skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Spatio-Temporal Crash Prediction: Effects of Negative Sampling on Understanding Network-Level Crash Occurrence
In projects centered around rare event case data, the challenge of data comprehension is greatly increased because of insufficient data for deriving insight and analysis. This is particularly the case with traffic crash occurrence, where positive events (crashes) are rare and, in most cases, no data set exists for negative events (non-crashes). One method to increase available data is negative sampling, which is the process of creating a negative event based on the absence of a positive event. In this work, four negative sampling techniques are presented with varying ratios of negative to positive data. These types of techniques are based on spatial data, temporal data, and a mixture of the two, with the data ratios acting as class balancing tools. The best performing model found was with a negative sampling technique that shifted temporal information and had an even 50/50 data split, with an F-1 score, a formulaic combination of precision and recall, of 93.68. These results are promising for Inteligent Transportation Systems (ITS) applications to inform of potential crash locations in an entire area for proactive measures to be put in place.  more » « less
Award ID(s):
1647161
PAR ID:
10221147
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Transportation Research Record: Journal of the Transportation Research Board
ISSN:
0361-1981
Page Range / eLocation ID:
036119812199183
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Transportation Research Record: Journal of the Transportation Research Board)
    The Safe System Approach (SSA) aims to eliminate fatal and serious injury roadway crashes through a holistic view of the road system, moving away from traditional safety analysis based exclusively on historical crash data. One reason for this is the classification of crashes into broad categories (e.g., head-on, sideswipe), which does not capture crash progression or contributing factors. In this context, this paper applies crash sequence analysis to historical crash data and uses the findings to proactively identify safety issues in similar contexts, in alignment with the SSA framework. The method uses sequence-of-events information from crash data to generate clusters of crashes with similar underlying characteristics. Data from fatal and serious injury crashes from urban intersections in the state of Ohio between 2018 and 2022 were used in the analysis. The results show 12 clusters with unique characteristics that consider the sequence of events of each crash. Although derived from crash data, the clusters offer an in-depth understanding of the factors associated with each one and help identify cluster-specific countermeasures related to various SSA elements. State and local jurisdictions can use the presented methodology in transportation safety programs, by focusing on the clusters that represent local challenges or on countermeasures related to the issues of multiple clusters. Finally, the method can also be associated with site-specific analysis, providing a comprehensive toolkit for practitioners. 
    more » « less
  2. ; ; (, Proceedings of the ACM on Programming Languages)
    Compute Express Link (CXL) memory sharing, persistent memory, and other related technologies allow data to survive crash events. A key challenge is ensuring that data is consistent after crashes such that it can be safely accessed. While there has been much work on bug-finding tools for persistent memory programs, these tools cannot guarantee that a program is crash-consistent. In this paper, we present a language, CrashLang, and its type system, that together guarantee that well-typed data structure implementations written in CrashLang are crash-consistent. CrashLang leverages the well-known commit-store pattern in which a single store logically commits an entire data structure operation. In this paper, we prove that well-typed CrashLang programs are crash-consistent, and provide a prototype implementation of the CrashLang compiler. We have evaluated CrashLang on five benchmarks: the Harris linked list, the Treiber stack, the Michael–Scott queue, a Read-Copy-Update binary search tree, and a Cache-Line Hash Table. We experimentally verified that each implementation correctly survives crashes. 
    more » « less
  3. ; ; (, Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering)
    Precise crash triage is important for automated dynamic testing tools, like fuzzers. At scale, fuzzers produce millions of crashing inputs. Fuzzers use heuristics, like stack hashes, to cut down on duplicate bug reports. These heuristics are fast, but often imprecise: even after deduplication, hundreds of uniquely reported crashes can still correspond to the same bug. Remaining crashes must be inspected manually, incurring considerable effort. In this paper we present Semantic Crash Bucketing, a generic method for precise crash bucketing using program transformation. Semantic Crash Bucketing maps crashing inputs to unique bugs as a function of changing a program (i.e., a semantic delta). We observe that a real bug fix precisely identifies crashes belonging to the same bug. Our insight is to approximate real bug fixes with lightweight program transformation to obtain the same level of precision. Our approach uses (a) patch templates and (b) semantic feedback from the program to automatically generate and apply approximate fixes for general bug classes. Our evaluation shows that approximate fixes are competitive with using true fixes for crash bucketing, and significantly outperforms built-in deduplication techniques for three state of the art fuzzers. 
    more » « less
  4. ; ; ; ; ; (, Journal of safety research)
    null (Ed.)
    Problem: Previous research have focused extensively on crashes, however near crashes provide additional data on driver errors leading to critical events as well as evasive maneuvers employed to avoid crashes. The Strategic Highway Research Program 2 (SHRP2) Naturalistic Driving Study contains extensive data on real world driving and offers a reliable methodology to study near crashes. The current study utilized the SHRP2 database to compare the rate and characteristics associated with near crashes among risky drivers. Methods: A subset from the SHRP2 database consisting of 4,818 near crashes for teen (16–19 yrs), young adult (20–24 yrs), adult (35–54 yrs), and older (70+ yrs) drivers was used. Near crashes were classified into seven incident types: rear-end, road departure, intersection, head-on, side-swipe, pedestrian/cyclist, and animal. Near crash rates, incident type, secondary tasks, and evasive maneuvers were compared across age groups. For rear-end near crashes, near crash severity, max deceleration, and time-to-collision at braking were compared across age. Results: Near crash rates significantly decreased with increasing age (p < 0.05). Young drivers exhibited greater rear-end (p < 0.05) and road departure (p < 0.05) near crashes compared to adult and older drivers. Intersection near crashes were the most common incident type among older drivers. Evasive maneuver type did not significantly vary across age groups. Near crashes exhibited a longer time-to-collision at braking (p < 0.01) compared to crashes. Summary: These data demonstrate increased total near crash rates among young drivers relative to adult and older drivers. Prevalence of specific near crash types also differed across age groups. Timely execution of evasive maneuvers was a distinguishing factor between crashes or near crashes. Practical Applications: These data can be used to develop more targeted driver training programs and help OEMs optimize ADAS to address the most common errors exhibited by risky drivers. 
    more » « less
  5. ; ; ; ; ; ; (, JAMA pediatrics)
    null (Ed.)
    IMPORTANCE One mechanism for teenagers’ elevated crash risk during independent driving may be inadequate learner driving experience. OBJECTIVE To determine how learner driver experience was associated with crash risk during the first year of independent driving. DESIGN, SETTING, AND PARTICIPANTS Youth aged 15.5 to 16.1 years at recruitmentwere eligible to participate. Participants’ vehicles were instrumented with sensors, and driving was recorded during the learner period through 1 year of independent driving. Data were collected from January 2011 through August 2014 in southwestern Virginia. EXPOSURES The amount, consistency and variety of practice, driving errors, and kinematic risky driving (KRD) rates during the learner period were recorded. Surveys, including one on sensation-seeking personality traits, were assessed at baseline. MAIN OUTCOMES AND MEASURES Cox proportional hazard regressions examined associations between individual characteristics and learner driving experience with driving time to first crash and all crashes in the first year of independent driving. So that hazard ratios (HRs) can be directly comparable, units of measurement were standardized to the interquartile range. RESULTS Of 298 individuals who responded to recruitment, 90 fulfilled the criteria and 82 completed the study (of whom 75 were white [91%] and 44 were girls [54%]). Teenage participants drove a mean (SD) of 1259.2 (939.7) miles over 89 days during the learner period. There were 49 property-damage crashes and/or police-reportable crashes during independent driving. Factors associated with driving time to first crash included higher sensation-seeking personality scale scores (HR, 1.67 [95%CI, 1.08-2.57] per 0.75-unit increase), learner driving KRD rates (HR, 1.27 [95%CI, 1.12-1.43] per 9.24-unit increase), and learner driving errors (HR, 0.44 [95%CI, 0.22-0.86] per increase of 6.48 errors). Similar results were obtained for all crashes in the first year, with the addition of consistency of learner driving practice (HR, 0.61 [95%CI, 0.38-0.99] per 0.23-unit increase). CONCLUSIONS AND RELEVANCE Individual characteristics and learner driving experiences were associated with crash risk during independent driving. As expected, there was an association between sensation seeking and crashes. Elevated KRD rates during the learner period may reflect risky driving behavior among novices or tolerance to abrupt maneuvers by parents who supervise driving. Consistent practice throughout the learner period could reduce teenage crash risk, which is supported by learning theories indicating distributed practice is effective for developing expertise. Errors during practice may constitute learning events that reinforce safer driving. Physicians could encourage parents to provide opportunities for regular practice driving and monitor their teenager’s KRD rates during the learner period using in-vehicle or smartphone-based technology. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email