Advancing automated pupillometry:a practical deep learning model utilizing infrared pupil images

AIM:To establish pupil diameter measurement algorithms based on infrared images that can be used in real-world clinical settings.METHODS:A total of 188 patients from outpatient clinic at He Eye Specialist Shenyang Hospital from Spetember to December 2022 were included,and 13470 infrared pupil images were collected for the study.All infrared images for pupil segmentation were labeled using the Labelme software.The computation of pupil diameter is divided into four steps:image pre-processing,pupil identification and localization,pupil segmentation,and diameter calculation.Two major models are used in the computation process:the modified YoloV3 and Deeplabv 3+models,which must be trained beforehand.RESULTS:The test dataset included 1348 infrared pupil images.On the test dataset,the modified YoloV3 model had a detection rate of 99.98% and an average precision(AP)of 0.80 for pupils.The DeeplabV3+model achieved a background intersection over union(IOU)of 99.23%,a pupil IOU of 93.81%,and a mean IOU of 96.52%.The pupil diameters in the test dataset ranged from 20 to 56 pixels,with a mean of 36.06±6.85 pixels.The absolute error in pupil diameters between predicted and actual values ranged from 0 to 7 pixels,with a mean absolute error(MAE)of 1.06±0.96 pixels.CONCLUSION:This study successfully demonstrates a robust infrared image-based pupil diameter measurement algorithm,proven to be highly accurate and reliable for clinical application.

Robust Facial Biometric Authentication System Using Pupillary Light Reflex for Liveness Detection of Facial Images

Pupil dynamics are the important characteristics of face spoofing detection.The face recognition system is one of the most used biometrics for authenticating individual identity.The main threats to the facial recognition system are different types of presentation attacks like print attacks,3D mask attacks,replay attacks,etc.The proposed model uses pupil characteristics for liveness detection during the authentication process.The pupillary light reflex is an involuntary reaction controlling the pupil’s diameter at different light intensities.The proposed framework consists of two-phase methodologies.In the first phase,the pupil’s diameter is calculated by applying stimulus(light)in one eye of the subject and calculating the constriction of the pupil size on both eyes in different video frames.The above measurement is converted into feature space using Kohn and Clynes model-defined parameters.The Support Vector Machine is used to classify legitimate subjects when the diameter change is normal(or when the eye is alive)or illegitimate subjects when there is no change or abnormal oscillations of pupil behavior due to the presence of printed photograph,video,or 3D mask of the subject in front of the camera.In the second phase,we perform the facial recognition process.Scale-invariant feature transform(SIFT)is used to find the features from the facial images,with each feature having a size of a 128-dimensional vector.These features are scale,rotation,and orientation invariant and are used for recognizing facial images.The brute force matching algorithm is used for matching features of two different images.The threshold value we considered is 0.08 for good matches.To analyze the performance of the framework,we tested our model in two Face antispoofing datasets named Replay attack datasets and CASIA-SURF datasets,which were used because they contain the videos of the subjects in each sample having three modalities(RGB,IR,Depth).The CASIA-SURF datasets showed an 89.9%Equal Error Rate,while the Replay Attack datasets showed a 92.1%Equal Error Rate.

Eating Patterns and Daily Dietary Recall of Primary School Pupils: An Empirical Evidence from A School Feeding Scheme

The objective of this study was to experimentally evaluate children’s daily food memory and eating habits.The study found that the gender and school location had an impact on the nutritional condition of primary school students as well as the school food scheme.The investigations were based on three hypotheses and three research questions.In this study,the Eating Habits and Daily Dietary Recall Scale was the tool utilized to gather data(EPDDRS).Four experts—three from the department of vocational education and one lecturer in test and measurement evaluation—validated the instrument’s face.The dependability indices of EPDDRS were calculated using Cronbach’s Alpha.While delivering the instruments,the researcher used the direct administration and retrieval approach.58 instructors and a sample size of 1240 students were selected using a systematic random selection approach.The obtained data was examined using mean and standard deviation to address the research objectives,and the null hypotheses were tested using t-test statistics and Analysis of variance(ANOVA)at the 0.05 level of significance.The main conclusions of this study were that the school meal program had a favorable impact on the students’nutritional status.Also,a balanced ration of nutrient-dense meals that were suitably varied was supplied for the students via the school food program.Also,the findings revealed a substantial difference in the mean assessments of male and female students about their eating patterns.On the school meal program’s dietary recall list,students from high,middle,and low socioeconomic status differ significantly.Recommendations were given to the government,schools,and parents based on the study’s findings.The study’s shortcomings were discussed,and recommendations for more research were made.

Pupils in Wenchuan Earthquake

A great earthquake broke out in WenChuan. A lot of people were killed, but somany people were rescused by soldiers.Here are stories about three recused pupils.Langzhen, aged three, was rescusedby the soldiers after being buried in ruinsfor 10 hours.

THE INVESTIGATION AND ANALYSIS OF THE PSYCHOLOGICAL DISORDERS OF THE PUPILS（9～12YEARS OF AGE）OF XI＇AN CITY

pupils aged 9～12 years from six primary schools were cross-sectionally investigated on the psychological disorders with Conner Scale and EPQ. The results showed that the incidence of psychological disorders was 18. 2%,with 21. 3% in male and 15. 5% in female. The incidehees were significantly difrerent between male and remal (P<0. 05). The incidences or learning difficulty,hyperactivity and impulsive behavior were 8. 2%, 5. 3%,and 5.3% respectively.The family factors influencing the psychological disorders were the pupils'birth problems,the relationship between the pupils and their parents, and the parents'inappropriate prospect for the pupils.The investigation also found that the pupils with psychological disorders had more poor experiences or their family and school and more of them had obvious personality tendencies towards unstability or emotion,eccentricity and social immaturity as compared with the normal pupils. The effective measures to promote pupils'psychological health were suggested in this article.

Research on the prevalence of conduct disorders among primary school pupils in Khartoum-Sudan

The aim of this research was to investigate conduct disorder among pupils of primary schools in Khartoum, the capital of Sudan. School survey descriptive method was used and 384 pupils were selected from primary schools through systematic sampling technique. Age ranged from 5 to 17 years old with a mean of (9.34) years. The tools of data collection consisted of the Sutter-Eyberg Student Behavior Inventory. The statis-tical tests used to analyze the collected data involve frequency and percentage, Pearson co-efficient of correlation, mean, t-test for one sample and t-test for two independent samples. The results of this research revealed that that the prevalence of conduct disorder among pupils of primary schools in Khartoum was low. There were significant differences in conduct disorder between male and females pupils. There were no significant differences between pupils of pre-paratory classes and pupils of elementary classes. There was no significant correlation between conduct disorder and age.

Food Behavior of Pupils in the City of Bobo-Dioulasso (Burkina Faso)

Introduction: Diet is a determinant of chronic non transmissible diseases. The aim of this study was to describe pupils’ diet in the city of Bobo-Dioulasso (Burkina Faso). Methods: This was a descriptive cross-sectional study that took place from March to April 2016, among 1st, 4th and 7th form pupils of public and private schools in the city of Bobo-Dioulasso. Diet survey methods were a reminder of the last 24 hours and the questionnaire of consumption frequency. Results: A total of 1993 pupils were surveyed. The mean age was 17.5 ± 3.6 years and the sex ratio 0.7. The majority of pupils (90.5%) reported eating at least 3 meals a day. Dietary recommendations were different according to food groups. For example, vegetables (90.0%), fruits (75.4%) and dairy products (79.3%) were the least well consumed foods compared to recommendations. Protein and starch intake were inadequate among these pupils with 39.7% and 58.2% respectively. Almost 1/4 had a regular weekly alcohol consumption (23.4%) while an excessive consumption of sweet drinks and fried foods was noted in 12.7% and 28.2% of them, respectively. Conclusion: This study has revealed a general insufficiency in the recommended dietary intakes of fruit, vegetables, proteins, starchy foods and dairy products among pupils, and on the other hand, a regular consumption of fatty, sugary and alcoholic foods for about a fifth of them. An intervention program such as “Communication for Continuous Behavior Change” would help improve these habits.

A Study of Anthropometric Indices among Pupils in Rural Communities around Kainji Dam, Niger State

The physical and mental development of pupils could be arrested by inadequate food intake and infection with immediate and long term consequences. This has implications on decreased school performances, lower intelligent quotient levels, poor psychosocial development, and decreased cognitive functions. This study assessed the growth and body fat distribution among pupils aged 5 - 19 years. A cross-sectional study was conducted among pupils from five primary schools in different communities around Kainji Dam. This assessment was based on a comparison with reference standards set by the World Health Organization to determine their deviations. A qualified registered nurse carried out physical measurements to obtain age, height, and body weight using electronic weighing scale and stadiometer. Data were analyzed using Anthroplusv1.0.4 software. The overall prevalence of stunting was 21.5% with 8% being severely stunted. The prevalence of thinness was 35.2% with 11.2% being wasted while the overall prevalence of underweight was not calculated for children > 10 years old. The prevalence of underweight for 5 - 10 years old children was 16.9% with 2.4% being severely underweight. The curves for both male and female children deviated from normal distribution. Females have higher percentage of stunting than males. This study revealed a high prevalence of thinness and stunting which is the consequence of poor nutrition arising from multifaceted and interrelated circumstances such as poor feeding, eating practices and repeated infection. Intervention such as Home Grown School Feeding Programme of the Government is a right step in improving the nutritional status of pupils in rural communities.

Too Sweet/Too Fatty Food Consumption: Determinants among Secondary School Pupils in the City of Bobo-Dioulasso (Burkina Faso)

Introduction: Nutrition, particularly when too sweet or too fatty, is a major determinant of chronic diseases. This study aims to determine the frequency and associate factors of the excessive consumption of sweet drinks and fried food among secondary school pupils. Methods: It is cross-sectional study which was conducted from March to April 2016 among 1st, 4th and 7th form pupils of public and private schools in the city of Bobo-Dioulasso. Nutritional investigation methods consisted in a reminder of the last 24 hours associated with a questionnaire on food consumption frequency. Excessive consumption of sweet drinks was defined as a consumption of more than 3 sweet drinks (soda) or sugary juice per day (~33 cl × 3);and excessive consumption of fried food as a consumption of more than 1 intake of fried food per day. Results: In total, 1993 pupils were interviewed. The mean age was 17.5 ± 3.6 years and sex-ratio 0.7. Excessive consumption of sweet drinks and fried food was recorded in 12.7% (n = 253) and 28.2% (n = 561) of pupils, respectively. The factors associated with excessive consumption of sweet drinks were: sex/female, sedentarily, desire to gain weight, lean or normal corpulence of the mother and breakfast intake;those associated with excessive consumption of fried food were: sex/female, being in 1st or 4th form, physical exercise practice and breakfast intake. But the fact to attend a private secondary school, to have a mother of normal corpulence and a concordance between self-image and actual weight status, were protective against excessive consumption of fried foods. Conclusion: This study has displayed prominently the fact that eating too sweet and too fatty concerned respectively 1/10 and 3/10 of pupils in the city of Bobo-Dioulasso. The main modifiable factors of these eating habits included the level of education, the composition of breakfast and the influence of mothers. An intervention program in the form of a Communication for Continuous Behavioral Change intended for pupils and their mothers could help to improve this situation.

Effect of socio-demographic status on dental caries in pupils by using a multilevel hurdle model

Introduction: Dental caries is the most prevalent chronic disease among schoolchildren. We aimed to investigate the association between dental caries index and socio-demographic status in schoolchildren by using a multilevel hurdle model. Materials and Methods: A cross-sectional epidemiological study was carried out on 906 primary school pupils in Kerman, Iran in 2012. The subjects were selected through a stratified cluster random sampling. At first, the whole target area was stratified according to two geographic areas, the north and south area. Then each area was stratified according to gender. In the next step, several schools were considered as clusters, which were selected randomly in each geographic area and gender strata. All the schoolchildren in these schools were included in this study as samples. Twelve-year-old pupils were examined for dental caries. The dependent variable in this study was the dmft/DMFT index. Eight variables, including socio-demographic information, were collected. Multilevel negative binomial hurdle model was employed for data analysis. Results: The prevalence of caries-free pupils was 30.1% and the mean dmft/DMFT was 3.6 ± 2.2. Negative binomial part of the adjusted model showed that the dmft/DMFT adjusted rate for females was 1.36 (95% CI: 1.10-1.79) times higher than males. Also, the dmft/DMFT adjusted rate for overweight pupils was 0.86 (95% CI: 0.74-0.98) times lower than those with normal weight. Logistic part of the adjusted model showed that the posibility of caries-free state in overweight pupils was 1.95 (95% CI: 1.22-3.11) times higher than those with normal weight. In addition, pupils whose fathers and mothers were workers and housewives, respectively, and those with a high maternal age were at a greater risk for caries experience than others (p < 0.05). Conclusion: BMI, gender, parent’s job and mother’s age at delivery were factors effecting on dental caries in schoolchildren. These pupils need more attention to dental care.

Asymptomatic Carriage of Salmonella and Intestinal Parasites in Pupils in Yaounde

Background: Feco-oral transmitted diseases (FOTD) remain a public health issue, particularly in developing countries. Data concerning the carriage of Salmonella and intestinal parasites in children are available worldwide but are lacking in Cameroon. This study aimed to determine the asymptomatic carriage of Salmonella and intestinal parasites in children of two primary schools in Yaoundé. Methods: A cross-sectional descriptive study was conducted from October 2017 to May 2018 in two primary schools (from rural and urban areas) in the 7th precinct of Yaoundé. Sociodemographic, clinical and paraclinical (rectal swab, direct examination of fresh stool and bacteriological culture on Hektoen medium) data were collected. Results: We included 368 (192 boys) pupils from both schools (184 in each school) with a mean age of 8.99 ± 2.21 years. None of the children was infected by Salmonella spp. Intestinal parasite prevalence was 9.80% (6.52% of children from the urban school vs 13.04% from the rural ones). The intestinal parasite prevalence tended to be higher in girls than in boys (11.98% vs. 7.39%). Among intestinal parasites, protozoa were the most widely found. Entamoeba histolytica and Giardia intestinalis were the most prevalent pathogenic intestinal protozoa (11.11% vs. 25% of all positive stool exams). The helminths, less frequent, were represented by Ascaris lumbicoides and Enterobius vermicularis. The factors associated with intestinal parasite carriage were mainly rural school location and age between 11 - 13 years. Conclusion: Among children in primary school, Salmonella infection was absent, while intestinal parasites are frequent, represented mostly by protozoa. This parasitism is in our cohort associated with the rural school location and the 11 - 13 years age group. This suggests that there is additional room for the implementation of prevention measures for intestinal parasite infections in our setting.

The Human Eye Pupil Detection System Using BAT Optimized Deep Learning Architecture

The pupil recognition method is helpful in many real-time systems,including ophthalmology testing devices,wheelchair assistance,and so on.The pupil detection system is a very difficult process in a wide range of datasets due to problems caused by varying pupil size,occlusion of eyelids,and eyelashes.Deep Convolutional Neural Networks(DCNN)are being used in pupil recognition systems and have shown promising results in terms of accuracy.To improve accuracy and cope with larger datasets,this research work proposes BOC(BAT Optimized CNN)-IrisNet,which consists of optimizing input weights and hidden layers of DCNN using the evolutionary BAT algorithm to efficiently find the human eye pupil region.The proposed method is based on very deep architecture and many tricks from recently developed popular CNNs.Experiment results show that the BOC-IrisNet proposal can efficiently model iris microstructures and provides a stable discriminating iris representation that is lightweight,easy to implement,and of cutting-edge accuracy.Finally,the region-based black box method for determining pupil center coordinates was introduced.The proposed architecture was tested using various IRIS databases,including the CASIA(Chinese academy of the scientific research institute of automation)Iris V4 dataset,which has 99.5%sensitivity and 99.75%accuracy,and the IIT(Indian Institute of Technology)Delhi dataset,which has 99.35%specificity and MMU(Multimedia University)99.45%accuracy,which is higher than the existing architectures.

The Level of General Physical Performance and Physical Development of 10-Year-Old Pupils

This contribution deals with the level of general physical performance of 10-year-old male and female pupils attending primary schools. Fourth grade pupils attending primary schools in Banska Bystrica were tested in the number of 433 pupils （220 boys and 213 girls）. The following indicators of general physical performance were monitored： sit-and-reach, standing long jump, sit-ups, flexed arm hang, shuttle run 4 ×10 m, endurance shuttle run. Also basic somatic indicators such as body height, body weight and BM! were found out. 10-year-old boys achieve better level in five tests of general physical performance. The girls achieve statistically better level in one test. When comparing it with the previous researches in Slovakia, we noted a lower level of general physical performance but a higher level of indicators of physical development of boys and girls from Banska Bystrica. Used set of tests affects the whole range of general physical performance, and it is adequate to the temporal, spatial and material conditions of schools.

The Influence of Parent-Child Relationship on Pupils’ Learning Motivation: The Mediating Role of Teacher-Student Relationship

Objective:The study is to analyze the influence of parent-child relationship on pupils’learning motivation,and to explore the mediating mechanism of teacher-student relationship in parent-child relationship and learning motivation.Method:This study conducted a questionnaire survey on 213 pupils in Grades 5 and 6 in two schools in Beijing using Pianta’s teacher-student relationship scale revised by Qu,Dornbush’s parent-child intimacy scale revised by Zhang and the learning motivation scale adapted by Hu.Results:Gender,grade,whether they are the only child and to be a class cadre or not show significant differences in some dimensions of parent-child relationship,teacher-student relationship and learning motivation.The total scores of parent-child relationship,teacher-student relationship and learning motivation are positively correlated,and some sub dimensions are also significantly correlated.Parent-child relationship and teacher-student relationship have a significant positive predictive effect on learning motivation,and parent-child relationship has a significant positive predictive effect on teacher-student relationship.Teacher-student relationship plays a mediating role in the influence of parent-child relationship on learning motivation.Conclusions:Parent-child relationship can promote the relationship between teachers and students,and then enhance pupils’learning motivation.

超声主导的瞳孔评估在ICU中的应用进展

瞳孔评估是重症患者病情监测的重要手段,超声主导的瞳孔评估可克服传统瞳孔评估存在的误差,为由于创伤性脑水肿致眶周软组织水肿而无法睁眼的患者提供准确的瞳孔评估,有助于及时、精确地进行病情观察,更客观地监测镇痛水平。本文对超声主导的瞳孔评估在ICU的应用进展进行综述,旨在为重症患者的临床诊疗和护理干预提供客观依据和参考。

小学高年级学生友善品质对助人行为的影响:积极情绪的中介作用

为探讨友善品质对小学高年级学生助人行为的影响,分析积极情绪在其中的作用,采用《中国中小学生积极心理品质量表》《积极-消极情绪量表》《小学生分享行为、助人行为问卷》对小学4~6年级的197名学生进行调查,运用SPSS 22.0软件进行独立样本t检验、方差分析和皮尔逊相关分析,以及Process 4.1宏程序插件中的偏差校正的非参数百分位Boot-strap方法对有效数据进行统计分析.结果发现:1)小学高年级学生友善品质和助人行为的均值都显著大于理论中值(p<0.05);2)性别与年级在小学高年级学生助人行为上交互作用显著(p<0.05);3)友善品质与积极情绪的不同水平在助人行为上存在显著差异(p<0.05);4)友善品质、积极情绪和助人行为三者两两之间呈显著的正相关关系,相关系数在0.28~0.49(p<0.05);5)友善品质能正向预测积极情绪(β=0.50,t=7.91),积极情绪和友善品质能共同正向预测助人行为(β=0.16,t=2.08;β=0.20,t=2.71);6)在中介模型中,友善品质的总效应(c=0.28)和直接效应(c′=0.20)、积极情绪的中介效应(ab=0.08)在Boot-strap 95%的置信区间均不包含0,表明积极情绪在友善品质与助人行为间的中介效应显著,中介效应占比为(ab/c)100%=28.57%.研究表明:小学高年级学生友善品质和助人行为发展较好,积极情绪在友善品质与助人行为间起部分中介作用.

考虑识别鲁棒性和虹膜颜色影响的瞳孔精准定位方法

准确的瞳孔定位广泛应用于疲劳监控、注意力分析、凝视跟踪等领域.当前,对于瞳孔定位的研究,还存在两个难点问题:(1)瞳孔检测的精准率受到图像分辨率、照明、头部姿态的影响,因而自然条件下的定位精准度较低;(2)虹膜颜色影响定位精准率,但当前对于不同虹膜颜色的瞳孔定位方法的研究还不完善.针对以上问题,提出一种新的适用于包含全脸图像的瞳孔定位方法.所提方法无需训练,可直接用于瞳孔定位任务.方法核心是将表示局部径向对称性的自相似性分数,与根据瞳孔和周围区域之间的梯度信息计算得到的眼部区域梯度辐射分数相结合,取联合分数峰值坐标为瞳孔中心.在BioID数据集和GI4E数据集上评估本方法.在归一化误差e≤0.05的情况下,准确率分别为94.67%(BioID),97.09%(GI4E),在e≤0.10的情况下,准确率分别为99.47%(BioID),99.51%(GI4E).所提方法在由低分辨率深色虹膜的人脸图像组成的自制数据集上准确率为98.66%(e≤0.05)和100%(e≤0.10),表明所提方法对于虹膜颜色有较好的鲁棒性.

郑州市近视小学生心理健康状况调查及影响因素分析

目的了解郑州市近视小学生心理健康状况及其影响因素,为提高近视小学生心理健康水平提供依据。方法采用分层整群随机抽样方法,在河南省人民医院视光学中心随机抽取325名就诊的近视小学生,选用小学生心理健康评定量表(MHRSP)调查心理健康状况,采用Logistic回归模型分析近视小学生心理健康状况的影响因素。结果近视小学生心理健康状况不良发生率为28.31%。多因素Logistic回归分析结果显示,年龄小、近视度数高、近视度数进展快和存在同伴交往问题是影响近视小学生心理健康的危险因素(P<0.05)。结论郑州市近视小学生心理健康状况仍需改善,相关部门应对其危险因素进行早期识别和有效干预,以改善近视小学生的心理状况。

小学生特质情绪智力与校园欺凌的现状特点及其关系

校园欺凌一直是我国社会各界关注的热点问题。通过问卷调查法,以906名小学生为研究对象,考察小学生校园欺凌的特点及特质情绪智力与校园欺凌的关系。研究发现:小学校园存在欺凌行为,男孩遭受身体欺凌显著高于女孩;母亲具有研究生学历所遭受的言语欺凌显著高于母亲具有初中、高中、大学学历;特质情绪智力与校园欺凌及其各维度显著负相关,且情绪倾向、自尊、同伴关系显著预测校园欺凌。小学校园欺凌防治建议:切实关注男孩校园欺凌现象,提高男孩特质情绪智力;不可忽视高学历家庭孩子的情绪问题与行为问题;高度重视小学生的情绪倾向、自尊及同伴关系。

去骨瓣减压术治疗颅脑损伤后血肿增大的风险因素分析

目的研究去骨瓣减压术治疗颅脑损伤后血肿增大的风险因素。方法回顾性分析2022年1月至2023年8月本院收治的颅脑损伤117例,所有患者均行去骨瓣减压术,根据术后CT检查血肿是否增大分为发生组(n=62)与未发生组(n=55)。比较两组一般资料及鹿特丹CT评分(Rotterdam CT)、格拉斯哥昏迷评分(GCS)间的差异,经多因素Logistic回归分析去骨瓣减压术治疗颅脑损伤后血肿增大的危险因素。结果两组患者性别、合并高血压、高脂血症、冠心病比较差异无统计学意义(P>0.05),发生组年龄≥65岁、瞳孔散大、发病至开颅时间<4h占比及RotterdamCT评分、血糖、骨瓣最大径明显高于非血肿增大组,GCS评分低于未发生组,差异有统计学意义(P<0.05);多因素Logistic回归分析结果显示,年龄、Rotterdam CT评分、GCS评分、瞳孔状态、发病至开颅时间、血糖、骨瓣最大径是颅脑损伤患者术后血肿增大的危险因素(P<0.05)。结论颅脑损伤患者术后血肿增大受诸多因素影响,其中年龄、瞳孔状态、GCS评分、Rotterdam CT评分、发病至开颅时间、血糖、骨瓣最大径可预测患者术后血肿情况,应予以密切关注。