Agent-based modeling can study any social behavior and decision making process, as agents make decisions based on an internal logic network and try to imitate human behavior. Companies use models to manage pricing, logistics, and operations; legislators use societal models to debate policy and macroeconomic action; economists use them to analyze stimuli and microeconomic behavior; doctors use modeling to study the spread and transmission of infectious diseases. Proponents say that models based on agent interactions can inspire insight into policy and predict aggregate human behavior. Detractors concern themselves with the applicability of these results and whether such agents can fundamentally capture the nuance of human behavior. The solution lies in additional scale and compliexity, often expensive to simulate and impossible to with current computational methods for simulation. In this paper, we explore a new approach to agent-based modeling incorporating the properties of quantum mechanics and quantum computing. We build quantum adaptive long-term learning agents to measure the influence of external stimuli on a simple business structure comprised of those agents and evaluate the performance benefits from a quantum approach. To our knowledge, we contribute the first quantum-based model of economic systems to the literature.

Flapping-fin unmanned underwater vehicle (UUV) propulsion systems enable high maneuverability for tasks ranging from station-keeping to surveillance but are often constrained by their limited computational power and battery capacity. Previous research has demonstrated that time-series neural network models can accurately predict the thrust and power of certain fin kinematics, based on the specified gait coupled with the fin configuration, but can not fit an inverse neural network that takes a thrust request and tunes the kinematics by weighting thrust generation, smooth movement transitions, and power attributes. We study various combinations of weights and fin materials to create different ‘modes’ of movement for a multi-objective UUV, based on controller intent. Finally, we validate our enhanced inverse model through benchmarking on the Raspberry Pi system and testing through generated simulated movements.

Flapping-fin unmanned underwater vehicle (UUV) propulsion systems provide high maneuverability for naval tasks such as surveillance and terrain exploration. Recent work has explored the use of time-series neural network surrogate models to predict thrust from vehicle design and fin kinematics. We develop a search-based inverse model that leverages a kinematics-to-thrust neural network model for control system design. Our inverse model finds a set of fin kinematics with the multi-objective goal of reaching a target thrust and creating a smooth kinematic transition between flapping cycles. We demonstrate how a control system integrating this inverse model can make online, cycle-to-cycle adjustments to prioritize different system objectives.

The last few decades have led to the rise of research focused on propulsion and control systems for bio-inspired unmanned underwater vehicles (UUVs), which provide more maneuverable alternatives to traditional UUVs in underwater missions. Propulsive efficiency is of utmost importance for flapping-fin UUVs in order to extend their range and endurance for essential operations. To optimize for different gait performance metrics, we develop a non-dimensional figure of merit (FOM), derived from measures of propulsive efficiency, that is able to evaluate different fin designs and kinematics, and allow for comparison with other bio-inspired platforms. We create and train computational models using experimental data, and use these models to predict thrust and power under different fin operating states, providing efficiency profiles. We then use the developed FOM to analyze optimal gaits and compare the performance between different fin materials. These comparisons provide a better understanding of how fin materials affect our thrust generation and propulsive efficiency, allowing us to inform control systems and weight for efficiency on an inverse gait-selector model.

The United Nations (UN) is the foremost international body helping uphold world peace through peacekeeping missions, ranging from deployments that enforce peace treaties, monitor conflicts, and protect civilians; However, determining when and how to intervene is complex. The updated UN General Debate Corpus (UNGDC), cataloging every speech from the UN's inception in 1946 to 2022, is a treasure trove of national policy, as the UNGD is the only body where every country can speak. We propose a discourse-driven intervention recommendation framework that categorizes ongoing conflicts based on UN precedent and recommends the magnitude of funds and forces that should be committed to addressing a conflict. We employ natural language processing techniques to tokenize, preprocess, and analyze word stem frequencies in the UNGDC, generating a timeseries of the number of UN mentions for any given country. Paired with historical analysis, we show that debate in the UNGDC is a potent indicator to determine UN intervention and response mechanisms for conflicts in Africa; further, by aggregating mention statistics across periods of active conflict, we provide quantitative backing for the correlation of mention dynamics and the presence of an active conflict, for a given country. Finally, we present and test an interpretable, shallow decision tree model that can perform intervention type classification and response magnitude recommendation with 91.7% accuracy. Our results, established by computational experiments and statistical testing, suggest that corpus analysis and broader computational diplomacy methods can drive intervention recommendations to improve the UN’s decision-making.

The effectiveness of international bodies such as the United Nations (UN) at addressing global crises has been debated. The updated UN General Debate Corpus (UNGDC) catalogues every speech from the UN's inception in 1946 to 2022. Using the corpus as an indicator of debate, we explore how African post-colonial states grow influence on the international stage. As these states join the UN immediately after independence, we superimpose historical events on metrics generated from UNGDC to demonstrate the corpus' robustness for forecasting shifts in international priorities. We develop a time series of relevance for each country using natural language processing methods to extract features and tokenize speeches. We conclude that the UNGD preludes intervention in multi-year violent conflicts, with insights into the efficacy of crisis resolution measures in Africa. Our results are established by computational experiments, with conditions validated by statistical significance tests.

Issues over the copyright of Large Language Models (LLMs) have emerged on two fronts: using copyrighted Intellectual Property (IP) in training data, and the ownership of generated content from LLMs. We propose adopting an opt-in system for IP owners with fair compensation determined by tagging metadata. We first suggest the development of new, multimodal approaches for calculating substantial similarity within generated derivative works by using tags for both content and style. From here, compensation and attribution can be calculated and determined, allowing for a generated work to be licensed and copyrighted while providing a financial incentive to opt-in. This system can allow for the ethical usage of IP and resolve copyright disputes over generated content.

The astronomic rise of Machine Learning models has raised regulation concerns among governments internationally, who now face the dilemma of both encouraging AI development but also preventing negative outcomes and results from AI. Generative AI is particularly relevant due to an apparent intelligence and size in those models, which has incited both excitement and concern in the public. This paper investigates the background and methods toward ensuring that generative AI is societally beneficial, companies are accountable, and responsible AI resources are present. We first conduct a formal stakeholder analysis of the different actors party to generative AI which demonstrates a certain power imbalance between producers and consumers, where the developers of intelligent systems have far more influence over the future of AI than the consumers of it. We then proceed to a technical analysis of the central issues in specifically generative AI, where causes and consequences of various policy problems are discussed at length. We finally propose 3 ideas to implement through national level legislation that are designed to be minimally destructive to the strength of the AI industry and that allow a rare technological coexistence with society. Such recommendations include a) an open-source auditing methodology to create transparency, b) an opt-in route for dataset creation, and c) creating education pipelines to equip corporations with necessary talent.

Current methods of diagnosis for neurodegenerative diseases are almost purely qualitative and highly apparent only when extensive neuronal dystrophy and degeneration have occurred. Therefore, creating a clinically viable tool that leverages early biomarkers of neurodegenerative disease is necessary. Past research indicates that ocular biomarkers are a potential source of quantitative assessment for the early diagnosis of neurodegenerative disease. In this paper, we identify specific ocular biomarkers that could be used as a basis for the early detection of neurodegenerative disease, potentially using machine learning techniques. Furthermore, we outline data collection procedures that can be implemented for patients completing Pro-Saccade, Anti-Saccade, Express-Saccadic, and Smooth Pursuit tasks. We expect that the findings in this paper can be utilized to guide the future creation of tools and datasets for developing a gaze-based diagnostic tool.