Vision Problems Research Articles

Global relations versus object relations in visual analogies

Based on the distinction between global and local levels of visual perception, here we studied different levels of reasoning in visual analogies. Specifically, we created problems that could be solved by inferring relations either between the global shapes (global path) or the underlying objects (object path). The problems varied in the saliency of the global shape, in the colour and familiarity of the objects, and in the presentation of the visual problem (simultaneous or sequential). The results of three studies showed that the global path was used more frequently than the object path, particularly for images with salient global shapes such as objects placed in a circle. However, neither colour nor object familiarity affected the tendency to use the object path. Importantly, the tendency to use the global path correlated with analogical problem-solving in other visual and verbal tasks. Overall, these findings suggest that the global precedence observed in image perception also applies to visual analogical reasoning. Furthermore, the tendency to use the global path can be regarded as an informative measure of individual differences.

Natural history in Malan syndrome: survey of 28 adults and literature review

BackgroundMalan syndrome (MALNS), previously referred to as “Sotos syndrome 2” due to its resemblance to Sotos syndrome (SS), is an ultra-rare neurodevelopmental disorder characterized by overgrowth, typical craniofacial features, intellectual disability (ID), and a range of psychobehavioral, musculoskeletal, vision and neurological signs. As MALNS and SS partly overlap, it is essential to more accurately profile their clinical presentations and highlight their differences in order to improve syndrome specific management. An increasing number of individuals with MALNS reach adult-age though the natural history of the disorder is poorly characterized due to the small number of adult individuals described so far. As a consequence, current guidelines are limited to the pediatric population. Further delineation of MALNS is essential to optimize care in adulthood.ResultsA mixed approach based on cross-sectional data collection with a survey disseminated to caregivers of adults with molecularly confirmed MALNS and literature review was conducted. Twenty-eight caregivers completed the survey. Clinical presentation in adulthood is multisystemic and defined by psychobehavioral comorbidities (96%), musculoskeletal involvement (96%), vision impairment (96%) and neurological complications (86%). The most common signs were anxiety (79%), hypotonia (75%), movement difficulty (75%), scoliosis (64%), problems with coordination (61%), strabismus (57%), constipation (54%), breastbone abnormalities (54%) and advanced bone age during childhood (54%). Impaired vision was complicated by vision decline (36%) and optic atrophy (32%). We report some previously unidentified features, including high pain threshold (46%), incontinence (25%), tremors (21%), muscle hypoplasia (18%) and tics (18%).ConclusionsThis survey in the adult population has allowed a more complete description of the natural history of MALNS. Our findings will contribute to the development and improvement of standards of care for adults with MALNS to assure optimal health monitoring and treatment of evolutive complications. We propose additional recommendations to the previous dataset of clinical evaluations specifically applied to adults. The comparison of MALNS and SS adult presentation highlights significant differences in terms of prevalence and severity of ID, behavioral issues, and vision problems, confirming that a proper differential diagnosis between the two conditions is indispensable to guide physicians and mental health professionals to syndrome specific management.

Improving deep learning based bluespotted ribbontail ray (Taeniura Lymma) recognition

This paper presents the novel task of bluespotted ribbontail (BR) ray (Taeniura lymma) recognition using deep learning based computer vision methods to enable the identification of specific individuals of this species. Mapping the specific individuals in relation to location and time will allow marine researchers to understand their movement patterns, habitat choice, life span, size of the population and more – data which could allow monitoring and establishing a tailor-made conservation plan for this species.Our work is pioneer on this recognition problem. We give a detailed description of the three basic steps of detection, feature extraction and recognition in this vision problem and perform experiments to explore the system configuration and what improves the performance. A feature extraction enhancement as well as a crucial effect of a split into different main poses are demonstrated. Though the precision results achieved in this paper are still moderate and should be further improved, they are nevertheless promising and reasonable for practical use if the six best matches are chosen. For this scenario, almost 85% precision for upper-pose model, and almost 80% precision for left- and right-pose models, are achieved demonstrating the feasibility of the pipeline suggested as well as opportunities for improvement.

A lean approach to enhance the visual experience during wayfinding in the emergency department spaces: a case study of a large-scale general hospital in China

ABSTRACT The wayfinding experience in the healthcare environment significantly impacts patients’ spatial cognition, mental health, and medical outcomes. However, patients often face challenges in wayfinding, encountering difficulties, and information gaps that result in negative emotions and decreased efficiency of medical services. This study proposes a Lean-led approach, coupled with eye-tracking simulation software analysis, to investigate the visual behavior of patients in the emergency department spaces and identify areas in medical environments that require improvement. The research methodology involves capturing images of 70 location nodes along the patient's route in ED spaces. Subsequently, the Lean tool, Value Stream Mapping, is employed to analyze the wayfinding process, dividing it into eight tasks and determining the visual information needs of patients during wayfinding. Moreover, the eye-tracking simulation software, 3M-VAS, is utilized to analyze the visual content of images and compare whether it meets the information needs of patients during wayfinding, thus identifying locations that require optimization. Finally, suggestions for optimization are proposed. The study identifies five types of visual environment problems during the wayfinding process and identifies 50 location nodes that need improvement, categorized into five types of visual environment issues. This paper explores how Lean theory can enhance the relevance of a patient-centered healthcare environment and introduces a methodology that connects hospital administrators and designers. However, this paper also has some limitations, such as the research scope, method, and angle, that need more exploration.

Accurate image alignment based on multi-warp optimization for large parallax

Image alignment with parallax is a challenging computer vision problem. While existing methods employing local-varying smooth warps have enhanced alignment accuracy for complex spacial deformations compared to global homography estimation, they fall short in adequately representing the discontinuous transformations evident in images with large parallax. In this paper, we propose an image alignment method grounded in the estimation and fusion of multiple warping models. To effectively tackle the challenges posed by discontinuous deformations in different regions, our method comprises two key stages: principal region alignment and fine region refinement. In both stages, multiple warping models are initially estimated using feature correspondences and are then concurrently optimized by minimizing pixel-level photometric loss. For each pixel, we select the optimal model that minimizes warping error. Additionally, we introduce a feature grouping method based on Delaunay triangulation. Experiments on real-world images demonstrate the superior alignment accuracy achieved by our proposed method compared to other state-of-the-arts.

Professional performance of the graduate in optometry and optics in the calculation and adaptation of contact lenses

Introduction: the appearance, evolution and development of contact lenses brought with it a therapeutic method to correct refractive error, treat corneal ectasias and improve the patient s visual quality, thereby improving the profesional performance of the graduate in Optometry and Optics in this area it constitutes an aspect of singular importance within the medical sciences. Objetive: define profesional performance of graduates in Optometry and Optics in the calculation and adaptation of contact lenses. Method: a search was carried out in the Google Academic/ Scholar PUBMED, SciELO Public Health, SciELo Cuba engines. In the search strategy, the terms were used: profesional performance, contact lenses, quality of health services. A bibliographic review of 43 articles related to the topic under investigation was carried out. Results: we work to train a profesional with scientific mastery who responds to social needs, without abandoning the humanistic conception, since contemporary times demand a high leve lof performance, with the purpose of providing better care to patients visual problems. Conclusions: professional performance has been studied from different angles, highlihting the works of different authors, who offer as results of research models, methodologies and strategies as options aimed at the process of improving professional performance in different educations, whichis why it is done it is necessary to highlight the work of the graduate in Optometry and Optics in the calculation and adaptation of contact lenses base don visual health

Validation of the interdisciplinary Norwegian vision assessment tool KROSS in stroke patients admitted to hospital or rehabilitation services

IntroductionIdentifying vision problems after stroke is important for providing appropriate referral and vision rehabilitation in healthcare services. In Norway, vision assessment is not a standard routine or integrated in stroke care, due to lack of knowledge, guidelines and validated Norwegian assessment tools for healthcare professionals (HCPs) without formal vision competence. This study aimed to validate and assess the reliability of the KROSS (Competence, Rehabilitation of Sight after Stroke) tool for identifying vision problems in stroke patients.MethodsThe KROSS tool has 21 items, including symptoms, observations, and assessment of visual acuity, visual field, eye movements and visual inattention. The primary outcome is to identify if a vision problem is present. Sixty-seven stroke survivors (69.8 years, 28 females) were assessed twice. The first KROSS assessment was by an HCP without formal vision competence and compared to a reference assessment by an optometrist/KROSS specialist within 2 days. Sensitivity, specificity, positive and negative predictive values (PPV/NPV) and inter-rater reliability (Gwet’s AC1/Cohen’s Kappa) were calculated with 95% confidence intervals.ResultsThe KROSS tool demonstrated high sensitivity (98%) and specificity (83%), with excellent reliability (AC1 > 0.86/Kappa > 0.83) and observer agreement (93%) for the primary outcome. A vision problem was identified in 64% of patients, where 44% reported a vision symptom. The PPV and NPV for identifying a vision problem were 0.91 and 0.95 respectively. Sensitivity scores for visual acuity, reading, and visual inattention assessments were all excellent (> 80%) and specificity scores were high for all items (> 70%). Most items showed excellent or substantial agreement (AC1 > 0.7/kappa > 0.6). The lowest agreements were for motility (AC1 > 0.8/kappa > 0.4) and peripheral visual fields (AC1 > 0.8/kappa > 0.5).ConclusionsThis study shows that the KROSS tool shows promise as a valuable tool for integrating vision assessment into stroke health services. It has high sensitivity and specificity, and excellent reliability, indicating high accuracy for identifying a vision problem. This indicates that the KROSS tool can reliably be used by HCPs without formal vision competence to identify a vision problem. The fact that many stroke survivors were identified with vision problems using the KROSS tool, even if they did not complain of visual symptoms, supports the significance of including structured vision assessment in stroke care.

HQC-MCDCNN: a novel hybrid quantum–classical multi-path denoising convolutional neural network

Image denoising is a longstanding and enduring visual problem, and with the continuous rise of quantum computing in the field of machine learning, its role in image processing has become increasingly important. This paper introduces for the first time the use of multiscale variational quantum circuits in the field of image denoising, aiming to enhance the performance of classical convolutional neural networks and explore the potential advantages of combining quantum and classical approaches. In this work, we propose a novel Hybrid Quantum-Classical Multi-Path Denoising Convolutional Neural Network, abbreviated as HQC-MCDCNN. The HQC-MCDCNN is composed of a hybrid of quantum and classical elements, with the quantum part using multiscale variational quantum circuits instead of classical convolutional layers for feature extraction, and the classical part employing a newly designed multi-path denoising convolutional neural network for supervised learning. Together, these components synergistically achieve image denoising. It is worth noting that this paper aims to build readers’ intuition for quantum computing, presenting all internal details of this work with rich images and visualizations. To demonstrate the denoising capability of HQC-MCDCNN, we conducted rigorous comparative experiments. Due to the constraints of Noisy Intermediate-Scale Quantum (NISQ) devices and the limited number of quantum bits, the experiments were based on the MNIST and Fashion-MNIST datasets with varying degrees of noise (noise factors ranging from 0.3 to 0.7), employing a 6-fold stratified sampling strategy for cross-validation. The experimental results indicate that HQC-MCDCNN is promising across all evaluation metrics, particularly outperforming other models by 56.5% in the average UIQ index. This suggests that our hybrid model exhibits outstanding feature extraction capabilities and excellent denoising performance, providing a promising path for addressing image denoising challenges.

Agenecy of the corposion callosum: report of a clinical case

The agenesis of the corpus callosum (ACC) supposes an interhemispheric disconnection due to lack of formation of said structure in the embryonic development. Prevalence: 0.3-0.5% in the general population and 2.3% in people with disabilities. It is associated with prematurity and advanced maternal age. Agenesis of the corpus callosum is a malformation that can occur in isolation or in association with other systemic or central nervous system disorders and is one of the most common malformations in the brain, with an estimated prevalence of 1 in 4,000 live births. Among the most common clinical findings are mental retardation, visual problems, and seizures. Prenatal diagnosis can be made by ultrasound and magnetic resonance imaging from the 20th week of gestation. Postnatal diagnosis can be made by ultrasound, computed tomography, and magnetic resonance imaging. Currently, there is no specific treatment, although it has been proposed to start an early stimulation program and, if possible, a psychomotor rehabilitation program that offers improvement in motor and learning disorders.

Computer Vision Model Compression Techniques for Embedded Systems:A Survey

Deep neural networks have consistently represented the state of the art in most computer vision problems. In these scenarios, larger and more complex models have demonstrated superior performance to smaller architectures, especially when trained with plenty of representative data. With the recent adoption of Vision Transformer (ViT) based architectures and advanced Convolutional Neural Networks (CNNs), the total number of parameters of leading backbone architectures increased from 62M parameters in 2012 with AlexNet to 7B parameters in 2024 with AIM-7B. Consequently, deploying such deep architectures faces challenges in environments with processing and runtime constraints, particularly in embedded systems. This paper covers the main model compression techniques applied for computer vision tasks, enabling modern models to be used in embedded systems. We present the characteristics of compression subareas, compare different approaches, and discuss how to choose the best technique and expected variations when analyzing it on various embedded devices. We also share codes to assist researchers and new practitioners in overcoming initial implementation challenges for each subarea and present trends for Model Compression.

How the Learning Style and Working Memory Capacity of Prospective Mathematics Teachers Affects Their Ability to Solve Higher Order Thinking Problems

<p style="text-align: justify;">This study aims to analyze the effects of working memory capacity and learning styles of prospective mathematics teachers on their ability to solve higher-order thinking problems. In the present study, learning style was considered students' tendency to learn visually or verbally. In addition, the types of higher-order thinking skills (HOTS) problems are complex and non-complex. Multiple regression tests were used to analyze the effects of learning style and working memory capacity. An ANOVA test was also conducted to analyze the ability of each group to solve each HOTS problem. In addition, one hundred twenty-six prospective mathematics teachers voluntarily participated in this study. The study found that learning styles only affected visual problems while working memory capacity (WMC) only affected the ability to solve complex problem-solving skills. Furthermore, WMC affected the ability to solve complex HOTS problems, not non-complex ones. The ability of visual students to solve HOTS problems will greatly increase when the problems are presented in visual form. On the other hand, the obstacle for visual students in solving verbal problems was to present the problem appropriately in visual form. The obstacle for students with low WMC in solving complex HOTS problems was to find a solution that met all the requirements set in the problem.</p>

Does Being In-Person Matter? Demonstrating the Feasibility and Reliability of Fully Remote Observational Data Collection.

Many conventional research methods employed in randomized controlled trials were not possible during the height of the COVID-19 pandemic. In particular, behavioral observations are nearly universally gathered in-person. Observational methods are valued for the rich, informative data they produce in comparison to non-observational methods and are a cornerstone of parenting and family research. COVID provided the opportunity to, and indeed necessitated, the transition to fully remote observation. However, little to no studies have investigated whether remotely collected observational data are methodologically sound. This paper assesses the feasibility of remote data collection by describing the transition between in-person and fully remote observational data collection during a Sequential, Multiple Assignment, Randomized Trial (SMART) of a parenting program that took place both before and during the pandemic. Using mixed-methods data from coders, the overall quality of video-recorded data collected both before and during COVID was examined. Coder reliability over time was assessed with intraclass correlation coefficients. Results suggest that the frequency of audio problems, the severity of visual problems, and the level of administration challenges decreased after transitioning to remote data collection. Additionally, coders showed good to excellent reliability coding remotely collected data, and reliability even improved on some measured tasks. Although challenges to remote data collection exist, this study demonstrated that observational data can be collected feasibly and reliably. As observational data collection is a key method to assess parenting practices, these findings should improve researcher confidence in utilizing remote observational methods in prevention science.

Dyskinetic Cerebral Palsy in Children: Clinical Perspectives on Common Comorbidities and Health-Related Quality of Life.

The data on specific comorbidities in children with dyskinetic cerebral palsy (DCP) is limited. We evaluated the pattern of comorbidities and health related quality of life (HRQOL) in these children and compared them between etiological and motor impairment subgroups. This cross-sectional study was conducted over 18 months in children with DCP of both sex, and age between one and 14 years. Comorbidities were assessed using standardized scales such as gross motor functioning scale (GMFCS), developmental profile-3 (DP-3), developmental behaviour checklist, sleep behaviour questionnaire (SBQ), and caregiver questionnaire. Sixty-five children with DCP were evaluated (hyperbilirubinemia n = 43, 66% and perinatal asphyxia n = 19, 29%). The majority of children were severely affected in gross motor functioning (level IV 29.2% and level V 53.8%). Epilepsy was seen in 21.5% of cases (19% in hyperbilirubinemia and 32% in asphyxia, p = 0.4). The mean age of onset of seizures was 15.4 + 20.6 months (range 2-72). Visual problems were seen in 54% of cases and included upgaze palsy, squint, refractive error, optic atrophy and cortical blindness. A significant proportion of children with hyperbilirubinemia had upgaze palsy as compared to those with perinatal asphyxia (70% vs. 32%, p 0.01). Rest of the visual problems were not significantly different between the two etiological subgroups. Drooling (87.6%), protein-energy malnutrition (66.6%), and reflux (57%) were the most common gastrointestinal problems in children with DCP. Children with DCP showed problems in social relating (33.8%), anxiety (26.2%), and self-absorbed behaviour (7.7%). However, there were no statistically significant differences between the etiological, motor impairment and age-based subgroups. Children with DCP had high scores on SBQ, suggesting sleep problems. Sleep scores were similar in the hyperbilirubinemia and perinatal asphyxia subgroups. Greater sleep problems were noted in children aged < 4y (70.6 + 10.1 vs. 56.5 + 11.3, p < 0.05 as compared to children above 4y of age) and severe motor impairments (68.2 + 11.3 vs. 57.2 + 13.1, p 0.008 as compared to mild-moderate motor impairment). Poor overall developmental scores were seen in 61.5% children and were significantly associated with GMFCS (p 0.04). The majority of children showed impairments in physical (58.5%), adaptive behaviour (58.5%), social-emotional (50.8%), cognitive (60%) and communication (52%) subscales of DP-3. Cognitive impairment was similar in the etiological (hyperbilirubinemia vs. perinatal asphyxia, p = 0.3), and motor impairment (mild-moderate vs. severe, p = 0.9) subgroups. HRQOL was significantly affected by motor impairment in positioning-transfer (p value 0.0001), and interaction-communication domains (p value 0.0001), however, there was no difference based on the etiology of hyperbilirubinemia and asphyxia. Children with DCP demonstrate several comorbidities and impaired quality of life. These are similar in hyperbilirubinemia and perinatal asphyxia cohorts, expect for significant proportion of upgaze palsy in DCP secondary to hyperbilirubinemia. Younger children have more problematic behaviour and impaired sleep quality. Severe motor disability influences the developmental outcomes, cognition, sleep and HRQOL in children with DCP.

Evaluation of pediatric vision screening and digital referral routines in an interprofessional setting in Norway

Vision is crucial for childhood development, and ensuring good vision in children is one of the United Nation’s sustainability goals. Most countries have a childhood vision screening programme, and in Norway screening in children aged 4–5 years is performed in community health centres (CHC). Specialist health services such as ophthalmology and/or orthoptics are the referral bodies. However, access to these may be limited and they may be a long distance away from the child’s home, while optometrists are often more available and accessible. This study aims to investigate if vision screening reliably detects vision problems and to explore if using paediatric optometry as a referral body can relieve the specialist health services. The study also aims to report frequency of refractive errors and management of vision problems in this age group. Of 274 children who attended vision screening by school nurses at the CHC in Kongsberg, Norway, parents of 213 (77.7%) consented to a separate eye and vision examination by a paediatric optometrist. Agreements in screening results between school nurses and the paediatric optometrists were evaluated. Separately, an ophthalmologist and an orthoptist assessed records from the eye examinations through a digital communication tool (Eyecheck System AS). Agreements in diagnoses and management decisions between optometrists and the specialist health services were evaluated. Amblyopia or ocular pathology was found in 1.9% of the children, which were all identified by the vision screening. The vision screening had a sensitivity and specificity of 62.3% and 58.6%, respectively, for detecting other vision problems in need of treatment or follow-up. Hypermetropia was present in 82.7% of the children (58.0% low, 18.5% moderate, 6.5% high hypermetropia), 16.4% had emmetropia and 1.0% had myopia. Glasses were prescribed to 8.5% of the children and 16.4% were scheduled for follow-ups. There was a high level of agreement in management between optometrists and specialists (ophthalmologist 80.3%, orthoptist 81.7%). The vision screening reliably detected amblyopia and ocular pathology, and most refractive errors were detected. The high degree of agreement between the three eye care professions suggests that paediatric optometrists can be used as the referral body for this age group. Availability of a digital communication tool provides support for the paediatric optometrists in their decision making and can help relieve the specialist health services by providing children with an eye examination and vision correction earlier and more easily.

Gambaran Penyesuaian Sosial pada Remaja Low Vision di Sekolah Inklusi Kota Padang

Adolescents will face developmental tasks that must be completed before entering the next stage of development. One of them is to build stronger social relationships with peers, both with the same sex and the opposite sex. Adolescents need social adjustment to adapt to new tasks. The purpose of this study is to find out about social adjustments made by adolescents who have vision problems at the Padang City Inclusion School. This research was conducted in a qualitative descriptive way. The three teenagers who experienced low vision impairment were junior high and high school students at the Padang City Inclusion School. They are the informants of this research. The purposive sampling method is used to select informants. Interviews and observations were used to collect data. The results showed that the three informants had good social adjustment while studying at an inclusion school. They use their abilities to participate in social activities, utilize the rest of their vision, provide assistance, be willing to cooperate, accept dissent, seek to forgive others, and obey the rules.

Challenges of parenting children born before 24 weeks of gestation.

To assess experience of care, well-being of parents and children's development in a cohort of extremely premature infants born <24 weeks of gestation in Sweden from 2007 to 2018. A survey based on multiple questionnaires answered by 124/349 (35.5%) parents. The median age of parents and children was 43 and 9 years, respectively; 74.2% were mothers. Parents expressed high healthcare satisfaction. Following discharge from neonatal care, the satisfaction with the infant's treatment, support from personnel and being respected as a parent significantly declined but remained high. The criteria for suspected developmental deviation according to the screening test early symptomatic syndromes eliciting neurodevelopmental clinical examinations-questionnaire was fulfilled by 84.3%, 55.6% had suspected avoidant restrictive food intake disorder and 47.9% had visual perception problems. Parents experienced severe fatigue (48.6%) despite strong social support and family self-efficacy. Economic support was provided to 30.6%, and 37.9% of children were enrolled in habilitation services. This study highlighted the substantial challenges faced by parents of infants born before 24 weeks of gestation, including decreased satisfaction post-discharge, fatigue and concerns about children's well-being. The findings underscore the need for comprehensive family-centred support and long-term multi-professional follow-up centres.

From CNNs to Transformers in Multimodal Human Action Recognition: A Survey

Due to its widespread applications, human action recognition is one of the most widely studied research problems in Computer Vision. Recent studies have shown that addressing it using multimodal data leads to superior performance as compared to relying on a single data modality. During the adoption of deep learning for visual modelling in the past decade, action recognition approaches have mainly relied on Convolutional Neural Networks (CNNs). However, the recent rise of Transformers in visual modelling is now also causing a paradigm shift for the action recognition task. This survey captures this transition while focusing on Multimodal Human Action Recognition (MHAR). Unique to the induction of multimodal computational models is the process of ‘fusing’ the features of the individual data modalities. Hence, we specifically focus on the fusion design aspects of the MHAR approaches. We analyze the classic and emerging techniques in this regard, while also highlighting the popular trends in the adaption of CNN and Transformer building blocks for the overall problem. In particular, we emphasize on recent design choices that have led to more efficient MHAR models. Unlike existing reviews, which discuss Human Action Recognition from a broad perspective, this survey is specifically aimed at pushing the boundaries of MHAR research by identifying promising architectural and fusion design choices to train practicable models. We also provide an outlook of the multimodal datasets from their scale and evaluation viewpoint. Finally, building on the reviewed literature, we discuss the challenges and future avenues for MHAR.

Detection Method of Manipulator Grasp Pose Based on RGB-D Image

In order to better solve the visual detection problem of manipulator grasping non-cooperative targets, we propose a method of grasp pose detection based on pixel point and feature fusion. By using the improved U2net network as the backbone for feature extraction and feature fusion of the input image, and the grasp prediction layer detects the grasp pose on each pixel. In order to adapt the U2net to grasp pose detection and improve its detection performance, we improve detection speed and control sampling depth by simplifying its network structure, while retaining some shallow features in feature fusion to enhance its feature extraction capability. We introduce depthwise separable convolution in the grasp prediction layer, further fusing the features extracted from the backbone to obtain predictive feature maps with stronger feature expressiveness. FocalLoss is selected as the loss function to solve the problem of unbalanced positive and negative samples in network training. We use the Cornell dataset for training and testing, perform pixel-level labeling on the image, and replace the labels that are not conducive to the actual grasping. This adaptation helps the dataset better suit the network training and testing while meeting the real-world grasping requirements of the manipulator. The evaluation results on image-wise and object-wise are 95.65% and 91.20% respectively, and the detection speed is 0.007 s/frame. We also used the method for actual manipulator grasping experiments. The results show that our method has improved accuracy and speed compared with previous methods, and has strong generalization ability and portability.

The association between screen time exposure, parent depression, and development of social communication skills among preschool children in Qassim Region

BackgroundScreen exposure among children continues to increase worldwide. It has negative effects on children of developmental age, including obesity, poor attention, sleep disorders, vision problems, language delays, and deficits in communication skills. It has been reported that parental depression is associated with both increased screen time for children and poor function and skills in children. However, other studies have reported no association between screen time and parental depression.Research methodologyA cross-sectional study was conducted using a convenience sample of 340 parents of 4- to 6-year-old children in the Qassim Region of Saudi Arabia. Data were collected from the primary health care vaccination clinic by contacting parents of children aged 4 to 6 years to fill out the Social Communication Questionnaire (SCQ) for the child and the Patient Health Questionnaire-9 (PHQ9) for the parents.Research resultsWe conducted a regression analysis to assess the influence of screen time exposure on social communication skills (SCQ score). The results of this study indicated that there was no significant effect observed (B = 0.283, P > 0.05), indicating that a positive correlation between screen time usage and SCQ score may not apply to the entire population. Conversely, we discovered a crucial link between screen time exposure and parental depression (PHQ), as it displayed noteworthy impact values (B = 1.136, P < 0.05), indicating an affirmative correlation between them. In addition, our results also indicated apparent positive associations between parental depression and SCQ scores (B = 0.229, P < 0.05).ConclusionOur findings revealed that there was a significant association between parental depression and both screen time exposure and SCQ score, while there was no correlation between screen time exposure and SCQ score.

Using a new analytic approach for genotyping and phenotyping chromosome 9p deletion syndrome.

Using a new analytic method ("unique non-overlapping region" (UNOR) analysis), we characterized the genotypes and phenotypes of a large cohort of individuals diagnosed with chromosome 9p deletion syndrome (9PMS) and defined critical genomic regions. We extracted phenotypic information from 48 individuals with 9PMS from medical records and used a guided interview with caregivers to clarify ambiguities. Using high-resolution whole-genome sequencing for breakpoint definition, we aligned deletions and drew virtual breakpoints to obtain UNORs associated with phenotypic characteristics. We next extracted genotype and phenotype data for 57 individuals identified from a systematic review of the 9PMS literature and analyzed these as above. Common phenotypic features included developmental delay/intellectual disability, dysmorphic features, hypotonia, genital defects in XY individuals, psychiatric diagnoses, chronic constipation, atopic disease, vision problems, autism spectrum disorder, gastroesophageal reflux disease, trigonocephaly, congenital heart disease, and neonatal hypoglycemia. Our approach confirmed previous literature reports of an association of FREM1 with trigonocephaly and suggested a possible modifier element for this phenotype. In conclusion, the UNOR approach delineated phenotypic characteristics for 9PMS and confirmed the critical role of FREM1 and a possible long-distance regulatory element in pathogenesis of trigonocephaly that will need to be replicated in future studies.