Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States
- Proceedings of the National Academy of Sciences of the United States of America
- Published 12 months ago
The United States spends more than $250 million each year on the American Community Survey (ACS), a labor-intensive door-to-door study that measures statistics relating to race, gender, education, occupation, unemployment, and other demographic factors. Although a comprehensive source of data, the lag between demographic changes and their appearance in the ACS can exceed several years. As digital imagery becomes ubiquitous and machine vision techniques improve, automated data analysis may become an increasingly practical supplement to the ACS. Here, we present a method that estimates socioeconomic characteristics of regions spanning 200 US cities by using 50 million images of street scenes gathered with Google Street View cars. Using deep learning-based computer vision techniques, we determined the make, model, and year of all motor vehicles encountered in particular neighborhoods. Data from this census of motor vehicles, which enumerated 22 million automobiles in total (8% of all automobiles in the United States), were used to accurately estimate income, race, education, and voting patterns at the zip code and precinct level. (The average US precinct contains [Formula: see text]1,000 people.) The resulting associations are surprisingly simple and powerful. For instance, if the number of sedans encountered during a drive through a city is higher than the number of pickup trucks, the city is likely to vote for a Democrat during the next presidential election (88% chance); otherwise, it is likely to vote Republican (82%). Our results suggest that automated systems for monitoring demographics may effectively complement labor-intensive approaches, with the potential to measure demographics with fine spatial resolution, in close to real time.
Outcomes of the Introduction of a Standardized Fitness-for-Duty Evaluation of Commercial Truck Drivers on the Incidence of Low Back Injuries and Workers' Compensation Costs
- Journal of occupational and environmental medicine / American College of Occupational and Environmental Medicine
- Published almost 5 years ago
To determine the incidence of low back injuries and associated workers' compensation costs before and after the introduction of a standardized fitness-for-duty evaluation of commercial truck drivers who present for their comprehensive Department of Transportation (DOT) physical examination.
- International journal of injury control and safety promotion
- Published over 3 years ago
Many traffic accidents take place throughout the world every day claiming lives as well as commodities and people involved in the accidents have to stay long periods at the hospitals. Traffic accidents are caused by many reasons. One of the reasons is the driver’s having a heart attack just before the accident took place. If the heartbeat of the driver can continuously be measured, then most probably one of the reasons of traffic accidents can be eliminated. The designed model aims to measure the driver’s heartbeat using infrared imaging. Some car models already have a driver heartbeat monitoring system and it measures the heartbeats by using the back seat electrodes. But these systems are expensive and unique to their models and what is more; its adaptation to other car models can pose a difficulty. Implementing on the car’s rear-view mirror this new design monitoring system is very cheap and also it can be mounted to all motor vehicles easily.
The working environment, the nature of the work, and the characteristics of truck drivers as a social group typically pose great challenges for the truck drivers' health and health promotion activities aiming to improve it.
Kelsh et al. : Occup Med (Lond) 57:581-589 published a paper reanalyzing one of the few data sources publicly available on mesothelioma amongst brake workers, the Australian Mesothelioma Surveillance Registry (AMSR). This reanalysis was commissioned by lawyers representing the automobile manufacturing companies and did not align with an independent analysis published by Leigh and Driscoll : Occup Environ Health 9:206-217.
Approximately 1,701,500 people were employed as heavy and tractor-trailer truck drivers in the United States in 2012. The majority of them were long-haul truck drivers (LHTDs). There are limited data on occupational injury and safety in LHTDs, which prompted a targeted national survey. The National Institute of Occupational Safety and Health conducted a nationally representative survey of 1265 LHTDs at 32 truck stops across the contiguous United States in 2010. Data were collected on truck crashes, near misses, moving violations, work-related injuries, work environment, safety climate, driver training, job satisfaction, and driving behaviors. Results suggested that an estimated 2.6% of LHTDs reported a truck crash in 2010, 35% reported at least one crash while working as an LHTD, 24% reported at least one near miss in the previous 7 days, 17% reported at least one moving violation ticket and 4.7% reported a non-crash injury involving days away from work in the previous 12 months. The majority (68%) of non-crash injuries among company drivers were not reported to employers. An estimate of 73% of LHTDs (16% often and 58% sometimes) perceived their delivery schedules unrealistically tight; 24% often continued driving despite fatigue, bad weather, or heavy traffic because they needed to deliver or pick up a load at a given time; 4.5% often drove 10miles per hours or more over the speed limit; 6.0% never wore a seatbelt; 36% were often frustrated by other drivers on the road; 35% often had to wait for access to a loading dock; 37% reported being noncompliant with hours-of-service rules (10% often and 27% sometimes); 38% of LHTDs perceived their entry-level training inadequate; and 15% did not feel that safety of workers was a high priority with their management. This survey brings to light a number of important safety issues for further research and interventions, e.g., high prevalence of truck crashes, injury underreporting, unrealistically tight delivery schedules, noncompliance with hours-of-service rules, and inadequate entry-level training.
Roadway incidents involving motorized vehicles accounted for 24% of fatal occupational injuries in the United States during 2013 and were the leading cause of fatal injuries among workers.* In 2013, workers' compensation costs for serious, nonfatal injuries among work-related roadway incidents involving motorized land vehicles were estimated at $2.96 billion.(†) Seat belt use is a proven method to reduce injuries to motor vehicle occupants (1). Use of lap/shoulder seat belts reduces the risk for fatal injuries to front seat occupants of cars by 45% and the risk to light truck occupants by 60%.(§) To characterize seat belt use among adult workers by occupational group, CDC analyzed data from the 2013 Behavioral Risk Factor Surveillance System (BRFSS) and found that not always using a seat belt was significantly associated with occupational group after controlling for factors known to influence seat belt use. Occupational groups with the highest prevalences of not always using a seat belt included construction and extraction; farming, fishing, and forestry; and installation, maintenance, and repair. To increase seat belt use among persons currently employed, states can enact and enforce primary seat belt laws, employers can set and enforce safety policies requiring seat belt use by all vehicle occupants, and seat belt safety advocates can target interventions to workers in occupational groups with lower reported seat belt use.
A 22-year-old man presented after a motor vehicle collision in which his head struck the windshield of a bus. A CT scan showed an incidental finding of grossly dilated occipital and temporal horns of the right lateral ventricle. MRI confirmed the presence of a large cystic lesion.
Recent research has found evidence of an association between motor vehicle accidents (MVAs) or near miss accidents (NMAs), and excessive daytime sleepiness (EDS) or its main medical cause, Obstructive Sleep Apnea (OSA). However, EDS can also be due to non-medical factors, such as sleep debt (SD), which is common among professional truck drivers. On the opposite side, rest breaks and naps are known to protect against accidents.
Drivers of heavy and tractor-trailer trucks accounted for 56% of all production and nonsupervisory employees in the truck transportation industry in 2011. There are limited data for illness and injury in long-haul truck drivers, which prompted a targeted national survey.