The emergence of low-cost air quality sensors may improve our ability to capture variations in urban air pollution and provide actionable information for public health. Despite the increasing popularity of low-cost sensors, there remain some gaps in the understanding of their performance under real-world conditions, as well as compared to regulatory monitors with high accuracy, but also high cost and maintenance requirements. In this paper, we report on the performance and the linear calibration of readings from 12 commercial low-cost sensors co-located at a regulatory air quality monitoring site in Dallas, Texas, for 18 continuous measurement months. Commercial AQY1 sensors were used, and their reported readings of O₃, NO₂, PM_2.5, and PM₁₀ were assessed against a regulatory monitor. We assessed how well the raw and calibrated AQY1 readings matched the regulatory monitor and whether meteorology impacted performance. We found that each sensor’s response was different. Overall, the sensors performed best for O₃ (R² = 0.36–0.97) and worst for NO₂ (0.00–0.58), showing a potential impact of meteorological factors, with an effect of temperature on O₃ and relative humidity on PM. Calibration seemed to improve the accuracy, but not in all cases or for all performance metrics (e.g., precision versus bias), and it was limited to a linear calibration in this study. Our data showed that it is critical for users to regularly calibrate low-cost sensors and monitor data once they are installed, as sensors may not be operating properly, which may result in the loss of large amounts of data. We also recommend that co-location should be as exact as possible, minimizing the distance between sensors and regulatory monitors, and that the sampling orientation is similar. There were important deviations between the AQY1 and regulatory monitors’ readings, which in small part depended on meteorology, hindering the ability of the low-costs sensors to present air quality accurately. However, categorizing air pollution levels, using for example the Air Quality Index framework, rather than reporting absolute readings, may be a more suitable approach. In addition, more sophisticated calibration methods, including accounting for individual sensor performance, may further improve performance. This work adds to the literature by assessing the performance of low-cost sensors over one of the longest durations reported to date.

This paper is focused on the effect of road geometry, and other accident causing conditions, on the binary response variable road accident severity. The data is collected from two interurban routes in Spain (Madrid-Irún and Barcelona-Almeria) and covers a 3 year period (2010-2012). Data mining techniques were applied for the treatment and combination of two databases for road accident associated factors and geometry standards respectively. The effect of the influential factors on road accident severity was estimated through a non-parametric statistical methodology, random forests. Several standards of the road geometry design were found to have a significant effect on the road accident severity

Identification of traffic crash hot spots is of great importance for improving roadway safety and maintaining the transportation system’s sustainability. Traditionally, police crash reports (PCR) have been used as the primary source of crash data in safety studies. However, using PCR as the sole source of information has several drawbacks. For example, some crashes, which do not cause extensive property damage, are mostly underreported. Underreporting of crashes can significantly influence the effectiveness of data-driven safety analysis and prevent safety analysts from reaching statistically meaningful results. Crowdsourced traffic incident data such as Waze have great potential to complement traditional safety analysis by providing user-captured crash and traffic incident data. However, using these data sources also has some challenges. One of the major problems is data redundancy because many people may report the same event. In this paper, the authors explore the potential of using crowdsourced Waze incident reports (WIRs) to identify high-risk road segments. The researchers first propose a new methodology to eliminate redundant WIRs. Then, the researchers use WIRs and PCRs from an I-35 corridor in North Texas to conduct the safety analysis. Results demonstrated that WIRs and PCRs are spatially correlated; however, their temporal distributions are significantly different. WIRs have broader coverage, with 60.24 percent of road segments in the study site receiving more WIRs than PCRs. Moreover, by combining WIRs with PCRs, more high-risk road segments can be identified (14 miles) than the results generated from PCRs (8 miles).