Stop Signs Research Articles

SSIM-Based Autoencoder Modeling to Defeat Adversarial Patch Attacks

Object detection systems are used in various fields such as autonomous vehicles and facial recognition. In particular, object detection using deep learning networks enables real-time processing in low-performance edge devices and can maintain high detection rates. However, edge devices that operate far from administrators are vulnerable to various physical attacks by malicious adversaries. In this paper, we implement a function for detecting traffic signs by using You Only Look Once (YOLO) as well as Faster-RCNN, which can be adopted by edge devices of autonomous vehicles. Then, assuming the role of a malicious attacker, we executed adversarial patch attacks with Adv-Patch and Dpatch. Trying to cause misdetection of traffic stop signs by using Adv-Patch and Dpatch, we confirmed the attacks can succeed with a high probability. To defeat these attacks, we propose an image reconstruction method using an autoencoder and the Structural Similarity Index Measure (SSIM). We confirm that the proposed method can sufficiently defend against an attack, attaining a mean Average Precision (mAP) of 91.46% even when two adversarial attacks are launched.

Older Adult Misuse of Over-the-Counter Medications: Effectiveness of a Novel Pharmacy-Based Intervention to Improve Patient Safety

Objectives Older adults’ (ages ≥65) inappropriate over-the-counter medications (OTC) use is prevalent, comprising Drug-Age, Drug-Drug, Drug-Disease, and Drug-Label types. Given that pharmacies sell many OTCs, structurally redesigning pharmacy aisles for improving patient safety (Senior Safe) was conceived to mitigate older adult OTC misuse, using Stop Signs and Behind-the-Counter Signs for high-risk OTCs. This study determined whether Senior Safe reduced high-risk OTCs misuse, while secondarily evaluating misuse changes for all OTCs. Methods A randomized controlled trial design matched and randomly allocated 20 health system community pharmacies to control or intervention groups. All 288 study participants completed an OTC choice task in which they chose a hypothetical symptom scenario (pain, sleep, cough/cold/allergy), selected an OTC, and described how they would use it at symptom onset and if symptoms persisted or worsened. Reported OTC use was evaluated for each misuse type. Intervention and control sites were compared for each misuse type using multivariate modeling. Results For high-risk OTCs, Drug-Age and Drug-Drug misuse were more likely in control sites (OR = 2.752, P = 0.004; OR = 6.199, P = 0.003, respectively), whereas Drug-Disease and Drug-Label misuse had too few occurrences in intervention sites for statistical comparisons. For all OTCs, only Drug-Age misuse was more likely for control sites (OR = 5.120, P = 0.001). Adults aged 85+ years had the greatest likelihood of all misuse types. Conclusions Results demonstrated that older adults frequently reported multiple misuse types, highlighting safety concerns. Senior Safe reduced high-risk OTC misuse, especially for older adults younger than 85 years. Cumulatively, these findings provide insights into practice recommendations supported through regulatory guidance.

Naturalistic Analysis of Bidirectional Gazing During Vehicle-Pedestrian Encounters at Road Crossings

This study quantifies bidirectional gazing—when drivers and pedestrians look at one another—in a naturalistic setting. Understanding bidirectional gazing provides insights into the communication dynamics between pedestrians and drivers, and their relation to infrastructural support (e.g., a stop sign). Findings demonstrate that 36% of observed road crossings included at least one bidirectional glance. There was a tendency for bidirectional gazing to be more prevalent (especially early in encounters) and longer for crossing types with less infrastructural support, such as undesignated crossings. This suggests that when pedestrians lack infrastructural support and are farther away from the lane, drivers and pedestrians rely more on visual communication (looking at each other) to determine things like gap size, trajectory, speed, and distance. However, when pedestrians are closer to the lane, we find similar gaze patterns across the crossing types, which may suggest another gaze-behavior type (e.g., checking if it is safe to cross).

Identifying the causal effects of driver distraction on hazardous actions at intersections based on propensity score weighting

Distracted driving is a threat to traffic safety that can result in more traffic crashes. Although previous studies have been conducted to explore the relationship between driver distraction and hazardous driving actions, few studies are available to identify the causation between them. Thus, the study intended to evaluate the causal effects of distraction on hazardous driving actions at intersections based on the crash data extracted from the Crash Report Sampling System (2021–2022). The multinomial logit model was employed to reveal the factors contributing to driver distraction. Then, propensity score weighting was adopted to balance the factor distributions between distraction and non-distraction cases to identify the causal effects on hazardous actions. Results indicated that 1) the propensity of distraction is relevant to factors such as the driver’s age, gender, vehicle type, speed limit, area, weather, and light condition, 2) driver distraction can significantly increase the probability of risky actions including speeding, running red lights, failing to obey stop signs, failing to yield, following too closely, and 3) the causal effects show great diversity for different distraction types. The findings serve to understand the influence mechanism of distraction on specific crash risks and develop countermeasures to reduce distraction and hazardous driving actions.

Alternative Emergency Vehicle Lighting Affects Traffic Behaviors

Emergency vehicle lightings (EVL) mitigate the risk of collision and make drivers move over. The present paper explored how new alternative EVL designs can improve driver behavior in different emergency vehicle interaction scenarios. From workshops with 14 emergency responders, three scenarios (Emergency driving, Police pull-over, Emergency vehicle alongside the road) and 19 EVL blink patterns were chosen. These alternative EVLs were presented in an online survey with 2627 Swedish respondents. Alternative EVL affected reported driving behavior. Drivers reported being most certain of what is expected from them in the emergency-driving scenario. It is important to ensure that the EVL is easy to interpret in more unfamiliar emergency-vehicle interactions such as police pull-over. Only a third of drivers had seen the pull-over EVL currently used in Sweden. The current pull-over EVL in combination with a stop sign increased the chance of drivers reporting that they would pull over.

Electrified fleet and infrastructure aware energy efficient routing

This paper presents an optimization framework to improve the energy efficiency and cost-effectiveness of fleets of commercial trucks operating pickups and deliveries in urban areas. As the electrification of transportation is moving from passenger cars to medium- and heavy-duty vehicles, the proposed analysis considers a fleet of pickup and delivery trucks that includes conventional internal combustion engine vehicles (ICEV), as well as battery electric vehicles (BEV), and plug-in hybrid electric vehicles (PHEV). Given a set of pickups and deliveries, and a fleet including different types of vehicles, the goal is twofold: assign the best vehicle to each task, and solve the vehicle routing problem, i.e., find the optimal route to navigate the vehicle from the origin to the destination(s). To estimate the energy consumption of the different vehicles, vehicle dynamics are considered, together with actual charging infrastructure and road data, including speed limits, road grade, and stop signs. Moreover, the total cost of ownership (TCO) is evaluated to estimate the cost-effectiveness of different fleet compositions and operations. To solve this problem, a hybrid simulated annealing (HSA) heuristic algorithm is proposed. The algorithm is validated against a benchmark exact solver based on mixed integer linear programming (MILP). The proposed methodology achieves optimal results with a 1.2% optimality gap compared to the benchmark, surpassing MILP in computational efficiency. The research findings highlight how fleet composition and operational strategies can vary significantly based on whether the focus is on energy efficiency, total cost of ownership, or a combination of the two, also depending on the number of years of operation. Simulation case studies in the Columbus, OH area demonstrate that integrating fleet and recharging infrastructure information alongside energy savings in vehicle routing problem solutions can achieve 20% to 50% savings in fleet operation costs compared to solely optimizing for minimum energy consumption.

Traffic Sign Board Recognition and Voice Alert System using CNN

Street to guarantee a secure and efficient flow of traffic. Street accidents sometimes occur on account of carelessness in reading traffic signs incorrectly. The suggested framework aids in recognizing the stop sign and giving a voice warning to the motorist for the speaker to make their point, and crucial decisions. The proposed framework is prepared Using a Convolutional Neural Network (CNN), which aids with the recognition and arranging of rush hour congestion sign pictures. To increase precision, a number are of classes generated and characterized on a particular dataset. Utilized was the German Traffic Sign Benchmarks Dataset, which includes 51,900 pictures of road signage in 43 classifications. Around 98.52 percent during execution was precise. After the framework recognizes the sign, the driver is informed through a voice alarm issued through the speaker. The suggested framework also includes a section where drivers are warned about nearby traffic signs so they can keep track of which laws to follow while on a highway. The system’s goal is to protect the driver, passengers, and pedestrians from harm.

Leveraging computer vision for predicting collision risks: a cross-sectional analysis of 2019–2021 fatal collisions in the USA

ObjectiveThe USA has higher rates of fatal motor vehicle collisions than most high-income countries. Previous studies examining the role of the built environment were generally limited to small geographic areas...

Behavioural Sciences Used by the United Nations to Achieve the Sustainable Development Goals: A Roadmap and Some Stop Signs

The United Nations (UN) and several UN Agencies have started to use behavioural sciences in order to achieve their policy goals, including for achieving the Sustainable Development Goals (SDG). While it is appreciated that insights into actual behavior inform the policymaking of international actors, they also raise scientific and normative considerations that warrant caution. First, for those considerations it matters, who the acting and the targeted actors are: behavioural interventions come in many facets and warrant a differentiated view – a finely built roadmap is thus desirable. Second, there are concerns about the internal and external validity of experimental research on which behavioural sciences largely, but not solely, draws. Third, taking a differentiated view on behavioral sciences also allows for a more finely grained view on normative concerns underlying the operations of the United Nations in environmental policy. This contribution spells out those considerations while still advocating for the approach as such.

A temporal statistical assessment of the effectiveness of bicyclist safety helmets in mitigating injury severities in vehicle/bicyclist crashes

This study estimates mixed logit models taking into account heterogeneity in means and partially constrained parameters in order to explore possible shifts within parameters over time to study factors influencing bicyclist injury severity outcomes. Separate statistical models are estimated for two bicyclist helmet-wearing scenarios (helmet and non-helmet) using a comprehensive dataset from Florida covering a three-year period to assess COVID-19 effects from the 1st of January 2019 to the 31st of December 2021. This research evaluates several factors influencing helmeted and non-helmeted bicyclist injury severity, encompassing the attributes of drivers and cyclists, the environment and weather, the features of the roads and their temporal aspects, and the different types of vehicles. The performed analysis further enhances model robustness by assessing the temporal stability and transferability across different contexts through likelihood ratio tests, alongside an in-depth examination of the temporal consistency of explanatory variables via marginal effects analysis, confirming significant variations between non-helmeted and helmeted bicyclist models and revealing temporal shifts in factors affecting injury severity during the study period. Findings from the model estimations identify several significant variables with consistent parameter estimates across years. Stop signs, cycling with traffic, and dark, unlit conditions increase severe injury risk in non-helmet models, while the stop sign indicator consistently reduces severe injury risk in helmet models. Statistically significant random parameters are identified across different years and helmet-wearing scenarios, including the male driver indicator, which exhibits varying effects on injury severity. Out-of-sample prediction analysis suggests helmets reduce severe injury probability but may increase minor injuries and decrease no-injury accidents, indicating potential risk compensation behavior among helmeted bicyclists. Although helmets offer protection against severe injuries for bicyclists, it is crucial to adopt a comprehensive safety approach, particularly given the evolving demographics of bicyclists amid the COVID-19 outbreak. This entails considering factors like bicyclist and driver behavior, environmental conditions, and infrastructure enhancements. Policymakers, road safety professionals, and advocacy groups should collaborate to develop holistic strategies to address the determinants of bicycle crash severity outcomes and enhance safety measures for bicyclists across diverse road environments.

Real-Time Navigation Roads: Lightweight and Efficient Convolutional Neural Network (LE-CNN) for Arabic Traffic Sign Recognition in Intelligent Transportation Systems (ITS)

Smart cities are now embracing the new frontier of urban living, with advanced technology being used to enhance the quality of life for residents. Many of these cities have developed transportation systems that improve efficiency and sustainability, as well as quality. Integrating cutting-edge transportation technology and data-driven solutions improves safety, reduces environmental impact, optimizes traffic flow during peak hours, and reduces congestion. Intelligent transportation systems consist of many systems, one of which is traffic sign detection. This type of system utilizes many advanced techniques and technologies, such as machine learning and computer vision techniques. A variety of traffic signs, such as yield signs, stop signs, speed limits, and pedestrian crossings, are among those that the traffic sign detection system is trained to recognize and interpret. Ensuring accurate and robust traffic sign recognition is paramount for the safe deployment of self-driving cars in diverse and challenging environments like the Arab world. However, existing methods often face many challenges, such as variability in the appearance of signs, real-time processing, occlusions that can block signs, low-quality images, and others. This paper introduces an advanced Lightweight and Efficient Convolutional Neural Network (LE-CNN) architecture specifically designed for accurate and real-time Arabic traffic sign classification. The proposed LE-CNN architecture leverages the efficacy of depth-wise separable convolutions and channel pruning to achieve significant performance improvements in both speed and accuracy compared to existing models. An extensive evaluation of the LE-CNN on the Arabic traffic sign dataset that was carried out demonstrates an impressive accuracy of 96.5% while maintaining superior performance with a remarkably low inference time of 1.65 s, crucial for real-time applications in self-driving cars. It achieves high accuracy with low false positive and false negative rates, demonstrating its potential for real-world applications like autonomous driving and advanced driver-assistance systems.

Securing AI Models Against Backdoor Attacks: A Novel Approach Using Image Steganography

<p>Artificial Intelligence (AI) has become ubiquitous, transforming numerous domains including traffic sign recognition, defect detection, and healthcare. However, this widespread adoption has brought about significant cybersecurity challenges, particularly in the form of backdoor attacks, which manipulate training datasets to compromise model integrity. While the integration of AI has proven beneficial, there is a lack of comprehensive strategies to protect AI models from these covert attacks, necessitating innovative approaches for securing AI systems. In this study, we demonstrate a novel methodology that integrates image steganography with deep learning techniques, aiming to obscure backdoor triggers and enhance the resilience of AI models against these attacks. We employ a diverse set of AI models and conduct extensive evaluations in a traffic sign recognition scenario, specifically targeting the STOP sign. The results reveal that shallow models are challenged in learning trigger information and are sensitive to trigger settings, while deeper models achieve an impressive 98.03% attack success rate. The image steganography technique used requires minimal data adjustments, making the triggers more challenging to detect than with traditional methods. Our findings underscore the stealth and severity of backdoor attacks, emphasizing the need for advanced security measures in AI and contributing to the broader understanding and development of robust protections against such attacks.</p> <p> </p>

Edge AI-Enabled Road Fixture Monitoring System

Effective monitoring of road fixtures is essential for urban safety and functionality. However, traditional inspections are time-consuming, costly, and error prone, while current automated solutions struggle with high initial setup costs, limited flexibility preventing wide adaptation, and reliance on centralized processing that can delay response times. This study introduces an edge AI-based remote road fixture monitoring system which automatically and continuously updates the information of the road digital twin (DT). The main component is a small-sized edge device consisting of a camera, GPS, and IMU sensors designed to be installed in typical cars. The device captures images, detects the fixture, and estimates their location by employing deep learning and feature matching. This information is transmitted to a dedicated cloud server and represented on a user-friendly user interface. Experiments were conducted to test the system’s performance. The results showed that the device could successfully detect the fixture and estimate their global coordinates. Outputs were marked and shown on the road DT, proving the integrated and smooth operation of the whole system. The proposed Edge AI device demonstrated that it could significantly reduce the data size by 80–84% compared to traditional methods. With a satisfactory object detection accuracy of 65%, the system effectively identifies traffic poles, stop signs, and streetlights, integrating these findings into a digital twin for real-time monitoring. The proposed system improves road monitoring by cutting down on maintenance and emergency response times, increasing the ease of data use, and offering a foundation for an overview of urban road fixtures’ current state. However, the system’s reliance on the quality of data collected under varying environmental conditions suggests potential improvements for consistent performance across diverse scenarios.

Characterization of Expert and Public Perceptions of Bicycle Rolling Stop Laws

In 2020, Oregon and Washington joined a growing number of states to sign up to new bicycle rolling stop (BRS) legislation that allows bicyclists to yield to pedestrians and motorists when approaching stop sign controlled intersections instead of coming to a complete, unconditional stop. The term “bicycle rolling stop” is synonymous with the “bicycle stop-then-yield” condition or the “Idaho Stop,” as first enacted in Idaho in 1982. This study involved a literature review capturing current BRS and similar laws throughout the United States, and collected and synthesized both expert and public opinions concerning BRS laws from experts and residents in Idaho, Oregon, and Washington. The results indicated that people were less likely to know about the laws in states where they were more recently enacted, although awareness of the laws indicated a need for broader educational outreach. The impacts of BRS laws tended to be viewed as neutral to positive among bicyclists, but mostly neutral among the broader public.

AI on the Road: NVIDIA Jetson Nano-Powered Computer Vision-Based System for Real-Time Pedestrian and Priority Sign Detection

Advances in information and signal processing, driven by artificial intelligence techniques and recent breakthroughs in deep learning, have significantly impacted autonomous driving by enhancing safety and reducing the dependence on human intervention. Generally, prevailing ADASs (advanced driver assistance systems) incorporate costly components, making them financially unattainable for a substantial portion of the population. This paper proposes a solution: an embedded system designed for real-time pedestrian and priority sign detection, offering affordability and universal applicability across various vehicles. The suggested system, which comprises two cameras, an NVIDIA Jetson Nano B01 low-power edge device and an LCD (liquid crystal system) display, ensures seamless integration into a vehicle without occupying substantial space and provides a cost-effective alternative. The primary focus of this research is addressing accidents caused by the failure to yield priority to other drivers or pedestrians. Our study stands out from existing research by concurrently addressing traffic sign recognition and pedestrian detection, concentrating on identifying five crucial objects: pedestrians, pedestrian crossings (signs and road paintings separately), stop signs, and give way signs. Object detection was executed using a lightweight, custom-trained CNN (convolutional neural network) known as SSD (Single Shot Detector)-MobileNet, implemented on the Jetson Nano. To tailor the model for this specific application, the pre-trained neural network underwent training on our custom dataset consisting of images captured on the road under diverse lighting and traffic conditions. The outcomes of the proposed system offer promising results, positioning it as a viable candidate for real-time implementation; its contributions are noteworthy in advancing the safety and accessibility of autonomous driving technologies.

Field Evaluation of a Mobile App for Assisting Blind and Visually Impaired Travelers to Find Bus Stops.

GPS location-based navigation apps are insufficient to aid blind and visually impaired (BVI) travelers for micro-navigation tasks, such as finding the exact location of bus stops. The resulting large gaps could lead to BVI travelers missing their bus. We evaluated the ability of a signage detection mobile app, All_Aboard, to guide BVI travelers precisely to the bus stops compared to Google Maps alone. The All_Aboard app detected bus stop signs in real-time via smartphone camera using a deep neural network model, and provided distance coded audio feedback to help localize the detected sign. BVI individuals used the All_Aboard and Google Maps app to localize 10 bus stops each in downtown and suburban Boston, Massachusetts. For each bus stop, the subjects used both apps to navigate as close as possible to the physical bus stop sign, starting from 30 to 50meters away. The outcome measures were success rate and gap distance between the app-indicated location and the actual physical location of the bus stop. The study involved 24 legally blind participants (mean age [SD] = 51 [14] years; 11 [46%] women). The success rate of the All_Aboard app (91%) was significantly higher than the Google Maps (52%, P < 0.001). The gap distance when using the All_Aboard app was significantly lower (mean = 1.8, 95% confidence interval [CI] = 1.2-2.3meters) compared to the Google Maps alone (mean = 7, 95% CI = 6.5-7.5meters, P < 0.001). All_Aboard micro-navigation app guided BVI travelers to bus stops more accurately and reliably than a location-based macro-navigation app alone. The All_Aboard app together with a macro-navigation app can potentially help BVI individuals independently access public transportation.

Driving through stop signs: predicting stop codon reassignment improves functional annotation of bacteriophages.

The majority of bacteriophage diversity remains uncharacterized, and new intriguing mechanisms of their biology are being continually described. Members of some phage lineages, such as the Crassvirales, repurpose stop codons to encode an amino acid by using alternate genetic codes. Here, we investigated the prevalence of stop codon reassignment in phage genomes and its subsequent impacts on functional annotation. We predicted 76 genomes within INPHARED and 712 vOTUs from the Unified Human Gut Virome Catalogue (UHGV) that repurpose a stop codon to encode an amino acid. We re-annotated these sequences with modified versions of Pharokka and Prokka, called Pharokka-gv and Prokka-gv, to automatically predict stop codon reassignment prior to annotation. Both tools significantly improved the quality of annotations, with Pharokka-gv performing best. For sequences predicted to repurpose TAG to glutamine (translation table 15), Pharokka-gv increased the median gene length (median of per genome median) from 287 to 481bp for UHGV sequences (67.8% increase) and from 318 to 550bp for INPHARED sequences (72.9% increase). The re-annotation increased median coding capacity from 66.8% to 90.0% and from 69.0% to 89.8% for UHGV and INPHARED sequences predicted to use translation table 15. Furthermore, the proportion of genes that could be assigned functional annotation increased, including an increase in the number of major capsid proteins that could be identified. We propose that automatic prediction of stop codon reassignment before annotation is beneficial to downstream viral genomic and metagenomic analyses.

Ultron and the Ultra-Age of Nanoparticles

Nanotechnology has advanced over the past 4 years and shows no signs of stopping. Nanotechnology-based technologies and products have completely changed every part of daily life, from the food sector to medical uses. With the use of nanoparticles, food products may now have much longer shelf life, hydrophobic medication distribution can be improved within cells, and the effectiveness of certain treatments, such anticancer medicines, can be increased. Consequently, the world economy has been influenced by nanotechnology in addition to the global level of life. This review discusses the properties of nanoparticles that give them appropriate and possibly harmful biological effects, as well as their uses in various biological fields, nanoparticlebased medications, and delivery systems in biomedicine, including nano-based medications that are currently FDA-approved. A potential remedy as well as the potential consequences of ongoing exposure to nanoparticles as a result of growing nanotechnology use are also discussed.

Structurization with probabilistic causal model for unsafe driving behavior of older people at stop sign intersections

Structurization with probabilistic causal model for unsafe driving behavior of older people at stop sign intersections

OLDER ADULT MISUSE OF OVER-THE-COUNTER MEDICATIONS: BENEFITS OF A NOVEL PHARMACY-BASED INTERVENTION

Abstract Older adults’ inappropriate use of over-the-counter medications (OTCs) is prevalent and comprises: (1) Drug-Age misuse – medication risks due to advanced age, (2) Drug-Drug misuse – medication interactions, (3) Drug-Disease misuse – contraindications with health conditions, and (4) Drug-Label misuse – deviations from label instructions. Since pharmacies are ubiquitous sources of OTC accessibility and medication safety expertise, a structural redesign of pharmacy aisles (Senior SafeTM) was conceived to mitigate older adult OTC misuse. A central feature of Senior Safe is the use of Stop Signs for high-risk OTCs and Behind-the-Counter Signs (BTC) for particularly high-risk OTCs. Given the signage’s practical importance, this study’ principal aim was to determine whether Senior Safe reduced misuse of Stop Sign/BTC OTCs. Twenty pharmacies from a mid-Western healthcare system were matched and randomly allocated to either control or intervention groups, from which 288 older adults were recruited (ages 65-91). Participants’ reported OTC use for a symptom scenario (pain, sleep, cough/cold/allergy) was evaluated to determine whether it fulfilled the four misuse types. Misuse occurrences between intervention/control sites were compared using multivariate modeling. Drug-Age and Drug-Drug misuse frequencies were significantly lower in intervention sites (Coef.=-1.012, p=.004; Coef.=-1.702, p=.004, respectively), while Drug-Disease and Drug-Label misuse had too few occurrences in intervention sites for statistical comparisons. Also, adults aged 85+ had the greatest likelihood of all misuse types. Senior Safe shows substantial benefit reducing high-risk OTC misuse, which is important particularly for vulnerable adults ages 85-91. Future research should document intervention mechanisms contributing to lower older adult OTC misuse.