Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
2 results
Search Results
Item Restricted Industrial AI-based Workload Performance Analytics: Applications to Mixed Reality Multitasking(University of Illinois at Chicago, 2025) Abbas, Safanah; He, DavidImmersive technologies such as augmented and virtual reality are increasingly integrated into our daily lives. As this digital transformation progresses, understanding human reactions to these technologies becomes crucial, particularly in the context of human factors engineering, which prioritizes human safety and well-being. Mixed reality (MR), which blends the physical and virtual worlds, introduces new multitasking possibilities but also presents challenges. One critical aspect is the impact of MR multitasking on human workload, a key performance measure. This research employs an Industrial AI approach, combining traditional machine learning with advanced pre-trained models to develop predictive models for estimating human workload in MR environments. An experiment was conducted in which participants multitasked between a physical and a digital task within a defined timeframe. Workload data, collected via the NASA Task Load Index (NASA-TLX), was used alongside synthetic data generated by a Generative Adversarial Network (GAN) to create an enriched dataset. The combined real and synthetic data were then used to train predictive models, enhancing accuracy. To improve workload prediction, this study integrates pre-trained models such as BERT (Bidirectional Encoder Representations from Transformers) from large language models (LLMs) and CLIP (Contrastive Language-Image Pretraining) from computer vision applications, alongside traditional machine learning techniques like regression and neural networks. Evaluation using the Root Mean Square Error (RMSE) metric demonstrates that the proposed hybrid models incorporating transfer learning and pre-trained models significantly outperformed conventional methods. The deviations between actual and predicted values were minimal, indicating a more reliable workload estimation. This dissertation advances knowledge in human factors engineering by addressing a critical gap in workload prediction within MR multitasking environments. The findings provide insights into human-computer interaction in complex digital settings. Organizations implementing MR technologies can leverage these predictive models to better understand worker workload and optimize conditions for well-being and efficiency.8 0Item Restricted Legal Judgment Prediction for Canadian Appeal Cases(University of Ottawa, 2024) Almuslim, Intisar; Inkpen, FianaLaw is one of the knowledge domains that are most reliant on textual material. In this age of legal big data, and with the increased availability of legal text online, many researchers started working on the development of legal intelligent systems and applications. These intelligent systems can provide great services and solve many problems in the legal domain. Over the last few years, researchers have focused on predicting judicial case outcomes using Natural Language Processing (NLP) and Machine Learning (ML) methods over case documents. Thus, Legal Judgment Prediction (LJP) is the task of automatically predicting the outcome of a court case given the case description. To the best of our knowledge, no prior research with this intention has been conducted in English for appeal courts in Canada, as of 2023. The NLP application to legal judgments, that our proposed methodology focuses on, is to predict the outcomes of cases by looking only at the text of cases. Because appeal court decisions are often binary, as in ’Allow’ or ’Dismiss’, the task is defined as a binary classification problem. This is the general approach in the literature as well. However, many of the previous LJP approaches utilized traditional classifiers or standard general language models (LMs). In our thesis, we constructed a Canadian Appeal-Law dataset (CanAL-DS) that contains a collection of decisions from different higher courts in Canada. In addition, we further pre-trained the LegalBERT model on our collected corpus that combines around 50,000 documents of Canadian case law and legislation which resulted in (CanAL) LegalBERT, a Canadian Appeal-Law BERT-based legal model. Moreover, we proposed a novel Ensemble-Hierarchical CanAL (EH-CanAL) architecture that simulates the actual voting setting in appellate courts showing great promise in LJP performance within Canadian case law. We improved the architecture with a multi-task component (MEH-CanAL) to help the model identify what legal paragraphs require the most attention and facilitate its explainability. Results from our study demonstrate the potential for the proposed approaches to reshape traditional judicial decision-making and the efficacy of domain-specific language models. Through this study, we hope to establish the basis for future research on the appellate law system of Canada and offer a baseline for future work.21 0