Engineering Commons^™

Integrating Generative Artificial Intelligence With Systems Architecting Diagram Creation: Advancement, Challenges, Opportunities And Future Perspectives, Cansu Yalim, Holly H. Handley

Engineering Management & Systems Engineering Faculty Publications

Generative AI (GenAI) serves as a powerful tool that can create a wide range of content, including but not limited to text, speech, images, code, videos, and 3D models. ChatGPT stands out as a particularly appealing Generative Pretrained Transformer (GPT) model that offers supplementary capabilities through GPTs and plugins. These extensions enable users to engage with the chatbot and improve its functionality, surpassing mere content generation. Our study delves into the potential of ChatGPT, specifically GPT-4, to expedite the creation of diagrams to support the system architecting process. To this end, we explored the use of ChatGPT's Diagrams Show Me …

การพยากรณ์ยอดขายรถยนต์ด้วยวิธีการเรียนรู้ของเครื่องเพื่อลดระดับสินค้าคงคลังของชิ้นส่วนนำเข้า, สุวิทย์ นันทร์ทิพย์

Chulalongkorn University Theses and Dissertations (Chula ETD)

งานวิจัยนี้มีวัตถุประสงค์เพื่อศึกษาการพยากรณ์ยอดขายรถยนต์เพื่อเปรียบเทียบความแม่นยำของค่าพยากรณ์จากตัวแบบวิธีการปรับเรียบเอกซ์โพเนนเชียลของโฮลท์และวินเทอร์ วิธีต้นไม้ตัดสินใจ วิธีป่าสุ่ม วิธีXGBoost วิธีโครงข่ายประสาทเทียมและวิธีผสม ด้วยค่าร้อยละความคลาดเคลื่อนสัมบูรณ์เฉลี่ยของข้อมูลยอดขายรถยนต์รายรุ่นย่อยของบริษัทผลิตรถยนต์กรณีศึกษา โดยใช้ข้อมูลยอดขายตั้งแต่เดือนมกราคม พ.ศ. 2557 ถึงเดือนธันวาคม พ.ศ. 2567 ในการฝึกตัวแบบพยากรณ์และหาความสัมพันธ์ของปัจจัยต่าง ๆ ที่มีผลต่อการตัดสินใจซื้อของลูกค้า โดยใช้คำสั่ง GridSearchCV ในการปรับแต่งค่าไฮเปอร์พารามิเตอร์เพื่อหาค่าที่เหมาะสมในการพยากรณ์ของตัวแบบวิธีการเรียนรู้ของเครื่องได้อย่างมีประสิทธิภาพ ผลการศึกษาพบว่าวิธีผสมเป็นวิธีที่สามารถพยากรณ์ยอดขายได้แม่นยำที่สุด เมื่อเทียบกับวิธีการพยากรณ์อื่น ๆ โดยผลลัพธ์ของวิธีผสมให้ค่าความแม่นยำที่ดีในรุ่นย่อย SM976 SM978 และ ST166 โดยมีค่าร้อยละความคลาดเคลื่อนสัมบูรณ์เฉลี่ยเท่ากับ 17.93% 10.31% และ 18.34% ตามลำดับ และให้ค่าความแม่นยำที่ยอมรับได้ในรุ่นย่อย SM972 SM974 ST164 และ ST168 ด้วยค่าร้อยละความคลาดเคลื่อนสัมบูรณ์เฉลี่ยเท่ากับ 23.19% 26.44% 21.71 และ 22.39% ตามลำดับ นอกจากนี้การนำผลการพยากรณ์ยอดขายของวิธีผสมมาใช้ในการกำหนดความต้องการสั่งซื้อ พร้อมทั้งทดสอบวิธีการสั่งซื้อในรูปแบบ Order-Up-To Level (OUL) ส่งผลให้ระดับคงคลังชิ้นส่วนนำเข้าเฉลี่ยต่อเดือนของทุกรุ่นย่อยลดลงอย่างมีนัยสำคัญ โดยผลลัพธ์ในรุ่นย่อย SM972 SM974 SM976 และ SM978 มีระดับชิ้นส่วนคงคลังลดลง 62.65% 79.65% 72.94% และ 69.21% ตามลำดับ และในส่วนของรุ่นย่อย ST162 ST164 และ ST168 มีระดับชิ้นส่วนคงคลังเฉลี่ยต่อเดือนลดลง 55.78% 52.18% และ 61.75% ตามลำดับ เมื่อเทียบกับระดับสินค้าคงคลังของวิธีการพยากรณ์และวิธีการสั่งซื้อในรูปแบบปัจจุบัน

Analysis Of Performance Deterioration During Prolonged Wakefulness, Aaron J. King

Open Access Master's Theses

In a variety of professions, personnel are asked to work extended shifts, straining themselves both physically and mentally. The strain in combination with the prolonged wakefulness can lead to mistakes on the job. This can be problematic for industries where mistakes are associated with high-risk consequences. A few professions that typically work in shifts include nurses, truck drivers, and oil-rig workers to name a few. Pertinent to this study is the performance of operators performing pilot related activities such as driving or monitoring; this is specifically interesting where the risk for failure can result in fatality or serious injury, such …

Training Practitioners For Real-Time Product Development Using Generative Artificial Intelligence, Antoine J. Jetter, Ameeta Agrawal, Dahm Mongkol Hongchai, Charles Weber, Yufei Tao

Engineering and Technology Management Faculty Publications and Presentations

A workshop to train practitioners in real-time new product development (NPD) using generative artificial intelligence (AI) was conducted. Three teams of graduate students in Engineering and Technology Management (many with work experience as managers and engineers) were given minimalist instructions to develop a product concept and a preliminary marketing plan for a product of their choosing within six hours using ChatGPT, search engines, and other Internet-based tools. The product was to be novel, and the plan was to include customer identification, market analysis, generating personas, and a 15-minute presentation at the end of the workshop. The goal was to 'inspire …

Traveling The Pathway To A Culturally Competent Health Care Provider: Incorporating Study Abroad Into Your Curriculum, A L. Johnston Green, C J. Heffner

Clinical Practice in Athletic Training

Introduction: As athletic training employment settings expand and diversify, so does the patient population with whom these healthcare providers interact. This growth furthers the need to ensure that students enrolled in an athletic training program (ATP) accredited by the Commission on Accreditation of Athletic Training Education (CAATE) are educated to provide culturally competent care. Culturally competent care is provided when decisions made diminish the inequalities that may be present in a system based upon a patient’s individual circumstances. Implementing cultural competency education may be integrated into athletic training education in various manners as necessitated by each institution’s unique circumstances. Programs …

The Precedence-Constrained Quadratic Knapsack Problem, Changkun Guan

Honors Theses

This thesis investigates the previously unstudied Precedence-Constrained Quadratic Knapsack Problem (PC-QKP), an NP-hard nonlinear combinatorial optimization problem. The PC-QKP is a variation of the traditional Knapsack Problem (KP) that introduces several additional complexities. By developing custom exact and approximate solution methods, and testing these on a wide range of carefully structured PC-QKP problem instances, we seek to identify and understand patterns that make some cases easier or harder to solve than others. The findings aim to help develop better strategies for solving this and similar problems in the future.

Contextualizing Renewable Energy Adoption: An Examination Of The Role Of Community Choice Aggregation, Ankit Agarwal

Doctoral Dissertations

"The rapid expansion of renewable energy generation in the U.S., both through distributed and utility-scale facilities, is largely driven by top-down policy measures and the growing engagement of residential consumers on both individual and community levels. Previous studies on motives behind residential renewable energy adoption have examined procurement options in isolation and within a static context, primarily focused on intrinsic attributes like economic incentives, emission reductions, and peer popularity. This research introduces a novel context, assessing renewable procurement options in the presence of Community Choice Aggregation (CCA), a more prevalent and accessible alternative. This dissertation makes four pivotal contributions, offering …

Les Pratiques Professionnelles Des Pomiculteurs Exposés Aux Pesticides : Des Savoir-Faire De Métier Aux Pratiques Stratégiques, Caroline Jolly, Alain Garrigou, Elise Ledoux

Études primaires

Dans les très petites entreprises pomicoles, le propriétaire assume majoritairement seul la préparation et la pulvérisation des pesticides. Le respect des mesures de prévention prescrites n’élimine pas l’exposition, pouvant occasionner des effets à la santé. L’objectif est de décrire les pratiques professionnelles développées par les pomiculteurs. Elles visent à limiter l’exposition aux pesticides tout en produisant des fruits de qualité, contribuant ainsi à l'essor de leur entreprise. La recherche-intervention mobilisant l’ergotoxicologie a été réalisée auprès de pomiculteurs au Québec. La diversité des pratiques professionnelles présentées s’inscrit dans les domaines d’activités de la gestion stratégique (p. ex. : développement de l’entreprise) …

Project Control System (Pcs) Implementation In Engineering And Construction Projects: An Empirical Study In Saudi's Petroleum And Chemical Industry, Sahar Jawad, Ann Ledwith, Rashid Khan

School of Cybersecurity Faculty Publications

Purpose

There is growing recognition that effective project control systems (PCS) are critical to the success of projects. The relationship between the individual elements of PCS and successfully achieving project objectives has yet to be explored. This research investigates the enablers and barriers that influence the elements of PCS success and drive project objectives.

Design/methodology/approach

This study adopts a mixed approach of descriptive analysis and regression models to explore the impact of six PCS elements on project outcomes. Petroleum and chemical projects in Saudi Arabia were selected as a case study to validate the research model.

Findings

Data from a …

3d Point Cloud Sensing And Analytics With Applications In Process Mining And Quality Control Of Additive Manufacturing, Zehao Ye

Industrial, Manufacturing, and Systems Engineering Dissertations - Archive

The rapid advancement in Additive Manufacturing (AM) technologies has developed significant innovations in various sectors, including medical, aerospace, and automotive industries. Despite these benefits, the adoption of AM is often hindered by quality inconsistencies related to the surface defects and geometrical inaccuracies in the fabricated products. These defects can significantly undermine the mechanical properties of the products, leading to material waste and potential safety issues. This dissertation addresses the critical challenges in quality control of AM processes through the integration of 3D point cloud data and machine learning techniques, aiming to enhance the reliability and efficiency of AM systems. The …

User-Interaction With A Web-Served Global Ground Motion Relational Database, T. E. Buckreis, C. C. Nweke, P. Wang, S. J. Brandenberg, R. Shams, M. E. Ramos-Sepulveda, R. Pretell, S. Mazzoni

Civil & Environmental Engineering Faculty Publications

We present an application programming interface (API) which facilitates public access to a global relational database of earthquake ground motion intensity measures, associated metadata, and time-series data. Next Generation Attenuation (NGA)-East and NGA-West2 project spreadsheets have been adapted into a relational database format composed of multiple tables through a series of primary and foreign keys. The combined dataset has been expanded to include contributions from earthquakes, generally with magnitudes greater than M3.9, that have occurred since the conclusion of the data synthesis component of both projects in 2011. Currently the database includes 62,449 ground motions recorded at 9,092 stations for …

‘I Know It When I See It’– Developing Quality Schedules Considering Subjective Or Unspecified Criteria, Douglas L. Moody

Publications and Research

Most timetabling problems have a given objective function to measure the quality of a solution. However, users may have a “I know it when I see it” recognition of a quality schedule, without specifying the complete basis for their judgment. In this situation, the objective function cannot be exclusively used as a solution quality measurement. This work presents an AI based approach to aid in categorizing the solution’s quality when the users have not explicitly defined all factors used in their criteria.

An Impedance Tube Technique For Estimating The Insertion Loss Of Earplugs, K. Carillo, O. Doutres, F. Sgard

Études primaires

This paper proposes a quick and straightforward technique for estimating the insertion loss (IL) of earplugs measured on an acoustical test fixture (ATF) using a commercial impedance tube. In this method, the earplug's acoustic properties (i.e., its transmission loss and the reflection coefficient of its medial surface) are determined from its transfer matrix measured using the three-microphones impedance tube method modified here for the current application. The IL is then estimated using a one-dimensional analytical model of open and occluded earcanals based on the wavefield decomposition theory. The method is evaluated numerically and experimentally from 50 Hz to 6.5 kHz. …

Methods That Support The Validation Of Agent-Based Models: An Overview And Discussion, Andrew Collins, Matthew Koehler, Christopher Lynch

Engineering Management & Systems Engineering Faculty Publications

Validation is the process of determining if a model adequately represents the system under study for the model’s intended purpose. Validation is a critical component in building the credibility of a simulation model with its end-users. Effectively conducting validation can be a daunting task for both novice and experienced simulation developers. Further compounding the difficult task of conducting validation is that there is no universally accepted approach for assessing a simulation. These challenges are particularly relevant to the paradigm of Agent-Based Modeling and Simulation (ABMS) because of the complexity found in these models’ mechanisms and in the real-world situations they …

Abmscore: A Heuristic Algorithm For Forming Strategic Coalitions In Agent-Based Simulation, Andrew J. Collins, Gayane Grigoryan

Engineering Management & Systems Engineering Faculty Publications

Integrating human behavior into agent-based models has been challenging due to its diversity. An example is strategic coalition formation, which occurs when an individual decides to collaborate with others because it strategically benefits them, thereby increasing the expected utility of the situation. An algorithm called ABMSCORE was developed to help model strategic coalition formation in agent-based models. The ABMSCORE algorithm employs hedonic games from cooperative game theory and has been applied to various situations, including refugee egress and smallholder farming cooperatives. This paper discusses ABMSCORE, including its mechanism, requirements, limitations, and application. To demonstrate the potential of ABMSCORE, a new …

Learning Social Fairness Preferences From Non-Expert Stakeholder Opinions In Kidney Placement, Mukund Telukunta, Sukruth Rao, Gabriella Stickney, Venkata Sriram Siddardh Nadendla, Casey I. Canfield

Computer Science Faculty Research & Creative Works

Modern kidney placement incorporates several intelligent recommendation systems which exhibit social discrimination due to biases inherited from training data. Although initial attempts were made in the literature to study algorithmic fairness in kidney placement, these methods replace true outcomes with surgeons' decisions due to the long delays involved in recording such outcomes reliably. However, the replacement of true outcomes with surgeons' decisions disregards expert stakeholders' biases as well as social opinions of other stakeholders who do not possess medical expertise. This paper alleviates the latter concern and designs a novel fairness feedback survey to evaluate an acceptance rate predictor (ARP) …

An Ai-Based Conceptual Framework To Improve Program Management Of Complex Systems, Michael D. Parrish, Steven Corns

Engineering Management and Systems Engineering Faculty Research & Creative Works

With evolving technologies, changing requirements, and limited budgets, governments and industries need to consider new methodologies to help streamline program lifecycle management, from cradle to grave, to ensure projects are delivered on time, on budget, and to the expected performance standards. Traditional approaches fail to adequately address the added complexities of System of Systems programs such as integration, interoperability, and variable lifecycle of subcomponents. The objective of this study is to assess and address the research question - can a new acquisition approach be designed to address and improve program lifecycle management of complex systems? A comparison study, using the …

Navigating Innovation Within A Contractor's Business Model: A System Dynamics Approach, Mariam Elazhary, Cihan Dagli, Islam H. El-Adaway

Engineering Management and Systems Engineering Faculty Research & Creative Works

Innovation is essential in the construction industry, but current practices often focus narrowly on specific aspects rather than taking a comprehensive approach. To address this, systematic innovation through business model innovation (BMI) is proposed to enhance overall performance. Despite increasing interest in BMI research, it remains in its early stages, lacking quantitative analysis of its impact on business model components. This paper develops a framework using system dynamics to assess changes to a construction company's BM when faced with a variety of innovations across various projects. This shall be accomplished by (1) establishing factors and their relationships that define a …

A Model-Adaptive Random Search Actor Critic: Convergence Analysis And Inventory-Control Case Studies, Yuehan Luo, Jiaqiao Hu, Abhijit Gosavi

Engineering Management and Systems Engineering Faculty Research & Creative Works

Reinforcement learning (RL) is an exciting area within the domain of Markov Decision Processes (MDPs) in which the underlying optimization problem is solved either in a simulator of the real-world system or via direct interaction with the real-world system, when its underlying transition probabilities are difficult to estimate. The latter is commonly true of large-scale, real-world MDPs with complex underlying transition dynamics. RL is currently being widely researched in the world of medicine/neuroscience after some spectacular success stories demonstrating super-human behavior in computer games. In this paper, we propose a new actor-critic-based RL algorithm for approximately solving continuous state/action MDPs …

A Simulation-Based Digital Twin For Data-Driven Maintenance Scheduling Of Risk-Prone Production Lines Via Actor Critics, Abhijit Gosavi, Aparna Gosavi

Engineering Management and Systems Engineering Faculty Research & Creative Works

Industry 4.0 mandates a shift from traditional total productive maintenance (TPM) methods, which rely on periodic data gathering and subsequent offline modeling for maintenance scheduling, towards more data-driven and online decision-making approaches. Further, Industry 4.0 emphasizes reducing intervention from high-skilled managers and leveraging real-time data for decision-making, which is characteristic of models rooted in either renewal-theoretic or Markov chains for traditional TPM methods. Digital Twins (DTs), which are virtual representations of physical systems, play a crucial role in this paradigm by enabling online decision-making of maintenance scheduling directly at the workstation level. In this paper, a simulation-based DT (S-DT) is …

Yankee Manufacturing Multi-Assembly Pvc-Gasket Assembly Mechanism, Lily Coss, Jessica Kun, Dana Chapin, Jenan Hasan

Williams Honors College, Honors Research Projects

This project focuses on designing and implementing an efficient mechanism to connect PVC and gasket pieces in the door assembly process at Yankee Manufacturing. The aim is to improve process efficiency and productivity by increasing the assembly rate from 130 to 195 assemblies per hour, a 38% improvement. The project involved research, design iterations, performance evaluations, and adherence to engineering codes and standards, particularly focused on safety, ergonomics, and sustainability. The design process includes addressing challenges from a previous attempt, redefining project scope, and incorporating new elements such as transitioning to the packaging process seamlessly. Ethical considerations include promoting operator …

Letac-Mpc: Learning Model Predictive Control For Tactile-Reactive Grasping, Zhengtong Xu, Yu She

School of Industrial Engineering Faculty Publications

Grasping is a crucial task in robotics, necessitating tactile feedback and reactive grasping adjustments for robust grasping of objects under various conditions and with differing physical properties. In this article, we introduce LeTac-MPC, a learning-based model predictive control (MPC) for tactile-reactive grasping. Our approach enables the gripper to grasp objects with different physical properties on dynamic and force-interactive tasks. We utilize a vision-based tactile sensor, GelSight (Yuan et al. 2017), which is capable of perceiving high-resolution tactile feedback that contains information on the physical properties and states of the grasped object. LeTac-MPC incorporates a differentiable MPC layer designed to model …

Leto: Learning Constrained Visuomotor Policy With Differentiable Trajectory Optimization, Zhengtong Xu, Yu She

School of Industrial Engineering Faculty Publications

This paper introduces LeTO, a method for learning constrained visuomotor policy with differentiable trajectory optimization. Our approach integrates a differentiable optimization layer into the neural network. By formulating the optimization layer as a trajectory optimization problem, we enable the model to end-to-end generate actions in a safe and constraint-controlled fashion without extra modules. Our method allows for the introduction of constraint information during the training process, thereby balancing the training objectives of satisfying constraints, smoothing the trajectories, and minimizing errors with demonstrations. This “gray box” method marries optimization-based safety and interpretability with powerful representational abilities of neural networks. We quantitatively …

Yankee Feedstock Project, Nathan Mcanany, Richard Gualtiere

Williams Honors College, Honors Research Projects

This report details the design process, application, considerations, costs, and functionality of an automated tape “feedstock” machine. Yankee Insulation Products will use this project to create rolls of Aluminum foil tape that are included in their Therma-Dome assembly kit. The goal of this design will aid in the streamlining and effectiveness of the current process. When designing the automated process, the current process was evaluated for areas of improvement. Design parameters were also given to the project by the sponsoring company that were to be considered and incorporated.

Conflict Profiles And Team Outcomes In Cross-Disciplinary Teams: An Integrated Latent Profile Analysis And Natural Language Processing Approach, Francisco Cima, Pilar Pazos

Engineering Management & Systems Engineering Faculty Publications

Team conflict is a naturally emerging phenomenon resulting from individuals' interactions during project execution. Cross-disciplinary teams can experience higher levels of conflict than single-discipline teams because of the increased diversity of knowledge and perspectives. Research has shown that team conflict can emerge from different types of disagreements (cognitive and interpersonal), which have different implications for team functioning. Past empirical research has focused on the impact of both conflict types independent from each other while overlooking their combined effects. This work examines the conflict profiles resulting from the combined levels of interpersonal and cognitive disagreements and their association with team outcomes. …

Collaborative Robotic Finishing Platform For Metal Part Processing Towards Industry 5.0, Seyedhossein Hajargarbashi, Gabriel Côté, Jonathan Boisvert, Ramy Meziane, Chen Xu, Corentin Hubert, Sabrina Jocelyn, Clément Gosselin

Articles dans des actes de congrès

Manual finishing operations in aerospace and ground transportation industries are often associated with health-and-safety-related issues such as musculoskeletal disorders, productivity loss, and challenges in workforce renewal. This work presents an innovative automated solution to address these challenges, prioritizing the ease of implementation and affordability for small and midsize enterprises (SMEs). Our proposed solution is a collaborative robotic (cobotic) finishing platform designed to eliminate labor-intensive work while keeping human operators in the loop to manage unforeseen situations. This platform aims to eliminate health risks, enhance repeatability, improve product quality, and increase productivity. This paper describes the mechanical design of the platform, …

Efficient Connectivity Management And Path Planning For Iot And Uav Networks, Amirahmad Chapnevis

Theses and Dissertations

This dissertation explores how to better manage resources in mobile networks, especially for enhancing the performance of Unmanned Aerial Vehicles (UAV)-supported IoT networks. We explored ways to set up a flexible communication architecture that can handle large IoT deployments by making good use of mobile core network resources like bearers and data paths. We developed strategies that meet the needs of IoT networks and enhance network performance. We also developed and tested a system that combines traffic from several mobile devices that use the same user identity and network resources within the core mobile network. We used everyday smartphones, SIM …

The Impact Of Social Media On Charitable Giving For Nonprofit Organization, Namchul Shin

Journal of International Technology and Information Management

Research has extensively studied nonprofit organizations’ use of social media for communications and interactions with supporters. However, there has been limited research examining the impact of social media on charitable giving. This research attempts to address the gap by empirically examining the relationship between the use of social media and charitable giving for nonprofit organizations. We employ a data set of the Nonprofit Times’ top 100 nonprofits ranked by total revenue for the empirical analysis. As measures for social media traction, i.e., how extensively nonprofits draw supporters on their social media sites, we use Facebook Likes, Twitter Followers, and Instagram …

How Does Digitalisation Transform Business Models In Ropax Ports? A Multi-Site Study Of Port Authorities, Yiran Chen, Anastasia Tsvetkova, Kristel Edelman, Irina Wahlström, Marikka Heikkila, Magnus Hellström

Journal of International Technology and Information Management

This article investigates the relationship between digitalisation and business model changes in RoPax ports. The study is based on six RoPax ports in Northern Europe, examining their digitalisation efforts and the resulting changes in their business models, leading to further digital transformation. The paper offers insights by reviewing relevant literature on digitalisation’s role in business model innovation and its application in ports. The findings reveal that digitalisation supports relevant business model changes concerning port operation integration within logistics chains, communication, documentation flow, and cargo flow optimisation. However, exploring digitalisation’s potential for diversifying value propositions is still limited. Most digitalisation efforts …

Key Issues Of Predictive Analytics Implementation: A Sociotechnical Perspective, Leida Chen, Ravi Nath, Nevina Rocco

Journal of International Technology and Information Management

Developing an effective business analytics function within a company has become a crucial component to an organization’s competitive advantage today. Predictive analytics enables an organization to make proactive, data-driven decisions. While companies are increasing their investments in data and analytics technologies, little research effort has been devoted to understanding how to best convert analytics assets into positive business performance. This issue can be best studied from the socio-technical perspective to gain a holistic understanding of the key factors relevant to implementing predictive analytics. Based upon information from structured interviews with information technology and analytics executives of 11 organizations across the …