Stop Signs Research Articles

FedSGDCOVID: Federated SGD COVID-19 Detection under Local Differential Privacy Using Chest X-ray Images and Symptom Information.

Coronavirus (COVID-19) has created an unprecedented global crisis because of its detrimental effect on the global economy and health. COVID-19 cases have been rapidly increasing, with no sign of stopping. As a result, test kits and accurate detection models are in short supply. Early identification of COVID-19 patients will help decrease the infection rate. Thus, developing an automatic algorithm that enables the early detection of COVID-19 is essential. Moreover, patient data are sensitive, and they must be protected to prevent malicious attackers from revealing information through model updates and reconstruction. In this study, we presented a higher privacy-preserving federated learning system for COVID-19 detection without sharing data among data owners. First, we constructed a federated learning system using chest X-ray images and symptom information. The purpose is to develop a decentralized model across multiple hospitals without sharing data. We found that adding the spatial pyramid pooling to a 2D convolutional neural network improves the accuracy of chest X-ray images. Second, we explored that the accuracy of federated learning for COVID-19 identification reduces significantly for non-independent and identically distributed (Non-IID) data. We then proposed a strategy to improve the model’s accuracy on Non-IID data by increasing the total number of clients, parallelism (client-fraction), and computation per client. Finally, for our federated learning model, we applied a differential privacy stochastic gradient descent (DP-SGD) to improve the privacy of patient data. We also proposed a strategy to maintain the robustness of federated learning to ensure the security and accuracy of the model.

Organizing is Hot in the Media Industry

“Union leaders at newspapers, digital outlets and broadcast stations are seeing historic levels of organizing that show little sign of stopping,” said a recent report from the Poynter Institute for Media Studies, a nonprofit journalism school and research organization. Since 2015, multiple media employers—largely in the digital space—have seen upticks in organizing activity.

Eye movement as a function to explore the effects of improved signs design and audio warning on drivers’ behavior at STOP-sign-controlled grade crossings

Train-vehicle collisions at STOP-sign-controlled grade crossings attract many concerns in China and across the world. Researchers have demonstrated that the cost-effective approaches to improve grade crossing safety are the redesign of signs and pavement markings as well as the application of in-vehicle audio warning. However, the impacts of improved signs design and audio warning on drivers’ visual performance have barely been discussed. This study explored the effects of improved signs design and audio warning on drivers’ eye movement patterns and driving behavior at STOP-sign-controlled grade crossings, by conducting a driving simulator experiment. Three types of grade crossing scenarios: 1) the conventional signs design (Baseline), 2) improved signs design (PS), and 3) improved signs design and three-stage audio warning (PSW), were modeled in a driving simulation system and tested under a series of train TTC (no train, 4 s, 7 s, 10 s, 13 s) conditions. Foggy conditions and drivers’ characteristics, i.e., gender and vocation were considered in the experiment design. Seven variables describing both drivers’ fixation patterns and driving performance were collected and analyzed in this study, e.g., total fixation duration, distance to stop line at the first fixation, fixation transition probability, stop compliance, speed, maximum deceleration rate and minimum time-to-collision. Results revealed that the improved design of signs and the audio warning could prime drivers’ expectation of the grade crossing in advance since drivers could drive at a lower speed, perceive signs timely, and conduct an earlier visual search for the train with these countermeasures. Besides, in PS and PSW scenarios, drivers attached more importance to the STOP sign, and they were more cautious in estimating the time-to-arrival of the train by repeatedly fixating on these two areas. The improvement in fixation performance of drivers in PS and PSW contributed to a more comfortable deceleration. Compared with no warning scenarios, higher compliance rates were observed with audio warning, especially with a short train TTC (4 s and 7 s). However, no significant difference was found between PS and Baseline, indicating the limited safety benefits of improved signs design. Minimum time-to-collision for those drivers who ignored the warning did not increase significantly in both PS and PSW. Additionally, heavy fog limited drivers’ perception of signs and led to a later and shorter fixation. For gender effect, males had a lower fixation duration on the STOP sign and lower compliance rate than females. Moreover, female drivers could perceive the approaching train earlier than males, especially in PS and PSW. These findings suggested that the improved signs design and in-vehicle audio warning improved drivers’ visual and behavioral performance and had the potential to enhance safety at STOP-sign-controlled grade crossings.

On-road tailpipe characterization of exhaust ammonia emissions from in-use light-duty gasoline motor vehicles

A Portable Emissions Monitoring System (PEMS) has been used to estimate ammonia emission rates from a representative fleet of 47 in-use light-duty gasoline motor vehicles over 145 on-road Real Driving Emissions (RDE) tests. The PEMS modules were carried onboard the tested vehicles and were wired such that their ceramic exhaust emission sensors were mounted directly in the tailpipe. The on-road RDE tests were conducted over an urban testing route that included residential and highway roads, uphill and downhill road segments, stop signs, traffic lights, and a school zone with a reduced speed limit. The entire vehicle test sample had an average ammonia emission rate of 114.7 mg/mile ±135.3 (StD). This would yield an estimated 2909 metric tons per year of NH3 emissions from the Wasatch fleet on-road gasoline motor vehicles. Old vehicles with aged Three-Way Catalyst (TWC) converters had higher NH3 emissions rates than newer vehicles with newer TWC converters. For instance, Tier 0, Tier I, NLEV, Tier II and Tier III vehicles had average emission rates of 563.1, 177.8, 213.6, 94.4 and 18.9 mg/mile, respectively. Carbon monoxide, and nitrogen oxides had a strong correlation with ammonia emission rates, with r ≥ 0.70. A Moderate correlation was found with vehicles’ mileage (r = 0.6), model year (r = −0.5), engine displacement (r = 0.4), and number of cylinders (r = 0.4). The outcomes highlight vehicle contributions to the atmospheric NH3 inventory and the impact of vehicle characteristics and ammonia precursor concentrations on ammonia emission rates from gasoline vehicles.

Characteristics of Cyclist Crashes Using Polytomous Latent Class Analysis and Bias-Reduced Logistic Regression

Although the number of cyclist crashes is decreasing in Japan, the fatality rate is not. Thus, reducing their severity is a major challenge. We used a polytomous latent class analysis to understand their characteristics and bias-reduced logistic regression to analyze their severity. Specifically, 90,696 combinations and 139,955 cyclist accidents were divided into 17 classes. The variable contributing the most to the classification was the crash location. Common fatality risks included older age groups and rural areas, whereas other factors differed among crash locations. Median strips, stop signs, and boundaries between the sidewalk and roadway affected the severity of crashes at intersections. Moreover, the existence of a median strip, collision partner, and time period affected the severity of crashes between intersections. On the sidewalks, the fatality risk was higher when the front part of the bicycle was subjected to the collision.

Mind, Value, and Cosmos: On the Relational Nature of Ultimacy

Mind, Value, and Cosmos: On the Relational Nature of Ultimacy

Miniature Model of Autonomous Vehicle Using Arduino UNO and Open CV

Abstract: The one thing that makes Tesla stand out from the crowd is its full automation Self-Driving feature. Not just the name itself but the technology behind it is even more interesting. It is not only about the luxury but also has a lot of advantages which backs the term. And what blows our mind is that not a lot of Indian car companies are focused on this technology on wide scale. So, inspired by that this paper presents to build a Self-Driving Autonomous car model but on minimalistic basis which basically will be focused on three main features which are to operate in accordance with the surrounding depending on the direction of the road, to detect stop sign and halt for 5-10 seconds and detect traffic signs and make decisions accordingly. The miniature self-driving car will detect the two-lane path and perform the above functions. Keywords: Autonomous Vehicles, Self-driving car, Computer Vision, Neural Network, Image processing, wireless sensor networks, control systems, path planning.

Analysis of Driver Gaze and Attention to Traffic Signs

A driver’s actions and intent can be factors in enabling advance driver assistance systems (ADASs) to assist drivers and avoid accidents. A driver’s gaze can provide insight into the driver’s intent or awareness of situations. Knowing that a driver gazed at a traffic sign or missed a traffic could provide indications of whether the driver is alert to impending changes in the driving environment, such as curves and stop signs. For ADASs to determine the importance of a driver seeing or missing a sign, it is important to understand the driving environment and situation. A first step is to understand what signs drivers do see or miss while driving. This contribution presents the results of analyzing driving sequences to assess traffic signs that drivers may or may not have gazed upon. The results suggest that drivers may miss 20% of traffic signs though the percentage varies depending on the type of sign. The analysis uses image sequences of the driving environment and gazes data captured during driving. The methods used in our analysis included determining whether a driver’s gaze has fallen on the image of a traffic sign or not and subsequently determining signs missed during driving. The methods presented can be useful in other scenarios involving the analysis of driver gaze and have implications for the design of future ADASs and for understanding of driver gaze and awareness.

Investigating risk factors associated with pedestrian crash occurrence and injury severity in Texas

Objective This study investigates various risk factors associated with pedestrian crash occurrence and injury severity based on 78,497 reported pedestrian-involved crashes across Texas from 2010 through 2019. Methods Crashes are mapped to over 708,738 road segments, along with road design, land use, transit, hospital, rainfall, and other location features. Negative binomial models examine the association between pedestrian crash frequency and various contributing factors, and a heteroskedastic ordered probit model investigates the severity of injuries at the individual crash level. Results Results from this study show the practical significance of microlevel variables in predicting pedestrian crashes. Proximity to schools and hospitals and presence of transit are all associated with higher pedestrian crash frequencies yet are rarely included in other models. Total pedestrian crash and fatal crash counts rise with the number of lanes, population, and job densities, though greater median and shoulder widths provide some protection. Higher speed limits are associated with lower crash frequencies but more deaths. Pedestrian crashes are more likely to be severe and fatal at night (8 p.m. to 5 a.m.), without overhead lighting, and when involved pedestrians and/or drivers are intoxicated. Use of light-duty trucks also significantly increases risk of severe or fatal pedestrian injury. Though newer vehicle safety features may be argued to lower crash severity or protect vehicle occupants, newer crash-involved vehicles in Texas are not found to deliver less severe pedestrian injury. Pedestrian and driver characteristics—both age and gender—are practically (and statistically) significant. Injury severity rises with pedestrian age, yet younger and/or female pedestrians on straight roadways, off the state (and interstate) highway system, and in the presence of a traffic control device (stop sign or signal) are less likely to be seriously injured, on average. Conclusions Findings underscore the benefit of enhanced vehicle safety features for pedestrians, campaigns against driving and walking while intoxicated, improved roadway design, enforcement of safety countermeasures near schools and bus stops, and installment of additional traffic controls and streetlights wherever more pedestrians exist.

TRNA molecules run a STOP sign.

tRNA molecules run a STOP sign.

FACTORS AFFECTING STOPPING BEHAVIOUR AT SUBURBAN INTERSECTIONS

This study focused on how drivers dealt with intersections controlled by a stop sign at suburban in Al-Husn city at Irbid governorate, Jordan. The videotape was used at eight unsignalized intersections for one complete peak hour on weekdays. Any at-grade intersection that is not controlled by a traffic signal is defined as an "unsignalized intersection." The results showed that 48% out of 1,208 drivers took the decision to stop completely compared to 52% who chose to keep driving. Female drivers (75%) were observed to stop at intersections more frequently than male drivers. In terms of vehicle type, drivers of buses stopped more frequently than drivers of small passenger cars, which are road car, other than a motorcycle, that is designed to transport passengers. Driver age and compliance to a stop sign were found to be directly proportional to each other, but as the number of passengers in the vehicle increased, the rate of non-compliance also increased. Compliance was highest among leading vehicles, followed by following vehicles, and lowest among single vehicles. A binary logistic model showed that age, vehicle occupancy, and arrival pattern significantly affected stopping the behaviour. Gender and vehicle type were not significantly related to stopping the behaviour.

A novel framework for verification and validation of simulations of autonomous robots

Modeling and simulation (M&S) plays a critical role in both engineering and basic research processes. However, M&S is only truly useful if the model and simulation outputs are accurate. As such, significant research has been undertaken to establish what “accurate” means for simulations and what subsequent level of “trust” should be given to M&S outputs. Trust in M&S outputs is established by verifying and validating the models and simulations. While a wealth of research can be found to define verification and validation (V&V) for traditional M&S, little research has been done to define a methodology for the V&V of simulations of complex, intelligent, and autonomous systems. Specifically, no methodology for V&V of simulations of autonomous robots has been developed to date. This paper presents a brief overview of the current V&V methods in use for traditional simulations. In light of this review, a novel framework for the V&V of simulations for predicting the behaviors of autonomous robots is developed, and this framework is presented in detail. This V&V framework is then applied to the use-case of an autonomous unmanned ground vehicle’s (UGV’s) navigation task. The framework is applied for model validation of Global Positioning System (GPS), inertial measurement unit (IMU), and RGB camera sensor models. The framework is further applied to validate these sensor models for an example camera-based autonomous navigation algorithm, stop sign detection.

Exploring the stop sign running at all-way stop-controlled intersections with the SHRP2 naturalistic driving data

IntroductionAll-way stop control (AWSC) has been widely used at unsignalized intersections in the United States for its safety effects. However, many drivers do not make a complete stop before stop signs in practice (i.e., stop sign running), which presents safety concerns. MethodThis study explores driver behaviors at AWSC intersections with the SHRP2 naturalistic driving data. ResultsFirst, it is found that the full-stop rate is only 20.2% at AWSC intersections. Then, the study quantitatively analyzes what factors might influence the stop sign running decisions at AWSC intersections, where driver, vehicle, intersection geometry, maneuver, and environmental features are taken into account. In addition, considering the possible unobserved heterogeneities across drivers and intersections, a logistic regression model with both driver and intersection random effects is adopted. The results show that young and older drivers are less likely to fully stop, but there is no gender difference found. SUVs and vans are less likely to fully stop, drivers are less likely to fully stop at 3-leg intersections, and drivers are more likely to fully stop in daytime and weekdays. In terms of maneuvers, left-turn traversals are more likely to make a complete stop. In addition, both the driver and intersection random effects are found to be significant, vary greatly by individuals, and can be used to identify the few but critical high-risk drivers/intersections. Practical applicationsThe findings are expected to provide new insights for transportation agencies to formulate effective measures to deter stop sign running.

Multistate Pilot Study Evaluating the Short-Term Efficacy of a Smartphone-Based Older Driver Support System on Modifying Risky Driving Behaviors

Older drivers are most at risk of serious and fatal injury in crashes per vehicle mile driven compared with other age groups owing to a combination of cognitive decline and increased fragility. A smartphone coaching application targeting risky driving behaviors (e.g., speeding, hard braking), was iteratively designed to ensure older driver acceptance and usability. A 12-week field operational test examined driving performance of 28 drivers aged 65 to 78 from Kansas and Minnesota using the RoadCoach app and an ABA reversal design. Participants’ baseline driving behaviors were recorded for 3 weeks, followed by a 6-week experimental phase of real-time app coaching, and concluded with a 3-week baseline phase with no feedback provided. Compared with the pretreatment phase, there was a significant reduction in the rates of hard braking and stop sign violations associated with system use. A protection effect was observed through the posttreatment phase. Excessive speeding violations were not significantly different across the phases; however, there were modest declines in the proportion of miles traveled 15 mph above the speed limit in the posttreatment phase compared with the prior two phases. No significant effect was found for excessive acceleration and aggressive turning measures posttreatment, despite an observed increase in both rates during the treatment phase compared with pretreatment. Overall, the results indicate that the RoachCoach app may be an effective intervention to reduce several risky driving behaviors while in use and may result in prolonged behavior changes (i.e., reduced hard braking and stop sign violations) after treatment cessation.

Co-occurence of risky driving behaviours and associations with seatbelt and helmet use - a descriptive cross-sectional study among young adults


 Background: Greece exhibits one of the highest rates of deaths and injuries due to motor vehicle crashes in young adults in Europe. The personal, social and financial cost is still very high as road traffic crashes account for 65.8% of all deaths among young people aged 10-24 years, with prominent gender differences that are not fully explained yet. 
 Methods: using a descriptive cross-sectional study design, we examined the associations of seatbelt and helmet use with the likelihood of manifesting multiple driving violations (fail to stop at STOP signs, running red traffic lights, driving towards the wrong direction, illegal overtaking, speeding, cellphone use while driving, driving under the influence of alcohol) in a sample of 536 1st year university students in Greece. A ‘Risky Driving Index’ score (RDI) was produced by summing the frequencies of all behaviours (range 0-28). 
 Results: only 8.8% of the students reported not performing any of the driving violations, whereas 8.6% engaged in all 7 of them when driving (male: 11.5%; female: 1.9%; score>8, male: 31.7%; female: 8.1%). Male, but not female participants, who never used seatbelts and helmets, reported significantly higher RDI scores with evidence of a dose-response effect in the increase. In adjusted logistic regression models, those who never used (vs regular use) seat belt ‘as drivers’ and ‘as rear seat passengers’ had increased odds of being in the higher score category of RDI (OR=5.239 95%CI=1.280-21.441 and OR=6.782 95%CI=1.891-24.324, respectively). 
 Conclusion: young male drivers and riders, but not their female counterparts, that do not take typical safety measures (seatbelt and helmet use), reported more illegal and risky driving behaviours. Preventive interventions using a gender-informed approach are needed to address co-occurring risk driving behaviours. 
 

Do stop-signs improve the safety for all road users? A before-after study of stop-controlled intersections using video-based trajectories and surrogate measures of safety

Converting minor-approach-only stop (MAS) intersections to all-way-stop (AWS) intersections is a prevailing safety countermeasure in North American urban areas. Although the general population positively perceives the installation of stop-signs in residential areas, little research has investigated the impact of AWS on road safety and road user behaviour. This paper investigated the safety effectiveness of converting MAS to AWS intersections using an observational before and after approach and surrogate measures of safety. More specifically, the safety impacts of AWS conversion were investigated using multiple indicators, including vehicle speed measures, vehicle–pedestrian, vehicle-cyclist, vehicles-vehicle interactions as well as yielding rates before and after the treatment implementation. A multi-level regression approach was adopted to determine the effect of stop signs controlling for built environments, traffic exposure, and intersection geometry factors as well as site-specific unobserved heterogeneity.A unique sample of 31 intersections were used in this before-after study. From this sample, video data were collected before and after implementing AWS. In total, 245 h of video were automatically processed and corrected using a specialized computer vision software. More than 68,000 (37,668 before and 31,305 after AWS treatment) road user trajectories were obtained from 104 approaches. The results show that the conversion of MAS to AWS intersections significantly decreased vehicle speed and increased post-encroachment time. This work also shows that implementing AWS significantly increased the yielding rates from 45.7% to 76.7% in MAS conditions and reduced the average speed of motor-vehicles. Using multi-level regression model, it is estimated that when the intersection was converted from MAS to AWS, the minimum speed in the major approaches was reduced by 60.0%.

Magnetic stop signs signal a European songbird's arrival at the breeding site after migration.

Although it is known that birds can return to their breeding grounds with exceptional precision, it has remained a mystery how they know when and where to stop migrating. Using nearly a century's worth of Eurasian reed warbler (Acrocephalus scirpaceus) ringing recoveries, we investigated whether fluctuations in Earth's magnetic field predict variation in the sites to which birds return. Ringing recoveries suggest that magnetic inclination is learned before departure and is subsequently used as a uni-coordinate "stop sign" when relocating the natal or breeding site. However, many locations have the same inclination angle. Data from populations with different migratory directions indicate that birds solve this ambiguity by stopping at the first place where the right inclination is encountered on an inherited return vector.

A Scalable Deep Learning Framework for Extracting Model Inventory of Roadway Element Intersection Control Types From Panoramic Images

In the United States, the Model Inventory of Roadway Element (MIRE) provides a comprehensive list of data that are needed to support states’ data-driven safety programs. The intersection control is part of the MIRE Fundamental Data Elements (FDE) for which state Departments of Transportation are required to complete the collection by September 30, 2026. It is essential roadway data that have been used widely in traffic safety studies. This study proposes a scalable and automated deep learning framework for detecting and classifying stop and yield intersection controls using panoramic street view images. The Faster Region-based Convolutional Neural Networks (Faster R-CNN) model architecture was used to detect and classify stop and yield signs from the images. A transfer learning process was deployed using the Inception-ResNet-v2 generic feature extractor to accelerate the training and performance of the deep learning model with less data collection effort. The effectiveness and scalability of the proposed framework were tested on a sample of road intersections in the state of Michigan. The proposed deep learning model achieved a recall value of 97.7% and 98.2% for detecting and classifying stop and yield signs respectively. The evaluation of the model performance at a county level suggests that the model can be scaled to a statewide level without a substantial increase in the demand for computational resources. As demonstrated in this study, state DOTs can leverage the advancement of deep learning techniques and the availability of imagery data to expedite the process of collecting the MIRE data.

A Study on Bicycle Behaviors at Intersections with a Stop Sign in Daily Bicycle Use

A Study on Bicycle Behaviors at Intersections with a Stop Sign in Daily Bicycle Use

Primena prepoznavanja saobraćajnih znakova na skaliranom modelu vozila

The popularity of autonomous vehicles has grown in the past few years as autonomous systems are more and more present on vehicles. The most accessible way for students of mechanical and software engineers to learn about autonomous vehicles is by applying algorithms and systems necessary for autonomous driving on the scaled vehicle model. These models are, as in this case, and are equipped with all systems necessary for autonomous driving, such as a four-wheel drive powertrain, a suspension system, an electrically controlled steering system, a brain-computer and a camera. The goal of projects such as this one is to make the vehicle capable of autonomous driving on a designated track, obeying regular traffic rules and signs (for example, the vehicle has to perform a full stop when it approaches the stop sign). To make this possible, it is necessary for a vehicle to "know" which traffic sign is nearby, i.e., traffic sign recognition is required. For this purpose, traffic sign recognition is done by an artificial neural network. The training process of the proper artificial neural network will be shown in this paper.