Nowadays, hand gestures have become a booming area for researchers to work on. In communication, hand gestures play an important role so that humans can communicate through this. So, for accurate communication, it is necessary to capture the real meaning behind any hand gesture so that an appropriate response can be sent back. The correct prediction of gestures is a priority for meaningful communication, which will also enhance human–computer interactions. So, there are several techniques, classifiers, and methods available to improve this gesture recognition. In this research, analysis was conducted on some of the most popular classification techniques such as Naïve Bayes, K-Nearest Neighbor (KNN), random forest, XGBoost, Support vector classifier (SVC), logistic regression, Stochastic Gradient Descent Classifier (SGDC), and Convolution Neural Networks (CNN). By performing an analysis and comparative study on classifiers for gesture recognition, we found that the sign language MNIST dataset and random forest outperform traditional machine-learning classifiers, such as SVC, SGDC, KNN, Naïve Bayes, XG Boost, and logistic regression, predicting more accurate results. Still, the best results were obtained by the CNN algorithm.
hand gesture recognitionsign language recognitionclassifier comparisonrandom forest
Background In the emergency department (ED), dealing with deaf patients presents unique difficulties and obstacles. There is insufficient time to arrange for an interpreter. While the voice of the deaf patient was the focus of earlier studies, in this study, we are interested in learning about ED physicians' difficulties and expertise. In addition, we aim to determine which approaches they suggest to address these issues. Methodology A cross-sectional analysis was conducted among 166 emergency physicians working in pediatric and adult departments. The data were collected from physicians working in different centers in Riyadh city from January 2022 to March 2022. The data analysis was performed using SPSS version 23 (IBM Corp., Armonk, NY, USA). Results In their department policy and procedures, 74.1% of participants claimed no policy or procedure for dealing with deaf patients. The majority of available communication methods were family interpreters (63.9%) and writing on paper (16.9%). Overall, 88% of respondents did not attend any training on dealing with deaf patients, despite the fact that 83.7% thought such training should be available. Furthermore, 90.4% of the participants did not know sign language. Concerning information about the Saudi Association for Hearing Impairment Services, 74.1% were unaware of such services. Concerning modern applications on smartphones, 97.6% were unaware of any existing communication app that could aid in communication with deaf patients. Conclusions In this study, we identified a significant deficiency in the knowledge and skills required to communicate with deaf patients. Hence, we recommend mandating education for physicians and requiring each institution to have an interpreter available 24 hours a day, either in person or via high-quality remote video.
deaf patientsemergency department communicationphysician-patient communicationsign language