The integration of Artificial Intelligence (AI) holds immense potential for revolutionizing education; especially, in contexts where multimodal learning experiences are designed. This paper investigated the potential benefits of Generative Artificial Intelligence (AI) in education, concentrating on the design and evaluation of an AI Educational Video Assistant tailored for multimodal learning experiences. The tool, utilizing the principles of the Cognitive Theory of Multimedia Learning (CTML), comprises three modules: Transcription, Engagement, and Reinforcement, each focusing on distinct aspects of the learning process. It Integraties Automatic Speech Recognition (ASR) using OpenAI's Whisper and Google's Large Language Model (LLM) Bard. Our twofold objective includes both the development of this AI assistant tool and the assessment of its effect on improving the learning experiences. For the evaluation, a mixed methods approach was adopted, combining human evaluation by nine educational experts with automatic metrics. Participants provided their perceptions on the tool's effectiveness in terms of engagement, content organization, clarity, and usability. Additionally, automatic metrics including Content Distinctiveness and Readability scores were computed. The results from the human evaluation suggest positive impacts across all assessed domains. The automatic metrics further proved the tool's ability in content generation and readability. Collectively, these preliminary results highlight the tool's potential to revolutionize educational design and provide personalized and engaging learning experiences.

The recent advancements in the fields of AI technology, generative AI, and Large Language Models (LLMs) have increased the potential of the deployment of such tools in educational environments, especially in contexts where student assessment fairness, quality, and automation are a priority. This study introduces an AI-enhanced evaluation tool that utilizes OpenAI’s GPT-4 and the recently released custom GPT feature to evaluate the typography designs of 25 students enrolled in the Visual Media diploma offered by King Abdulaziz University. A mixed methods approach is adopted to evaluate the performance of this tool against the rubric-based evaluations offered by two human evaluators, considering both grading and text feedback. The results indicate that there are statistically significant differences between the AI tool’s grading and feedback when compared to that of Evaluator 2; however, none is reported with Evaluator 1. The study presents a qualitative interpretation of the comprehensive feedback by the evaluator and reflects in further research in this area.

Arabic Sign Language (ArSL) is similar to other sign languages in terms of the way it is gestured and interpreted and used as a medium of communication among the hearing-impaired and the communities in which they live in. Research investigating sensor utilization and natural user interfaces to facilitate ArSL recognition and interpretation, is lacking. Previous research has demonstrated that there is not a single classifier modeling approach that can be suitable for all hand gesture recognition tasks, therefore, this research investigated which combination of algorithms, set with different parameters used with a sensor device, produce higher ArSL recognition accuracy results in a gesture recognition system. This research proposed a dynamic prototype model (DPM) using Kinect as a sensor to recognize certain ArSL gestured dynamic words. The DPM used eleven predictive models of three algorithms (SVM, RF, KNN) based on different parameter settings. Research findings indicated that highest recognition accuracy rates for the dynamic words gestured were achieved by the SVM models, with linear kernel and cost parameter = 0.035.

In the field of Cyber Threat Intelligence (CTI), the scarcity of high-quality and labelled datasets that include Indicators of Compromise (IoCs) impact the design and implementation of robust predictive models that are capable of classifying IoCs in online communication, specifically in social media contexts where users are potentially highly exposed to cyber threats. Thus, the generation of high-quality synthetic datasets can be utilized to fill this gap and develop effective CTI systems. Therefore, this study aims to fine-tune OpenAI’s Large Language Model (LLM), Gpt-3.5, to generate a synthetic dataset that replicates the style of a real social media curated dataset, as well as incorporates select IoCs as domain knowledge. Four machine-learning (ML) and deep-learning (DL) models were evaluated on two generated datasets (one with 4000 instances and the other with 12,000). The results indicated that, on the 4000-instance dataset, the Dense Neural Network (DenseNN) outputs the highest accuracy (77%), while on the 12,000-instance dataset, Logistic Regression (LR) achieved the highest accuracy of 82%. This study highlights the potential of integrating fine-tuned LLMs with domain-specific knowledge to create high-quality synthetic data. The main contribution of this research is in the adoption of fine-tuning of an LLM, Gpt-3.5, using real social media datasets and curated IoC domain knowledge, which is expected to improve the process of synthetic dataset generation and later IoC extraction and classification, offering a realistic and novel resource for cybersecurity applications.

The objective of this research is to detect, recognize and interpret hand gestures of Arabic Sign Language (ArSL) letters using two sensor devices - Microsoft's Kinect and a Leap Motion Controller (LMC). The image data captured of the body and the hands' skeletal structure were processed using a supervised learning approach and natural user interface libraries. This research developed a model to examine 1400 signs gestured by 20 users for 28 ArSL letters. The depth images of the hand captured by the sensors extracted 77 angles for each joint and 26 angles between each two bones. To overcome the challenge of time complexity of capturing and interpreting data for this model, the Principle Component Analysis (PCA) algorithm was used for simplification of the large dataset by deleting redundant, irrelevant or erroneous data due to noise. By using PCA, the 103 captured data for each gestured letter was reduced to 36 which is enough to provide more than 99% variance of the data. Then by implementing the Kernel Support Vector Machine (KSVM) classifier on the remaining dataset, the overall accuracy results for the training data increased to approximately 93% using the SVM algorithm, while the accuracy for identifying the corresponding Arabic sign language letters from the test data was at 86%.

Background: The efficient performance of an Emergency Department (ED) relies heavily on an effective triage system that prioritizes patients based on the severity of their medical conditions. Traditional triage systems, including those using the Canadian Triage and Acuity Scale (CTAS), may involve subjective assessments by healthcare providers, leading to potential inconsistencies and delays in patient care. Objective: This study aimed to evaluate six Machine Learning (ML) models K-Nearest Neighbors (KNN), Support Vector Machine (SCM), Decision Tree (DT), Random Forest (RF), Gaussian Naïve Bayes (GNB), and Light GBM (Light Gradient Boosting Machine) for triage prediction in the King Abdulaziz University Hospital using the CTAS framework. Methodology: We followed three essential phases: data collection (7125 records of ED patients), data exploration and processing, and the development of machine learning predictive models for ED triage at King Abdulaziz University Hospital. Results and conclusion: The overall predictive performance of CTAS was the highest using GNB = 0.984 accuracy. The CTAS-level model performance indicated that SVM, RF, and LGBM achieved the highest performance regarding the consistency of precision and recall values across all CTAS levels.