Engineering Commons^™

Unpacking Bias, Accountability, And Ethical Practices In Ai, Manya Chandra, Micol Hebron

Student Scholar Symposium Abstracts and Posters

This study is based on understanding how text-to-image generative AI platforms perpetuate biases such as racism and sexism and decoding how this bias is programmed within large language models and datasets. In this study, the results of generative AI are analyzed through the lens of affect and affect theory, as they are applied to investigate the machine learning and computer theory behind generative AI algorithms. The purpose of the study is to explain why generative AI is biased and whether this bias is generated due to current trends or to deficits and biases within the database that it draws information …

Applying Positive Unlabeled Learning Techniques And Using The Kullback-Leibler Divergence To Improve Geothermal Surveying Assessments, Martín Thomas Rodriguez

Dissertations and Theses

As we face the current climate crisis, the discovery of geothermal energy resources has the potential to greatly reduce our dependence on fossil fuels worldwide. However, the development of any new energy infrastructure is expensive and depends on the willingness of energy agencies and developers to make initial investments based on calculated risk measures. One such measure, called geothermal favorability, is the likelihood that a site has conditions favorable for geothermal systems containing recoverable energy potential. Its prediction from existing geophysical datasets proves to be a nontrivial task. The prediction of geothermal favorability can be framed as a binary classification …

Graph Neural Networks Powered Scientific Paper Recommendation, Junhao Shen

Computer Science and Engineering Theses and Dissertations

Scientific paper recommendation systems aim to help researchers discover relevant papers amidst the vast and ever-growing body of literature. With the exponential yearly increase in scientific publications, the demand for effective paper recommendation solutions has become both critical and increasingly challenging. In recent years, deep learning techniques have revolutionized recommender systems, and scientific paper recommendations have naturally integrated these advancements. In this dissertation, we address these challenges through three progressive contributions.

First, we enhance traditional content-based methods using Graph Neural Networks (GNNs) by introducing a Graph Convolutional Network-strengthened Topic Modeling (GCN-TM) approach. This method improves upon conventional topic modeling techniques …

Universal Shape Replication Via Self-Assembly With Signal-Passing Tiles, Andrew Alseth, Daniel Hader, Matthew J. Patitz

Computer Science and Computer Engineering Faculty Publications and Presentations

In this paper, we investigate shape-assembling power of a tile-based model of self-assembly called the Signal-Passing Tile Assembly Model (STAM). In this model, the glues that bind tiles together can be turned on and off by the binding actions of other glues via “signals”. Specifically, the problem we investigate is “shape replication” wherein, given a set of input assemblies of arbitrary shape, a system must construct an arbitrary number of assemblies with the same shapes and, with the exception of size-bounded junk assemblies that result from the process, no others. We provide the first fully universal shape replication result, namely …

Learning To Represent Temporal Dynamics And Generative Factors For Intelligent Visual Navigation, Sahand Khoshdel

All Theses

Visual navigation systems are crucial in various applications, including autonomous driving, unmanned aerial systems (UAS), and industrial automation. For these systems to operate efficiently in dynamic environments, they must not only interpret complex surroundings but also anticipate changes over time. Temporal prediction—forecasting environmental changes like moving obstacles or shifting lighting conditions—enables navigation systems to act proactively, enhancing both safety and performance. This dissertation investigates representation learning methods both as a backbone feature extractor for RL agents as well as a proxy for systems oriented for Explainable AI (XAI). Two main projects are presented as case studies to achieve the aforementioned …

Patterns Of Interactions In Human-Machine Teams, Kazuhiko Momose

Theses and Dissertations

Increasingly capable machines, including Artificial Intelligence (AI) agents are playing a more important role in a wide range of applications, including human daily activities and safety-critical systems. They can benefit even more when humans and such machines agents work together as a team by leveraging each other's strengths and complementing each other to enhance overall performance. To design high-performing teams, it is critical to analyze the team dynamics and understand how humans and machines interact with each other. Collaboration, Coordination, and Cooperation (3Cs) are terms typically used to describe the behavior of teams. However, these terms tend to be used …

Basic Safety Message Generation Through A Video-Based Analytics For Potential Safety Application, Abyad Enan

All Theses

With the advancement of modern artificial intelligence techniques, computer vision can play a vital role in enhancing roadway safety by reducing the risk of imminent collisions. To do so, a vision-based safety application is required, where a roadside camera can monitor the roadway traffic and predict potential risks of crashes in real-time. If any risky situation or behavior is observed that may lead to a crash, then a safety application can send warnings to the vehicles at risk. For vision-based safety applications on a roadway section, it is important to accurately monitor each vehicle’s location, speed, acceleration, heading direction, etc. …

Neural Network Architecture Search Enabled Wide-Deep Learning (Nas-Wd) Integrated Hyperspectral Imaging Understanding For Woody Breast In Poultry Processing, Chaitanya Kumar Reddy Pallerla

Graduate Theses and Dissertations

The development and implementation of a Wide & Deep (WD) learning model tailored for classification and regression tasks utilizing spectral data provides a robust solution to evaluate woody breast (WB) conditions in poultry fillets. This process begins with thorough data preprocessing, which includes loading spectral and classification datasets, imputing missing values with medians, and splitting the data into training and testing sets to ensure rigorous model evaluation. The WD model architecture integrates wide linear models and deep neural networks to harness the strengths of both approaches. The wide component excels at memorizing sparse feature interactions, while the deep component captures …

Reference Dependence In Queue Design And Pricing Strategies, Jian Liu, Yongpin Zhou, Jian Chen, Peng Li

Electrical and Computer Engineering Faculty Research & Creative Works

This research investigates the effect of reference dependence on waiting times in service systems which formerly used a first-in-first-out (FIFO) service but have introduced a priority line with a fee. Our model combines reference-dependent gain-loss utility with standard customer utility, and we posit that customers are pleased with shorter-than-expected waiting times, whereas longer-than-expected times lead to dissatisfaction and an increased likelihood of balking. The study explores two scenarios: a captive customer system (CCS) and a noncaptive customer system (NCCS), with a focus on optimal pricing and segmentation strategies for revenue and social welfare maximization. The results reveal that, in a …

Quantum Visual Feature Encoding Revisited, Xuan-Bac Nguyen, Hoang-Quan Nguyen, Hugh Churchill, Samee U. Khan, Khoa Luu

Computer Science and Computer Engineering Faculty Publications and Presentations

Although quantum machine learning has been introduced for a while, its applications in computer vision are still limited. This paper, therefore, revisits the quantum visual encoding strategies, the initial step in quantum machine learning. Investigating the root cause, we uncover that the existing quantum encoding design fails to ensure information preservation of the visual features after the encoding process, thus complicating the learning process of the quantum machine learning models. In particular, the problem, termed the “Quantum Information Gap” (QIG), leads to an information gap between classical and corresponding quantum features. We provide theoretical proof and practical examples with visualization …

Computational Representation, Analysis And Verification Of Requirements In Engineering Design And Systems Engineering, Chandan Kumar Sahu

All Dissertations

Systems are developed to satisfy a set of requirements derived from stakeholders’ needs, defining the problem space for which the system is created as a feasible solution. The system design process begins with eliciting these requirements and concludes with validating whether the created system meets them. Requirements engineering (RE) encompasses elicitation, representation, analysis, documentation, verification, and validation. However, challenges in RE, such as imprecision in natural language (NL), proprietary restrictions, and a lack of standardized quality metrics, hinder the creation of well-formed and comprehensive requirements. These challenges complicate formalization and analysis of requirements.

This dissertation addresses these challenges by proposing …

Mechanically Cost-Effective Approach For Bipedal Walking In Robots Using Instantaneous Collision Angle, Smit R. Patel

UNLV Theses, Dissertations, Professional Papers, and Capstones

Humans, as bipedal locomotors, are effective at reducing the mechanical cost of transport (CoTmech) by adopting movement strategies and gaits that minimize energy expenditure for a given distance. By using different gaits at different speeds, leveraging their long spring-like tendons and muscle elasticity which store and release energy during movement, humans reduce the mechanical effort required for locomotion. Current locomotion solutions offered in bipedal robots, based on legacy walking and running gait models, are not great at energy efficiency unless walking at very low speeds. Additionally, the control system of robots, designed to ensure stability and adaptability, requires substantial resources, …

Designing Customized Loss Functions For Training Deep Neural Networks, Ali Pourramezan Fard

Electronic Theses and Dissertations

This dissertation explores the critical role of loss functions in enhancing the predictive performance of deep machine learning models. Loss functions are an integral element of all the ongoing advances we witness daily in this domain. I design custom loss functions and their impacts on various machine learning tasks, particularly in computer vision.

In the first stage of my research, I aim to improve the prediction performance of deep learning models by providing them with more precise feedback associated with task requirements. This led me to create the concept of assistive loss functions. My first proposed loss function, inspired by …

Autonomous Driving Trajectory Prediction, Carlos Funes

Undergraduate Research Symposium Lightning Talks

Autonomous driving is undoubtedly one of the world's most revolutionary technologies, opening the door to a more secure traffic environment. This innovation has led to vehicles being able to drive by themselves without the necessity of a person behind the wheel, as well as cruise control, lane-keeping assist, and automatic emergency braking. Unfortunately, there is still plenty of work before autonomous driving becomes more popular among drivers. While at UNLV as an undergraduate student/research assistant, one of my goals is to learn how these technologies work to bring ideas into the automotive industry by refining solutions to problems within these …

It's Not As Bad As You Think: Detecting Ai-Generated Voices, Yong Qin Xu

Undergraduate Research Symposium Lightning Talks

Advances in machine learning have opened up the world to a brand new frontier of fraudulent phone calls which the average person may not be in any way prepared for. From imitations of a loved one's voice to lifelike mimicry of human callers, telephone scams may become harder than ever to anticipate or prevent now that criminals have the help of AI on their side. This is why in my research paper, I aim to analyze and compare two existing methods of detecting the authenticity of human voice recordings in order to demonstrate and explain currently available technology that's capable …

Machine Learning-Driven Process Analysis And Optimization In Solid-State Welding And Fusion-Based Additive Manufacturing, Radif Uddin Ahmed

Master's Theses

In the modern era of advanced manufacturing, optimizing process parameters is pivotal in ensuring the quality and reliability of sophisticated component fabrication. This study presents a novel, data-driven approach to parameter optimization in two cutting-edge manufacturing techniques: Friction Stir Welding (FSW) and Laser Powder Bed Fusion (LPBF). By leveraging machine learning methodologies, this research addresses the critical challenge of efficiently determining optimal process parameters, a task traditionally relying on time-consuming and resource-intensive trial-and-error methods. This study will lead to a robust data-driven framework for process analysis of more advanced manufacturing techniques like the Additive Friction Stir Deposition (AFSD) process. Friction …

Robotic Multi-Object Grasping From A Pile: Techniques And Algorithms For Enhanced Dexterity, Tianze Chen

USF Tampa Graduate Theses and Dissertations

As robots become increasingly integrated into real-world applications such as warehousing, fulfillment centers, and manufacturing, the need for efficient and adaptable robotic systems grows. One of the key challenges is enabling robots to grasp multiple objects simultaneously, as this significantly boosts the efficiency of tasks like batch picking, sorting, and object transferring, reducing both time and energy consumption. This dissertation presents a comprehensive multi-object grasping (MOG) pipeline that includes pre-grasp selection, end-pose selection, grasping synergy calculation, and a data-driven model for estimating the number of objects being grasped. Central to this work is the development of the Experience Forest structure, …

A Method For Key Node Identification In Operational Target System Based On War Gaming, Yongfu Zhang, Yang Liu, He Yuan

Journal of System Simulation

Abstract: The identification of key nodes in an operational target system is an important basis for combat command decision-making. Due to the lack of experimental verification of key node identification in the current operational target system in a campaign-level dynamic confrontation environment, a complex network model of operational target system with large-scale entities and complex interaction relationship was constructed by taking integrated air defense network as an example, with the help of the data derived from the large joint war gaming; the characteristics of wargame data were considered, and the value characteristics of combat targets and network structure characteristics were …

Platform Path Optimization Method Based On Cumulative Detection Probability Of Sonar Search, Xiang Wei, Xingxuan Liu, Dianzheng Fu, Tianji Yang, Jiaxuan Yang

Journal of System Simulation

Abstract: To address the lack of research on the optimal path of mobile search platform to search for moving targets, this paper proposes a path optimization method of mobile search platform based on cumulative search probability theory. Based on the cumulative detection probability (CDP), one of the important criteria of sensor performance evaluation, a single-peak CDP calculation formula is constructed by using a time series correlation model, namely the (λ, σ) process model. A set of target motion scenarios are constructed, and the trajectory probability of target scenarios and their CDP at different time are corrected by Bayesian posterior probability. …

Modeling For Decision Support Of Flight Ground Support Process, Zhiwei Xing, Ruiwen Yu, Biao Li, Zhaoxin Chen

Journal of System Simulation

Abstract: Aiming at the problems of insufficient decision-making ability and low operational efficiency of the flight ground support process, a decision support model of the flight ground support process based on the department of defense architecture framework (DoDAF) is proposed. Starting from the support operation, support resources, and the relationship between them, the quantitative description of the flight ground support process is performed. DoDAF and the model-based systems engineering (MBSE) modeling method are combined to establish a decision support model of the flight ground support process. The decision utility function is established to analyze the utility value of the comprehensive …

End-To-End Motion Planning Of Unmanned Vehicles Based On Multimodal Deep Reinforcement Learning, Kaiyuan Ding, Askar Hamdulla, Bin Zhu, Eksan Firkat, Zhengtang Ma

Journal of System Simulation

Abstract: Since the agent cannot sense the surrounding environment and cannot successfully avoid obstacles, reinforcement learning fails to be generalized to robot motion planning in difficult terrain. Therefore, a solution based on multimodal deep reinforcement learning, which learns to blend proprioceptive states with high-dimensional depth sensor inputs, is proposed for the motion planning of unmanned vehicles. To be specific, proprioceptive states offer contact measurement for immediate reaction, and the unmanned vehicle can learn and forecast environmental changes with its attached visual sensors, proactively navigating around obstacles and uneven terrains numerous time steps ahead. TransProAct (transformer-based proactive action), a unique end-to-end …

Flexible Job Shop Scheduling Method Based On Collaborative Agent Reinforcement Learning Algorithm, Jian Li, Huankun Li, Pengbo He, Huabei Wang, Liping Xu, Kui He

Journal of System Simulation

Abstract: To enhance the efficiency of flexible job shop scheduling, this paper develops a Markov decision process with specific constraints tailored to the scheduling problem. A cooperative agent reinforcement learning method is proposed to solve the problem of concurrent selection of workpieces and machines. During the construction of the Markov decision process, a disjunctive graph is introduced to represent the state characteristics. Two agents are introduced to select the workpieces and machines. The reward parameters governing the entire scheduling process are established by predicting variations in the minimum-maximum completion time across different time points. A GIN(graph isomorphic network) graph neural …

Dual-Resource Constrained Distributed Flexible Scheduling For Aerospace Structural Components, Yufang Wang, Dianqing Zhang, Xiaolin Hua, Binbin Yao, Fan Chen

Journal of System Simulation

Abstract: A dual-resource constrained distributed flexible job-shop scheduling model was established by taking into account the worker constraints of the finishing process and the requirements of distributed multi-factory collaboration in the production of aerospace structural components. A hybrid grey wolf optimization algorithm based on the critical factory was proposed to solve this problem. The model contained four subproblems: factory selection, operation sequencing, machine selection, and worker selection. In view of these four sub-problems, a four-layer coding and a new decoding method were designed to avoid the use conflict of machines and workers. In addition, a new mechanism for hunting and …

Automatic Detection Algorithm For Typical Defects Of Substation Based On Improved Yolov5, Zhongkai Xu, Yanling Liu, Xiaojuan Sheng, Chao Wang, Wenjun Ke

Journal of System Simulation

Abstract: In response to the challenges present in the context of defect recognition in substations, such as complex substation defects and sample imbalance, an improved YOLOv5 algorithm was proposed. The Transformer model was introduced into the YOLOv5 network structure, leveraging the self-attention mechanism to capture long-range dependencies among features. A focal loss-based optimization was employed to improve the loss function, as well as the detection accuracy and robustness of defects of small sample substations. To meet the requirements of substation defect recognition, a dedicated dataset was constructed. A clustering algorithm was applied to the real annotation boxes to generate more …

Object Detection Of Lightweight Transformer Based On Knowledge Distillation, Gaihua Wang, Kehong Li, Qian Long, Jingxuan Yao, Bolun Zhu, Zhengshu Zhou, Xuran Pan

Journal of System Simulation

Abstract: In autonomous driving, the efficiency and accuracy of object detection are significant. Object detection based on Transformer structure has gradually become the mainstream method, eliminating the complex anchor generation and non-maximum suppression (NMS). It has problems of high computing cost and slow convergence. An object detection model of the based lightweight pooling transformer (LPT) is designed, which contains a pooling backbone network and dual pooling attention mechanism. A general knowledge distillation method is intended for the DETR (detection transformer) model, which transfers prediction results, query vector, and features extracted by the teacher as knowledge to the LPT model to …

A Hybrid Genetic Search Algorithm For Capacitated Electric Vehicle Routing Problem, Dongyao Jin, Mi Liu, Yena Zhu, Yijiang Zhao

Journal of System Simulation

Abstract: The capacitated electric vehicle routing problem (CEVRP) is an NP-hard combinatorial optimization problem in logistics distribution, aiming to minimize the total delivery distance of electric vehicles while satisfying carrying capacity and battery charge constraints. A hybrid genetic search algorithm is proposed to solve CEVRP by decomposing it into two subproblems: capacitated vehicle routing problem (CVRP) and fixed-route vehicle charging problem (FRVCP). A coding scheme with a two-layer chromosome structure is designed to represent the decision variables of these two subproblems. A Split operation is employed to generate vehicle routes for solving CVRP, and five neighborhood search operators, including Relocate, …

Traffic Sign Recognition Model With Long-Tail Distribution Based On Yolox-Tiny, Yunpeng Wu, Yingxiong Fu, Lijun Shen, Feng Cui

Journal of System Simulation

Abstract: Accurate recognition of traffic signs plays an important role in the field of intelligent driving. Traffic sign training datasets with long-tail distribution increase the difficulty of traffic sign recognition. A traffic sign recognition model with long-tail distribution based on YOLOX-Tiny was proposed to improve the poor performance of the model trained on long-tail distribution datasets. A long-tail traffic sign dataset was created based on the TT100K_2021 (tsinghua-tencent 100K 2021) dataset. YOLOX-Tiny was chosen as the underlying model by considering picture numbers in datasets, sample distribution, and model size. Equalization loss v2 (EQL v2) was used as classification loss to …

Real-Time Lidar Slam Algorithm Based On Distribution Optimal Registration, Weigang Li, Chuxiang Yu, Yongqiang Wang, Shaofeng Zou

Journal of System Simulation

Abstract: When scanning the surrounding environment, a lidar will generate some cluttered and sparse point cloud, which will cause excessive distribution fitting errors and correlation distances in the registration process, thus affecting the accuracy of the registration algorithm and the effect of simultaneous localization and mapping (SLAM). To address this problem, a real-time lidar SLAM algorithm based on distribution optimal registration is proposed. An eigenspectrum filter is designed, which takes the normalized minimum eigenvalue as the filtering object to filter out the points that do not match the set distribution in order to reduce the distribution fitting error. Secondly, a …

Research On Green Job Shop Scheduling Based On Herd Immunity Optimizer, Xunde Ma, Li Bi, Junjie Wang

Journal of System Simulation

Abstract: In view of the green flexible job shop scheduling problem where machines have multiple speeds, a green flexible job shop scheduling model under multiple speeds was constructed to minimize the makespan and total energy consumption under different speeds. A discrete coronavirus herd immunity optimizer (DCHIO) was proposed for a solution. A discrete individual updating method was introduced for the relatively large solution space of the multi-speed problem, based on which a population updating mechanism with multi-scale joint search was proposed to search the solution space quickly and uniformly. A dynamic mutation operation was designed to enhance the population diversity …

Agv Scheduling Problem At Automated Terminals Based On Improved Dqn Algorithm, Chengji Liang, Shidong Zhang, Yu Wang, Bin Lu

Journal of System Simulation

Abstract: A future tasks considering deep Q-network (F-DQN) algorithm was proposed to output realtime scheduling results of automated guided vehicles (AGVs) at automated terminals. This algorithm combined the advantages of real-time scheduling and static scheduling, improving the system status by considering static future task information when making real-time decisions, so as to obtain a better scheduling solution. In this study, the actual layout and equipment conditions of the Yangshan phase IV automated terminal were considered, and a series of simulation experiments were conducted using the Plant Simulation software. The experimental results show that the F-DQN algorithm can effectively solve the …