Real-Time Arabic Sign Language Recognition Using a Hybrid Deep Learning Model.

Sign language is an essential means of communication for individuals with hearing disabilities. However, there is a significant shortage of sign language interpreters in some languages, especially in Saudi Arabia. This shortage results in a large proportion of the hearing-impaired population being deprived of services, especially in public places. This paper aims to address this gap in accessibility by leveraging technology to develop systems capable of recognizing Arabic Sign Language (ArSL) using deep learning techniques. In this paper, we propose a hybrid model to capture the spatio-temporal aspects of sign language (i.e., letters and words). The hybrid model consists of a Convolutional Neural Network (CNN) classifier to extract spatial features from sign language data and a Long Short-Term Memory (LSTM) classifier to extract spatial and temporal characteristics to handle sequential data (i.e., hand movements). To demonstrate the feasibility of our proposed hybrid model, we created a dataset of 20 different words, resulting in 4000 images for ArSL: 10 static gesture words and 500 videos for 10 dynamic gesture words. Our proposed hybrid model demonstrates promising performance, with the CNN and LSTM classifiers achieving accuracy rates of 94.40% and 82.70%, respectively. These results indicate that our approach can significantly enhance communication accessibility for the hearing-impaired community in Saudi Arabia. Thus, this paper represents a major step toward promoting inclusivity and improving the quality of life for the hearing impaired.

Awareness and Attitudes Toward Childhood Mental Disorders Among Primary School Teachers in Taif, Saudi Arabia.

Background and aim Early detection and intervention can improve the treatment outcome of childhood mental disorders, and primary school teachers may play an important role in referring suspected cases to mental health facilities if they have good awareness and attitudes toward these disorders. The aim of this study is to assess the awareness and attitudes of primary school teachers toward childhood mental disorders in Taif, Saudi Arabia. Methods This is a cross-sectional study conducted among classroom teachers in primary schools in Taif, Kingdom of Saudi Arabia. It was conducted during the period from 2022 to 2023 in both public and private schools. An anonymous, self-administered, online questionnaire was used to assess participants' awareness and attitudes toward pupils with mental health issues. The collected data were analyzed using the chi-square test to examine the associations between various categories and the ANOVA test to compare means. Results The study included 417 teachers, 63.5% of whom were males, the mean of their ages was 39.59 years (SD±8.66), and the mean of their work experience was 12.8 years (SD±8.02) in different teaching specialties. Among participants, 60.2% claimed that no pupils had mental health problems in their classes, 80.1% had not referred any pupils to mental health facilities, and 88.5% did not receive any training related to childhood mental health problems. A humble percent (12.2%) of the participants claimed a good awareness of the signs and symptoms of childhood disorders. Only 54% of teachers advise visiting a psychiatric clinic in case of psychiatric problems, and a similar percentage of teachers believe that psychiatric drugs cause addiction. The male gender, being specialized in humanitarian subjects, having relatives or friends with childhood mental disorders, and receiving training related to childhood mental health were significantly associated with teachers' better awareness. Conclusion Primary school teachers generally lack awareness of childhood mental health and have underestimation and poor recognition of cases of mental disorders. There are many teachers who also have unfavorable attitudes toward psychiatric disorders, patients, and treatments, which requires much effort to improve their awareness and attitudes toward childhood mental disorders.

Childhood Obesity May Be Linked to Feeding Habits and Screen Time.

Background Childhood obesity is an alarming health problem. Early feeding habits and factors are among the etiological factors contributing to obesity. Objectives The objective of this study is to evaluate the correlation between breastfeeding, alongside other relevant factors, and their potential role as preventative measures against obesity. Methods A cross-sectional hospital-based study was conducted on children who attended a pediatric clinic. Demographic, clinical, and anthropometric measurements were taken from the hospital records. A questionnaire was completed by parents telephonically. Overweight was identified as a body mass index (BMI) of > 85-95% and obesity as a BMI of > 95%. Results A total of 101 children, with a mean age of 8.88 ± 4.01 (range one to 18) years, were involved, of whom 58.4% were boys. A high BMI (overweight or obese) was found in 30 (29.7%) children. The highest BMIs were among soft drink consumers [two children (66.7%) consumed daily and eight children (40%) consumed monthly], high birth weight in two children (40%), cow's milk formula feeding in eight children (38%), and weekly fast food consumption in 18 children (35%), none of these were statistically significant. Nevertheless, there was a significant association between mean electronic device usage and high (204.5 ± 164.76 hours) and normal BMI (147.61 ± 110.24 hours) (p-value < 0.05). Conclusion This small cross-sectional study shows that almost one-third of the included children were overweight or obese, which is comparable to what has been published in the literature. Moreover, there was a potential link between some factors and obesity, especially screen time, which may contribute to the controversial literature.