Tyler Ward

Functional connectivity analysis is widely used for computer-aided brain disorder diagnosis, but conventional atlas- based approaches can introduce structural bias and overlook subject-specific brain function. Addressing this, we propose Advanced Brain Function Representation with Kolmogorov-Arnold Networks (ABFR-KAN), a transformer- based framework that combines anatomically adaptive brain function representation components with the power of Kolmogorov–Arnold Networks (KANs) to mitigate structural bias, improve anatomical conformity, and improve the reliability of FC estimation. We evaluate the proposed method on resting-stage functional magnetic resonance imaging (rs-fMRI) data from the Autism Brain Imaging Data Exchange (ABIDE) I and II datasets (281 subjects and 211 subjects, respectively). Extensive experiments, including 5-fold cross validation, cross-site evaluation, and ablation studies across varying model backbones and KAN configurations, demonstrate that ABFR-KAN consistently outperforms state-of-the-art baselines for autism spectrum disorder (ASD) classification. These results highlight the potential of combining advanced brain function representation strategies with KAN-based architectures for robust neuroimaging analysis. Our code is available at https://github.com/tbwa233/ABFR-KAN

Generative artificial intelligence (AI), especially large language models (LLMs) that can write and debug code, is changing how students approach programming work in engineering education. Unlike more open-ended conceptual or modeling tasks, programming fits closely with what these systems do well: generating syntax, fixing errors, building procedural logic, and completing code structures. Hence, programming coursework may be one of the areas in which AI changes performance patterns in a measurable way. This study examines whether that shift appears in actual student outcomes. Using a retrospective pre/post design, it compares results from a pre-AI period (2021–2022) with results from a post-AI period (2023–2025), when generative AI tools became widely available to students. The focal assessment is a comprehensive programming project graded with the same rubric across multiple sections and terms. Performance is evaluated through descriptive statistics, distributional comparisons, and mastery thresholds (≥80%). The post-AI period shows a rise in overall scores, along with strong clustering near the top of the scale. Lower- and middle-range scores become much less common, most students fall in the highest score band, and overall variability declines. These results suggest that generative AI acts as a procedural equalizer in programming contexts, referring to the role of generative AI in reducing performance differences by assisting with rule-based, syntax-driven, and execution-oriented aspects of tasks, thereby raising baseline outcomes while compressing variation among students. It appears to raise lower-end performance and make outcomes more consistent, but it also narrows the spread among stronger students and creates a ceiling effect. That pattern raises questions about assessment validity, skill differentiation, and what “mastery” means when AI can handle much of the procedural work. Using multi-term data from authentic online courses, this study adds empirical evidence to the growing literature on AI in engineering education and identifies programming coursework as a setting where generative AI may have already changed performance dynamics in a structural way.

The presence of silica in iron ore concentrate can have significant negative impacts on the efficiency and quality of steel production. As such, providing engineers with early and reliable information about the purity of iron ore concentrate is crucial for smooth mining operations. This paper reports on the development of a long short-term memory (LSTM) network and an ensemble data interpolation technique to enhance quality prediction in the froth flotation process of an iron ore mine. Our results demonstrate the ability of our model to accurately predict the silica content of iron ore concentrate on a minute-by-minute basis, as well as the ability to forecast hours in advance.

Segmentation is one of the most important tasks in the medical imaging pipeline as it influences a number of image-based decisions. To be effective, fully supervised segmentation approaches require large amounts of manually annotated training data. However, the pixel-level annotation process is expensive, time-consuming, and error-prone, hindering progress and making it challenging to perform effective segmentations. Therefore, models must learn efficiently from limited labeled data. Self-supervised learning (SSL), particularly contrastive learning via pre-training on unlabeled data and fine-tuning on limited annotations, can facilitate such limited labeled image segmentation. To this end, we propose a novel self-supervised contrastive learning framework for medical image segmentation, leveraging inherent relationships of different images, dubbed PolyCL. Without requiring any pixel-level annotations or unreasonable data augmentations, our PolyCL learns and transfers context-aware discriminant features useful for segmentation from an innovative surrogate, in a task-related manner. Additionally, we integrate the Segment Anything Model (SAM) into our framework in two novel ways: as a post-processing refinement module that improves the accuracy of predicted masks using bounding box prompts derived from coarse outputs, and as a propagation mechanism via SAM 2 that generates volumetric segmentations from a single annotated 2D slice. Experimental evaluations on three public computed tomography (CT) datasets demonstrate that PolyCL outperforms fully-supervised and self-supervised baselines in both low-data and cross-domain scenarios. Our code is available at https://github.com/tbwa233/PolyCL

Functional connectivity (FC) analysis, a valuable tool for computer-aided brain disorder diagnosis, traditionally relies on atlas-based parcellation. However, issues relating to selection bias and a lack of regard for subject specificity can arise as a result of such parcellations. Addressing this, we propose ABFR-KAN, a transformer-based classification network that incorporates novel advanced brain function representation components with the power of Kolmogorov-Arnold Networks (KANs) to mitigate structural bias, improve anatomical conformity, and enhance the reliability of FC estimation. Extensive experiments on the ABIDE I dataset, including cross-site evaluation and ablation studies across varying model backbones and KAN configurations, demonstrate that ABFR-KAN consistently outperforms state-of-the-art baselines for autism spectrum distorder (ASD) classification. Our code is available at https://github.com/tbwa233/ABFR-KAN.

Virtual reality (VR) has emerged as a promising tool for transforming science, technology, engineering, and mathematics (STEM) education, yet its adoption in K–12 classrooms remains uneven and often limited to short-term pilots. While prior studies highlight VR’s potential to increase engagement and support conceptual understanding, questions persist about scalability, sustainability, and equity in implementation. This paper addresses these gaps by synthesizing recent scholarship and proposing a structured framework of best practices for integrating VR into K–12 STEM education. Drawing on academic literature, U.S. policy reports, and case studies, we identify persistent challenges that include high costs, lack of teacher preparation, infrastructure disparities, and overlooked accessibility concerns. We use these findings to inform a phased implementation roadmap. Our framework emphasizes assessment and planning, technical integration, teacher preparation, student implementation, and iterative evaluation, providing actionable strategies for schools and districts. Results of this synthesis indicate that successful VR adoption requires coordinated attention to pedagogy, funding, professional development, and equity. We conclude that moving VR from isolated novelty projects to sustainable and equitable tools in STEM classrooms depends on aligning technology with curricular goals, investing in teacher pipelines, and embedding VR within long-term evaluation and improvement cycles.

In modern advanced manufacturing systems, the use of smart sensors and other Internet of Things (IoT) technology to provide real-time feedback to operators about the condition of various machinery or other equipment is prevalent. A notable issue in such IoT-based advanced manufacturing systems is the problem of connectivity, where a dropped Internet connection can lead to the loss of important condition data from a machine. Such gaps in the data, which we call irregular truncated signals, can lead to incorrect assumptions about the status of a machine and other flawed decision-making processes. This paper presents an adaptive data imputation framework based on machine learning (ML) algorithms to assess whether the missing data in a signal is missing completely at random (MCAR), missing at random (MAR), or missing not at random (MNAR) and automatically select an appropriate ML-based data imputation model to deal with the missing data. Our results demonstrate the potential for applying ML algorithms to the challenge of irregularly truncated signals, as well as the capability of our adaptive framework to intelligently solve this issue.

Since 2014, the California Department of Motor Vehicles (CDMV) has compiled information from manufacturers of autonomous vehicles (AVs) regarding factors that lead to the disengagement from autonomous driving mode in these vehicles. These disengagement reports (DRs) contain information detailing whether the AV disengaged from autonomous mode due to technology failure, manual override, or other factors during driving tests. This paper presents a machine learning (ML) based analysis of the information from the 2023 DRs. We use a natural language processing (NLP) approach to extract important information from the description of a disengagement, and use the k-Means clustering algorithm to group report entries together. The cluster frequency is then analyzed, and each cluster is manually categorized based on the factors leading to disengagement. We discuss findings from previous years' DRs, and provide our own analysis to identify areas of improvement for AVs.