METHODS: The model adopts an architecture which detects each person in the crowd, spots head location with a bounding box and does the counting in our own novel dataset (HAJJ-Crowd).
RESULTS: Our algorithm outperforms the state-of-the-art method, and attains a remarkable Mean Absolute Error result of 200 (average of 82.0 improvement) and Mean Square Error of 240 (average of 135.54 improvement).
CONCLUSIONS: In our new HAJJ-Crowd dataset for evaluation and testing, we have a density map and prediction results of some standard methods.
SUBJECTS AND METHODS: An online questionnaire in a Google form link was circulated among the target population via various online platforms. It consisted of 14 close-ended questions assessing these students' knowledge and source of COVID-19-related information. SPSS software version 21.0 (IBM Corp., Armonk, NY, USA) was used to compute descriptive statistics, Chi-square test, independent t-test, and ANOVA tests for comparing various variables, and a p-value<0.05 was considered statistically significant.
RESULTS: The study yielded 809 responses from dental undergraduate students from India, Saudi Arabia, Malaysia, and Turkey. Dental students from Turkey reported a higher mean knowledge score of 7.91±1.34 and 7.88±0.58 for Malaysian dental students. In contrast, the lower scores were achieved by Saudi Arabia (7.36±1.22) and India (7.37±1.21) dental students, and the findings were statistically significant (p<0.05). The study population used various sources to attain information regarding COVID-19. Most respondents (63.1%) utilized information regarding COVID-19 from multiple sources rather than single sources (36.9%).
CONCLUSIONS: Reliable and validated information sources resulted in higher knowledge scores. Turkey and Malaysia dental students reported a higher mean knowledge score and the lowest for Saudi Arabia and India dental students. There is increased popularity of social media platforms as information sources.