scholarly journals Predicting Critical Bicycle-Vehicle Conflicts at Signalized Intersections

2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
Alireza Darzian Rostami ◽  
Anagha Katthe ◽  
Aryan Sohrabi ◽  
Arash Jahangiri
Keyword(s):  
Prediction Models ◽  
Model Performance ◽  
Safety Evaluation ◽  
Signalized Intersections ◽  
Video Data ◽  
Sustainable Transportation ◽  
Support Vector ◽  
Monitoring Period ◽  
Crash Data ◽  
Intersection Safety

Continuous development of urban infrastructure with a focus on sustainable transportation has led to a proliferation of vulnerable road users (VRUs), such as bicyclists and pedestrians, at intersections. Intersection safety evaluation has primarily relied on historical crash data. However, due to several limitations, including rarity, unpredictability, and irregularity of crash occurrences, quantitative and qualitative analyses of crashes may not be accurate. To transcend these limitations, intersection safety can be proactively evaluated by quantifying near-crashes using alternative measures known as surrogate safety measures (SSMs). This study focuses on developing models to predict critical near-crashes between vehicles and bicycles at intersections based on SSMs and kinematic data. Video data from ten signalized intersections in the city of San Diego were employed to train logistic regression (LR), support vector machine (SVM), and random forest (RF) models. A variation of time-to-collision called T2 and postencroachment time (PET) were used to specify monitoring periods and to identify critical near-crashes, respectively. Four scenarios were created using two thresholds of 5 and 3 s for both PET and T2. In each scenario, five monitoring period lengths were examined. The RF model was superior compared to other models in all different scenarios and across different monitoring period lengths. The results also showed a small trade-off between model performance and monitoring period length, identifying models with monitoring period lengths of 10 and 20 frames performed slightly better than those with lower or higher lengths. Sequential backward and forward feature selection methods were also applied that enhanced model performance. The best RF model had recall values of 85% or higher across all scenarios. Also, RF prediction models performed better when considering just the rear-end near-crashes with recalls of above 90%.

scholarly journals Safety evaluation of signalized intersections with automated vehicles at various penetration levels based on conflict analysis of simulated traffic

2021 ◽  
Author(s):  
Maria Espinosa
Keyword(s):  
Prediction Models ◽  
Safety Evaluation ◽  
Driving Behavior ◽  
Signalized Intersections ◽  
Automated Vehicles ◽  
Crash Frequency ◽  
Left Turn ◽  
Intersection Safety ◽  
Potential Safety ◽  
Traffic Conflicts

Automated vehicles (AVs) are expected to offer great benefits by potentially reducing crashes. The safety at signalized intersections is influenced by several factors, one of them being the driving behavior. By introducing AVs on the roads, the unpredictability of this factor will potentially decrease and eventually, reduce crashes. By using microsimulation, it was possible to use simulated traffic conflicts as indicators of potential crashes, to analyze the potential safety of signalized intersections in the presence of automated vehicles. The objective was to compare crash frequency for signalized intersections at various AVs penetration levels (0%, 50% and 100%) by using prediction models that relate crashes to conflicts. Furthermore, the effect on crashes of introducing hypothetical left turn treatments was also evaluated. The results indicated that intersection safety may improve in the presence of AVs. However, the safety effects of treatments may be reduced compared to the effects with no AVs.

scholarly journals Safety evaluation of signalized intersections with automated vehicles at various penetration levels based on conflict analysis of simulated traffic

2021 ◽  
Author(s):  
Maria Espinosa
Keyword(s):  
Prediction Models ◽  
Safety Evaluation ◽  
Driving Behavior ◽  
Signalized Intersections ◽  
Automated Vehicles ◽  
Crash Frequency ◽  
Left Turn ◽  
Intersection Safety ◽  
Potential Safety ◽  
Traffic Conflicts

Automated vehicles (AVs) are expected to offer great benefits by potentially reducing crashes. The safety at signalized intersections is influenced by several factors, one of them being the driving behavior. By introducing AVs on the roads, the unpredictability of this factor will potentially decrease and eventually, reduce crashes. By using microsimulation, it was possible to use simulated traffic conflicts as indicators of potential crashes, to analyze the potential safety of signalized intersections in the presence of automated vehicles. The objective was to compare crash frequency for signalized intersections at various AVs penetration levels (0%, 50% and 100%) by using prediction models that relate crashes to conflicts. Furthermore, the effect on crashes of introducing hypothetical left turn treatments was also evaluated. The results indicated that intersection safety may improve in the presence of AVs. However, the safety effects of treatments may be reduced compared to the effects with no AVs.

Forecasting the risk at infractions: an ensemble comparison of machine learning approach

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Lei Li ◽  
Desheng Wu
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Short Term Memory ◽  
Model Performance ◽  
Large Data ◽  
Support Vector ◽  
Learning Approaches ◽  
Content Type ◽  
Day To Day Operations ◽  
Prediction Approach

PurposeThe infraction of securities regulations (ISRs) of listed firms in their day-to-day operations and management has become one of common problems. This paper proposed several machine learning approaches to forecast the risk at infractions of listed corporates to solve financial problems that are not effective and precise in supervision.Design/methodology/approachThe overall proposed research framework designed for forecasting the infractions (ISRs) include data collection and cleaning, feature engineering, data split, prediction approach application and model performance evaluation. We select Logistic Regression, Naïve Bayes, Random Forest, Support Vector Machines, Artificial Neural Network and Long Short-Term Memory Networks (LSTMs) as ISRs prediction models.FindingsThe research results show that prediction performance of proposed models with the prior infractions provides a significant improvement of the ISRs than those without prior, especially for large sample set. The results also indicate when judging whether a company has infractions, we should pay attention to novel artificial intelligence methods, previous infractions of the company, and large data sets.Originality/valueThe findings could be utilized to address the problems of identifying listed corporates' ISRs at hand to a certain degree. Overall, results elucidate the value of the prior infraction of securities regulations (ISRs). This shows the importance of including more data sources when constructing distress models and not only focus on building increasingly more complex models on the same data. This is also beneficial to the regulatory authorities.

scholarly journals Classification models using circulating neutrophil transcripts can detect unruptured intracranial aneurysm

2020 ◽  
Vol 18 (1) ◽  
Author(s):  
Kerry E. Poppenberg ◽  
Vincent M. Tutino ◽  
Lu Li ◽  
Muhammad Waqas ◽  
Armond June ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Prediction Models ◽  
Model Performance ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Learning Methods ◽  
Training Cohort ◽  
Network Analyses ◽  
Machine Learning Methods

Abstract Background Intracranial aneurysms (IAs) are dangerous because of their potential to rupture. We previously found significant RNA expression differences in circulating neutrophils between patients with and without unruptured IAs and trained machine learning models to predict presence of IA using 40 neutrophil transcriptomes. Here, we aim to develop a predictive model for unruptured IA using neutrophil transcriptomes from a larger population and more robust machine learning methods. Methods Neutrophil RNA extracted from the blood of 134 patients (55 with IA, 79 IA-free controls) was subjected to next-generation RNA sequencing. In a randomly-selected training cohort (n = 94), the Least Absolute Shrinkage and Selection Operator (LASSO) selected transcripts, from which we constructed prediction models via 4 well-established supervised machine-learning algorithms (K-Nearest Neighbors, Random Forest, and Support Vector Machines with Gaussian and cubic kernels). We tested the models in the remaining samples (n = 40) and assessed model performance by receiver-operating-characteristic (ROC) curves. Real-time quantitative polymerase chain reaction (RT-qPCR) of 9 IA-associated genes was used to verify gene expression in a subset of 49 neutrophil RNA samples. We also examined the potential influence of demographics and comorbidities on model prediction. Results Feature selection using LASSO in the training cohort identified 37 IA-associated transcripts. Models trained using these transcripts had a maximum accuracy of 90% in the testing cohort. The testing performance across all methods had an average area under ROC curve (AUC) = 0.97, an improvement over our previous models. The Random Forest model performed best across both training and testing cohorts. RT-qPCR confirmed expression differences in 7 of 9 genes tested. Gene ontology and IPA network analyses performed on the 37 model genes reflected dysregulated inflammation, cell signaling, and apoptosis processes. In our data, demographics and comorbidities did not affect model performance. Conclusions We improved upon our previous IA prediction models based on circulating neutrophil transcriptomes by increasing sample size and by implementing LASSO and more robust machine learning methods. Future studies are needed to validate these models in larger cohorts and further investigate effect of covariates.

scholarly journals Modeling and Application of Pedestrian Safety Conflict Index at Signalized Intersections

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Wei Cheng ◽  
Ning Zhang ◽  
Wei Li ◽  
Jianfeng Xi
Keyword(s):  
Safety Evaluation ◽  
Pedestrian Safety ◽  
Evaluation Study ◽  
Signalized Intersections ◽  
Safety Level ◽  
Intersection Safety ◽  
Road Users ◽  
Traffic Conflict ◽  
Vulnerable Road Users ◽  
The City

Traffic conflict between turning vehicles and pedestrians is the leading cause of pedestrian fatalities at signalized intersections. In order to provide a solution for evaluating intersection safety for vulnerable road users, this paper first determines the most important factors in analyzing pedestrian-vehicle conflict and puts forward a pedestrian safety conflict index (SCI) model to establish a quantitative standard for safety evaluation of two- or multiphase intersections. A safety level system is then designed based on SCI to help categorize and describe the safety condition of intersections applicable to the model. Finally, the SCI model is applied to the evaluation of two intersections in the city of Changchun, the result of which complies with expectation, indicating the model’s potential in providing an improved approach for pedestrian-vehicle conflict evaluation study.

Safety-Based Left-Turn Phasing Decisions for Signalized Intersections

2017 ◽  
Vol 2619 (1) ◽  
pp. 13-19 ◽  
Author(s):  
Kiriakos Amiridis ◽  
Nikiforos Stamatiadis ◽  
Adam Kirk
Keyword(s):  
Urban Areas ◽  
Primary Objective ◽  
Signalized Intersections ◽  
Safety Performance ◽  
Signal Timing ◽  
Left Turn ◽  
Crash Data ◽  
Intersection Safety ◽  
Traffic Volumes

The efficient and safe movement of traffic at signalized intersections is the primary objective of any signal-phasing and signal-timing plan. Accommodation of left turns is more critical because of the higher need for balancing operations and safety. The objective of this study was to develop models to estimate the safety effects of the use of left-turn phasing schemes. The models were based on data from 200 intersections in urban areas in Kentucky. For each intersection, approaches with a left-turn lane were isolated and considered with their opposing through approach to examine the left-turn–related crashes. This combination of movements was considered to be one of the most dangerous in intersection safety. Hourly traffic volumes and crash data were used in the modeling approach, along with the geometry of the intersection. The models allowed for the determination of the most effective type of left-turn signalization that was based on the specific characteristics of an intersection approach. The accompanying nomographs provide an improvement over existing methods and warrants and allow for a systematic and quick evaluation of the left-turn phase to be selected. The models used the most common variables that were already known during the design phase, and they could be used to determine whether a permitted or protected-only phase would suit the intersection when safety performance was considered.

scholarly journals Prediction of soil classes in a complex landscape in Southern Brazil

2019 ◽  
Vol 54 ◽  
Author(s):  
Jean Michel Moura-Bueno ◽  
Ricardo Simão Diniz Dalmolin ◽  
Taciara Zborowski Horst-Heinen ◽  
Luciano Campos Cancian ◽  
Ricardo Bergamo Schenato ◽  
...  
Keyword(s):  
Random Forest ◽  
Prediction Models ◽  
Expert Knowledge ◽  
Model Performance ◽  
Spatial Prediction ◽  
Support Vector ◽  
Kappa Index ◽  
Digital Elevation ◽  
Complex Landscape ◽  
Elevation Model

Abstract: The objective of this work was to evaluate the use of covariate selection by expert knowledge on the performance of soil class predictive models in a complex landscape, in order to identify the best predictive model for digital soil mapping in the Southern region of Brazil. A total of 164 points were sampled in the field using the conditioned Latin hypercube, considering the covariates elevation, slope, and aspect. From the digital elevation model, environmental covariates were extracted, composing three sets, made up of: 21 covariates, covariates after the exclusion of the multicollinear ones, and covariates chosen by expert knowledge. Prediction was performed with the following models: decision tree, random forest, multiple logistic regression, and support vector machine. The accuracy of the models was evaluated by the kappa index (K), general accuracy (GA), and class accuracy. The prediction models were sensitive to the disproportionate sampling of soil classes. The best predicted map achieved a GA of 71% and K of 0.59. The use of the covariate set chosen by expert knowledge improves model performance in predicting soil classes in a complex landscape, and random forest is the best model for the spatial prediction of soil classes.

scholarly journals Predicting Learning Outcomes with MOOC Clickstreams

2019 ◽  
Vol 9 (2) ◽  
pp. 104 ◽  
Author(s):  
Chen-Hsiang Yu ◽  
Jungpin Wu ◽  
An-Chi Liu
Keyword(s):  
Machine Learning ◽  
Learning Outcomes ◽  
Prediction Accuracy ◽  
Nearest Neighbor ◽  
Prediction Models ◽  
Video Data ◽  
Support Vector ◽  
Completion Rates ◽  
K Nearest Neighbor ◽  
Learning Behaviors

Massive Open Online Courses (MOOCs) have gradually become a dominant trend in education. Since 2014, the Ministry of Education in Taiwan has been promoting MOOC programs, with successful results. The ability of students to work at their own pace, however, is associated with low MOOC completion rates and has recently become a focus. The development of a mechanism to effectively improve course completion rates continues to be of great interest to both teachers and researchers. This study established a series of learning behaviors using the video clickstream records of students, through a MOOC platform, to identify seven types of cognitive participation models of learners. We subsequently built practical machine learning models by using K-nearest neighbor (KNN), support vector machines (SVM), and artificial neural network (ANN) algorithms to predict students’ learning outcomes via their learning behaviors. The ANN machine learning method had the highest prediction accuracy. Based on the prediction results, we saw a correlation between video viewing behavior and learning outcomes. This could allow teachers to help students needing extra support successfully pass the course. To further improve our method, we classified the course videos based on their content. There were three video categories: theoretical, experimental, and analytic. Different prediction models were built for each of these three video types and their combinations. We performed the accuracy verification; our experimental results showed that we could use only theoretical and experimental video data, instead of all three types of data, to generate prediction models without significant differences in prediction accuracy. In addition to data reduction in model generation, this could help teachers evaluate the effectiveness of course videos.

scholarly journals Safety evaluation of unconventional outside left-turn lane using automated traffic conflict techniques

2016 ◽  
Vol 43 (7) ◽  
pp. 631-642 ◽  
Author(s):  
Yanyong Guo ◽  
Tarek Sayed ◽  
Mohamed H. Zaki ◽  
Pan Liu
Keyword(s):  
Urban Areas ◽  
Safety Evaluation ◽  
Signalized Intersections ◽  
Video Data ◽  
Contributing Factors ◽  
Left Turn ◽  
Time To Collision ◽  
Traffic Conflicts ◽  
Traffic Conflict ◽  
The Right

The objective of this study is to evaluate the safety impacts of unconventional outside left-turn lane at signalized intersections. New designed unconventional outside left-turn lanes are increasingly used at signalized intersections in urban areas in China. The unconventional outside left-turn lane design allows an exclusive left-turn lane to be located to the right of through lanes to improve the efficiency and increase the capacity of left-turn movements. However, the design also raises some concerns regarding potential negative safety impacts. The evaluation is conducted using an automated video-based traffic conflict technique. The traffic conflicts approach provides better understanding of collision contributing factors and the failure mechanism that leads to road collisions. Traffic conflicts are automatically detected and time to collision is calculated based on the analysis of the vehicles’ positions in space and time. Video data are collected from a signalized intersection in Nanjing, China, where both traditional inside and unconventional outside left-turn lanes are installed on two intersection approaches. The other two approaches have only inside left-turn lanes. The study compared frequency and severity of conflict for left-turning vehicles as well as the percentage of vehicles involved in conflicts from the inside and outside left-turn lanes. The results show that the intersection approaches with outside left-turn lanes had considerably more conflicts compared to approaches without outside left-turn lanes. As well, the approaches with outside left-turn lanes had significantly higher conflict severity than the approaches without outside left-turn lanes. As such, it is recommended that the trade-off between the improved mobility and negative safety impact of outside left-turn lanes be carefully considered before recommending their installation.

Safety Evaluation and Improvements for Highway Intersections

2008 ◽  
Vol 2060 (1) ◽  
pp. 46-52 ◽  
Author(s):  
Li Yuan ◽  
Jian Lu
Keyword(s):  
Traffic Control ◽  
Cost Benefit Analysis ◽  
Safety Evaluation ◽  
Cost Benefit ◽  
Safety Performance ◽  
Crash Analysis ◽  
Traffic Crash ◽  
Crash Data ◽  
Intersection Safety ◽  
Traffic Signal Timing

Intersection safety is one of the most important issues in transportation. Traffic crash analysis—the most popular method to evaluate or assess the safety performance of an intersection—has been used for a long time. However, it is based on a lot of crash data, which need to be accumulated over a long period. In addition, traffic crashes sometimes occur randomly as a result of human driving behavior. Therefore, without sufficient data and crash history, traffic crash analysis may not give an overall evaluation of an intersection's safety performance. This paper introduces an approach to evaluating highway intersection safety performance. It is fully based on the existing conditions of the intersection, including geometrics, sight distance, pavement surface conditions, traffic control devices, traffic signal timing, and phasing. The non-accident-based approach is based on field surveys under the conditions mentioned previously. The approach will also result in a safety index to indicate the safety performance of the intersection. Corresponding countermeasures are ranked and recommended based on cost–benefit analysis. This paper is based on research results from part of a project (entitled Safety Design of Highway Intersections) sponsored by the China Department of Transportation. In this paper, the approach (called a diagnostic approach) is practically applied to evaluate the safety performance of some intersections in Shan Dong Province. Results from the real application indicate that the approach has good applicability and can be used by field safety engineers in real applications.

Sign in / Sign up

Export Citation Format

Share Document