Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
3 results
Search Results
Item Restricted SERVICE NETWORK OPTIMIZATION TO GUIDE DECISIONS ON INFRASTRUCTURE INVESTMENT(George Mason University, 2023-12-13) Alyahya, Bedor; Brodsky, AlexanderInterrelated infrastructures, such as manufacturing, supply chain, renewable energy and smart grid, are critical for achieving long-term organizational and societal goals and enabling future growth. Deciding on infrastructure portfolio investment is a complex problem, given the uncertainty in future supply and demand, the rapid emergence of new technologies, and non-trivial operational interactions among the infrastructure components. Today, models and systems supporting stakeholders in infrastructure investment decisions either (1) express the investment model in high-level financial terms, which fails to accurately express the underlying operational system behavior over the investment time horizon, or (2) are hard- wired to a siloed domain-specific investment problem, which does not take into account interactions with interrelated infrastructures across the silos and inhibits the widespread adoption and re-usability of these models. Thus, both accurate and flexible investment decision models and systems are needed to recommend investment alternatives and guide stakeholders in making Pareto-optimal trade-o↵s between competing performance indicators such as total cost of ownership, carbon emissions and quality of service. This dissertation is driven by the need to overcome the aforementioned gap of investment decisions made in silos, as opposed to accounting for the synergistic value of strongly interdependent infrastructures. More specifically, the key contributions of this dissertation are as follows. First, designed and developed are formal predictive Analytic Models (AM) for both steady-state and tran- sient Service Networks. These models express metrics, capacity, and demand constraints over a specified time horizon as functions of fixed and controllable parameters, representing investment choices and precise operational settings throughout investment periods. Second, developed is a modular, extensible repository of investment component models, such as pumps, renewable energy sources, water and energy storage, Reverse Osmosis plants, transformers, energy contracts and electric and gas boilers, renewable energy certificates (RECs) and carbon o↵sets. Third, designed and developed are Decision Guidance Systems for both steady-state and transient models for investment in Service Networks. These systems optimize performance metrics and analyze Pareto-optimal trade-o↵s between di↵erent financial, environmental, and quality-of-service investment objectives leveraging a mixed-integer linear programming solver. As a specialization in the domain of Energy and Sustainability, developed is the Green Assessment and Decision Guidance Tool (GADGET.) Finally, a case study is conducted to provide recommendations to George Mason Uni- versity’s stakeholders on the most cost-e↵ective approach to achieve its carbon neutrality goals by 2040. GADGET provides recommendations for Pareto-optimal operational settings and investment choices related to the integration of renewable energy sources and related infrastructures with existing systems.4 0Item Restricted Utilising Technical Analysis, Commodities Data, and Market Indices to Predict Stock Price Movements with Deep Learning(Cardiff University, 2024) Aloraini, Osama Mohammed A; Sun, XianfangThis study investigates the efficacy of deep learning models, specifically Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), for forecasting stock price movements in the U.S. stock market. The dataset used includes 133 stocks across 19 different sectors and covers the period from 2010 to 2023. Moreover, to enrich the dataset, eleven technical indicators and their corresponding trading strategies, represented as vectors, were integrated along with market indices and commodities data. Consequently, various experiments were conducted to assess the effectiveness of different feature combinations. The findings reveal that the CNN model outperforms the LSTM model in both accuracy and profitability, achieving the highest accuracy of 59.7%. Furthermore, models demonstrated an ability to identify significant trend-changing points in stock price movements. Another finding shows that translating trading strategies into vector form plays a critical role in enhancing the performance of both models. However, it was observed that incorporating external features like market indices and commodities data led to model overfitting. Conversely, relying only on stock-specific features triggered a risk of model underfitting.64 0Item Restricted A Review Of Small Fish Movement And Personality Behavior To And From Ephemeral Wetlands Of The Florida Everglades(Saudi Digital Library, 2022-10-31) Alsharif, Rola; Jeffrey, Hoch; Lauren, NadlerEverglades freshwater fish communities are increasingly under threat from anthropogenic pressures, particularly alteration to the hydrological regime (e.g. drainage ditches that lower water tables or culverts that direct agricultural or urban runoff into the site). The ecological consequences of altered hydrology for ephemeral wetland ecosystems include declining fish abundance and diversity, food web connectivity, microhabitat availability for reproduction, refuge, and migration. Understanding how individual behaviors and personality of freshwater fish in ephemeral wetlands scale up to population and landscape-level processes is critical to develop the best management and conservation strategies for preserving fish biomass in freshwater ecosystems. Therefore, in this thesis, I review the studies focused on fish movement behavior and personality in wetlands to aid resource managers in developing evidence-based conservation strategies, to develop parameterized models of animal migration across landscapes, and to improve our understanding of metacommunities.9 0