Artificial Intelligence and Robotics Commons^™

A Novel Federated Llm Framework For Distributed Traffic Modelling In Intelligent Transportation Systems, Seerat Kaur

Theses and Dissertations (Comprehensive)

Intelligent transportation systems (ITS) depend on accurate traffic prediction to support congestion management, infrastructure planning, and real-time operational decisions. Despite substantial progress in data-driven forecasting, several challenges continue to limit practical deployment: traffic data is distributed across independent regional authorities, making centralized aggregation infeasible, standard federated aggregation strategies ignore traffic-specific characteristics that meaningfully affect model quality, and existing models produce only numerical outputs without interpretable reasoning that urban planners can act upon. This thesis addresses these challenges through four contributions that collectively advance privacy-preserving, explainable, and scalable traffic forecasting.

The first contribution provides a systematic review of 129 peer-reviewed publications, …

Healthcare Digital Twins: A Methodological Literature Review On Integrating Iot And Ai For Personalized Medicine And Predictive Care, Sara Shahnazinia, Mahsa Tavasoli, Abdolhossein Sarrafzadeh, Ali Karimoddini

Electrical & Computer Engineering Faculty Publications

Digital Twin (DT) technology has the potential to revolutionize healthcare delivery and enhance patient outcomes through personalized and precision medicine, simulation models for operations and interventions, and drug discovery. However, successful implementation of DTs in Internet of Things (IoT) and artificial intelligence (AI) healthcare is contingent upon addressing key challenges such as privacy, ethics, and robust data security. This paper presents a methodological literature review of DT applications in healthcare, systematically analyzing the current state of research, key enabling technologies, and implementation challenges. The review summarizes DT categorization approaches (application-based, technology-based, and real-time function-based); delineates core DT components such as …

Deep Learning-Based Co-Current Upward Gas-Liquid Two-Phase Flow Regime Identification In An Annular Conduit, Joshua Robert Macomber

Graduate Theses, Dissertations, and Problem Reports (ETD)

Flow regime identification in co-current upward gas-liquid flow through annular conduits remains a significant challenge in petroleum engineering, with major safety and operational implications. It is also important across industries involving the transport of multiphase fluids. Misidentifying flow regimes can introduce major operational risk, yet regime boundaries in annular gas-liquid flow are often visually complex and context dependent.

The objective of this study was to evaluate the utility of convolutional neural network (CNN) classifiers for flow regime identification. The CNN was trained using annular flow image dataset published by Texas A&M University. The dataset consists of approximately 947 RGB images …

Adaptive Multi-Grade Deep Learning For Highly Oscillatory Fredholm Integral Equations Of The Second Kind, Jie Jiang, Yuesheng Xu

Mathematics & Statistics Faculty Publications

This paper studies the use of Multi-Grade Deep Learning (MGDL) for solving highly oscillatory Fredholm integral equations of the second kind. We provide rigorous error analyses of continuous and discrete MGDL models, showing that the discrete model retains the convergence and stability of its continuous counterpart under sufficiently small quadrature error. We identify the DNN training error as the primary source of approximation error, motivating a novel adaptive MGDL algorithm that selects the network grade based on training performance. Numerical experiments with highly oscillatory (including wavenumber 500) and singular solutions confirm the accuracy, effectiveness and robustness of the proposed approach.

Recent Advances In Triboelectric Nanogenerators For Biomedical And Cardiovascular Monitoring, Amit Sarode, Jegan Rajendran, Gymama Slaughter

Center for Bioelectronics Publications

Triboelectric nanogenerators (TENGs) have emerged as versatile self-powered platforms for wearable and implantable biomedical sensing, offering an alternative to battery-dependent electronic devices. By converting biomechanical energy from physiological motion into electrical signals, TENGs enable simultaneous energy harvesting and active sensing within flexible, lightweight, and biocompatible architectures. This review summarizes recent advances from 2020 to 2025 in triboelectric nanogenerator (TENG)-based cardiovascular monitoring. The discussion focuses on material systems, device configurations, sensing mechanisms, and applications including pulse detection and cuffless blood pressure estimation. Representative studies are compared to highlight emerging trends in wearable and self-powered sensing technologies. However, differences in experimental conditions, …

A Comprehensive Survey Of Prompt Engineering Techniques In Large Language Models, Tonmoy Debnath, Md Nurul Absar Siddiky, Muhammad Enayetur Rahman, Prosenjit Das, Antu Kumar Guha, Muhammad Rezaur Rahman, H. M. Dipu Kabir

Electrical & Computer Engineering Faculty Publications

Prompt engineering has arisen as a pivotal discipline in optimizing the performance of Large Language Models (LLMs) by structuring inputs to enhance coherence, accuracy, and task alignment. This paper comprehensively surveys various prompting techniques, systematically categorizing them according to their application domains and methodological foundations. Fundamental approaches like zero-shot and few-shot prompting are examined along with advanced strategies, including chain-of-thought reasoning, retrieval-augmented generation, and self-consistency mechanisms. A rigorous qualitative analysis is conducted to evaluate each technique's strengths, limitations, and optimal use cases, offering a structured framework for selecting the most effective prompting strategies. Theoretical insights and empirical findings are consolidated …

Physics-Informed Temperature Prediction Of Lithium-Ion Batteries Using Decomposition-Enhanced Lstm And Bilstm Models, Seyed Saeed Madani, Yasmin Shabeer, Michael Fowler, Satyam Panchal, Carlos Ziebert, Hicham Chaoui, François Allard

Electrical & Computer Engineering Faculty Publications

Accurately forecasting the operating temperature of lithium-ion batteries (LIBs) is essential for preventing thermal runaway, extending service life, and ensuring the safe operation of electric vehicles and stationary energy-storage systems. This work introduces a unified, physics-informed, and data-driven temperature-prediction framework that integrates mathematically governed preprocessing, electrothermal decomposition, and sequential deep learning architectures. The methodology systematically applies the governing relations to convert raw temperature measurements into trend, seasonal, and residual components, thereby isolating long-term thermal accumulation, reversible entropy-driven oscillations, and irreversible resistive heating. These physically interpretable signatures serve as structured inputs to machine learning and deep learning models trained on temporally …

Machine Learning-Based Lifetime Prediction Of Lithium Batteries: A Comparative Assessment For Electric Vehicle Applications, Abdelilah Hammou, Raffaele Petrone, Demba Diallo, Boubekeur Tala-Ighil, Philippe Makany Boussiengue, Hicham Chaoui, Hamid Gualous

Electrical & Computer Engineering Faculty Publications

This paper evaluates and compares four data-driven methods (Gaussian Process Regression (GPR), echo state network (ESN), gated recurrent unit (GRU), and long short-term memory (LSTM)) for lithium-ion capacity prognostics adapted to electric vehicle conditions. This comparison aims to find the most efficient prognosis method considering two constraints: the limitation of computational power and the unavailability of on-board capacity measurement that requires full charge and discharge conditions. The machine learning models are trained using capacity values estimated under vehicle conditions. The ageing data is collected from cycling tests of two battery chemistries, Lithium Fer Phosphate (LFP) and Nickel Manganese Cobalt (NMC), …

Digital Twin Technologies For Battery Systems: Advancements, Applications, And Future Directions, Seyed Saeed Madani, Yasmin Shabeer, Michael Fowler, Satyam Panchal, Carlos Ziebert, Hicham Chaoui, François Allard

Electrical & Computer Engineering Faculty Publications

The relationships among deep learning, edge computing, artificial intelligence (AI), and the most recent advancements in digital twin (DT) technology for battery energy storage systems are discussed in this paper. The study highlights the need for improved cloud-edge coordination, AI model development, and stronger cybersecurity features by demonstrating real-world applications of digital twin technology in electric vehicles (EVs), aircraft, and grid storage. It also described DT-based structures for fault detection, real-time monitoring, and optimization through standardization and battery management system (BMS) fusion. Because DT-based solutions for distributed energy resources (DERs) offer improved energy management systems, various studies have been conducted …

Interpretable Battery Soh Prediction: A Comparative Interpretability Framework For Multi-Architecture Ml Models, Shafiyee Islam, Gon Namkoong

Electrical & Computer Engineering Faculty Publications

This work introduces a unified interpretability-efficiency framework for lithium-ion battery state of health (SOH) prediction using hybrid deep learning architectures. We comparatively analyze four hybrid models: CNN LSTM MultiHead, CNN Feature Extractor LSTM, DNN LSTM, and DNN BiLSTM to disentangle how network topology, feature composition, and computational design influence both predictive fidelity and physical interpretability. By integrating Monte Carlo Shapley (MC Shapley), background occlusion SHAP (BoSHAP), and ablation analysis, we quantify the contribution and robustness of five electrochemical feature groups: time, capacity, voltage, dQ/dV and peaks of dQ/dV from NASA battery dataset. The results reveal a consistent dominance of differential …

An Explainable Cs-Mitigation Triangular (Ecsmt) Framework To Secure Graph Neural Networks, Sabah Ettahri, Sergio Pallas Enguita, Chung-Hao Chen, Wen-Chao Yang

Electrical & Computer Engineering Faculty Publications

This research addresses cyber risk by defending against backdoor attacks on Graph Neural Networks (GNNs). We propose the Explainable Complex System-Mitigation Triangular (ECSMT) Framework, which integrates Robust Training, Graph Regularization, and Data Sanitization into a lightweight, hardware-efficient defense layer. To evaluate structural generalizability, we conducted empirical evaluations across three distinct benchmark domains (AIDS, MUTAG, and PROTEINS) using a Graph Isomorphism Network (GIN) backbone. Under a baseline 5% backdoor subgraph trigger injection ratio, ECSMT achieves excellent utility retention, securing a Clean Accuracy (CA) of 97.33% (±0.62%) while reducing the Attack Success Rate (ASR) from 97.00% down to 69.45% on the primary …

Autonomous Weapons And Strategic Stability, Chick Edmond

Political Science & Geography Faculty Publications

The increasing number of artificial intelligence (AI) elements within military systems has introduced new forms of security dilemmas related to speed, level of secrecy, and transfer of responsibility from humans to machines. This article addresses the question of whether or how AI enabled autonomous weapons can lead to greater levels of strategic instability. Three causal mechanisms were determined by this study to potentially create destabilizing effects due to the introduction of autonomy; the first mechanism is a reduction in time available for decision making. The second mechanism involves the creation of multiple pathways of escalation. The third mechanism is the …

Cybersecurity Center For Offshore Wind Energy (Final Project Round), Sachin Shetty

Center for Secure and Intelligent Critical Systems (CSICS) Publications

This project establishes a Cybersecurity Center for Offshore Wind Energy with the objective of designing and operating a cyber-physical testbed for wind energy farms (WEFs) that enables comprehensive cybersecurity research. The testbed incorporates a Supervisory Control and Data Acquisition (SCADA) system connected to turbine models via industrial-grade programmable logic controllers (PLCs) and remote terminal units (RTUs). It supports side-channel data acquisition, implementation and analysis of various cyberattack scenarios, and development of attack detection, mitigation, and best-practice guidance tailored to wind energy systems. During the project, the team expanded the number and fidelity of mathematical turbine models (MTMs), integrated these models …

Standardization Of Neuromuscular Reflex Analysis—Role Of Fine-Tuned Vision-Language Model Consortium And Openai Gpt-Oss Reasoning Llm-Enabled Decision Support System, Eranga Bandara, Ross Gore, Sachin Shetty, Ravi Mukkamala, Christopher K. Rhea, Brittany S. Samulski, Amin Hass, Atmaram Yarlagadda, Shaifali Kaushik, Malith De Silva, Andriy Maznychenko, Inna Sokolowska, Kasun De Zoysa

VMASC Publications

Background/Objectives: Accurate assessment of neuromuscular reflexes, such as the Hoffmann reflex (H-reflex), plays a critical role in sports science, rehabilitation, and clinical neurology. Conventional interpretation of H-reflex electromyography (EMG) waveforms is subject to inter-rater variability and interpretive bias, limiting reliability and standardization. This study aims to develop an automated, interpretable, and robust agentic AI–driven framework for H-reflex waveform analysis. Methods: We propose a fine-tuned Vision–Language Model (VLM) consortium combined with a reasoning Large Language Model (LLM)–enabled decision support system for automated H-reflex interpretation. Multiple VLMs were fine-tuned on curated datasets of H-reflex EMG waveform images annotated with expert clinical observations, …

Improved Pid Search Algorithm For Uav Path Planning In Mountainous Environments, Yi Peng, Yunkui Lei, Qingqing Yang, Hui Li, Jianming Wang

Journal of System Simulation

Abstract: To address the challenges of UAV path planning in mountainous environments, including high computational complexity and suboptimal optimization performance, and the disadvantages of the PIDbased search algorithm, such as low optimization accuracy and slow convergence rate, this paper proposed an improved PID search algorithm (IPSA). The method introduced a good point set to ensure a more uniform population distribution, thereby enhancing population diversity and global search capability. The Q-learning algorithm was employed to adapt PID parameter adjustments, incorporating an exploration rate factor to further improve the algorithm's exploration and computational capabilities. A lens imaging opposition-based learning mechanism was also …

Dynamic Characteristic Simulation And Optimization Of Ground Test System For Airborne Launch Rack, Yuguang Bai, Sheng Zhang, Yushun Cao, Xiaoshi Zhang, Hu Huang

Journal of System Simulation

Abstract: To solve the ground equivalent test problem of the airborne launch system, an optimization method for the dynamic characteristics of the ground launch rack test system based on a multi-variable optimization approach was proposed. Through the discussion on the boundary conditions of the foundation, an effective dynamic simulation model of the ground launch test system was established. By comparing the dynamic characteristics of the launch rack structure in the airborne state and the ground test state, the objectives and constraints of the optimization design were determined. The dynamic characteristics of the ground test system were optimized and designed. …

Optimization Of Dynamic Weapon Target Assignment Considering Random Disturbances, Zhenzu Bai, Yizhi Hou, Zhangming He, Juhui Wei, Haiyin Zhou, Jiongqi Wang

Journal of System Simulation

Abstract: The impact of various random disturbances in the actual command and control environment of unmanned systems on problem modeling and solving of weapon target assignment was considered, and three types of uncertainty disturbance constraints were investigated. A multi-objective dynamic sensor weapon target assignment model was established. By considering the issues of model property changes caused by disturbances and insufficient robustness of the traditional single-operator solving algorithm, a multi-operator constrained multi-objective evolutionary framework based on the deep Q-network was proposed. The algorithm described the convergence, diversity, and feasibility of the population in both the objective and decision spaces. It established …

Survey Of Cooperative Multi-Agent Path Finding, Jun Xiong, Wenbo Zhang, Zhi Xiong, Feng Zhou, Bo Yang

Journal of System Simulation

Abstract: Cooperative multi-agent path finding (Co-MAPF) has been widely applied in fields such as UAV formation and multi-agent systems, which enhances the overall system efficiency through task collaboration, path planning, and task execution among multiple agents. This paper introduced three main system architectures, namely centralized, distributed, and hybrid, along with their advantages and disadvantages based on the definition of the Co-MAPF problem, categorized, and reviewed mainstream Co-MAPF algorithms, including those based on sampling, search, intelligent optimization, and learning. Furthermore, this paper analyzed the main current challenges faced by Co-MAPF algorithms on the basis of summarizing existing research and outlined the …

Optimization Of Order Picking And Sorting Coordintion In “Goods-To-Person” System, Liang Ren, Zerong Zhou, Yunfeng Ma

Journal of System Simulation

Abstract: To improve the order picking and sorting collaboration with time windows in the "goods-to-person" system, a mathematical model aiming to minimize the number of sorting batches was established. With the characteristics of this issue considered, a hybrid variable neighborhood search (HVNS) algorithm based on the "classified loading" strategy was proposed for solutions. The numerical experimental results show that the HVNS algorithm can obtain high-quality solutions while shortening the solution time; different order structures have varying effects on the utilization of the loading capacity of sorting automated guided vehicles (AGVs); under the tested experimental conditions, the collaborative operation mode …

Interoperability Model And Application Of Military Training System For Combination Of Virtuality And Reality, Jianxing Gong, Hai Hu, Haihui Ren, Ruixiang Wu

Journal of System Simulation

Abstract: With the development of AI technology, VR technology, and combat simulation technology, in order to achieve the practical training effect of "how to fight and how to train soldiers", virtual and real training has become a widely popular military training mode. It has become a trend to integrate digital systems, virtual equipment, semi-physical models, physical models, and other heterogeneous systems to carry out training in the same training environment. Therefore, it is necessary to study the interoperability model and application of training systems for the combination of virtuality and reality. This paper proposed the definition of interoperability between virtuality …

Research On Infrared And Visible Light Fusion Method Based On Resnet-50 And Laplacian Filtering, Xiao Wang, Xiangyang Li, Feng Liang, Zhili Zhang

Journal of System Simulation

Abstract: In order to solve the problem that existing infrared and visible light image fusion techniques often suffer from artifacts caused by insufficient contrast, spectral distortion, and high computational complexity, a fusion framework based on ResNet-50 and Laplacian filtering was proposed. ResNet-50 was used to extract shallow and deep features, followed by multi-scale feature fusion. Laplacian filtering was applied to optimize feature information, and an automatic discriminator was introduced to further improve the fusion effect. Simulation results show that, compared with comparison algorithms, the proposed method achieves an average increase of 2.71% and 2.16% in information entropy, 5.98% and …

Analysis Of Optimal Spectral Bands For Thermal Infrared Hyperspectral Image Reconstruction Driven By Physical Simulation Model, Yonghao Yang, Xiaoyu He

Journal of System Simulation

Abstract: To achieve accurate reconstruction of thermal infrared hyperspectral images under limited spectral bands, this paper proposed a reconstruction method based on physical modeling and simulation. Semi-global decomposition algorithm was adopted to invert the thermophysical properties of the scenario based on the physical model of thermal radiation, simulating and generating full-band hyperspectral data. An optimal spectral band selection strategy driven by a physical model was proposed, which integrated the sensitivity of temperature inversion and the separability of material spectra. Experiments were conducted on both simulated and measured datasets to evaluate the performance of material identification, temperature inversion, and spectral …

Research On Pac-Bayes-Based A2c Algorithm For Multi-Objective Reinforcement Learning, Xiang Liu, Qiankun Jin

Journal of System Simulation

Abstract: To address the theoretical challenges of exploration and exploitation trade-offs and uncertainty modeling in multi-objective reinforcement learning (MORL), this study developed a learning framework, MO-PAC, based on PAC-Bayes theory. By introducing a multi-objective stochastic Critic network and a dynamic preference mechanism, the framework extended the conventional A2C architecture, enabling adaptive and efficient approximation of complex Pareto fronts. Experimental results demonstrate that in multi-objective MuJoCo environments, MO-PAC outperforms baseline algorithms, achieving approximately 20% improvement in hypervolume and 60% increase in expected utility, while exhibiting superior convergence efficiency and robustness. It verifies both theoretical value and practical performance advantages in …

Dual-Channel Supply Chain Network Equilibrium Model Under Retailers’ Risk Aversion, Hongchun Wang, Caifeng Lin, Xinyi He, Haiyue Yin

Journal of System Simulation

Abstract: To study the network equilibrium problem of dual-channel supply chains under the background of retailers' risk aversion, a dual-channel supply chain network equilibrium model including multiple competitive suppliers, manufacturers, retailers, and demand markets was established. The Mean-CVaR method was employed to quantify retailers' risk aversion characteristics, and variational inequalities were utilized to characterize the equilibrium conditions of decision-makers at each tier of the supply chain. The projection contraction algorithm was applied to solve the model and conduct numerical analysis, thereby revealing the impact of retailers' risk aversion behavior on equilibrium outcomes. The simulation results indicate that a higher …

Spatiotemporal Graph Convolution-Based Demand Forecasting And Simulation Analysis For Automotive Parts Supply Chain, Xiaobin Li, Bing Hu, Chao Yin, Bo Li, Jun Ma

Journal of System Simulation

Abstract: To address complex automotive after-sales parts supply network operations with insufficient demand forecasting accuracy, slow response, and low service efficiency, this study proposed a spatiotemporal graph convolution-based method for automotive parts supply chain demand forecasting. Sales network data of the automotive parts sales network was constructed as a heterogeneous graph, integrating node features like parts sales volume and value to build multi-dimensional node dependencies. A node update mechanism of the graph convolutional neural network was designed, combined with long short-term memory neural networks to capture temporal features, using spatiotemporal attention to integrate temporal and spatial features into updated nodes …

A Method Of Heuristic Human-Llm Collaborative Source Search, Yi Chen, Sihang Qiu, Zhengqiu Zhu, Yatai Ji, Yong Zhao, Rusheng Ju

Journal of System Simulation

Abstract: Traditional source search algorithms are prone to local optimization, and source search methods combining crowdsourcing and human-AI collaboration suffer from low cost-efficiency due to human intervention. In this study, we proposed a lightweight human-AI collaboration framework that utilized multi-modal large language models (MLLMs) to achieve visual-language conversion, combined chain-of-thought (CoT) reasoning to optimize decision-making, and constructed a heuristic strategy that incorporated probability distribution filtering and a balance between exploitation and exploration. The effectiveness of the framework was verified by experiments. The human-AI alignment heuristic strategy with large language model adaptation design provides a new idea to reduce manual …

Robust Emergency Dispatch Method Considering Dynamic Frequency Security And N-K Contingency, Tao Huang, Zhi Zhang, Yujie Ding, Yanbo Chen, Jing Wang, Wenqian Zhang

Journal of System Simulation

Abstract: To address the risk of system inertia loss and frequency instability caused by grid integration of high-proportioned new energy and unit failures, an N-k robust emergency dispatch method considering dynamic frequency security constraints was proposed. With the consideration of the frequency response characteristics of variable-speed pumped storage, a dynamic frequency response model incorporating variable-speed pumped storage was constructed, and the nadir frequency constraint was established through second-order cone transformation. Information entropy theory was employed to quantify the uncertainty of unit failures, and an uncertainty set considering N-k unit failures was developed. A twostage robust emergency dispatch model considering N-k …

Scheduling Method For Virtual Power Plants Based On Analysis And Forecasting Of Heterogeneous Load Characteristics, Runzhao Zhang, Yanbo Chen, Tao Huang, Haoxin Tian, Tuben Qiang, Zhi Zhang

Journal of System Simulation

Abstract: To improve the electricity supply-demand situation by rationally utilizing demand response resources, a two-layer optimal scheduling model for virtual power plants (VPPs) based on the analysis and forecasting of heterogeneous load characteristics was proposed. With the differences in response characteristics of multi-type loads considered, a demand response model for multi-type loads was constructed by using a customer baseline load (CBL) curve forecasting method that integrated dynamic scenario generation and K-means++ clustering. A two-layer optimal scheduling model for VPPs that incorporated load aggregators and demand response was established. In this model, the upper layer conducted optimal scheduling targeting maximizing the …

Vibration Control Of Offshore Wind Turbine Towers Based On Eddy Current Nonlinear Energy Sink, Xiangxing Yu, Yandong Zhao, Baolin Zhang

Journal of System Simulation

Abstract: To address the issue of tower vibrations induced by wind loads, which can damage the structure of wind turbines, a vibration control method for monopile offshore wind turbine towers based on an eddy current-nonlinear energy sink (EC-NES) was proposed. The dynamic model of monopile offshore wind turbines based on EC-NES was constructed according to the Euler-Lagrange equation, and based on the output response of FAST software, the unknown parameters of the model and the wind loads were identified in terms of parameters. The optimal parameters of EC-NES stiffness and damping were obtained using PSO. The eddy current damper …

Fault Diagnosis Method For Photovoltaic Systems Based On Multi-Strategy Fusion, Bin Li, Yuchuo Wang

Journal of System Simulation

Abstract: To address the problem of frequent PV system faults, a multimodal fusion fault diagnosis model based on the optimization of the improved lemming algorithm was proposed. The one-dimensional time series signals of PV currents and voltages were converted into two-dimensional images by Markov transformation field, and the spatial features of the original waveforms were mined by using multiscale CNN (MCCNN); BiGRU was used to extract the temporal dynamic features of the original waveforms, and complementary enhancement of the temporal and spatial features was realized by the feature fusion layer. The improved lemming algorithm was innovatively introduced to adaptively optimize …