Search

This paper aims to promote technology usage among older Saudi people by addressing the common problems they encounter around adhering to medication schedules and using mobile health applications. An interactive mobile user interface has been designed based on requirements determined using three inputs: (1) relevant existing research work, (2) interviews with medicine specialists, and (3) a survey of 602 older Saudis. The output from the first input is a set of updated guidelines adapted to the older Saudi population and reconstructed based on cognitive process attributes. The interview output identifies medication adherence issues and proposed solutions. The survey output produced a mobile technology model for older Saudis. The guidelines have been applied to a prototype and then tested in two phases: (1) pilot testing and (2) usability testing. In the testing phase, 50 older Saudi users provided insights into the effectiveness, error safety, and productivity factors of the solution developed, with the results confirming that designing mobile applications based on the model of older users and cognitive attributes improved effectiveness and reduced errors when performing mobile tasks, specifically around adherence to medications. For the productivity factor, the results align with the physical characteristics of the targeted older individuals, who typically require more time than younger people to perform certain tasks. [ABSTRACT FROM AUTHOR]

Recognizing and localizing anomalous events in crowd scenes is a challenging problem that has attracted the attention of researchers in computer vision. Surveillance cameras record scenes that require an automated examination to identify anomalous events. Existing approaches in the field have utilized different feature descriptors, modeling methods, and recognition strategies to accurately and efficiently detect anomalies in the scene. Existing techniques in the field have focused mainly on performing global frame-level identification of abnormal events. Only a small number of studies have considered locating abnormal action in the frame. Proposed methods are also often evaluated on scenes that contain a sparse number of individuals performing abnormal and normal staged acts. This research aims to detect and locate anomalies in a structured and unstructured dense crowd scene. The proposed model first detects moving objects and individuals in the scene using a deep convolutional neural network and tracks objects and individuals using spatial and temporal features. Then, spatial-temporal features are extracted from consecutive frames of interest points. The extracted features include the histogram of optical flow, velocity and direction of moving objects, and other features that can indicate sudden motion change. A support vector machine model is then used to classify abnormal events into one of seven classes. The proposed methodology is evaluated on Hajj2 dataset that has 18 videos and 7 different types of abnormal events. [ABSTRACT FROM AUTHOR]

Distracted driving plays a significant role in road accidents worldwide. Detecting distracted driving in real time is a significant challenge faced by law enforcement officers. Although efforts are continuing to identify this type of infraction in an automated manner, most of the techniques proposed for this problem use images obtained internally from vehicles. Few studies have looked into using roadway images collected in naturalistic situations. We propose in this research a complete and fully automated deep-learning approach that locates vehicles in roadway images, detects and extracts license plate numbers, detects the windshield region, and classifies images into predefined violations. The proposed approach is complete in that it does not rely on roadway license plate systems to localize the vehicle of interest and extract the license plate numbers. The model performance-both overall and in each stage-was evaluated, achieving 90 % overall classification accuracy. The model is trained and tested on a real-world local dataset of 10,000 images. The dataset used in this study is the first dataset acquired from roadway license plate cameras in the Middle Eastern region showing unique variations of plate forms, driving habits, regional attire, and weather conditions. [ABSTRACT FROM AUTHOR]