Engineering Commons^™

Envis: A User-Centered Web-Based Tool For Interactive Visualization Of Environmental Geospatial Data, Saima Sanjida Shila

LSU Master's Theses

Data visualization is an essential part of analyzing environmental geospatial data. Despite having the availability of large environmental datasets, there remains a lack of easily accessible, user-friendly, and interactive visualization tools in this field. Therefore, this study aims to develop a user-friendly and easily available web-based visualization tool. Before developing the tool, we conducted a survey of researchers at the LSU Coastal Studies Institute to collect their opinions on currently available visualization tools. In the survey, 55% of participants responded between somewhat satisfied to dissatisfied with their current visualization tools. Most of the participants mentioned two major limitations of existing …

Cv: Young "Paul" Kim (Computer Engineering), Young "Paul" Kim

ECaMS Department Faculty Curricula Vitae

No abstract provided.

A Robust And Energy-Efficient Federated Ids For Iiot Using Spiking Neural Networks And Differential Evolution With Adversarial Resilience, Mohammad Othman Nassar

Iraqi Journal for Computer Science and Mathematics

The Industrial Internet of Things (IIoT) is faced with increasing cybersecurity threats that require lightweight, fast, and resilient intrusion detection systems (IDS). This study presents a novel federated IDS framework that integrates federated learning (FL), Spiking Neural Networks (SNNs), and differential evolution (DE). The use of SNNs within a federated context is a rare and innovative contribution that enables effective temporal feature extraction from IIoT traffic. DE is employed as a global optimization mechanism, enhancing robustness and generalization beyond conventional federated aggregation. To further strengthen resilience, synthetic adversarial noise is injected during training, allowing evaluation in realistic poisoning scenarios. The …

Design Considerations For Conversational Agents To Assess The Social-Emotional Well-Being Of Young Children In Low-Income South African Communities, Lucretia A. Williams, Elizabeth A. Ankrah, Catherine E. Draper, Caylee J. Cook, Franceli L. Cibrian, Jesus A. Beltran, Kimberley D. Lakes, Gillian R. Hayes

Engineering Faculty Articles and Research

A variety of digital technologies have been used to support early childhood development (ECD) programs in low-income South African communities. Even though technology has provided opportunities to increase access to health interventions, the lack of trust and socio-economic constraints under which these tools would need to work pose complex challenges. We examine home visitors’ work processes, experiences, and preferences of a conversational agent to support their work of administering social-emotional well-being assessments to young children ages 0-5. Analysis of the results of focus groups with 51 home visitors indicates the need for designing conversational agents that support ECD in the …

Utilizing A Virtual Firewall Appliance For Introducing And Reinforcing The Concepts And Implementation Of Devices To Improve Security In A Computing Environment, Stanley Mierzwa, Christopher Eng

Center for Cybersecurity

The educational realm of higher education cybersecurity curriculum continues to evolve to provide more opportunities for experiential hands-on and work role-related practical applications of technology solutions. Gaining greater competencies is quickly becoming a normal requirement for such programs that are designated by the National Security Agency Center of Academic Excellence programs. The work roles of cybersecurity include a variety of knowledge, skills, and abilities, depending on the category of the activity or task. Firewalls have been a staple cybersecurity, network security, and information security device and strategy to protect organization networks and computing environments. This paper will provide details and …

Seeing What Matters: Safety-Critical Semantic Segmentation Via Transfer Learning On Construction Sites, Obiora J. Odugu

LSU Master's Theses

Autonomous robots are increasingly deployed on construction sites for tasks such as progress monitoring, inspection, and safety assessment. For these robots to operate effectively, they must perceive and interpret complex, dynamic environments populated by workers, machinery, and unstructured terrain. Achieving reliable perception depends on high performing semantic segmentation models trained on large volumes of annotated data—an expensive and logistically challenging requirement in construction due to privacy restrictions, variable site access, and slow digitalization. This research addresses the challenge of limited labeled data by investigating transfer learning as a label-efficient approach for construction-site segmentation. Specifically, it explores whether road construction imagery—abundant …

Truck Drivers And Autonomous Trucks: A Topic Modeling Analysis Of Truck Driver Posts, Noah Britt, Amy M. Schuster, Shubham Agrawal, Chu-Hsiang Chang, Jenna A. Van Fossen, Elizabeth A. Mack, Sheila R. Cotten

Publications

Social media provides a rich, alternative data source to interviews or survey-based research to study hard-to-reach populations (e.g., truck drivers, because of their transient work structure and unique subculture). This study uses public social media posts from the largest trucking forum in the United States to examine truck drivers’ views on autonomous trucks (ATs), which are poised to transform the trucking industry. We expand on traditional qualitative strategies of analyzing social media data by combining newer methods, including BERT-based topic modeling, sentiment analysis, stance detection, emotion analysis, topic similarity, and location analysis through a social interaction network, to analyze a …

Analysis Of A Cloud-Based Robot Motion Planning System, Yusif Mardanzade, Latafat Abbas Gardashova

Chemical Technology, Control and Management

As a result of the integration of cloud computing technologies into the field of robotics, the concept of "cloud robotics" has emerged. Unlike traditional robots, cloud-based robot systems remove computation, memory, and even some software from the local device and rely on remote resources obtained over the network. This approach ensures that robots are not limited only by their internal computing capabilities and allows them to take advantage of the wide range of opportunities offered by the cloud infrastructure. As a result, robots have access to large databases, highly parallel computing, and collective learning capabilities anytime and anywhere. In addition, …

Towards Automated And Explainable Insider Threat Response In Electronic Health Records: A Role-Aware Machine Learning Framework, Luca Lippi Ornstil

Master's Theses

Healthcare remains a prime target for cyberattacks, with insider misuse and credential compromise posing major risks to Electronic Health Records (EHRs). This thesis introduces a role-aware, explainable anomaly detection and response framework integrated with OpenEMR to address post-authentication threats. Four models—Local Outlier Factor (LOF), Isolation Forest, Autoencoder, and Graph Neural Network (GNN)—detect behavioral deviations across temporal, device, and role-based features, with LOF serving as the primary runtime detector. A configurable policy engine maps anomaly severity to proportional actions, from email alerts to read-only restrictions or account suspension, all reversible and auditable. Evaluation on real EHR logs shows the system’s operational …

Cal Poly (Cp) Legged Robot, Sebastian Barboza, Jonathan Mchale, Isabella Sorensen, Isaac Golan

Mechanical Engineering

The Navy spends $60 billion annually on dangerous ship maintenance performed by sailors. To save lives and resources, the Naval Surface Warfare Center (NSWC) is looking for robots to replace sailors and navigate ships to perform various tasks. Robots with tracks and wheels have been most recently explored by NSWC, however they have encountered significant problems navigating the ships, especially through naval ship doorways with a significant ledge. By using a legged robot, our team hopes to solve these problems and have a robot that can navigate the ship with relative ease and stability.

Crisis Observatory: Extracting Credible Signals During A Crisis In The Age Of Llms, Kuan-Chieh Lo, Pranav Maneriker, Sriram Sai Ganesh, Dominik Winecki, Kelly Garrett, Ayaz Hyder, Arnab Nandi, Valerie Shalin, Shannon A. Bowen Ph.D., Amit Sheth, Srinivasan Parthasarathy

Publications

Systems for crisis response have required several different models for the analysis of unstructured text, such as identifying needs, locations, topics, routing, and matching of needs with available responders. Large Language Models (LLMs) have replaced task-specific models across various language processing tasks. However, LLMs are known to be limited by their training data, collected before the crisis. In this demo, we explore the use of LLMs for crisis response scenarios with rapidly evolving information environments. We show how the augmentation of these models with external reliable sources of crisis-specific information can help build adaptive systems for response. The demonstration video …

Environment Mapping And Gps-Based Trailer Parking Using Low-Cost Peripheral Sensors And Post-Processing Algorithms, Connor Best

Journal of Undergraduate Research at Minnesota State University, Mankato

This paper explores the merit of software data optimization through two practical examples: environment mapping & GPS navigation.

Sistemas De Información Geográfica En La Era De La Digitalización, Jairo Eduardo Márquez Díaz, Luis Gonzalo Benavides Ramírez, Arles Prieto Moreno, Martha Andrea Manrique Castro

Ingeniería

En la era digital, la información geográfica es esencial para la toma de decisiones en áreas como la planificación urbana, la gestión de recursos naturales y la seguridad. Los Sistemas de Información Geográfica (SIG) se han establecido como herramientas indispensables para gestionar, analizar y visualizar datos georreferenciados que permite la creación de mapas digitales y la toma de decisiones basada en evidencia. Este libro aborda los fundamentos, las tecnologías y las aplicaciones de los SIG, explorando su evolución y su potencial en un entorno digital en constante transformación. A lo largo de sus cinco capítulos, el libro aborda temas esenciales …

Mosquito Classification And Explainability From Image Data Via Deep Learning Techniques, Farhat Binte Azam

USF Tampa Graduate Theses and Dissertations

According to the World Health Organization (WHO), mosquitoes are the deadliest animals on Earth, responsible for more human deaths annually than any other species. Mosquito-borne illnesses continue to pose severe risks to global health. In 2015 alone, there were an estimated 214 million malaria cases worldwide. Similarly, a 2016 report from the Centers for Disease Control and Prevention (CDC) revealed that Puerto Rico’s Department of Health received over 62,500 suspected cases of Zika, with 29,345 confirmed positive cases. In 2019, Southeast Asia experienced its worst dengue outbreak in recorded history. Of the approximately 4,500 mosquito species distributed across 34 genera, …

Blockchain-Driven Pharma Supply Chains Towards Industry 6.0, Vijay Ramasamy R

Theses and Dissertations

The pharmaceutical supply chain is undergoing an unprecedented evolution in the wake of Industry 6.0, driven by the need for heightened transparency, security, and real-time intelligence. However, current systems suffer from legacy Enterprise Resource Planning (ERP) constraints, the risk of counterfeit products, temperature sensitivity, and scalability issues due to the surge in Internet of Things (IoT) data.

This research proposes a unified, blockchain-based framework that integrates legacy ERP systems, advanced AI driven forecasting, IoT-enabled traceability, and quantum-enhanced blockchain security to modernize pharmaceutical supply chains.

The study begins by addressing interoperability between ERP and blockchain using middleware and smart contracts, facilitating …

Retracted: Analysis Of Energy Sector Co2 Emanations Using Wavelet-Based Numerical Technique, Yeshwanth R., Kumbinarasaiah S.

Iraqi Journal for Computer Science and Mathematics

This study aims to present the modified Chebyshev wavelet collocation method (CWCM) to investigate and obtain the numerical approximation of $CO_2$ emissions from the energy sector utilizing the fractional mathematical model. The need for energy rises as the population grows. Burning fossil fuels produces a significant portion of the world's energy, which raises the atmospheric concentration of $CO_2$ and causes global warming. The combination of mathematical modeling studies and numerical simulations allows us to understand the $CO_2$ emissions from the energy sector. Our objective is to build an operational matrix of integration (OMI) based on Chebyshev wavelets and use it …

Shifted Frequency Analysis Hybrid Simulation Algorithm Based On Multi-Rate Asynchronous Coordination, Yankan Song, Libin Wen, Ying Chen, Jinji Xi, Haoyuan Zhang, Li Xiong

Journal of System Simulation

Abstract: Large-scale AC/DC power systems exhibit complex dynamics across multiple time scales, and existing hybrid simulations suffer from interface delays and frequency losses during multi-rate coordination, compromising accuracy. To address this issue, a multi-rate asynchronous coordination method was proposed to construct hybrid simulations using shifted frequency analysis (SFA). Within the multi-area Thevenin equivalence (MATE) framework, the algorithm introduced an interpolation-based asynchronous coordination mechanism, effectively eliminating interface delays; by extending SFA theory and designing a universal interface model, it achieved lossless data exchange between partitions with different rates and model types. Case studies on an AC/DC test system demonstrate that …

Soft Sensor Modeling Based On Improved Transformer In Dual-Stream Framework, Hao Gu, Jiayu Wang, Weili Xiong

Journal of System Simulation

Abstract: Industrial process information is highly nonlinear and dynamic, with long-term dependencies between data, making it difficult to adequately extract time-series features. To address this issue, an improved Transformer-based soft sensor model in a dual-stream framework was proposed. The data were segmented and expanded. The features were extracted in parallel using a dual-stream structure combining a convolutional neural network with a self-attention mechanism and the improved Transformer model. The dual-stream features were fused for soft sensor regression. Residual connections were further introduced to accelerate the convergence speed of the model, and an orthogonal random features-based improved multi-head attention mechanism was …

Path Planning Of Improved Rrt Algorithm Based On Deep Reinforcement Learning, Xiuman Liang, Ziliang Liu, Zhendong Liu

Journal of System Simulation

Abstract: To address the low planning efficiency, poor safety, and limited practicability of the RRT algorithm in global path planning within complex three-dimensional environments, which fail to meet the requirements of planning the safe flight path of UAVs, an improved SAC-RRT algorithm was proposed, which fused SAC deep reinforcement learning algorithm and RRT algorithm. A target point bias strategy and a dynamic step size based on the SAC decision-making network were designed to reduce the blindness of RRT. A random point correction process was designed to optimize the position of random points based on actions from the decision network and …

Low-Energy Multi-Robot Path Planning Algorithm Under Hca* Framework, Ning Wang, Jianlin Mao, Dayan Li, Chengyuan Fang, Chengze Qian

Journal of System Simulation

Abstract: To address the energy optimization problem in multi-robot path planning, this paper proposed a multi-robot path planning algorithm based on the energy-guided hierarchical cooperative A* (E-HCA*) algorithm. To address the issue of robot oscillations caused by mutual avoidance at bottlenecks and narrow passages in multi-robot systems, a node expansion method with path length as a secondary feature was introduced, and a greedy suppression strategy under the cooperative A* framework was proposed. A differential-drive robot energy consumption model was established, and an energy-guided heuristic function was constructed by integrating energy metrics into the underlying A* algorithm to guide low-energy path …

Multi-Objective Optimization Of Signal Timing At Intersections Considering Tailpipe Emissions, Xinhuan Ding, Huaqing Wang, Xu Dang

Journal of System Simulation

Abstract: In order to alleviate urban road congestion and improve the traffic and environmental benefits at intersections, a multi-objective timing optimization model with total delay time, total number of stops, capacity, and total tailpipe emission at intersections as optimization objectives was developed. The model incorporated tailpipe emissions into a mathematical optimization model and quantified the mathematical relationship between traffic efficiency indicators and tailpipe emissions by constructing a specific power-based algorithm for measuring total tailpipe emissions. According to the intersection delay time and the number of stops, the total tailpipe emissions could be estimated. Both the NDX crossover operator and the …

Multisource Information Fusion Method For Human Gait Perception, Guiliang Chen, Guowei Liu, Yongchao Li, Chao Cai, Zihao Li, Dong Yang

Journal of System Simulation

Abstract: In response to the insufficient gait perception capability during lower limb exoskeleton assistance, a human lower limb gait phase optimization classification model was proposed. A wireless transmission gait information collection system was designed for collecting the required gait phase feature information. Human joint angles were accurately calculated by fusing acceleration and angular velocity information using extended Kalman filtering. Additionally, kernel principal component analysis was applied to reduce dimensionality in conjunction with plantar pressure data. The LSSVM algorithm was employed to classify gait data, and the PSO algorithm was utilized to find the optimal classification parameters. Experimental results demonstrate that …

Optimal Scheduling Of Integrated Energy Systems Considering Source-Load Uncertainty And Linear Carbon Trading, Huaping Zhong, Yubo Fan, Jijun Shui, Danhao Wang, Daogang Peng

Journal of System Simulation

Abstract: In order to overcome the impact of source-load uncertainty on the scheduling of integrated energy systems (IES) and reflect the flexibility of the carbon trading price with the change in trading volume, an optimal scheduling method for integrated energy systems considering source-load uncertainty and linear carbon trading was proposed. The equipment within the IES was modeled, and nonparametric kernel density estimation was used to obtain the probability density function for each time period, generating the set of scenes through Monte Carlo simulation and calculating the probability of each scene. For the time shift of wind and solar output peaks …

Simulation Of Three-Degree-Of-Freedom Internal Mode Sliding Mode Control For Non-Ideal Single-Inductor Dual-Output Boost Converter, Bingli Liu, Jiarong Wu, Lin Yang, Dinglin Yan

Journal of System Simulation

Abstract: To reduce the cross-interference in the single-inductor dual-output (SIDO) Boost converter and to enhance the output accuracy and stability of the system, the parasitic resistances of the circuit components were considered, and a three-degree-of-freedom internal model sliding mode control strategy was proposed for the non-ideal SIDO Boost converter. An affine nonlinear mathematical model of the non-ideal SIDO Boost converter was established, and the nonlinear system was linearized and decoupled into two linear subsystems based on the differential geometry theory. The linear subsystem was designed as a three-degree-of-freedom internal model controller and a sliding mode controller, respectively. The robustness …

An Improved Virtual Terrain Generation Method Based On Simplex Noise, Bo Shen, Jianqin Zhang, Shuaibao Ma, Zheng Wen

Journal of System Simulation

Abstract: To address the issues of high computational complexity, slow generation speed, and insufficient realism present in traditional virtual terrain generation methods, this study proposed an improved virtual terrain generation method based on Simplex noise. This method leveraged the advantages of Simplex noise, such as high computational efficiency, low hardware overhead, and more natural randomness, to construct a basic terrain template. A fractal algorithm was introduced to enhance the level of terrain details through the superposition of noises with multiple frequencies and amplitudes. With the integration of a turbulence algorithm, random perturbations and complexity were added to further improve the …

Research On Constrained Programming Of Manipulator Using Rrt* Algorithm And Ellipse Prior, Zhen Yang, Li Su, Zhiyu Cheng

Journal of System Simulation

Abstract: There are problems in the traditional RRT* algorithm using a uniform sampling strategy applied in constrained programming problems, such as inaccurate turning guidance of sampling points and unnecessary node cost comparisons, which lead to an increase in additional time costs. To address these issues, an improved RRT* algorithm was proposed. This algorithm leveraged a heuristic function cost of the projected sampling points to make an ellipse prior judgment on the sampling points. Based on the ellipse prior, the sampling points were judged to determine whether they could optimize the path and shorten the programming time. The geodesics were used …

Robust Identification Of Dual-Rate Sampled Nonlinear Systems Based On Salr Network, Wenbin Jiang, Yuqing Cao, Li Xie, Huizhong Yang

Journal of System Simulation

Abstract: A robust identification algorithm based on the self-join adjacent-feedback loop reservoir (SALR) network was proposed for dual-rate sampled nonlinear systems with complex nonlinear characteristics and measurement outputs containing outliers. The SALR network was applied to describe the nonlinear characteristics of the target system, and wavelet neurons were injected into the reservoir to enhance its memory and nonlinear description capabilities. The identification problem of the nonlinear system was transformed into the identification problem of the network's output weight matrix. The Huber loss function was used to construct the criterion function, and an error threshold was introduced to improve the robustness …

Optimization Dispatch Method For High-Proportion Renewable Energy Power Systems Based On Sc-Ppo, Zhongkai Xu, Chenyang Chu, Kai Xie, Ruizhuo Zhao, Wenjun Ke

Journal of System Simulation

Abstract: The high proportion of renewable energy integration brings significant challenges of randomness, multi-objective coupling, and security constraints to power systems. Traditional model-driven methods have limitations in modeling accuracy and adaptability. To address these issues, this paper proposed a safety-constrained PPO algorithm (SC-PPO). The method included three improvements. A temporal convolutional network was utilized to construct a dynamic state encoder that integrated historical operation, real-time monitoring, and prediction data to form a causal state representation. A hierarchical reward structure was designed, and an adaptive weighting mechanism based on constraint satisfaction degree was introduced to coordinate multi-objective optimization. Physical constraint projection …

Microsimulation Of Infectious Disease Transmission Considering Virus Release, Transmission, And Action, Zhiming Fang, Shengdong Yuan, Ge Huang, Jingqian Yang, Zhongyi Huang

Journal of System Simulation

Abstract: Existing infection risk assessment methods mostly evaluate infection probability through mathematical models or simulation, but they lack analysis of the relationship between air circulation and individual infection probability. This study proposed a risk prediction model for infectious disease transmission based on indoor air circulation. At the microscopic scale, the space was discretized into grid points. By integrating CFD numerical simulation, the entire process of virus droplet release, transmission, and action was fully simulated. The simulation results show that in an obstacle-free room, the error between the total indoor viral load predicted by the model under windless and low wind …

Modeling And Simulation Of Traffic Signal Control Based On Mlp With Improved Gcn-Td3, Deqi Huang, Yating Tu, Zhenhua Zhang, Xin Guo

Journal of System Simulation

Abstract: To address the issues of uneven traffic flow at urban intersections, limited road capacity, and the poor coordination of existing traffic signal control algorithms, a traffic signal control algorithm based on graph convolutional reinforcement learning was proposed. By utilizing a multilayer perceptron, the dynamic features of vehicles and phase information at the controlled intersection and its neighboring intersections were extracted. A graph convolutional neural network was then employed to aggregate these vehicle dynamic features into potential features representing regional traffic. The control strategy was derived through multiple iterations of an improved twin delayed deep deterministic policy gradient (TD3) algorithm. …