Visual Warning Research Articles

Detection of Driver Drowsiness to Avoid Accidents and Prevent Alertness

Drowsy driver is one of the leading causes of road accidents that leads to life-threatening injuries and death around the globe. The goal of this project is to develop a Driver Drowsiness Detection System that uses computer vision and machine learning to monitor a driver’s face and detect signs of fatigue using real time analysis. The system consists of a camera module that can capture video frames of a driver, which is processed with OpenCV, Dlib, and deep learning models to detect eye closure, blink frequency, and head movements. Once symptoms of drowsiness are detected, the system triggers an alert mechanism that could either be an alarm or a pop-up visual warning to encourage the driver to recuperate or restore focus. This method is very accurate, non-monitoring, and offers real-time results, hence, it is very effective for personal and commercial vehicles. This report captures the problem statement, methodologies, implementations, experimental results and future scope of the system. The goal of the project is to promote safety on the road by preventing accidents due to excessive driver fatigue, which, in turn, helps to advance the intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS).

Interfacial Confinement Derived High-Strength MXene@Graphene Oxide Core-Shell Fibers for Electromagnetic Wave Regulation, Thermochromic Alerts, and Visible Camouflage.

Although electrically conductive Ti₃C₂Tx MXene fibers are promising for wearable electronics, the poor inter-sheet interactions and the random stacking structure of MXene sheets seriously hinder electron transport and load transfer of the fibers. Herein, mechanically strong and electrically conductive MXene@graphene oxide (GO) core-shell fibers are fabricated with a coaxial wet-spinning methodology for electromagnetic wave regulation, thermochromic alerts, and visible camouflage. During the coaxial wet-spinning, the trace-carboxylated GO sheets in the shell align readily because of the spatial confinement of the coaxial needle, while the MXene sheets in the core are progressively oriented and flattened because of the spatial confinement of the GO shell. The positively charged chitosan in the coagulating solution enhances the interfacial interactions between the GO and MXene sheets and facilitates the sheet's orientation inside the fibers.Consequently, the highly aligned core-shell fibers exhibit an ultrahigh tensile strength of 613.7 MPa and an outstanding conductivity of ≈7766 S cm-1. Furthermore, fiber-woven textiles not only offer excellent electromagnetic interference shielding performance but also achieve quantitative regulation of electromagnetic wave transmission by adjusting the angle of the double-layered textiles. The textiles can combine with thermochromic coatings for thermotherapy alerts, visual thermochromic warnings, and visible camouflage.

Enhancing Tractor Safety on Road With Multi-Stage Overtake Warning System

Tractor safety on public roads is a critical concern in modern agriculture, necessitating the integration of advanced safety technologies to mitigate risks and enhance operational efficiency. This paper explores the significance of the Overtake Warning (OTW) system as a proactive safety solution designed to address the challenges associated with overtaking manoeuvres and vehicle interactions on roadways. The OTW system serves as a vital component of Operator Assistance Systems, providing tractor operators with real-time alerts and warnings when vehicles attempt to overtake. This enhances situational awareness and reduces the likelihood of collisions. By leveraging radar sensors, intelligent algorithms, and warning logic, the OTW system offers a comprehensive approach to road safety, enabling operators to make informed decisions and navigate roadways with heightened safety consciousness. Statistics reveal the prevalence of road accidents related to overtaking manoeuvres, rear-end collisions, poor visibility conditions, and driver distraction, underscoring the urgent need for advanced safety systems like the OTW system. By incorporating visual and acoustic warnings, the OTW system aims to prevent accidents, streamline tractor operations, and promote a culture of safety compliance among operators and road users. This dives deeper into the OTW system's design, functionality, and benefits, highlighting its role in enhancing tractor safety protocols, reducing accident risks, and fostering a safer road environment for agricultural operations. The insights presented underscore the importance of technological innovations in improving road safety and advancing the efficiency of tractor and in general off-road vehicle operations on public roads Keywords: Overtake Warning System, Radar sensor, Tractor Safety on the road, Safe Lane change for tractors, Operator Assistance System

The Effectiveness of EMG Biofeedback to Improve Ankle Dorsiflexion in Stroke Patients: A Systematic Review

Background: Stroke, results in some form of residual deficits even after recovery. Patients face difficulty in ambulating, probably because of reduced ankle dorsiflexion. Present systematic review aims to explore the literature-related to studies conducted on patients with Stroke for the effectiveness of electromyography biofeedback (EMG BF) therapy in the treatment of ankle dorsiflexion. Methodology: This study included nine randomised trials, all including patients who developed stroke after an episode of acute Ischemic infract. Use of databases Google Scholar, PubMed and CINHAL full text was done. Results: EMG muscle activity also showed improvement in 3 out of 9 studies. This may be attributed to gradual weight bearing and improving in muscle activity over the period of time. Discussion: EMG BF is useful for improving motor functions and walking speed as well as increasing ROM and muscle activation maybe because new pathways are formed or previous cerebral and spinal pathways and networks are activated by the stimulation with feedback or remaining proprioceptive senses are regulated by visual and acoustic warnings. Conclusion: There is gradual weight bearing and improvement in muscle activity post EMG BFB over the period of time.

Muscle twitch thresholds depending on the direction of current stimulation

Abstract Acoustic or visual warning signals for workers in hazardous situations might fail under loud and/or lowvisibility work situations. A warning system that uses electrocutaneous stimulation can overcome this problem. This study aimed to compare vertical, diagonal, and horizontal current stimulation directions at the upper arm to select the one with the lowest amount of muscle twitching. Fourteen electrodes were attached in two rows to the upper right arm of 15 participants. The stimulation was conducted with bi-phasic rectangular pulses of 150 μs and amplitudes of up to 25 mA. Muscle twitch thresholds have been determined and a circumferential stimulation signal was presented as warning pattern for the three current stimulation directions and evaluated regarding alertness, discomfort, and urgency. For single stimulation pulses, muscle twitches occurred slightly less often at the horizontal stimulation direction compared to the other two and muscle twitch thresholds showed no systematic differences. For the warning patterns, no considerable differences were found regarding the evaluation of alertness, discomfort, and urgency and no differences were found for muscle twitching. In conclusion, all orientations seem suitable for warning pattern presentation and none of the directions has a clear advantage in reducing muscle twitch.

I remember you! Multicomponent warning signals and predator memory.

To avoid potentially noxious prey, predators need to discriminate between palatable and unpalatable prey species. Unpalatable prey often exhibits visual warning signals, which can consist of multiple components, such as color and pattern. Although the role of particular components of visual warning signals in predator discrimination learning has been intensively studied, the importance of different components for predator memory is considerably less understood. In this study, we tested adult wild-caught great tits (Parus major) to find out, which components of prey visual warning signals are important when the birds learn to discriminate between palatable and unpalatable prey, and when they remember their experience over a longer time period. Birds were trained to discriminate between palatable and unpalatable artificial prey items that differed in both color and pattern. After 4wk, the birds were retested in 3 groups: the first group was presented with the same prey as in the training, the second group was tested with the two prey types differing only in color, and the third group could use only the pattern as a discrimination trait. The results suggest that the birds remember their experience with unpalatable prey even after the period of 4wk. Although the color appears to be more important than the pattern, the combination of both signal components is more effective for prey recognition after several weeks than either the color or pattern alone.

Effectiveness of pictorial-warning intervention to reduce consumption of sugar-sweetened-beverages

Abstract Background & Aims Limited research have looked at pictorial-health-warnings (PHW) for sugar- sweetened beverages (SSB), despite the potential for behaviour change that pictorial warnings on tobacco products hold. This study aimed to examine how visual warnings impacted parents’ decisions to buy SSB for their children. Materials and methods All residents dwelling in the communities and local vendors available were subjected to a ten-week multi-strategy intervention by randomized stepped-wedge controlled trial to support the introduction of PHW labels. Stepped implementation of a two-week PHW intervention was delivered in a randomly selected order at one-week intervals. Follow-up data were collected for all three sectors two weeks following the completion of the PHW intervention in the third sector. The trial outcome was determined by comparing the overall perception change towards SSB among parents between the baseline and follow-up periods for three sectors combined. Secondary outcomes included reactions to the trial labels, attitudes toward SSB, and intentions to serve their child SSB. Results PHW led to a 30 % (-37.12%, -22.37%) reduction in purchases of SSB, along with lower intentions to serve SSB to children, higher thoughtfulness about the harms of SSB, more perceived control of healthy eating decisions, stronger negative emotional reactions, lower perceived healthfulness of SSB for their child, and greater injunctive norms to limit SSB for their child (all p < 0.05). No differences by sector or within sector were found between pre and post-intervention in the appeal of SSB or perceived tastiness of SSB (all p > 0.05). Nearly 53% of participants reported being more in control of making healthy eating decisions. Conclusions Warnings on SSB are a promising policy approach to reduce sugary drink purchasing. This evidence will support the health service adoption of implementation strategies to support PHW labels across the entire country. Key messages • Warnings on SSB are a promising policy approach to reduce sugary drink purchasing. • Support the health service adoption of implementation strategies to support PHW labels across the entire country.

Real-time quality analysis of baked goods using advanced technologies

Real-time quality analysis of baked goods using advanced technologies

Smart Rumble Strip System to Prevent Over-Height Vehicle Collisions.

Collisions of over-height vehicles with low clearance bridges is commonly encountered worldwide. They have caused damage to bridge structures, interruption to traffic, injuries or even fatalities to road users. To mitigate such risks, passive systems that involve warning gantries, flashing lights and illuminated signage are commonly installed. Semi-active systems using laser- or infrared-based detection systems in conjunction with visual warnings have been implemented. Nevertheless, some drivers ignore these visual warnings and collisions continue to occur. This paper presents a novel concept for a collision prevention system, which makes use of a series of sensor-activated, motorized rumble strips. These rumble strips span across a certain distance ahead of a low clearance bridge. When an over-height vehicle is detected, a mechanism is triggered which elevates the rumble strips. The noise and vibrations produce a vigorous alert to the offending driver. They also increase effective friction of the road surface, thus assisting to slow down the vehicle and shorten the stopping distance. The strips will be lowered after a certain time has elapsed, thus minimizing their effects on other vehicles. This article presents a conceptual framework and quantifies the vibration and noise caused by rumble strips in road tests. Road tests indicated that the vibration level typically exceeded 1 g and noise level reached approximately 90 dB in the cabin of a 3.5-ton truck. Fabrication of a proof-of-concept mechanized rumble strip model was presented and verified in an outdoor environment. The circuitry and mechanical design, and requirements in actual implementation, are discussed. The proposed event-triggered rumble strip system could significantly mitigate over-height vehicle collisions that cause major disruptions and injuries worldwide. Further works, including a comprehensive road test involving various types of vehicles, are envisaged.

Enhancing Safety in Autonomous Vehicles: The Impact of Auditory and Visual Warning Signals on Driver Behavior and Situational Awareness

Semi-autonomous vehicles (AVs) enable drivers to engage in non-driving tasks but require them to be ready to take control during critical situations. This “out-of-the-loop” problem demands a quick transition to active information processing, raising safety concerns and anxiety. Multimodal signals in AVs aim to deliver take-over requests and facilitate driver–vehicle cooperation. However, the effectiveness of auditory, visual, or combined signals in improving situational awareness and reaction time for safe maneuvering remains unclear. This study investigates how signal modalities affect drivers’ behavior using virtual reality (VR). We measured drivers’ reaction times from signal onset to take-over response and gaze dwell time for situational awareness across twelve critical events. Furthermore, we assessed self-reported anxiety and trust levels using the Autonomous Vehicle Acceptance Model questionnaire. The results showed that visual signals significantly reduced reaction times, whereas auditory signals did not. Additionally, any warning signal, together with seeing driving hazards, increased successful maneuvering. The analysis of gaze dwell time on driving hazards revealed that audio and visual signals improved situational awareness. Lastly, warning signals reduced anxiety and increased trust. These results highlight the distinct effectiveness of signal modalities in improving driver reaction times, situational awareness, and perceived safety, mitigating the “out-of-the-loop” problem and fostering human–vehicle cooperation.

Thermally stimulated color-tunable performance of Ca3Ga4O9: Bi3+ by co-doping with alkali metal ions

Thermally stimulated color-tunable performance of Ca3Ga4O9: Bi3+ by co-doping with alkali metal ions

AI-Based Visual Early Warning System

Facial expressions are a universally recognised means of conveying internal emotional states across diverse human cultural and ethnic groups. Recent advances in understanding people’s emotions expressed through verbal and non-verbal communication are particularly noteworthy in the clinical context for the assessment of patients’ health and well-being. Facial expression recognition (FER) plays an important and vital role in health care, providing communication with a patient’s feelings and allowing the assessment and monitoring of mental and physical health conditions. This paper shows that automatic machine learning methods can predict health deterioration accurately and robustly, independent of human subjective assessment. The prior work of this paper is to discover the early signs of deteriorating health that align with the principles of preventive reactions, improving health outcomes and human survival, and promoting overall health and well-being. Therefore, methods are developed to create a facial database mimicking the underlying muscular structure of the face, whose Action Unit motions can then be transferred to human face images, thus displaying animated expressions of interest. Then, building and developing an automatic system based on convolution neural networks (CNN) and long short-term memory (LSTM) to recognise patterns of facial expressions with a focus on patients at risk of deterioration in hospital wards. This research presents state-of-the-art results on generating and modelling synthetic database and automated deterioration prediction through FEs with 99.89% accuracy. The main contributions to knowledge from this paper can be summarized as (1) the generation of visual datasets mimicking real-life samples of facial expressions indicating health deterioration, (2) improvement of the understanding and communication with patients at risk of deterioration through facial expression analysis, and (3) development of a state-of-the-art model to recognize such facial expressions using a ConvLSTM model.

Performance Analysis on the Safety and Automation System of a Modified Cutting Machine: Repurposing Initiatives

A circular economy is an alternative to the traditional linear economy. The concept reduces waste by recovering resources at the end of a product’s life cycle and repurposing them to reduce environmental impact. The repurposing of machines is a model of production and consumption that involves re-pairing, refurbishing, and recycling to reduce waste. This project aims to improvise and repurpose existing mangosteen peeling machines into another suitable manufacturing process. The designed potato-cutting machine uses the existing conveyor system of a customised mangosteen peeling machine. The cutting mechanism incorporates safety and automation systems using through-beam infrared and capacitive proximity sensors. For the safety system, detecting objects within a range of 2.0 cm to the conveyor region indicates that the machine is unsafe to operate. The system will stop the machine and send audio and visual warnings to notify the users. Based on the trial runs the machine cuts the potato with approximately 1-tenth of the time needed in manual labour. The most significant benefit, however, is the overall savings in production costs, which are more than 85%. This is achieved as the machine re-purposes more than 50% of the components from the existing mangosteen peeling machine, such as sensors, control panel boxes, and PLC system. Consequently, this has helped minimise the overall cost of new equipment while encouraging a circular economy approach to engineering practices.

Determining the Perception Created by Health Warnings on Plain Cigarette Packs with Visual Attention: Eye-Tracking Technique

This study examines the effects of the plain packaging policy implemented in Türkiye, analyzing how different demographic groups perceive health warnings on cigarette packaging. Employing advanced eye-tracking technology, the research identifies distinct visual attention patterns between smokers and non-smokers when exposed to ‘Anxiety’ and ‘Disturbing’ visual cues. Detailed metrics, including fixation counts, durations, and saccade amplitudes, are used to measure and analyze the responses of these groups to the health warnings. The findings reveal that non-smokers significantly focus more on textual warnings, suggesting that text-based elements are more impactful for this group. Conversely, smokers tend to either avoid or become desensitized to disturbing imagery. Additionally, the study finds that female participants exhibit higher saccade amplitudes compared to males, indicating a more thorough examination of the packaging. This gender-specific difference is especially pronounced in their responses to ‘Disturbing’ images, where females show greater engagement, pointing to an increased sensitivity to such stimuli. These insights not only advance our understanding of effective health communication but also underscore the importance of designing public health interventions that cater to the unique responses of different demographic groups. This research significantly enriches the field of tobacco control, providing evidence-based strategies to enhance the effectiveness of visual warnings, thereby supporting targeted smoking cessation efforts.

Behind the yellow sticker: paradoxical effects of a visual warning of body-worn cameras on the use of police force

Abstract Objectives Research on police body-worn cameras (BWCs) draws attention to the need for suspects to be aware of the devices for them to exert a deterrent, “civilising effect”, which can manifest as a reduction in the use of force in police-public interactions. This awareness can be manipulated audibly, visually, or both, yet no trials exist to test a visual stimulus that increases awareness of BWCs relative to BWCs without this function. In this field experiment, we test the effect of a visual warning of BWCs on use-of-force incidence. Methods A six-month cluster-randomised controlled trial involving spatiotemporal police units was conducted in Miami Beach, USA. The units were randomly assigned to the experimental group, which included officers who wore BWCs featuring multiple yellow stickers and “VIDEO & AUDIO” logo (used as a visual warning). Officers in the control group were equipped with BWCs without yellow stickers. Neither group was required to announce the presence of the BWCs, thus isolating the visual warning from the audial warning. Poisson regression models estimate the treatment effect, with confirmatory subgroup analyses based on the proactive versus reactive interactions. Results Statistically significant differences in the use of force by officers, but in the contrary direction: higher rate of use of force due to equipping officers with BWCs with yellow stickers relative to BWCs without the yellow stickers. Relative change analysis indicates that yellow stickers cause an increase in the rate of use of force in incidents involving proactive policing, with a less pronounced increase in reactive policing. Conclusion Without contextualising their use to citizens, raising awareness of the presence of BWCs can aggravate police-public encounters.

Using Eye-Tracking to Measure Worker Situation Awareness in Augmented Reality

Augmented Reality (AR) technology has emerged as a promising tool for enhancing safety in the construction industry by improving the Situation Awareness (SA) of onsite workers. However, there is a lack of methods to quantify the impact of real-time AR visual warnings on developing and updating SA. To address this gap, this paper presents an eye-tracking-based method that quantifies the impact using three metrics: Time to First Fixation (TFF), Dwell Time (DT), and Revisit Interval (RI). A quasi-onsite experiment validated the feasibility of the proposed method and confirmed that AR warnings could reduce the time to reach Level 1 SA by 40.7% and reduce the interval for updating Level 2 and Level 3 SA by 43.45%. This method can be further combined with advanced visualisation measures to address perception, memory, thinking and mobility, eventually leading to insights on mental effort, decision making, interaction with computers, human reliability and work stress.

Tunable thermoresponsive hydrogels for temperature regulation and warning in fruit and vegetables preservation

Fresh fruit and vegetables usually suffer from quality deterioration when exposed to inappropriate temperatures. Common energy-input temperature regulation is widely applied but there remain challenges of increasing energy consumption. Passive temperature management regulates the heat transfer without energy consumption, showing a sustainable strategy for food preservation. Here, thermoresponsive hydrogels were constructed by incorporating NaCl and sodium dodecyl sulfate (SDS) micelles into a poly(N-isopropylacrylamide-co-acrylamide) (P(NIPAM-co-AM)) network. Due to the excellent mechanical properties and reversible thermochromism at 14 °C and 37 °C, Gel-8 wt%-NaCl could inhibit temperature rise and avoid sunburn damage to peppers under direct sunlight by blocking the input of solar energy and accelerating moisture evaporation. Additionally, hydrogels could act as a feasible sensor by providing real-time visual warnings for inappropriate temperatures during banana storage. Based on the self-adaptive thermoresponsive behaviour, the prepared hydrogels showed effective performance of temperature regulation and quality preservation of fruit and vegetables.

Alcohol Detection and Over-Speed Alert System for Vehicles

Road accidents stemming from alcohol impairment and over-speeding remain critical global issues, necessitating proactive safety measures. To address these challenges, we present an integrated system combining alcohol detection and over-speed alert functionalities for vehicles. Leveraging advanced sensor technologies and real-time data processing, the system detects alcohol presence via breath or touch-based sensors and triggers visual and audible warnings upon exceeding permissible limits, thus deterring drunk driving. Simultaneously, GPS and vehicle speed sensors monitor real-time speed, activating alerts when predefined thresholds are surpassed to caution against over-speeding. Through synergistic integration, this system offers comprehensive safety measures, evaluated through simulations and real-world testing to demonstrate effectiveness in reducing accidents caused by alcohol impairment and over-speeding, thereby contributing to a safer transportation ecosystem. Keywords: alcohol detection, integrated system, over-speed alert, road safety.

Impact of warning labels on sugary beverages on risk perception, attention, and purchase intentions

The issue of warning labels on sweet beverage product packaging needs to be tested to determine its role in reducing product consumption. This study aims to examine the impact of warning labels on attention, risk perception, and purchase intention for sweet drink products. The paper conducted an experiment involving 120 participants. Most respondents fall within the age range of 25 to 34 years (38.30%). The analysis was conducted at sports facilities, schools, and playgrounds – in three major cities in Indonesia (Jakarta, Bandung and Surabaya). Two stimuli, sugar content labels and visual warning labels, were used after a pilot study. For data analysis, the study used univariate analysis of variance to assess the significance of each label stimulus interaction. Furthermore, this paper employed t-tests to check the significance of comparisons between cells. Through the difference test, the three hypotheses were accepted and had a significant effect. The findings reveal that the influence of visual warning labels on attention (t-value = 66.015), perceived risk (t-value = 68.064), and purchase intention (t-value = 60.483) is more significant than sugar content labels. These findings can serve as a set of innovative policies to support the success of demarketing strategies for sweet beverage products by governments and social marketing activists.

A self-healing and recyclable polyurethane composite film for durable pH responsive coating

A self-healing and recyclable polyurethane composite film for durable pH responsive coating