Objectives:To investigate the prevalence and correlates of smartphone addiction among university students in Saudi Arabia.Methods:This cross-sectional study was conducted in King Saud University, Riyadh, Kingdom of Saudi Arabia between September 2014 and March 2015. An electronic self administered questionnaire and the problematic use of mobile phones (PUMP) Scale were used.Results:Out of 2367 study subjects, 27.2% stated that they spent more than 8 hours per day using their smartphones. Seventy-five percent used at least 4 applications per day, primarily for social networking and watching news. As a consequence of using the smartphones, at least 43% had decrease sleeping hours, and experienced a lack of energy the next day, 30% had a more unhealthy lifestyle (ate more fast food, gained weight, and exercised less), and 25% reported that their academic achievement been adversely affected. There are statistically significant positive relationships among the 4 study variables, consequences of smartphone use (negative lifestyle, poor academic achievement), number of hours per day spent using smartphones, years of study, and number of applications used, and the outcome variable score on the PUMP. The mean values of the PUMP scale were 60.8 with a median of 60.Conclusion:University students in Saudi Arabia are at risk of addiction to smartphones; a phenomenon that is associated with negative effects on sleep, levels of energy, eating habits, weight, exercise, and academic performance.

In recent years, handwritten character recognition has become an active research field. In particular, digitalization has triggered the interest of researchers from various computing disciplines to address several handwriting related challenges. Despite these efforts, there are still opportunities for the development and improvement of the recognition of the handwritten Arabic letters. In this paper, we designed and developed a deep ensemble architecture in which ResNet-18 architecture is exploited to model and classify character images. Specifically, we adapted ResNet-18 by adding a dropout layer after all convolutional layer and integrated it in multiple ensemble models to automatically recognize isolated handwritten Arabic characters. A standard Arabic Handwritten Character Dataset (AHCD) was used in the experiments to train and assess all the proposed models. Satisfactory results were obtained using all models. The best-attained accuracy was 98.30% using a typical ResNet-18 model. Similarly, 98.00% and 98.03% accuracies were obtained using an ensemble model with one fully connected layer (1 FC) and an ensemble with two fully connected layers (2 FC) coupled with a dropout layer, respectively.

No abstract

No abstract

No abstract