Other Engineering Commons^™

Multi-Modal Tensor Fusion For Alzheimer’S Disease Recognition, Mason Li, Tiffany Le, Jiajing Huang, Yuxin Wen

Engineering Faculty Articles and Research

---

Accurate and early diagnosis of Alzheimer’s disease (AD) is critical for effective intervention, disease monitoring, and patient care. Traditional diagnostic approaches rely on a single modality, such as clinical assessments, neuroimaging, or genetic markers, which may fail to capture the complex, multifaceted nature of AD. Multimodal learning has therefore been explored to integrate complementary information across data sources. However, conventional fusion strategies, including early feature concatenation and late decision-level fusion, often model modalities independently and fail to capture high-order cross-modal interactions. To address these limitations, we propose a multimodal tensor fusion network (MTFN) that integrates heterogeneous data sources, including visual …

---

Dual-Function Plasmonic Structure For Logic Operations And Circular Polarization Detection, Marjan Bazian, Mark C. Harrison

Engineering Faculty Articles and Research

---

Many integrated photonic devices have a high potential for dual applications, making them more versatile components in photonic integrated circuits. In this study, we show that a plasmonic XOR gate structure, originally designed to perform logic operations, can also be used as a circular polarization detector. This multi-purpose capability stems from the phase-encoded input mechanism that controls the output response of the structure. We adapted this mechanism to select the output based on the polarization state of light. The design of this structure, utilizing the subwavelength field confinement of plasmonic waveguides, enables the integration of logic and detection functions into …

---

Computational Modeling Of Enhanced Nonlinear Optical Response In Plasmonic Waveguide Devices With Epsilon-Near-Zero Films, Kevin T. Le, Mark C. Harrison

Engineering Faculty Articles and Research

---

Silicon photonics faces fundamental limitations in nonlinear applications due to weak Kerr nonlinearity, substantial two-photon absorption, and coupling challenges with subwavelength structures. This work investigates epsilon-near-zero (ENZ) materials integrated into plasmonic waveguide architectures for enhanced nonlinear photonic devices. ENZ materials exhibit nonlinear refractive indices several orders of magnitude higher than conventional materials near their zero-permittivity wavelength, enabling giant optical effects over deeply sub-wavelength interaction lengths. We present finite element method simulations of plasmonic ENZ waveguides, investigating layer thickness optimization for nonlinear enhancement while minimizing optical losses. Initial modal analysis confirms superior field confinement in hybrid plasmonic-ENZ structures compared to conventional …

---

The Role Of Artificial Intelligence In Reducing Internet Crimes Against Children, Malyssa Shaw

Student Scholar Symposium Abstracts and Posters

---

When generative artificial intelligence (AI) first surfaced and broke into the public sphere, my immediate concern was in its development, implementation, and harmful applications. I was not surprised when deepfake technology rapidly advanced alongside these new developments and impacted women and children worldwide. Disproportionately, they have been made victims of intimate media forgery as early as the 1990s, with an unprecedented uptick in recent years as a direct result of these developments. In response, I wrote "Deepfake, Real Harm: Protecting Children in the Age of AI", analyzing data specifically regarding child sexual abuse material (CSAM) created with artificial intelligence while …

---

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 …

---

Assembly Of Non-Close-Packed Poly(N-Isopropylacrylamide) Microgels On Metal Halide Perovskite Films, Amal Alruwaili, Osama M. Alkhudhari, Ran Wang, Zhenyu Jia, Jennifer M. Saunders, Eugenio Picheo, Daniel T.W. Toolan, L. Andrew Lyon, Brian R. Saunders

Engineering Faculty Articles and Research

---

Hypothesis

Poly(N-isopropylacryamide) microgels (PNIPAM MGs) are interesting model colloids with remarkable self-ordering properties. Metal halide perovskites (MHPs) are solution processable semiconductors that have attracted great interest for optoelectronics applications. Very few studies have considered complex co-crystallizing systems and their effects on structural order formation. This work examines PNIPAM MG ordering within a MHP matrix and investigates whether these pure PNIPAM MGs could form arrays on the MHP surface, passivate MHP defects and provide structurally colored films and solar cells.

Experiments

We use a mixed cation MHP (FA0.88MA0.12PbI3) (FA and MA are formamidinium and methylammonium) and investigate the effects …

---

Connecting The Montessori Philosophy Through Edtech, Olivia Chilvers

Electrical Engineering and Computer Science (MS) Theses

---

This thesis explores the evolving landscape of Educational Technology (EdTech) and examines how the Montessori educational philosophy is translated into digital learning environments. The study aims to identify design implications for children’s educational applications (apps) that seek to align with Montessori principles and what aspects of a Montessori-based application excel over a non-Montessori-based application. A qualitative thematic analysis was conducted using a custom-developed codebook to analyze user reviews posted by guardians of children on the Apple App Store. These reviews pertained to apps identified as Montessori-based, either through explicit labeling or meta-data. In addition to this review analysis, a user …

---

Biobased Acrylate Composites With Enhanced Strength For Additive Manufacturing, Nicole Wagner, Joseph Mcwherter

Engineering Faculty Articles and Research

---

With the expanding use of polymers in additive manufacturing, sustainable resins for use in vat photopolymerization are required to reduce their environmental impact. One promising approach to achieve this is to incorporate biobased fillers that replace the acrylates in photopolymer resins as ‘green’ alternatives. In this study, photopolymer composites consisting of a methacrylate resin with varying calcium carbonate powder content between 0 and 50 wt.% were investigated. A digital light processing technique was used to fabricate tensile test specimens for mechanical testing. Good printability, dimensional accuracy, and good interlayer adhesion were observed for composite resin formulations that incorporated calcium carbonate …

---

Movian: Advancing Human Motion Analysis With 3d Visualization And Annotation, Trudi Di Qi, Isaac Browen, David Zhang, Hector M. Camarillo-Abad, Franceli L. Cibrian

Engineering Faculty Articles and Research

---

Human motion analysis, including data visualization and annotation, is crucial for understanding human behavior and intentions during various activities, aiding in the development of innovative tools that support independent living. Current wearable sensing technology provides rich 3D spatial movement data but generates multimodal complex datasets that require specialized skills for effective analysis. Despite the need, limited research exists on tools for effective visualization and easy annotation of such complex motion data. MoViAn (Motion Data Visualization and Annotation) is an innovative 3D data analysis system offering enriched visual representations of 3D human motion data (e.g., gaze, hand movements), along with an …

---

Digital Health Intervention For Children With Adhd To Improve Mental Health Intervention, Patient Experiences, And Outcomes: A Study Protocol, Nancy Herrera, Franceli L. Cibrian, Lucas M. Silva, Jesus Armando Beltran, Sabrina E. B. Schuck, Gillian R. Hayes, Kimberley D. Lakes

Engineering Faculty Articles and Research

---

Background

Attention Deficit Hyperactivity Disorder (ADHD) is the most prevalent childhood psychiatric condition with profound public health, personal, and family consequences. ADHD requires comprehensive treatment; however, lack of communication and integration across multiple points of care is a substantial barrier to progress. Given the chronic and pervasive challenges associated with ADHD, innovative approaches are crucial. We developed the digital health intervention (DHI)—CoolTaCo [Cool Technology Assisting Co-regulation] to address these critical barriers. CoolTaCo uses Patient-Centered Digital Healthcare Technologies (PC-DHT) to promote co-regulation (child/parent), capture patient data, support efficient healthcare delivery, enhance patient engagement, and facilitate shared decision-making, thereby improving access to …

---

Joint Modeling Of Degradation Signals And Time-To-Event Data For The Prediction Of Remaining Useful Life, Sebastian Brumm, Erik Linstead, Junde Chen, Narayanaswamy Balakrishnan, Yuxin Wen

Engineering Faculty Articles and Research

---

Accurate prediction of remaining useful life (RUL) for in-service systems plays an important role in ensuring efficient operation of industrial equipment and in preventing unexpected equipment failures. In this paper, we present a prognostic framework for real-time RUL prediction based on joint modeling of both degradation signals and time-to-event data. The proposed model employs a change point-based general path model to capture signal non-linearity and Neural network (NN) based Cox model to link the time-to-event data with the estimated degradation trend. An empirical two-step scheme for hyperparameter estimation is proposed to enhance prognostic accuracy. Furthermore, an efficient Bayesian model updating …

---

A Bayesian Approach For Lifetime Modeling And Prediction With Multi-Type Group-Shared Missing Covariates, Hao Zeng, Xuxue Sun, Kuo Wang, Yuxin Wen, Wujun Si, Mingyang Li

Engineering Faculty Articles and Research

---

In the field of reliability engineering, covariate information shared among product units within a specific group (e.g., a manufacturing batch, an operating region), such as operating conditions and design settings, exerts substantial influence on product lifetime prediction. The covariates shared within each group may be missing due to sensing limitations and data privacy issues. The missing covariates shared within the same group commonly encompass a variety of attribute types, such as discrete types, continuous types, or mixed types. Existing studies have mainly considered single-type missing covariates at the individual level, and they have failed to thoroughly investigate the influence of …

---

Furthering Development Of Smart Fabrics To Improve The Accessibility Of Music Therapy, Ellie Nguyen, Daisy Z. Fernandez-Reyes, Franceli L. Cibrian

Engineering Faculty Articles and Research

---

In this paper, we present the design and development of HarmonicThreads, a smart, cost-effective fabric augmented by generative machine learning algorithms to create music in real time according to the user's interaction. In this manner, we hypothesize that individuals with sensory differences could take advantage of the fabric's flexibility, the music will adapt according to users' interaction, and the affordable hardware we propose will make it more accessible. We follow a design thinking methodology using data from a multidisciplinary team in Mexico and the United States. Then we will close this paper by discussing challenges in developing accessible smart fabrics …

---

Self-Dual Systems For Backscattering Cancellation, Nasim Mohammadi Estrakhri

Engineering Faculty Articles and Research

---

Using carefully arranged electric and magnetic components, we have recently demonstrated that backscattering from otherwise arbitrarily shaped two- and three-dimensional structures can be fully eliminated. Here, first we investigate the possibility of creating self-dual microwave absorbers that may provide advantages compared to typical commercial magnetoelectric absorbers. Next, we demonstrate that the self-duality condition is not limited to homogenous structures and may be extended to effective material properties, opening the door to realistic implementation of these structures at microwave and optical frequencies.

---

Adaptive Octree Meshes For Simulation Of Extracellular Electrophysiology, Christopher Bc Girard, Dong Song

Engineering Faculty Articles and Research

---

Objective. The interaction between neural tissues and artificial electrodes is crucial for understanding and advancing neuroscientific research and therapeutic applications. However, accurately modeling this space around the neurons rapidly increases the computational complexity of neural simulations. Approach. This study demonstrates a dynamically adaptive simulation method that greatly accelerates computation by adjusting spatial resolution of the simulation as needed. Use of an octree structure for the mesh, in combination with the admittance method for discretizing conductivity, provides both accurate approximation and ease of modification on-the-fly. Main results. In tests of both local field potential estimation and multi-electrode stimulation, dynamically adapted meshes …

---

Weakly-Supervised Learning Method For The Recognition Of Potato Leaf Diseases, Junde Chen, Xiaofang Deng, Yuxin Wen, Weirong Chen, Adnan Zeb, Defu Zhang

Engineering Faculty Articles and Research

---

As a crucial food crop, potatoes are highly consumed worldwide, while they are also susceptible to being infected by diverse diseases. Early detection and diagnosis can prevent the epidemic of plant diseases and raise crop yields. To this end, this study proposed a weakly-supervised learning approach for the identification of potato plant diseases. The foundation network was applied with the lightweight MobileNet V2, and to enhance the learning ability for minute lesion features, we modified the existing MobileNet-V2 architecture using the fine-tuning approach conducted by transfer learning. Then, the atrous convolution along with the SPP module was embedded into the …

---

A Deep Learning-Based Approach To Extraction Of Filler Morphology In Sem Images With The Application Of Automated Quality Inspection, Md. Fashiar Rahman, Tzu-Liang Bill Tseng, Jianguo Wu, Yuxin Wen, Yirong Lin

Engineering Faculty Articles and Research

---

Automatic extraction of filler morphology (size, orientation, and spatial distribution) in Scanning Electron Microscopic (SEM) images is essential in many applications such as automatic quality inspection in composite manufacturing. Extraction of filler morphology greatly depends on accurate segmentation of fillers (fibers and particles), which is a challenging task due to the overlap of fibers and particles and their obscure presence in SEM images. Convolution Neural Networks (CNNs) have been shown to be very effective at object recognition in digital images. This paper proposes an automatic filler detection system in SEM images, utilizing a Mask Region-based CNN architecture. The proposed system …

---

Handwriting Correction System Using Wearable Sleeve With Optimal Tactor Configuration, Dhanya Nair, Grant Stankaitis, Sean Duback, Robert Geoffrion, Justin B. Jackson

Engineering Faculty Articles and Research

---

Handwriting remains an elusive skill with practice worksheets being the common method of learning. Since these worksheets provide only visual feedback and no quantitative feedback, it can often be a challenge to improve. For children with learning disabilities, learning handwriting skills is one of the most difficult tasks. We propose a handwriting training system that uses off-the-shelf webcam, a pen tracking software and a haptic sleeve which provides active feedback to the user based on their deviation from the original pattern. The sleeve has 4 individual motors that vibrate at different intensities based on the direction (right, left, up or …

---

Scalability Of The Size Of Patterns Drawn Using Tactile Hand Guidance, Dhanya Nair

Engineering Faculty Articles and Research

---

Haptic feedback for handwriting training has been extensively studied, but with primary focus on kinematic feedback. We provide vibrotactile feedback through a wrist worn sleeve to guide the user to recreate unknown patterns and study the impact of vibrational duration (1, 2, 3 seconds) on pattern scaling. User traces a line at 90° angles, while attempting to maintain a constant speed, in the direction of the motor activated till a different motor activation is perceived. Shape and size are two features of good letter formation. Study performed on three subjects showed the ability to utilize four vibrotactile motors to guide …

---

The Adoption Of Collaborative Robots Toward Ubiquitous Diffusion: A Research Agenda, Yuhua (Jake) Liang, Seungcheol Austin Lee

Communication Faculty Articles and Research

---

This paper proposes a framework to study the adoption of collaborative robots (co-robots or cobots) as an innovation and their diffusion into the larger population. Collaborative robots are only starting to appear in our society, yet challenges such as fear and distrust may impede their further adoption. This paper discusses the foundational work necessary to understand collaborative robot adoption and the core elements to achieve ubiquitous diffusion, with a focus on human users and the communication processes.

---

Calcium Phosphate As A Key Material For Socially Responsible Tissue Engineering, Vuk Uskoković, Victoria M. Wu

Pharmacy Faculty Articles and Research

---

Socially responsible technologies are designed while taking into consideration the socioeconomic, geopolitical and environmental limitations of regions in which they will be implemented. In the medical context, this involves making therapeutic platforms more accessible and affordable to patients in poor regions of the world wherein a given disease is endemic. This often necessitates going against the reigning trend of making therapeutic nanoparticles ever more structurally complex and expensive. However, studies aimed at simplifying materials and formulations while maintaining the functionality and therapeutic response of their more complex counterparts seldom provoke a significant interest in the scientific community. In this review …

---

Evaluating A Collaborative Ipad Game's Impact On Social Relationships For Children With Autism Spectrum Disorder, Louanne E. Boyd, Kathryn E. Ringland, Oliver L. Haimson, Helen Fernandez, Maria Bistarkey, Gillian R. Hayes

Engineering Faculty Articles and Research

---

This article describes how collaborative assistive technologies, housed on off-the-shelf, low-cost platforms such as the iPad, can be used to facilitate social relationships in children with autism spectrum disorder (ASD). Through an empirical study of the use of a collaborative iPad game, Zody, we explore how assistive technologies can be used to support social relationships, even without intervention from adults. We discuss how specific design choices can encourage three levels of social relationship: membership, partnership, and friendship. This work contributes to research on both assistive technologies and collaborative gaming through a framework that describes how specific in-game elements can foster …

---