv.kyoto-u.ac.jp/its/Schmoecker.html
Pedestrian Accident Scenario of Dhaka City and Development of a Prediction ModelRafidTahmid1
Conference: International Conference on Recent Innovation in Civil Engineering for Sustainable Development (IICSD).
Year: 2015.
Place: Department of Civil Engineering, DUET - Gazipur, Bangladesh.
Type: Conference Paper.
Paper ID: TE-049.
Authors: H. M. Ahsan (1); M. H. Rahman (2).
(1) Professor, Department of Civil Engineering, BUET.
Email: hmahsan@ce.buet.ac.bd
(2) Undergraduate Student, Department of Civil Engineering, BUET.
Email: md.hasibur.rahman.buet.ce@gmail.com
Study On Traffic Conlict At Unsignalized Intersection In Malaysia IOSR Journals
The research conducted is traffic conflict at unsignalized intersections . The purpose of this research
is to study accident data used as an identification of hazardous location leads to less accurate countermeasures.
It is because accidents are not always reported especially accident involving damage only and this situation can
reduce good comparative analysis. To overcome these lacks of accident data, many ways of employing nonaccident
data have been suggested. One of the ways using non-accident data is traffic conflicts, which is defined
as critical incidents not necessarily involving collisions. The traffic conflict technique was originally set up to
provide more reliable data and information of traffic problems at intersections which actually would replace the
unclear and incomplete recorded data accident. The conflict study was done at the selected unsignalized
intersection where types of traffic conflict can be identified and classified. Various road users involved in the
conflict at the unsignalized intersection were also observed. Then conflicts data captured were analyzed using
the computer program to observe for any conflicts at the intersections. The linear regression graph was used to
show the relationship between conflict and accident data where two different equations were derived from the
graph. This equation may be used to make a prediction for the relationship that might exist between those two
variables at another location.
Spatial Risk Diffusion: Predicting risk linked to human behaviorAccenture Insurance
To compete with digital disrupters, carriers must use new data sources, analytics methods to predict how customer behavior will affect risk across society.
An Exploration of Prosocial Aspects of Communication Cues between Automated V...Shadan Sadeghian
Road traffic is a social situation where participants heavily interact
with each other. Consequently, communication plays an important
role. Typically, the communication between pedestrians and drivers
is nonverbal and consists of a combination of gestures, eye contact,
and body movement. However, when vehicles become automated,
this will change. Previous work has investigated the design and
effectiveness of additional communication cues between pedestrians
and automated vehicles. It remains unclear, though, how this
impacts the perceptions of the quality of communication and impressions
of mindfulness and prosociality. In this paper, we report
an online experiment, where we evaluated the perception of communication
cues in the form of on-road light projections, across
different traffic scenarios and roles. Our results indicate that, while
the cues can improve communication, their effect is dependent on
traffic scenarios. These results provide preliminary implications
for the design of communication cues that consider their prosocial
aspects.
Portland Tames Speed for Safety, a Case Study for Vision Zero Citiesvisionzeronetwork
Portland, Oregon has a comprehensive approach to managing speed for safety. Their work provides a model for other Vision Zero cities to ensure action on this core value of Vision Zero.
1. Toronto Traffic Safety Analysis:
Unveiling Risk Factors in Fatal Collisions
Professor: Richard Boire
CAPSTONE DATA PROJECT
Vishal Sang 101458132
Yiran Hu 101442783
3. Background
Overview of the Company:
• TPS mission: "To Serve and Protect."
• Role in maintaining public safety and upholding
the law in Toronto.
• Partnership with the community for safety, law
enforcement, and emergency services.
• Commitment to transparency and continuous
improvement.
3
4. Business Problem
4
• Data Overload
• Public Safety
• Community Engagement
• Resource Allocation
Key Expectations of the Client:
• Insightful Analysis
• Predictive Analytics
• Strategic Recommendations
• Community-Oriented Solutions
Key Challenges of the Client:
5. Identification of the Problem
5
Need to effectively analyze and
interpret extensive traffic collision
data for enhanced public safety.
Specific Challenges:
• Understanding Collision Patterns
• Addressing Road Safety Issues
• Data-Driven Decision Making
Primary Problem:
10. Frequency Distribution Reports
• Significant occurrences on specific
streets like "LAWRENCE AVE E,"
"FINCH AVE W," and "EGLINTON AVE E"
highlight high-risk locations.
• Pedestrians (517 incidents) are notably
vulnerable road users in fatal collisions.
• Contributing factors include
speeding (187 incidents),
aggressive driving (427
incidents), and alcohol
involvement (44 incidents).
• Temporal patterns across 846
unique dates and 629 unique
times emphasize the diverse
circumstances of fatal
collisions.
14. Selected Variables
The Target Variable:'SPEEDING', because collisions involving
speeding are more likely to be severe.
Other Variable:
TIME, INVAGE, ROAD_CLASS, TRAFFCTL, RDSFCOND,
LIGHT, ALCOHOL
14
16. The Exploratory Data Analysis
16
Traffic Control
Certain types of traffic control are more commonly
associated with collisions.
1.0 refers to No traffic Control and 5.0 refers to
Traffic Signal.
This shows that there were most no. of collisions
in the places where traffic wasn’t being controlled.
17. The Exploratory Data Analysis
17
INVAGE
• The age distribution shows a wide range,
indicating that individuals of various ages are
involved in collisions.
• There appears to be a higher frequency of
younger individuals involved in speeding and
collisions.
18. The Exploratory Data Analysis
18
Road Class
• The distribution across different road classes shows a varied number of
collisions associated with each class. This variation can be indicative of
the traffic volume, road conditions, or other factors specific to each
road class that may influence the occurrence of speeding-related
accidents.
• 1.0 refers to Expressway Ramp
• 6.0 refers to Major Arterial
• Major Arterial road class have a noticeably higher count of
collisions, suggesting that these classes might be more prone
to accidents or have higher traffic flow.
19. The Exploratory Data Analysis
19
LIGHT
The distribution across different light conditions
shows variability in collision occurrences.
1.0 refers to Dark light Condition
4.0 refers to Day Light Conditions
This Shows that most no. of Collisions
happen in Day light and Dark light
Conditions.
20. The Exploratory Data Analysis
20
Alcohol
• The majority of collisions did not involve alcohol,
as indicated by the higher count for '0' (No
Alcohol Involvement).
• However, there is still a notable number of
incidents where alcohol was involved,
highlighting its significance in traffic accidents.
21. ROC Curve
21
ROC Curve Overview:
• Shows how well the model distinguishes
instances with and without speeding.
AUC Score Significance:
• Quantifies overall model performance;
higher values indicate better discrimination.
22. Decile/Gains Chart
22
• Reveals how accurately the model ranks instances
by predicted probabilities.
• Divides the dataset into deciles, showing
cumulative true positive percentages for each.
• Visualizes alignment between model predictions
and actual instances of speeding.
• Steep increases indicate the model effectively
identifies a higher percentage of positive instances
within subsets.
23. Key Findings
23
Identified influential features: TRAFFCTL and ‘ROADCLASS' play crucial roles
in predicting speeding and Collision incidents.
Model accuracy: Achieved an overall accuracy of approximately 77.54% on
the test set.
ROC Curve and AUC Score: The ROC curve and AUC score (around 0.80)
demonstrate good discriminative power in distinguishing speeding incidents.
Decile/Gains Chart: Indicates the model's effective ranking of instances, with
a cumulative increase in true positive rate across deciles.
24. Conclusion
• Identified influential features: ‘TRAFFCTL’ and
‘ROADCLASS.'
• Suggested model refinement for improved accuracy.
• Emphasized ongoing validation, ethical deployment
considerations, and stakeholder collaboration for an
impactful solution in predicting and preventing speeding
and Collision incidents.
24