Eye Region Research Articles

An assessment of dynamic facial emotion recognition and theory of mind in children with ADHD: An eye-tracking study.

Deficits in social cognition in attention deficit hyperactivity disorder (ADHD) have been associated with difficulties in functioning. Since recognizing emotional facial expressions is essential for developing the perceptual components of the theory of mind (ToM), it is important to assess this relationship in children with ADHD. This study therefore compared the recognition of emotional stimuli and gaze patterns between children with ADHD and healthy children using eye-tracking with dynamic facial images. It also examined the relationship between facial emotion recognition accuracy, gaze patterns, ToM scores, and ADHD symptoms. Children with ADHD aged 8-13 (n = 47) and a control group (n = 38) completed a facial emotion recognition test, ToM tests, and the Conners' Parent Rating Scale. Participants' gaze patterns in response to dynamic facial emotion expressions were recorded using eye-tracking technology. Children with ADHD exhibited significantly lower accuracy in the recognition of the facial expressions of disgust and anger. The percentage fixation in the eye region was also significantly lower for happy, angry, sad, disgusted, and neutral emotions in the children with ADHD compared to the control group. No relationship was determined between the percentage of fixations on facial areas of interests and ADHD symptoms or ToM tests. This study provides evidence that children with ADHD experience deficits in visual attention to emotional cues. In addition, it suggests that facial emotion recognition deficits in children with ADHD represent a separate domain of social cognition that develops independently of ToM skills and core symptoms. Understanding and treating the social difficulties of individuals with ADHD may help improve their social functioning.

Rectal temperature and body surface temperature rhythm in Red Sokoto goats infected with <i>Trypanosoma evansi</i> during the rainy season

There are limited studies on circadian rhythmicity in farm animals affected by protozoan diseases. The rectal temperature (RT) and body surface temperature (BST) rhythmic patterns in experimental Trypanosoma evansi-infected Red Sokoto goats (T. evansiinfected RSG) July – September were evaluated. Five goats were assigned to each experimental group, with group I as the negative control (CRSG), while animals in group II were individually infected with about 2.0x106 /2ml T. evansi-inoculum. Temperature reaction patterns were monitored by digital clinical and infrared thermometry. The RT and BST of goats, the ambient temperature (AT) and relative humidity (RH) inside the pen were measured at 06:00, 12:00 and 18:00 hours (GMT+1) three times a week for 12 weeks. The AT had maximum, minimum and mean values of 27.0°C, 24.2°C and 25.6±0.26°C, respectively, while RH had maximum, minimum and mean values of 94.5%, 53.6% and 80.5±11.5%, respectively. Results obtained, via the application of a single Cosinor procedure showed that the RT and BST exhibited daily rhythmicity in both groups with the pattern distorted in T. evansi-infected RSG which showed an ascent from the 5th to the 10th week. The rhythmic characteristic of RT of the T. evansi-infected RSG showed that the mesor and amplitude were higher (p˂0.05) than those recorded for CRSG. Both groups showed no difference (p˃0.05) in acrophase. The eye region in both groups showed the highest BST, while the coronary band had the lowest. The result, for the first time, reported rhythmicity of RT and BST in T. evansi- infected goats under tropical conditions. The results obtained from our study may be useful for the early screening, diagnosis, treatment and prevention of protozoan diseases.

Optical coherence tomography and shear wave elastography findings in Graves ophthalmopathy.

The main feature of Graves ophthalmopathy (GO) is revealed by determining the activity and severity of the disease. We aimed to evaluate the use of imaging methods can also provide additional information about the severity of this disease. Optical coherence tomography (OCT) and shear wave elastography (SWE) findings were compared in 32 patients with mild GO group and in the healthy control group. Measuring for TSH receptor antibody (TRAb) serum level is used third-generation assay. In Graves group, optic nerve sheath diameter (ONSD) values were increased in both eyes (p < 0.001, p < 0.001). SWE measurements showed a significant increase both eye optic nerve (ON) and right eye soft tissue elasticity values in GO group (p < 0.001, p < 0.001, p < 0.001, respectively). There was a significant thinning in left temporal retinal nerve fiber layer (RNFL) thickness and left RNFL peripapillary thickness in GO group (p < 0.001, p < 0.025, respectively). There was a correlation between left eye OCT and SWE findings. Also, there was a significant difference between the median left eye ON and soft tissue elasticity results in the TRAb-positive GO group (p = 0.049, p = 0.048, respectively). SWE measurements showed a significant increase both eyes ONSD, ON and right eye soft tissue elasticity values in GO group. GO group was significant thinning in some left eye regions in OCT measurements. There was a correlation between left eye OCT and SWE findings. In addition to clinical activity score and TRAb, SWE and OCT can be used to monitor in patients with GO.

Shear-Relative Asymmetric Kinematic Characteristics of Intensifying Hurricanes as Observed by Airborne Doppler Radar

Abstract While recent observational studies of intensifying (IN) versus steady-state (SS) hurricanes have noted several differences in their axisymmetric and asymmetric structures, there remain gaps in the characterization of these differences in a fully three-dimensional framework. To address these limitations, this study investigates differences in the shear-relative asymmetric structure between IN and SS hurricanes using airborne Doppler radar data from a dataset covering an extended period of time. Statistics from individual cases show that IN cases are characterized by peak wavenumber-1 ascent concentrated in the upshear-left (USL) quadrant at ∼12-km height, consistent with previous studies. Moderate updrafts (2–6 m s−1) occur more frequently in the downshear eyewall for IN cases than for SS cases, likely leading to a higher frequency of moderate to strong updrafts USL above 9-km height. Composites of IN cases show that low-level outflow from the eye region associated with maximum wavenumber-1 vorticity inside the radius of maximum wind (RMW) in the downshear-left quadrant converges with low-level inflow outside the RMW, forming a stronger local secondary circulation in the downshear eyewall than SS cases. The vigorous eyewall convection of IN cases produces a net vertical mass flux increasing with height up to ∼5 km and then is almost constant up to 10 km, whereas the net vertical mass flux of SS cases decreases with height above 4 km. Strong USL upper-level ascent provides greater potential for the vertical development of the hurricane vortex, which is argued to be favorable for continued intensification in shear environments.

Best low-cost methods for real-time detection of the eye and gaze tracking

Abstract The study of gaze tracking is a significant research area in computer vision. It focuses on real-world applications and the interface between humans and computers. Recently, new eye-tracking applications have boosted the need for low-cost methods. The eye region is a crucial aspect of tracking the direction of the gaze. In this paper, several new methods have been proposed for eye-tracking by using methods to determine the eye area as well as find the direction of gaze. Unmodified webcams can be used for eye-tracking without the need for specialized equipment or software. Two methods for determining the eye region were used: facial landmarks or the Haar cascade technique. Moreover, the direct method, based on the convolutional neural network model, and the engineering method, based on distances determining the iris region, were used to determine the eye’s direction. The paper uses two engineering techniques: drawing perpendicular lines on the iris region to identify the gaze direction junction point and dividing the eye region into five regions, with the blackest region representing the gaze direction. The proposed network model has proven effective in determining the eye’s gaze direction within limited mobility, while engineering methods improve their effectiveness in wide mobility.

Less attention to emotional faces is associated with low empathy and prosociality in 12-to 20-month old infants.

The development of empathy and prosocial behavior begins in infancy and is likely supported by emotion processing skills. The current study explored whether early emerging deficits in emotion processing are associated with disruptions in the development of empathy and prosociality. We investigated this question in a large, diverse sample of 147, 11- to 20-month-old infants (42% female; 61% Black; 67% low socioeconomic status). Infants completed two observational tasks assessing prosocial helping and one task assessing empathy and prosocial comforting behavior. Infants also completed an eye-tracking task assessing engagement and disengagement with negative emotional faces. Infants who attended less to angry, sad, and fearful faces (i.e., by being slower to look at and/or quicker to look away from negative compared to neutral faces) engaged in fewer helping behaviors, and effect sizes were larger when examining infants' attention toward the eye regions of faces. Additionally, infants who were quicker to look away from the eye regions of angry faces, but not the whole face, displayed less empathy and comforting behaviors. Results suggest that as early as 12months of age, infants' decreased attention toward negative emotional faces, particularly the eye regions, is associated with less empathy and prosociality during a developmental period in which these abilities are rapidly maturing.

Hemangiosarcoma conjuntival en una perra: reporte de caso

Hemangiosarcomas are tumors of mesenchymal origin, potentially deleterious, associated with areas of high vascularization. Tumor progression and growth are associated with these tumors’ ability to retain blood and give rise to tortuous blood vessels. They have a vast metastatic capacity, often occurring in organs such as the spleen, liver, and aorta artery. However, other sites may be affected, although less frequently, such as the third eyelid and the conjunctiva and cutaneous regions. This article aims to report the case of an 8-year-old female dog with a history of conjunctival hemangiosarcoma, in the medial region of the left eye, with a hemorrhagic appearance. The animal was submitted to the surgical procedure of enucleation after the involvement of the surgical margins in a previous histopathological examination.

Journey tracker: driver alerting system with a deep learning approach.

Negligence of public transport drivers due to drowsiness poses risks not only to their own lives but also to the lives of passengers. The designed journey tracker system alerts the drivers and activates potential penalties. A custom EfficientNet model architecture, based on EfficientNet design principles, is built and trained using the Media Research Lab (MRL) eye dataset. Reflections in frames are filtered out to ensure accurate detections. A 10 min initial period is utilized to understand the driver's baseline behavior, enhancing the reliability of drowsiness detections. Input from drivers is considered to determine the frame rate for more precise real-time monitoring. Only the eye regions of individual drivers are captured to maintain privacy and ethical standards, fostering driver comfort. Hyperparameter tuning and testing of different activation functions during model training aim to strike a balance between model complexity, performance and computational cost. Obtained an accuracy rate of 95% and results demonstrate that the "swish" activation function outperforms ReLU, sigmoid and tanh activation functions in extracting hierarchical features. Additionally, models trained from scratch exhibit superior performance compared to pretrained models. This system promotes safer public transportation and enhances professionalism by monitoring driver alertness. The system detects closed eyes and performs a cross-reference using personalization data and pupil detection to trigger appropriate alerts and impose penalties.

Fast eye centre localization using combined unsupervised technics

Eye movements offer precious information about persons? state. Video surveillance, marketing, driver fatigue as well as medical diagnosis assistance applications manage eye behavior. We propose a new method for efficiently detecting eye movement. In this paper, we combine circle eye model with eye feature method to improve the accuracy. A set of detectors estimate the eyes centers to increase the localization rate. As a pre-processing stage, the mean of the edges yields the center of the two eye regions. Image treatment operations reduce the ROI. A Circle Hough Transform (CHT) algorithm is adopted in a modified version as a detector to find the circle eye in the image; the circle center found represents the eye's pupil estimation. We introduced the Maximally Stable Extremal Region (MSER) as a second detector, which has never been used for eye localization. Invariant to continuous geometric transformations and affine intensity changes and detected at several scales, MSERs efficiently detect regions of interest, in our case eye regions, and precisely, their centers. Ellipses fit MSERs, and their centroid estimation match eyes center. We demonstrate that the true eye centers can be found by combining these methods. The validation of the proposed method is performed on a very challenging BioID base. The proposed approach compares well with existing state-of-the-art techniques and achieves an accuracy of 82.53% on the BioID database when the normalized error is less than 0.05, without prior knowledge or any learning model.

Assessing silver nanoparticle uptake dynamics in young zebrafish using swept source optical coherence tomography

Understanding the uptake and accumulation of nanoparticles in living organisms is crucial for assessing their potential effects on health and the environment. In this study, we employed a Swept Source Optical Coherence Tomography (SSOCT) system to investigate the dynamics of silver nanoparticle (AgNP) uptake during various developmental stages of zebrafish. Silver nanoparticles in the 20 nm range were synthesized and their uptake and accumulation in developing zebrafish embryos were studied over time. Changes in optical attenuation properties observed in SSOCT images allowed identification of nanoparticle uptake and accumulation in the eye, intestine, and gill region of developing zebrafish. The changes were quantified by deriving average local attenuation coefficient values. To validate our findings, inductively-coupled plasma optical emission spectrometry (ICP-OES) analysis was performed.

Multiple axes of visual system diversity in Ithomiini, an ecologically diverse tribe of mimetic butterflies.

The striking structural variation seen in arthropod visual systems can be explained by the overall quantity and spatio-temporal structure of light within habitats coupled with developmental and physiological constraints. However, little is currently known about how fine-scale variation in visual structures arises across shorter evolutionary and ecological scales. In this study, we characterise patterns of interspecific (between species), intraspecific (between sexes) and intraindividual (between eye regions) variation in the visual system of four ithomiine butterfly species. These species are part of a diverse 26-million-year-old Neotropical radiation where changes in mimetic colouration are associated with fine-scale shifts in ecology, such as microhabitat preference. Using a combination of selection analyses on visual opsin sequences, in vivo ophthalmoscopy, micro-computed tomography (micro-CT), immunohistochemistry, confocal microscopy and neural tracing, we quantify and describe physiological, anatomical and molecular traits involved in visual processing. Using these data, we provide evidence of substantial variation within the visual systems of Ithomiini, including: (i) relaxed selection on visual opsins, perhaps mediated by habitat preference, (ii) interspecific shifts in visual system physiology and anatomy, and (iii) extensive sexual dimorphism, including the complete absence of a butterfly-specific optic neuropil in the males of some species. We conclude that considerable visual system variation can exist within diverse insect radiations, hinting at the evolutionary lability of these systems to rapidly develop specialisations to distinct visual ecologies, with selection acting at the perceptual, processing and molecular level.

Visual scanning of faces with neutral expression in patients with Alzheimer’s disease and amnestic mild cognitive impairment

AbstractBackgroundDeficits in face perception and face processing have been reported in Alzheimer’s disease (AD) (Kawagoe et al., 2017). However, conflicting findings were presented in these functions in amnestic mild cognitive impairment (aMCI) compared to older adults (Lim et al., 2011). This study aimed to examine eye movement patterns during visual scanning of faces with neutral expressions in AD, aMCI, and healthy controls (HC).MethodNinety‐five participants, including 29 patients with AD (mean age 72.5±7.9), 34 patients with aMCI (mean age 70.6±6.7 years), and 32 HC (mean age 68.5±6.2 years) were participated in the study. Eye movements were recorded from the right eye with the EyeLink 1000 Plus video‐based eye tracker. In the face scanning task, neutral face images without emotional expressions produced by artificial intelligence were used. In this task, which consists of a practical trial and 20 trials, each stimulus was shown for 3000 ms. Participants were instructed to examine the neutral face images presented. Number of saccade, fixation counts, mean fixation duration, and first fixation duration were analysed separately on the regions of eyes, mouth, nose, and face.ResultThe mean number of fixation, the number of saccades, and mean fixation duration across the face were significantly reduced in AD patients compared to HC. The mean number of fixation and fixation durations in the eye were significantly reduced in AD compared to HC. No significant difference was observed in all groups in eye movements in the nose and mouth. In addition, aMCI and HC exhibited similar eye movement patterns in the face‐scanning task.ConclusionStudies with healthy individuals have reported typical eye movement patterns focusing primarily on the eyes, but also on the nose and mouth regions. It is stated that the decrease in the gaze towards the face and eye region in AD patients may be related to face processing difficulties. To our knowledge, this is the first study to examine eye movement patterns during neutral face scanning in AD and aMCI.This work was supported by the TUBITAK project number 119S560.

Investigation of barium sulphate shielding during panoramic radiography

BackgroundRadiation shielding in radiology has historically been achieved with lead; however, there has been an increasing demand for radiation shielding to be more environmentally friendly. Barium has shown promise as a substitute in many radiology applications. This study aims to investigate a barium sulphate shield in protecting the thyroid and the eye lens during panoramic radiography.MethodsDuring a simulated panoramic examination, an anthropomorphic phantom and a solid-state detector measured the radiation dose to the surface thyroid and the eye lens. The measurements were taken using no shield and a barium sulphate shield. A Welch's T-test was employed to compute the shield's effect on radiation. Two radiologists assessed the image quality with and without the thyroid shields.ResultsThe dose reduction was between 66 and 75% for the barium shield at the thyroid. The dose reduction ranged between 15 and 61% in the eye region. Images using a barium shield were deemed adequate for diagnostic interpretation.ConclusionsBarium shields effectively reduce the radiation dose in the thyroid region during panoramic radiography without degrading image quality. The dose reduction depends on the tube voltage and the area of interest.

Choriocapillaris and choroidal thickness in all Leber hereditary optic neuropathy stages using swept source technology.

The role of the choroid in Leber hereditary optic neuropathy (LHON) remains unclear. The literature is scarce, with conflicting results and lacks axial length measurements. Therefore, we aimed to analyse the choriocapillaris (CC) vessel density (VD) and choroidal thickness (ChT) in all stages of LHON using swept source (SS) technology and considering the possible influence of axial length on choroidal parameters. This was a prospective cross-sectional observational study. A total of 119 eyes of 60 patients with molecularly confirmed LHON across all stages and 120 eyes of 60 control participants were included. We obtained the CC VD using optical coherence tomography angiography maps centred on the fovea. ChT was measured from the Bruch's membrane to the choroid-sclera interface in the macular and peripapillary regions. The CC VD was not significantly affected in any sector or average, except for a slight change in the superior region of chronic eyes (52.08 ± 1.62% vs. 53.50 ± 2.29%, p = 0.002). ChT demonstrated a trend towards decreased values in asymptomatic eyes and increased values in the symptomatic stages that failed to reach statistical significance in sectors corresponding to the papillomacular bundle except for the macular nasal inner sector of chronic eyes (281.10 ± 67.12 μm vs. 252.08 ± 70.55 μm, p = 0.045). No significant correlations were observed between visual acuity and CC VD or ChT. The CC VD remained stable across the LHON stages. Choroidal vasculature does not appear to play a role in LHON pathophysiology. Further research is needed on ChT as a potential biomarker of LHON.

FPGA-Based CNN for Eye Detection in an Iris Recognition at a Distance System

Neural networks are the state-of-the-art solution to image-processing tasks. Some of these neural networks are relatively simple, but the popular convolutional neural networks (CNNs) can consist of hundreds of layers. Unfortunately, the excellent recognition accuracy of CNNs comes at the cost of very high computational complexity, and one of the current challenges is managing the power, delay and physical size limitations of hardware solutions dedicated to accelerating their inference process. In this paper, we describe the embedding of an eye detection system on a Zynq XCZU4EV UltraScale+ multiprocessor system-on-chip (MPSoC). This eye detector is used in the application framework of a remote iris recognition system, which requires high resolution images captured at high speed as input. Given the high rate of eye regions detected per second, it is also important that the detector only provides as output images eyes that are in focus, discarding all those seriously affected by defocus blur. In this proposal, the network will be trained only with correctly focused eye images to assess whether it can differentiate this pattern from that associated with the out-of-focus eye image. Exploiting the neural network’s advantage of being able to work with multi-channel input, the inputs to the CNN will be the grey level image and a high-pass filtered version, typically used to determine whether the iris is in focus or not. The complete system synthetises other cores and implements CNN using the so-called Deep Learning Processor Unit (DPU), the intellectual property (IP) block released by AMD/Xilinx. Compared to previous hardware designs for implementing FPGA-based CNNs, the DPU IP supports extensive deep learning core functions, and developers can leverage DPUs to conveniently accelerate CNN inference. Experimental validation has been successfully addressed in a real-world scenario working with walking subjects, demonstrating that it is possible to detect only eye images that are in focus. This prototype module includes a CMOS digital image sensor that provides 16 Mpixel images, and outputs a stream of detected eyes as 640 × 480 images. The module correctly discards up to 95% of the eyes present in the input images as not being correctly focused.

Vascular abnormalities in fellow eyes of patients with unilateral coats’ disease

Coats’ disease is an idiopathic retinal vascular disorder, known to usually occur unilaterally; however, recent studies have highlighted vascular abnormalities in the fellow unaffected eyes. This retrospective study investigated the peripheral vascular features and macular vascular structure of unaffected fellow eyes in patients with unilateral Coats’ disease using multimodal imaging tools. We analysed images of patients, including bilateral ultra-widefield imaging, fluorescein angiography (FA), ultra-widefield FA, or standard fundus photography. Available bilateral optical coherence tomography angiography (OCT-A) images were used for macular vascular structure analysis. OCT-A parameters, including foveal avascular zone (FAZ), perfusion index, and vessel density (VD) in the superficial and deep capillary plexuses (SCP, DCP), were calculated using Image J software. The mean age at diagnosis was 34.5 ± 17.9 years. The mean final best-corrected visual acuity of the affected eyes was logMAR 0.78 ± 0.79, while that of the fellow eyes was logMAR 0.04 ± 0.12. Ten fellow eyes had microaneurysms (47.6%), two had tortuous vessel abnormalities (9.5%), and 11(52.4%) had abnormal vascular findings on FA. Although there was a trend towards larger DCP FAZ (1.201 ± 0.086 vs. 1.072 ± 0.226), and lower DCP VD (8.593 ± 1.583 vs. 10.827 ± 3.392) in the affected eyes as measured by the Cirrus machine, the difference was not statistically significant between affected and fellow eyes when measured using the Zeiss Cirrus machine (P = 0.686, P = 0.343, respectively). However, when measured with the Spectralis machine, DCP FAZ was larger in affected eyes (0.828 ± 0.426 vs. 0.254 ± 0.092, P = 0.002) and DCP VD was lower in affected eyes (6.901 ± 2.634 vs. 17.451 ± 7.207, P = 0.002) compared to the fellow eyes, while other parameters showed no significant variations. These findings indicate that there may be subtle vascular abnormalities primarily located in the peripheral regions of the unaffected fellow eyes in patients with unilateral Coats’ disease, while the macular microvasculature remains unaffected.

Segmental biomechanics of the normal and glaucomatous human aqueous outflow pathway

The conventional aqueous outflow pathway, encompassing the trabecular meshwork (TM), juxtacanalicular connective tissue (JCT), and inner wall endothelium of Schlemm's canal (SC), governs intraocular pressure (IOP) regulation. This study targets the biomechanics of low-flow (LF) and high-flow (HF) regions within the aqueous humor outflow pathway in normal and glaucomatous human donor eyes, using a combined experimental and computational approach. LF and HF TM/JCT/SC complex tissues from normal and glaucomatous eyes underwent uniaxial tensile testing. Dynamic motion of the TM/JCT/SC complex was recorded using customized green-light optical coherence tomography during SC pressurization in cannulated anterior segment wedges. A hyperviscoelastic model quantified TM/JCT/SC complex properties. A fluid-structure interaction model simulated tissue-aqueous humor interaction. FluoSpheres were introduced into the pathway via negative pressure in the SC, with their motion tracked using two-photon excitation microscopy. Tensile test results revealed that the elastic moduli of the LF and HF regions in glaucomatous eyes are 3.5- and 1.5-fold stiffer than the normal eyes, respectively. The FE results also showed significantly larger shear moduli in the TM, JCT, and SC of the glaucomatous eyes compared to the normal subjects. The LF regions in normal eyes demonstrated larger elastic moduli compared to the HF regions in glaucomatous eyes. The resultant strain in the outflow tissues and velocity of the aqueous humor in the FSI models were in good agreement with the digital volume correlation and 3D particle image velocimetry data, respectively. This study uncovers stiffer biomechanical responses in glaucomatous eyes, with LF regions stiffer than HF regions in both normal and glaucomatous eyes. Statement of significanceThis study delves into the biomechanics of the conventional aqueous outflow pathway, a crucial regulator of intraocular pressure and ocular health. By analyzing mechanical differences in low-flow and high-flow regions of normal and glaucomatous eyes, this research unveils the stiffer response in glaucomatous eyes. The distinction between regions' properties offers insights into aqueous humor outflow regulation, while the integration of experimental and computational methods enhances credibility. These findings have potential implications for disease management and present a vital step toward innovative ophthalmic interventions. This study advances our understanding of glaucoma's biomechanical basis and its broader impact on ocular health.

Numerical Investigations and Artificial Neural Network-Based Performance Prediction of a Centrifugal Fan Having Innovative Hub Geometry Designs

It is a well-known fact that air approaches the eye region of the rotating impeller of a centrifugal fan with shock-less entry conditions in an ideal scenario. The flow in this region is associated with induced swirl losses, leading to cumulative performance losses. Proper flow guidance in the vicinity of the eye region is essential to minimize possible flow losses. The flow guiding structure may be in the form of a projection or extrusion connected to the rotating impeller of the turbo machines and is generally named a hub. These attachments enhance the overall flow augmentation of the turbo machines in terms of static pressure improvement by reducing a significant amount of inlet turning losses. This article attempts to highlight the efficacy of hubs of various shapes and sizes on the pressure rise of the centrifugal fan using Computational Fluid Dynamics (CFD). Simulation results revealed that the optimized hub configuration yields about an 8.4% higher head coefficient and 8.6% higher relative theoretical efficiency than that obtained for the hub-less base configuration. This improvement in these paraments therefore also commemorates the global progress in energy efficiency as per the UN’s Sustainable Development Goals, SDG 7 in particular. Simultaneously, in the Artificial Neural Network (ANN), a Multi-Layer Perceptron (MLP) model is used to forecast the performance of a centrifugal fan with an optimized hub design. The results predicted by the ANN model are found to be in close agreement with the optimized hub shape’s numerical results.

Local eye-net: An attention based deep learning architecture for localization of eyes

Development of human machine interface has become a necessity for modern day machines to catalyze more autonomy and more efficiency. Gaze driven human intervention is an effective and convenient option for creating an interface to alleviate human errors. Facial landmark detection is very crucial for designing a robust gaze detection system. Regression based methods capacitate good spatial localization of the landmarks corresponding to different parts of the faces. But there are still scope of improvements which have been addressed by incorporating attention. In this paper, we have proposed a deep coarse-to-fine architecture called LocalEyenet for localization of only the eye regions that can be trained end-to-end. The model architecture, build on stacked hourglass backbone, learns the self-attention in feature maps which aids in preserving global as well as local spatial dependencies in face image. We have incorporated deep layer aggregation in each hourglass to minimize the loss of attention over the depth of architecture. Our model shows good generalization ability in cross-dataset evaluation and in real-time localization of eyes.

44 Develop A Social Perception Test: The Psychometric Properties of Child's version Reading the Mind in the Eyes Test in Taiwan

Objective:Expertise in social perception, defined as the ability to decode another person's mental states based on basic behavioral signals (Allison et al., 2000; Beauchamp et al., 2008). The Reading the Mind in the Eyes Test (RMET) is a social-perception task of theory of mind (ToM, Meinhardt-Injac et al., 2020) and used to test different clinical disorders, like autism spectrum disorders (ASD, Peñuelas-Calvo et al., 2019). RMET has been used to demonstrate gender, cultural, genetic, and personality trait influences on ToM and elucidate its neurobiological mechanisms (Adams et al., 2010). In Taiwan, there has few sensitive tools to evaluate children's social perception, thus the purpose of this study is to examine psychometric properties of child's version of RMET in Taiwan (RMET-C-TW) and cross-cultural comparisons.Participants and Methods:RMET-C (Baron-Cohen et al., 2001) was used to assess mental state/emotion recognition (Vellante et al., 2013). It consists of photographs of the eye regions of 28 faces. Participants were asked to make a choice between four words presented, choose the one that best described for feel or think. One point was given to each correctly response. RMET-C-TW was double-translation of words to ensure cultural applicability in Taiwan. This study included both a normative sample and criteria sample. The normative sample consisted of 769 (385 male, 384 female) 3 to 9 grades students from northern Taiwan. The normative sample completed both the RMET-C-TW and Chinese Vocabulary Test (CVT) in groups at their own schools, the CVT was to ensure that participants had sufficient vocabulary skills to understand the options provided in REMT-C-TW. The criteria sample were collected from 46 matched, school-aged children with ASD (age mean = 10.52, SD = 1.62; IQ = 108.39, SD = 11.75), and normally developing controls (age mean = 10.66, SD=1.68; IQ = 109.70, SD = 12.12). These two groups were administered the (1) WISC-III (2) CVT (3) RMET-C-TW and (4) ToM Test.Results:The results showed that RMET-C-TW had acceptable test-retest reliability and internal consistency (test-retest reliability = .71, Cronbach α= .40). There were significant gender and age difference in the performance of RMET-C-TW, example female, older participants performed better. Item analysis showed 93% of items in the RMET-C-TW had cross- cultural consistency in the distribution of respondents' choices. In criteria sample, the control group's RMET-C-TW scores significantly better than ASD group. Physician diagnosis (r = .49, p &lt; .01) and high-order ToM's scores (r = .33, p &lt; .01) were significantly associated with RMET-C-TW scores.Conclusions:RMET-C-TW has acceptable reliability and good developmental validity (age-related growth) in three to nine grades, and future can be extended to different age and clinicians to understand the development of social perception. Therefore, RMET-C-TW can be used as an initial screening and cross-cultural tool for ASD. In addition, EF is divided into cold and hot, and hot EF makes a unique contribution to ToM in ASD (Kouklari et al., 2017), thus this tool may also be used in the future to understand the association of hot EF with social perception.