Blink Research Articles

Evaluation of mechanomyogram efficacy as a tool for assessing paired-pulse inhibition of blink reflex early R1 component.

Paired-pulse stimulation provides clinically useful information regarding sensory inhibition. When supraorbital nerve stimulation is repeated within a short interval, the response to the second stimulation is reduced to varying degrees. This magnitude of change in stimulation response can be monitored by electromyogram (EMG) or by mechanomyogram (MMG) as in this report. MMG has some advantages such as being less time consuming and lacking stimulus artifact. We compared the use of MMG and EMG to validate MMG as an effective method of assessing blink reflex paired-pulse inhibition. Eight volunteers participated. Participants received electrical stimulation to the supraorbital nerve of each side. A paired-pulse paradigm was employed, varying the conditioning-test interval between 5 and 800 ms. The R1 component of the induced blink reflex was simultaneously recorded by EMG using a pair of electrodes placed on the lower eyelid and by MMG using an accelerometer placed between the electrodes. The correlation coefficient of the R1 amplitude between MMG and EMG of the grand-averaged waveforms was 0.99. The average participant r value was .91 (range .76-.99). Similar analyses were performed for the amplitude variation of the second response relative to the first response. Results correlated well, yielding r values of .97 and .86 for the grand-averaged waveform and the average for each subject. The present results demonstrate that MMG could be an alternative to EMG in assessing paired-pulse inhibition of the electrical blink reflex R1 component.

Design of a LabVIEW-Based Virtual Instrument for the Disabled

The eye is a prominent organ with complex functions that play a crucial role in our daily lives. The ability to perceive objects from varying distances and angles is vital for navigation, interaction, and understanding the world around us. The coordination of multiple muscles to move the eye allows us to focus on specific points of interest and gather visual information effectively. The concept of using the electrical signals generated by eye movements, known as the electrooculogram (EOG), has been studied in this research. EOG signals can be captured by placing electrodes around the eyes and measuring the potential differences generated as the eyes move. It was noted that a limited number of studies were carried out on EOG-based designs. However, continued research and development in this area have the potential to enhance the quality of life for individuals with disabilities and contribute to our understanding of both the visual system and human-computer interaction. This paper focuses on addressing the relatively underexplored areas of vertical and horizontal eye movements, as well as eye blinking, in the context of electrooculogram (EOG)-based designs. In this research, sharp EOG signals were observed in different eye movement patterns, and those signals were utilized to control assistive devices for individuals with mobility impairments with the LabVIEW software interface.

Sensor Based Shopping using Eye-Blink and IoT Technology

The proposed research is an innovative system designed to enhance the shopping experience for physically challenged individuals. The system makes use of relay motors, LCD displays, and Arduino-based eye-blink sensors to provide a user-friendly interface that enables people with physical limitations to explore and engage with shopping environments. Additionally, IoT is used for user interaction. The main functionality of the system is based on eye-blink technology. By detecting eye blinks, the sensors interpret user commands, enabling individuals to control shopping cart movement, and select items from shelves.

Influential Signs of Dry Eye-Related Ocular Symptoms in Participants With Unstable Tear Film.

The aim of this study was to investigate the factors influencing dry eye disease (DED)-related ocular symptoms in participants with short fluorescein tear break-up time (FTBUT). This cross-sectional study included 82 participants with short FTBUT (<10 seconds). Examinations included Ocular Surface Disease Index (OSDI), FTBUT, average noninvasive tear break-up time (NIBUTave), lid wiper epitheliopathy, lipid layer thickness, blink rate, partial blink, tear meniscus height, and meibomian gland (MG) evaluation which included ratio of residual MG area (RMGA) and MG grade in tarsal plates. One-way analysis of variance was used to detect differences between symptomatic tear film instability group (FTBUT <5 s, OSDI ≥13), asymptomatic tear film instability group (FTBUT <5 s, OSDI <13), and control group (FTBUT ≥5 s, OSDI <13). A bivariate correlation, partial correlation, and multiple linear regression analyses were used to identify major factors. Only the right eye was included. Among the participants with FTBUT <5 seconds, symptomatic group showed less upper RMGA ( P < 0.001) and NIBUTave ( P = 0.010). OSDI was negatively associated with upper RMGA ( r = -0.450, P < 0.001) and NIBUTave ( r = -0.414, P = 0.001), and positively associated with upper MG grade ( r = 0.277, P = 0.027). Linear regression analysis showed that the upper RMGA significantly affected OSDI (B = -41.895, P = 0.001), while not significantly correlated with age, upper MG grade, and NIBUTave. The upper RMGA might be the main factor affecting DED-related discomfort in participants with unstable tear film, indicating an early ocular change in DED.

The Effect of Ambient Illumination and Text Color on Visual Fatigue under Negative Polarity.

This study investigates the effects of ambient illumination and negatively polarized text color on visual fatigue, exploring the issue of visual fatigue when using visual display terminals in low-illumination environments. The research methodology utilizes an experimental design to collect data on changes in pupil accommodation and blink rate through an eye tracker. Participants completed a reading task while exposed to various text colors and ambient light conditions to evaluate visual fatigue and cognitive performance. The study's findings suggest that text color significantly affects visual fatigue, with red text causing the highest level of visual fatigue and yellow text causing the lowest level of visual fatigue. Improvements in ambient lighting reduce visual fatigue, but the degree of improvement varies depending on the text color. Additionally, cognitive performance is better when using yellow and white text but worse when using red text. Yellow text is the most effective choice for reducing visual fatigue under negative polarity. Increasing ambient lighting can also improve visual fatigue in low-illumination conditions. These findings will offer valuable guidance for designing visual terminal device interfaces, especially for low-illumination or night environments, to minimize visual fatigue and improve user experience.

Arousal, interindividual differences and temporal binding a psychophysiological study

The sense of agency varies as a function of arousal in negative emotional contexts. As yet, it is unknown whether the same is true for positive affect, and how inter-individual characteristics might predict these effects. Temporal binding, an implicit measure of the sense of agency, was measured in 59 participants before and after watching either an emotionally neutral film clip or a positive film clip with high or low arousal. Analyses included participants’ individual differences in subjective affective ratings, physiological arousal (pupillometry, skin conductance, heart rate), striatal dopamine levels via eye blink rates, and psychopathy. Linear mixed models showed that sexual arousal decreased temporal binding whereas calm pleasure had no facilitation effect on binding. Striatal dopamine levels were positively linked whereas subjective and physiological arousal may be negatively associated with binding towards actions. Psychopathic traits reduced the effect of high arousal on binding towards actions. These results provide evidence that individual differences influence the extent to which the temporal binding is affected by high arousing states with positive valence.

EYE-BLINK DETECTION ASSISTIVE SYSTEM FOR PARALYZED PATIENT

Paralysis is defined as the complete loss of muscle function in any part of the body. It occurs when there is a problem with the passage of messages between the muscles and the brain. Some paralyzed people cannot move even a single part of the body other than their eyes. Hence, the main aim of this project is to design a real time interactive system that can assist the paralyzed to control appliances such as lights, fans or by playing pre-recorded audio messages, through a predefined number of eye blinks. Image processing techniques have been implemented in order to detect the eye blinks. In our system, the face tracking is accomplished by using a set of trained Haar cascade classifier, and a template matching technique is employed to track the eye. Initially, the involuntary blinks of the paralyzed person are used to locate the patients eyes by finding the number of connected components in a frame.

High-speed eye tracking based on a synchronized imaging mechanism by a dual-ring infrared lighting source

It is a challenge for conventional monocular-camera single-light source eye-tracking methods to achieve high-speed eye tracking. In this work, a dual-ring infrared lighting source was designed to achieve bright and dark pupils in high speed. The eye-tracking method used a dual-ring infrared lighting source and synchronized triggers for the even and odd camera frames to capture bright and dark pupils. A pupillary corneal reflex was calculated by the center coordinates of the Purkinje spot and the pupil. A map function was established to map the relationship between the pupillary corneal reflex and gaze spots. The gaze coordinate was calculated based on the mapping function. The average detection time of each gaze spot was 3.76 ms.

Combination of PEGylation and Cationization on Phospholipid-Coated Cyclosporine Nanosuspensions for Enhanced Ocular Drug Delivery.

Strong precorneal clearance mechanisms including reflex blink, constant tear drainage, and rapid mucus turnover constitute great challenges for eye drops for effective drug delivery to the ocular epithelium. In this study, cyclosporine A (CsA) for the treatment of dry eye disease (DED) was selected as the model drug. Two strategies, PEGylation for mucus penetration and cationization for potent cellular uptake, were combined to construct a novel CsA nanosuspension (NS@lipid-PEG/CKC) by coating nanoscale drug particles with a mixture of lipids, DSPE-PEG2000, and a cationic surfactant, cetalkonium chloride (CKC). NS@lipid-PEG/CKC with the mean size ∼173 nm and positive zeta potential ∼+40 mV showed promoted mucus penetration, good cytocompatibility, more cellular uptake, and prolonged precorneal retention without obvious ocular irritation. More importantly, NS@lipid-PEG/CKC recovered tear production and goblet cell density more efficiently than the commercial cationic nanoemulsion on a dry eye disease rat model. All results indicated that a combination of PEGylation and cationization might provide a promising strategy to coordinate mucus penetration and cellular uptake for enhanced drug delivery to the ocular epithelium for nanomedicine-based eye drops.

Normative values of the nociceptive blink reflex habituation

Introduction: Habituation is a physiological phenomenon, characterized by response reduction to repeated stimulus presentation. In headache disorders, habituation studies have involved different paradigms with several stimulation parameters and sensory modalities, and consistently showed impaired habituation in primary headaches in the interictal phase. The nociceptive blink reflex (nBR) and its related R2 response, modulated by a polysynaptic network in the trigeminocervical complex, is one of the most studied in the field. The lack of nBR habituation normative data hampered the possibility to draw conclusions regarding the functional status of individual patients. The present study aims to define normative values for the nBR habituation process in healthy subjects without a personal diagnosis and family history of migraine, or other headache disorders.Methods: We enrolled 40 healthy subjects (24 females, 32.7±11.6 years) for nBR recording and nBR habituation assessment. To assess the habituation of nBR, 26 consecutive stimuli were administered at three different and randomized stimulus frequencies (0.2, 0.3, 0.5 Hz). After excluding the first response, the remaining 25 area under the curve (AUC) were divided in 5 blocks, and the average values of the AUC was calculated for each block. The percentage reduction in the AUC of the fifth block, compared to the first, represents the habituation index (HI) value. We considered a one-tailed 10th percentile threshold as the lower threshold of normative values for nBR HI.Results: The habituation phenomenon was confirmed for all study frequencies. The absolute AUC of the R2 component across the five blocks of stimulation was higher in female subjects when compared to male for 0.5 Hz (p=0.021) and 0.2 Hz (p=0.007). We found a frequency-dependent habituation pattern, being lower at the 0.2 Hz stimulation when compared to 0.5 Hz (p=0.001), and 0.3 Hz (p=0.008). The average HIs were 73.1±13.6 at 0.5 Hz, 69.2±15.0 at 0.3 Hz, and 61.1±21.4 at 0.2 Hz. HIs were comparable between male and female subjects, without correlations with age, intensity of stimulation, and latency of the R2 component. The 10th percentile of the HIs was 43.5% for 0.5 Hz, 55.8% for 0.3 Hz, and 28.6% for 0.2 Hz.Conclusions: We investigated the nBR habituation in a population of healthy subjects for normative data collection. We described a frequency- dependent degree of habituation, being more pronounced at higher frequencies of stimulation. Moreover, we described gender-related features of response behaviour, which is extremely important in the migraine field. Our study further characterized the physiological habituation phenomenon in healthy controls exposed to a nociceptive stimulation. The definition of a normative habituation value will open novel possibilities in the study of migraine, as well as other headache and pain disorders.

Analysis of Factors Associated with Anterior Location of Marx’s Line

Purpose The study aimed to investigate the factors associated with anterior location of Marx’s line in ocular surface and living habits, especially in tear film. Materials and methods This cross-sectional study enlisted 483 participants with meibomian gland dysfunction, who were divided into two groups: 160 participants with mild anterior location of Marx’s line and 323 participants with moderate-to-severe anterior location. Participants completed a survey of demographic characteristics (sex, age, length of visual terminal use, sleep duration, skin property), and the Ocular Surface Disease Index and Standard Patient Evaluation of Eye Dryness questionnaires. They also underwent slit-lamp examinations of the lids, and measurements of non-invasive tear break up time, tear meniscus height, fluorescein tear break up time, lipid layer thickness, partial blink rate, lid wiper epitheliopathy, and meibomian gland dropout. Results The tear meniscus height (mild:0.21(0.18–0.25), moderate-to-severe:0.19(0.16–0.23), p = 0.004), fluorescein tear break up time(mild:3(2–4),moderate to severe:2(1–3), p = 0.000), max LLT(mild:87(62–100), moderate-to-severe:99(69–100), p = 0.04), average LLT(mild:64.5(47.5–96.75), moderate-to-severe:74(53–100), p = 0.012), min LLT(mild:52(38–75), moderate-to-severe:59(41–85), p = 0.029) differed significantly between mild and moderate-to-severe anterior location of Marx’s line, and associated to the anterior location of Marx’s line(r=-0.134, p = 0.03; r=-0.194, p = 0.000; r = 0.093, p = 0.041; r = 0.119, p = 0.009; r = 0.105, p = 0.022) However, no statistical significance was observed in the OSDI, SPEED, partial blink rate, non-invasive tear breakup time, lipid layer thickness, meibomian gland dropout and lid wiper epitheliopathy(p > 0.05). Meanwhile, in the demographic characteristics, statistically significant correlations were associated with skin property(r = 0.154, p = 0.001) and sleep duration(r=-0.124, p = 0.006), but not with age, sex, and the length of visual terminal use (p > 0.05). Conclusions Lower TMH and shorter TBUT positively correlated with anterior location of the Marx’s line, and were risk factors. Meanwhile, participants with oily skin and shorter sleep duration were more likely to exhibit anterior location of Marx’s line.

Feeding behaviour related to different feeding devices.

Slow feeding devices (SFDs) are useful tools in order to improve the horse well-being and to reduce wastage, but their use may result in unnatural posture during feeding and frustration behaviours. Moreover, it may be important to evaluate the laterality during feeding. The aim of the study was to investigate ponies' feeding behaviour (i.e., lateralisation, frustration, postural eating style) with different hay feeding methods: on the ground (G), a fully filled hay net (HF), a partially filled hay net (HL), and a slow feeder hay box (HB). Nine ponies of two different breed types (Shetland and Welsh/Cob) were evaluated. Video recordings were obtained and then behavioural analysis was conducted. Data were analysed statistically using k-means cluster analysis, repeated measurement mixed model procedure, principal component analysis (PCA) and Pearson's correlation coefficient. Head tilting was more often performed during feeding from HF and HL compared to G and HB. Forelimb forward, referring to the position that ponies assumed during feeding, was performed less frequently with the hay nets. Ponies, in particular Welsh/Cobs, tended to be more left-lateralized and performed more backward ears when feeding from the hay nets. Blink rate was observed to be greater when ponies were fed from G. No head pushing, striking with forelimb and pawing while feeding was seen. Animals fed from HF tended to eat from the top of the hay net and consequently showed an arched neck; while HL and HB showed for elongated neck an intermediate pattern between G and HF. From our results, HB seemed to be a useful compromise between natural feeding on the ground and the use of hay nets.

Utility and Prognostic Value of Intraoperative Blink Reflex in Trigeminal or Facial Nerve Monitoring in Skull Base Surgeries: A Systematic Review

Blink reflex (BR) is an oligosynaptic reflex that involves the ophthalmic branch of the trigeminal nerve (TN), ipsilateral main sensory and trigeminospinal nuclei, bilateral facial nuclei, and the facial nerves (FNs). Theoretically, as BR tests the function of both TN and FNs simultaneously, it is an ideal tool for monitoring the status of TN and FNs during skull base surgeries. Nevertheless, it has been used only recently in surgeries as the use of anesthesia limits its use. For this systematic review, 2 authors input the search terms [(Blink Reflex) AND (Intraoperative Neuromonitoring OR Neuro Intraoperative Monitoring OR Intraoperative OR NIOM OR IONM) AND (skull base surgery OR Facial Nerve OR Trigeminal Nerve OR Microvascular Decompression OR Hemifacial Spasm)] in MEDLINE through its PubMed interface and other search engines. Articles that fulfilled the inclusion and exclusion criteria were obtained and scrutinized. Seven observational articles with a total of 437 participants were included. All 5 studies that described the use of BR in FN surgery noted that intraoperative BR is beneficial, safe, sensitive, specific, and predictive of outcomes, while 2 articles describing patients with trigeminal neuralgia recommended use of BR in microvascular decompression of TN. Intraoperative BR is a sensitive, specific, and safe monitoring technique that has good predictability of facial paresis and paresthesia among patients undergoing MVD for trigeminal neuralgia and primary hemifacial spasm and patients undergoing cerebellopontine angle tumor resection.

Optimization of Wheelchair Control via Multi-Modal Integration: Combining Webcam and EEG

Even though Electric Powered Wheelchairs (EPWs) are a useful tool for meeting the needs of people with disabilities, some disabled people find it difficult to use regular EPWs that are joystick-controlled. Smart wheelchairs that use Brain–Computer Interface (BCI) technology present an efficient solution to this problem. This article presents a cutting-edge intelligent control wheelchair that is intended to improve user involvement and security. The suggested method combines facial expression analysis via a camera with EEG signal processing using the EMOTIV Insight EEG dataset. The system generates control commands by identifying specific EEG patterns linked to facial expressions such as eye blinking, winking left and right, and smiling. Simultaneously, the system uses computer vision algorithms and inertial measurements to analyze gaze direction in order to establish the user’s intended steering. The outcomes of the experiments prove that the proposed system is reliable and efficient in meeting the various requirements of people, presenting a positive development in the field of smart wheelchair technology.

Compatibility of eugenol anesthesia with classroom physiology experiments on nerve and muscle of frogs

Frogs serve as valuable model organisms for studying physiological responses of nerve, skeletal muscle and the heart in undergraduate biology labs. Heretofore, induced hypothermia has been the preferred technique for pain and stress reduction prior to euthanasia by pithing. However, AVMA guidelines discourage hypothermia for restraint or euthanasia of amphibians and advocate anesthetic overdose as preferable to pithing alone. Unfortunately, the primary anesthetic used in fish and other aquatic invertebrates, MS-222, blocks normal nerve and muscle function in leopard frogs and renders them useless for classroom physiology experiments, as demonstrated by Medler (2019). Eugenol is a safe and affordable anesthetic that is effective in amphibians. We sought to test the hypothesis that eugenol anesthesia is compatible with classroom nerve and muscle experiments on frogs. Bullfrogs and leopard frogs were immersed in a bath of eugenol suspended in tap water at 275 to 350 mg/L. At various time points, a four step reflex test was performed including tests of righting response, superficial pain reflex, deep pain reflex, and corneal blink reflex. Once all reflexes were absent, the frog was euthanized by pithing and the gastrocnemius muscle was prepared for force recordings. The sciatic nerve was stimulated with a bipolar stimulating electrode while gastrocnemius force was measured using an isometric force transducer. The threshold voltage eliciting a muscle contraction and the peak isometric twitch force were recorded at 15 minute intervals for 2 hours. Control frogs were sedated by immersion in ice water for 20 to 30 minutes, pithed when reflexes were substantially weakened, and then subjected to the same stimulation protocol and force measurements. At these doses, eugenol reliably induces loss of reflexes in 20 to 35 minutes and neuromuscular preparations maintain the ability to respond to electrical stimulation. Preliminary results suggest that eugenol may produce a modest elevation of threshold voltage and a modest reduction in maximum twitch force compared to control frogs euthanized without chemical anesthesia. Eugenol may be an effective anesthetic to prepare bullfrogs and leopard frogs for classroom experiments on nerve and muscle. Funding was provided by the Bill and Linda Frost Fund. This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Swift-Eye: Towards Anti-blink Pupil Tracking for Precise and Robust High-Frequency Near-Eye Movement Analysis with Event Cameras.

Eye tracking has shown great promise in many scientific fields and daily applications, ranging from the early detection of mental health disorders to foveated rendering in virtual reality (VR). These applications all call for a robust system for high-frequency near-eye movement sensing and analysis in high precision, which cannot be guaranteed by the existing eye tracking solutions with CCD/CMOS cameras. To bridge the gap, in this paper, we propose Swift-Eye, an offline precise and robust pupil estimation and tracking framework to support high-frequency near-eye movement analysis, especially when the pupil region is partially occluded. Swift-Eye is built upon the emerging event cameras to capture the high-speed movement of eyes in high temporal resolution. Then, a series of bespoke components are designed to generate high-quality near-eye movement video at a high frame rate over kilohertz and deal with the occlusion over the pupil caused by involuntary eye blinks. According to our extensive evaluations on EV-Eye, a large-scale public dataset for eye tracking using event cameras, Swift-Eye shows high robustness against significant occlusion. It can improve the IoU and F1-score of the pupil estimation by 20% and 12.5% respectively, compared with the second-best competing approach, when over 80% of the pupil region is occluded by the eyelid. Lastly, it provides continuous and smooth traces of pupils in extremely high temporal resolution and can support high-frequency eye movement analysis and a number of potential applications, such as mental health diagnosis, behaviour-brain association, etc. The implementation details and source codes can be found at https://github.com/ztysdu/Swift-Eye.

Exploring the health and ocular hazards of gadget usage in optometry students after COVID-19 lockdown: A qualitative study.

Prolonged screen time and abnormal postures can cause backache, neck pain, headache, and finger pain. Studies have shown that excessive usage of gadgets has increased during the coronavirus disease 2019 (COVID-19) pandemic, causing health and ocular hazards. This study used qualitative research methods to understand the health and ocular effects of gadget usage following the COVID-19 postlockdown in optometry students. A qualitative study using a semi-structured face-to-face interview was conducted for undergraduate and postgraduate students in different optometry institutes who underwent at least 3 months of online teaching learning during the pandemic after obtaining informed consent. The interviews were conducted online; the sessions were audio-recorded, transcribed, and analyzed. Thematic analyses were conducted to understand the challenges faced. Twenty participants were interviewed, of which 70% (n = 14) were females. Thematic analysis identified seven major themes: gadget usage (frequency of usage, type of device, and time spent), challenges during online classes (comprehension, distraction, and network issues), ocular effects (asthenopic symptoms and ocular symptoms), health effects (musculoskeletal disorders), ways to relieve symptoms, recreational activities (breaks and entertainment), and environment and ergonomics (posture and study area and preferred lighting). All the participants reported ocular/health-related symptoms, including eye strain, burning sensation, headache, back pain, finger pain, and neck pain post the lockdown period due to prolonged gadget usage and poor ergonomic postures. Given the significant increase in digital usage following the pandemic, the study's findings are currently relevant. The prolonged usage of gadgets and poor ergonomic postures have led to ocular and musculoskeletal problems among optometry students. To improve gadget usage without any health-related consequences, students should have access to information regarding ergonomics, increasing the blink rate, and taking regular digital breaks.

Deep fakes Detection Using Human Eye Blinking Pattern: Deep Vision

Abstract: Deepfake technology is developing rapidly and has the ability to create fake videos that pose a threat to people. Modern depth detection methods often rely on facial disparity, but as technology advances these methods become obsolete. In this study, we propose a new method for deepfake detection based on observation of human eye blink patterns. Human eye blinking is a natural and involuntary action that is difficult to accurately replicate in deepfake video. In our study, we used the unique characteristics of individual blink patterns, which are influenced by many factors such as genetics, muscle tone and unconscious reflexes. We use computer vision and machine learning techniques to extract and identify these patterns from video clips. Our preliminary tests show good results in detecting deepfakes with high accuracy. We are focused on continuing to support the fight against the spread of fraud by focusing on a part of human behaviour that is difficult to replicate. This approach has the potential to improve existing tools for in-depth discovery and increase the overall security and reliability of multimedia content in the digital age. This research opens new avenues for the development of more robust, reliable and flexible deep recognition technologies. This represents a significant step forward in the ongoing fight against malicious misuse of electronic devices.

The effect of processing partial information in dynamic face perception

Face perception is a major topic in vision research. Most previous research has concentrated on (holistic) spatial representations of faces, often with static faces as stimuli. However, faces are highly dynamic stimuli containing important temporal information. How sensitive humans are regarding temporal information in dynamic faces is not well understood. Studies investigating temporal information in dynamic faces usually focus on the processing of emotional expressions. However, faces also contain relevant temporal information without any strong emotional expression. To investigate cues that modulate human sensitivity to temporal order, we utilized muted dynamic neutral face videos in two experiments. We varied the orientation of the faces (upright and inverted) and the presence/absence of eye blinks as partial dynamic cues. Participants viewed short, muted, monochromic videos of models vocalizing a widely known text (National Anthem). Videos were played either forward (in the correct temporal order) or backward. Participants were asked to determine the direction of the temporal order for each video, and (at the end of the experiment) whether they had understood the speech. We found that face orientation, and the presence/absence of an eye blink affected sensitivity, criterion (bias) and reaction time: Overall, sensitivity was higher for upright compared to inverted faces, and in the condition where an eye blink was present compared to the condition without an eye blink. Reaction times were mostly faster in the conditions with higher sensitivity. A bias to report inverted faces as ‘backward’ observed in Experiment I, where upright and inverted faces were presented randomly interleaved within each block, was absent when presenting upright and inverted faces in different blocks in Experiment II. Language comprehension results revealed that there was higher sensitivity when understanding the speech compared to not understanding the speech in both experiments. Taken together, our results showed higher sensitivity with upright compared to inverted faces, suggesting that the perception of dynamic, task-relevant information was superior with the canonical orientation of the faces. Furthermore, partial information coming from eye blinks, in addition to mouth movements, seemed to play a significant role in dynamic face perception, both when faces were presented upright and inverted. We suggest that studying the perception of facial dynamics beyond emotional expressions will help us to better understand the mechanisms underlying the temporal integration of facial information from different -partial and holistic- sources, and that our results show how different strategies, depending on the available information, are employed by human observers when judging the temporal order of faces.

FATIGUE DETECTION OF DRIVERS USING MACHINE LEARNING

In this project, the aim is to develop a prototype drowsiness detection system to address driver fatigue, a major cause of accidents worldwide. The system detects driver drowsiness by monitoring eye blinks and yawning. If the driver's eyes remain closed for an extended period or if yawning is detected, an alarm is sounded. Programming for this system is conducted in OpenCV, utilizing the Haar cascade library for face detection and other machine learning libraries to detect facial features. The system operates in real-time and is nonintrusive, prioritizing driver safety without being obtrusive. By effectively monitoring driver alertness and issuing timely warnings, this system contributes significantly to enhancing road safety. Keywords - Driver fatigue, drowsiness detection, eye blink, yawn detection, OpenCV, Haar cascade, machine learning, facial features.