Computer Engineering Commons^™

A Drl⁃Based Approach For Distributed Equipment Nodes Selection, Ziyi Wang, Kai Zhang, Dianwei Qian, Yuzhen Liu

Journal of System Simulation

Abstract: Aiming at the problem of insufficient solution speed and poor generalization of traditional algorithms in large-scale scenarios, this paper intelligently solves the large-scale distributed equipment system preference problem based on deep reinforcement learning. According to the characteristics of distributed equipment system combat, using the complex network to its graph form modeling, and based on the attention mechanism to the equipment between the connecting edge relationship for the characterization, in order to build a distributed equipment system digital simulation environment. Simulation results show that compared with the genetic evolutionary algorithm, the obtained model has obvious advantages in terms of solution …

Meta-Learning Hyperparameters For Foundation Model Adaptation In Remote-Sensing Imagery, Zichen Tian, Yaoyao Liu, Qianru Sun

Research Collection School Of Computing and Information Systems

Training large foundation models of remote-sensing (RS) images is almost impossible due to the limited and long-tailed data problems. Fine-tuning natural image pre-trained models on RS images is a straightforward solution. To reduce computational costs and improve performance on tail classes, existing methods apply parameter-efficient fine-tuning (PEFT) techniques, such as LoRA and AdaptFormer. However, we observe that fixed hyperparameters -- such as intra-layer positions, layer depth, and scaling factors, can considerably hinder PEFT performance, as fine-tuning on RS images proves highly sensitive to these settings. To address this, we propose MetaPEFT, a method incorporating adaptive scalers that dynamically adjust module …

Adversarial Deep Reinforcement Learning For Tank Duel Simulation Using Lidar-Based Observations, Braedan Kennedy

Master's Theses

Previous research has demonstrated that reinforcement learning agents can learn to steer differential-drive robots around obstacles using 2D lidar scans as observations. However, these studies typically treat all range returns as undifferentiated obstacles—objects to avoid—without distinguishing between different object types. This thesis builds upon previous research by introducing an adversarial task in which an agent must interpret raw range readings to both avoid static obstacles and identify, pursue, and engage a hostile target.

To investigate this problem, this thesis introduces TankGame, a novel, lightweight 2D tank duel simulator. Each agent receives a 360° lidar scan, controls its motion via tread …

Adversarial Robustness In Advanced Machine Learning Models Integrating Graph Neural Networks And Large Language Models, Mahmoud Nazzal

Dissertations

Artificial intelligence (AI) has achieved remarkable performances across various domains. In most real-world applications, data often takes relational forms, such as graphs and networks, or sequential forms, such as text and time series. As AI evolves, specialized models have emerged to handle these structures; Graph Neural Networks (GNNs) for relational mining and Large Language Models (LLMs) for sequential understanding. Despite their success, these models face challenges in security, robustness, and interpretability. GNNs excel in relational reasoning but are vulnerable to adversarial manipulation and lack interpretability, while LLMs are strong in linguistic reasoning and generalization yet struggle with relational data and …

Gamified Gait Rehabilitation Via Real-Time Biofeedback And Adaptive Hip-Exoskeleton Control, Mariya Huzaifa Tohfafarosh

Theses

Gait impairments arise from systemic diseases, age-related degeneration, musculoskeletal dysfunctions, or neurological conditions. While traditional rehabilitation can be effective, they often face challenges such as high costs, inaccessibility, and low patient engagement. To address these challenges, my work introduces a virtual reality-based rehabilitation (VRBR) system, integrating real-time motion and electromyographic (EMG) muscle activation feedback with a gamified virtual environment for enhanced adaptability and engagement. The system includes a custom-designed hip-exoskeleton that provides adaptive spring-like assistance or resistance, supporting both mobility-impaired users and strength training. Assistance levels can be tuned to match the user's progress. Additionally, a custom pressure insole was …

Selected Artificial Intelligence Provisions In U.S. Fiscal Year 2025 National Defense Authorization Act, Bert Chapman

Libraries Faculty and Staff Presentations

The 2025 Fiscal Year National Defense Authorization Act contains multiple provisions relating to artificial intelligence (AI). These congressionally mandated provisions direct various sections of the Department of Defense (DOD) and individual U.S. armed service branches to execute congressional intent for AI policymaking. Examples of such intent include identifying and planning DOD's AI workforce, demonstrating AI biotechnology applications for national security, improving the human usability of AI systems, and establishing an AI security center. This presentation will note that reports on these initiatives must be prepared for relevant congressional oversight committees, and, in many cases, are in many cases, publicly released …

Research On Grey-Box Modeling Method Of Digital Twins For Cantilever Structure, Wenjia Zhang, Heming Zhang

Journal of System Simulation

Abstract: The construction of accurate and highly real-time digital twin models in complex industrial setting presents several challenges. Traditional model construction approaches based only on mechanism or data show certain limitations. Therefore, this study is based on the idea of grey-box modeling, taking the cantilever structure within a boom-type roadheader as the object, and proposes a novel modeling approach that combines the characteristics of the mechanism model and introduces a self-attention mechanism. This method performs grayscale transformation on the original input and splices it with physical features to achieve organic fusion of mechanism information, which not only enhances the expressiveness …

An Extended Image Features Based Uncalibrated Visual Servoing Method, Shuzhen Zhang, Yukun Cheng, Yangbo Liu, Fusheng Zha

Journal of System Simulation

Abstract: Aiming at the traditional uncalibrated visual servo relying on the estimation of image Jacobi matrix and the coupling of the motion of each degree of freedom of the camera, on the basis of imagebased uncalibrated visual servo, an extended image features based uncalibrated visual servo method is proposed. By analyzing the relationship between image features and camera frames change in the visual servoing process, the visual servoing process in the image space is decomposed into four basic processes: translation, stretching, rotation and scaling; by analyzing the changing of image features in the visual servoing process, extended image features are …

A Modeling And Simulation Method For Firepower Intelligent Decision-Making Of Directed Energy System Basedon Joint Dqn, Changhong Qu, Junjie Wang, Kun Wang, Qingyong Cui, Jiangyang Chen, Xinpeng Wang

Journal of System Simulation

Abstract: In order to solve the problem of dynamically addressing firepower intelligent decision-making in anti-UAV cluster combat using a directed energy system, a deep reinforcement learning model is established. Based on the high multi-agent state and action space dimensions of this model, a modeling and simulation method of firepower intelligent decision-making of directed energy system based on joint deep Q network (DQN) is proposed. The state space is constructed from the state of directed energy system, UAV cluster and the directed energy system deployment area. The joint mechanism is used to share the state information of each equipment and the …

Research On Modeling, Optimization And Application Of Aeroengine Oil System, Shijie Huang, Zhensheng Zhang, Jing Cai, Rui Zhang

Journal of System Simulation

Abstract: In response to the high cost and long cycle of using experimental methods for monitoring, diagnosing, and predicting lubricating oil system, a simulation model for oil system is constructed and optimized, and the application of the model in health management of oil system is proposed. Based on the physical characteristics of the components in the oil system, subsystem models for ventilation, oil supply, thermodynamics, and oil return are constructed using a certain engine oil system as an example, and the whole oil system model is constructed and solved iteratively. The model is optimized by combining particle swarm optimization and …

Adaptive Multi-Scale Feature Pyramid Network For Occlusion Pedestrian Detection, Huaping Zhou, Tao Wu, Kelei Sun

Journal of System Simulation

Abstract: To address the issue of current pedestrian detectors, which struggle to extract complete features in occlusion-heavy environments and consequently have low detection accuracy. A novel adaptive multiscale feature pyramid network is proposed. A multi-scale feature enhancement module (MFEM) is developed. It captures the visible area of pedestrians at different scales through a multi-branch network with different receptive fields. An AFM (adaptive fusion module) is proposed. It calculates the importance of different pixels by optimizing the mean variance at the spatial and feature levels. It enhances the texture and semantic features of pedestrians and fuses the features of different scales …

Design And Realization Of Integrated Energy System Dynamic Stability Simulation And Steady-State Simulation System, Guixiong He, Xiaoqiang Jia, Shufeng Dong, Yonglu Han, Yonghua Chen, Yiming Zheng

Journal of System Simulation

Abstract: Aiming for“carbon peak”and“carbon neutrality”, the energy sector is undergoing significant reform. To address energy flow and planning optimization in integrated energy systems, a comprehensive simulation platform is developed. This platform combines physical and digital simulations with real-world validation and is modular in design, It includes an integrated energy model library, energy flow optimization, modeling management, real-time simulation, and energy monitoring. The platform enhances system safety, stability, and economic efficiency, While also improving planning and energy management. The paper analyzes the platform′s functional and physical architecture, introduces key modules, establishes dynamic and steady-state model libraries, and optimizes energy flow using …

Research On Modeling Methods For Industrial Core Capability Architecture Based On The Dodaf Framework, Xiaoqiang Dou, Yan Liu, Zhilong Zhao, Chao Fu, Fulin Zhang, Shanshan Zou

Journal of System Simulation

Abstract: Against the backdrop of the industrial sector actively pursuing digital capability building, this paper describes the necessity and current status of architecture theory methods guiding industrial core capability construction. It proposes the conceptual connotation of industrial core capability architecture and four key modeling elements. Based on DoDAF, it conducts the overall design of industrial core capability architecture. By integrating systems engineering principles, it establishes a five-stage process model for capability-building activities, embedding critical elements such as capability/business/ application/data/technology architecture viewpoint, and explains data model design, and logical compositions of various viewpoints. By selecting a capability building project in a …

Survey On Large Language Agent Technologies For Intelligent Game Theoretic Decision-Making, Xueqiang Gu, Junren Luo, Yanzhong Zhou, Wanpeng Zhang

Journal of System Simulation

Abstract: The development of artificial intelligence technology has greatly promoted the transformation of the solving paradigm of intelligent game decision problems. From optimal solution, equilibrium solution to adaptive variable solution, how to build an intelligent game adaptive decision agent based on generative large model is full of challenges. The force distribution and multi-entity coordination in the game strong confrontation environment are the core issues in the study of troop deployment and operational coordination. Based on the methods of strategy reinforcement learning, strategy game tree search and strategy preference voting based on skill, ranking and preference meta-game model construction, a large …

Method For Dynamic Coalition Formation Of Wargame Agent For Force Cooperation, Changhua Yao, Shanning Bi, Rufei Ma, Xiaohan Yu, Jiaqiang Li, Jinli Chen

Journal of System Simulation

Abstract: Regarding the issue of cooperative task alliance formation and adjustment in multi-agent dynamic confrontation scenarios at the tactical level, this method comprehensively considers factors such as target value, task allocation, and operator characteristics, as well as the benefits and costs of executing different types of tasks. we propose a targeted force coordination adjustment for dynamic task alliance formation based on behavioral constraints. The “MiaoSuan-Wise Winning Instant Strategy Human-Computer Confrontation Platform” of Chinese Academy of Sciences (CAS) is used as an experimental platform to conduct confrontation experiments. The experiment demonstrates that the proposed method improves the dynamic coordination ability of …

Modeling And Simulation Of Intelligent Underwater Acoustic Countermeasure Based On The Matrix Game, Huijin Zhao, Yu Chen

Journal of System Simulation

Abstract: Due to the great threat of torpedo against surface warships, an efficient hydroacoustic countermeasure system must output real-time strategies to accommodate varied antagonizing scenarios. Aiming at the decision-making problem in the anti-torpedo hydroacoustic countermeasure cases, an intelligent adversarial strategy is proposed based on the game theory. By discretizing the strategy space of both sides, a matrix game model is established where the payoff is characterised by the capture probability of attacking torpedo. An improved simplex algorithm is then developed to get the mixedstrategy Nash equilibrium of the game model, which can be used to obtain preferred avoidance strategies to …

Hierarchical Optimal Scheduling Of Integrated Energy System With Electric Vehicles Based On Empc, Miaomiao Ma, Zijuan Long, Zhiwei Ren, Yongqiang Cheng

Journal of System Simulation

Abstract: A hierarchical real-time optimization (HRTO) based on economic model predictive control is designed to address the issues of randomness and uncertainty of renewable energy and demand-side in integrated energy systems (IES) with electric vehicles. The optimization problem of the entire system is divided into three sub-problems: day-ahead rolling optimization, real-time rolling optimization, and tracking control. The day-ahead optimization strategy based on economic model predictive control is constructed to ensure that the operational units can meet users' demands. The optimal steady-state operating points of the entire IES are obtained through the real-time optimization layer. The tracking model predictive controller is …

Optimal Scheduling Of Virtual Power Plant With Coupled Operation Of Ccs-P2g Considering Wind And Photovoltaic Uncertainty, Xurong Jin, Jiang Yin, Guohua Yang, Wei Li, Guobin Wang, Lele Wang, Na Yang, Xuenian Zhou

Journal of System Simulation

Abstract: In order to solve the problem that the uncertainty of wind power and photovoltaic power generation output easily affects the scheduling of virtual power plant, a new optimal scheduling model of virtual power plant is proposed based on information gap decision theory (IGDT) . In order to reduce the carbon emission of the system, carbon capture and storage (CCS) is installed on the combined heat and power units; in order to improve the utilization rate of renewable energy, the power to gas (P2G) device is introduced into the system, and the operation mode of CCS-P2G coupling is proposed; based …

A Quadrotor Trajectory Tracking Control Method Based On Deep Reinforcement Learning, Guohua Wu, Jiaheng Zeng, Dezhi Wang, Long Zheng, Wei Zou

Journal of System Simulation

Abstract: Traditional quadrotor controllers, constrained by fixed model equation structures, encounter challenges in addressing control errors stemming from variations in parameters and environmental disturbances. This paper proposes a deep reinforcement learning solution for the quadrotor trajectory following control problem. We present the PPO-SAG algorithm incorporated into the PPO framework, utilizing adaptive mechanisms and PID expert knowledge to enhance training convergence and stability. Target functions incorporating distance constraint penalties and entropy policies are designed in alignment with the characteristics of the given problem. We also devise innovative disturbance-adaptive structures and trajectory feature selection mechanisms to augment control error information and extract …

Improved Hybrid Optimization Algorithm For Multi-Objective Ipps Problem, Wenbin Gu, Jiexia Qing, Jie Fang, Siqi Liu

Journal of System Simulation

Abstract: For the problem of multi-objective integrated process planning and scheduling (MOIPPS), an improved hybrid optimization algorithm considering global and local optimum is proposed to optimize two objectives about minimum makespan and energy consumption. A multi-objective problem model and solution framework are established by analyzing the difference and connection between process planning and scheduling in integrated system. A hybrid optimization algorithm is proposed for the two-stage integration problem. In the process planning stage, global search algorithm is employed to provide a variety of process schemes for the integrated system and to ensure the global search performance of the integrated algorithm. …

Optimization Of Cargo Location Allocation In Four-Way Shuttle Warehousing System Based On Two-Stage Hybrid Algorithm, Zisong Wu, Daofang Chang, Yuchun Gai

Journal of System Simulation

Abstract: To address issues such as the dense distribution of storage locations and the potential congestion of shuttle vehicles in the four-way shuttle dense storage system, a grid-based approach to the storage location distribution is developed. A location allocation model is then constructed with the goals of ensuring shelf stability, improving warehousing efficiency, and balancing equipment utilization. A twostage hybrid algorithm is designed for the model. In the first stage, the local search strategy of nondominant sequencing genetic algorithm(NSGA-II) is enhanced by incorporating the hill climbing algorithm to address a set of Pareto front sets. In the second stage, the …

Research On Decision-Making Of Autonomous Driving In Highway Environment Based On Knowledge And Large Language Model, Xiang Wang, Guozhen Tan

Journal of System Simulation

Abstract: Aiming at the lack of continuous learning and interpretability of current autonomous driving system, a decision model with cognition, generalization and learning ability is proposed. The model utilizes large language model (LLM) and attention mechanisms to understand and explain driving scenes. the system can accumulate and learn from driving experiences, continuously improving its decisionmaking ability. In a simulation environment, the closed-loop test decision model is applied in high-speed scenarios.The simulation results show that the success rate of the knowledge-driven model is 7% and 4% higher than those of the rule-based and data-driven methods. Additionally, the model exhibits generalization and …

Robot Path Planning Based On Ant Colony Algorithm With Dual Heuristic Information, Xiaohui Zhou, Yanqiang Li, Yong Wang, Decai Zhao, Xiaoyao Yang

Journal of System Simulation

Abstract: The traditional ant colony algorithm is characterized by a slow convergence speed, numerous turning points, and a tendency to fall into local minima. These characteristics make the algorithm less effective for path planning research in mobile robotics. Therefore, this paper proposes an improved ant colony algorithm and applies it to global path planning for robots. The A* algorithm is used to quickly plan a path and increase the initial pheromone of that path, so that the improved algorithm is guided by the global path during the local search, preventing excessive ants from entering dead ends, and reducing the randomness …

A Simulating Framework Construction Method About New Distributed Confrontation, Zhipeng Liu, Yanyang Gu, Baojie Hu, Fangjun He, Zhipeng Fan

Journal of System Simulation

Abstract: The new distributed confrontation in future emphasizes systematic combat and flexible use of power in the resistance environment. To study and analyze the potential threats of such new forms of distributed confrontation, this paper proposes a system confrontation strategy focused on decisionmaking confrontation from the perspective of network and electromagnetic space. In addition, a highly flexible and saleable behavior model adversarial framework is proposed. By parameterizing the network and electrical countermeasure strategy, an adversarial model based on typical airspace scenarios is designed, and the confrontation effectiveness of traditional multifunctional platforms and distributed units is quantitatively compared and analyzed. The …

Research On A Credibility Information Management Method Of Simulation Modeling, Qiming Gu, Jiazhi Chen, Guoyan Cao, Chenchu Zhou, Dengxiu Yu, Haifeng Hu

Journal of System Simulation

Abstract: A proposed method for managing credibility information in simulation modeling draws insights from the NASA-STD-7009 standard for modeling and simulation. From the perspective of credibility information recording, definition, and assessment, this method aims to address the core issue of whether the credibility requirements are met in simulation modeling research. A simulation system credibility information extraction tool is designed to extract three types of information including modeling credibility information, data credibility information, and development process credibility information, enabling recording, definition, and traceability of credibility information in simulation models. Taking a servo system credibility evaluation as an example, a simulation system …

Developments On Abbreviations Towards Machine Reading Comprehension, Sing Choi

UNLV Theses, Dissertations, Professional Papers, and Capstones

Machine reading comprehension is a critical step in development of applications that require the semantic understanding of human speech-to-text driven work. Many devices such as smart home appliances like the Amazon Echo Dot, Google Home, or smart assistants like Apple Siri or Microsoft Cortana are examples of these applications. The comprehension task involves a deeper understanding and recognition of named entities such as person names, locations, medicals codes, quantities, abbreviations, and acronyms in speech or text data. In this dissertation, we explore and extend the different approaches and techniques in modern research that tackles the problem of recognition and definition …

Elevating Education: Leveling Up Individual Learning Plans, Maximum Mgrdich-Ararat Sirabian

UNLV Theses, Dissertations, Professional Papers, and Capstones

This three-article dissertation investigated the effectiveness, implementation quality, and automation of Individual Learning Plans (ILPs) in promoting college and career readiness. Article 1 analyzed High School Longitudinal Study of 2009 data and found that ILPs did not significantly guide course alignment. Article 2 examined ILP implementation across Nevada high schools, revealing inconsistent quality, limited standardization, and few culturally responsive practices. These findings informed the creation of a new high-quality ILP framework. Article 3 employed a convergent parallel mixed methods design to assess an automated ILP prototype based on this framework. Participants in the automated group reported significantly higher scores in …

Soft Modular Robots: From Modular Tensegrity Structures To Bioinspired Sea Robots, Luyang Zhao

Dartmouth College Ph.D Dissertations

The rapid advancement of robotics necessitates systems capable of adapting to complex, unstructured environments. Soft robots, with their flexibility and compliance, excel in delicate interactions, making them ideal for medical applications and search-and-rescue missions. Modular robots, on the other hand, offer reconfigurability, enabling diverse task-specific adaptations in dynamic settings. Despite their individual advantages, the integration of soft and modular robotics remains underexplored. This proposal aims to develop soft modular robots that combine the adaptability of soft robotics with the versatility of modularity. These systems will be capable of autonomously transitioning between locomotion, manipulation, and infrastructure assembly across land, water, and …

Controlling A Mobile Inverted Pendulum And Optimizing Leaning Angle To Apply Force Using Reinforcement Learning, Aryan Mediratta

2025 Spring Honors Capstone Projects - Archive

Reinforcement Learning is a Machine Learning paradigm that involves simulating learning through rewards and penalties in intelligent systems. This technique is often employed in robotics when traditional control methods are insufficient or when human intuition does not provide a good solution on how to control robot systems, This project involves training a Segway-style Mobile Inverted Pendulum (MIP) robot to balance and push a box forward. The BeagleBone Blue board is used that includes a built-in Inertial Measurement Unit (IMU) and encoder ports. These sensors enable the system to measure its current state. The goal is to find the optimal leaning …

Computer Vision In Soccer: Yolov11 Analytics Engine For Quantifying Game Strategy, Connor S. Maurer

Data Science Undergraduate Honors Theses

Single-shot object detection capabilities significantly reduce computational overhead for real-time computer vision in sports analytics at 60 FPS. YOLO11’s lightweight CNN gives promising accuracy while meeting the low-latency demand of dynamic soccer matches. As data-driven approaches take over the sport of soccer, efficient player tracking systems become critical for informing coach’s strategies. I prototype the ETL (Extract, Transform, Load) process of data collected from a single- shot detection program and evaluate its viability for estimating player fatigue. YOLO11 detects players, the ball, and other characteristics, with the output transformed by homography to estimate the positions in the real world. These …