Merrimack College

Employing γ-valerolactone (GVL) as a cosolvent in the ultrasonic-assisted synthesis of the metal–organic framework (MOF) [Cu3(BTC)2·xH2O]n where [BTC]3– = 1,3,5-benzenetricarboxylate = 1,3,5-[C6H3(CO2)3]3– (HKUST-1) enables a “greener” approach than the current published experiment which uses hazardous N,N-dimethylformamide (DMF). Equally important, the revision of the oven-drying step to 200 °C for at least 15 h instead of 1 h at 130 °C removes sequestered solvent from the MOF pores and markedly improves the adsorption characteristics of the final material. A further small gain in adsorption capacity is realized by the inclusion of a second, short ultrasonic treatment during workup as a so-called “swelling step” to maximize the MOF’s pore size and thus its effective surface area. The overall student experience is enhanced by incorporating a nontoxic cosolvent derived from biomass and by augmenting the established test of HKUST-1 activity, namely removal of methylene blue from aqueous solution, with an operationally simple determination of water vapor adsorption capacity. A new perspective is suggested to help students understand the complex extended HKUST-1 structure by having them first appreciate the molecular structure of copper(II) acetate hydrate, which is best formulated as Cu2(O2CCH3)4·2H2O. The revised experiment is flexible and accommodates a variety of laboratory schedules, student skill levels, and pedagogic objectives.

Holographic visualization promises faster, safer surgical decisions, yet most solutions rely on stable cloud links that fail in contested or disaster settings. Objective: To propose a Disposable Holographic Surgery Site (DHSS) that blends immersive guidance with on-device, parallel edge analytics to sustain care under degraded connectivity. Methods: Requirements were elicited from domain literature and stakeholder interviews, then organized into a five-phase framework spanning system architecture, workflow modeling, scenario validation, and ethical/regulatory considerations. Results: The framework specifies lightweight head-worn or boom-mounted displays; sub- <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$200-\text{ms}$</tex> local processing; adaptive synchronization that opportunistically backhauls data; ruggedized power; cryptographic safeguards; and end-of-use disposability. Scenario analyses indicate that local computation maintains near-real-time imaging, triage support, and checklists during outages, with automatic reconciliation when bandwidth returns. Conclusions: DHSS operationalizes resilient holographic surgical support with reduced latency and logistics, offering a practical blueprint for prototyping and field evaluation in military, remote, and disaster environments.

The widespread applications of machine learning algorithms in high-stakes fields have demanded the development of effective explanation methods to help decision-makers interpret the black-box models. Post-hoc local feature attribution methods are among the most prevalent explainability approaches. These methods are often evaluated through human-subject studies, whose heterogeneous designs make results difficult to compare and sometimes unreliable. Although several quantitative evaluation metrics have been proposed, many suffer from different limitations, such as computational complexity and generalizability to complicated real-world datasets. Additionally, to our knowledge, there is no current work that establishes a comprehensive and reliable benchmark to evaluate all aspects of the methods in high-stakes settings. In this work, we introduce and assess a benchmark including a suite of quantitative metrics that provide a thorough evaluation of post-hoc feature attribution methods on 2 medical imaging datasets. We formalize 4 evaluation lenses, propose a new metric, and also apply a novel technique to prepare AI explanation artifacts for processing by explanation evaluation metrics. Our results show cross-dataset consistency, meaningful-random separation, sensitivity to model strength, and the value of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{4}$</tex> lenses. We provide reliable statistics that can guide the choice of explanation algorithms in medical imaging and beyond and help prioritize methods before investing in costly human-subject experiments.

BackgroundRepeated cognitive testing can boost performance due to practice effects (PEs). Follow‐up scores are rarely adjusted for PEs, but such correction can be highly important as it has been shown to result in earlier detection of MCI and increased validity based on concordance with Alzheimer's biomarkers. However, it remains unclear to what extent PEs persist across multiple follow‐ups and long durations, which are further complicated by normative age‐related decline. We examined PEs across 17 years from midlife to old age in a nonclinical sample.MethodMen (N = 1,608) in the longitudinal Vietnam Era Twin Study of Aging (VETSA) completed neuropsychological batteries over 4 waves: wave 1(N = 1,290, mean age=56); wave 2, mean ages=62); wave 3 (mean age=68); wave 4 (mean age=73). Waves 2 and 3 also included age‐matched attrition replacements. By comparing returnees’ performance to replacements being assessed for the first time, we estimated PEs for 30 tests at each wave using generalized estimating equations, accounting for normative age effects and differential patterns of missingness. We calculated unadjusted and PE‐adjusted cognitive scores (episodic memory, executive function, fluency, processing speed, visual memory, and visuospatial). At each wave we compared MCI prevalence based on unadjusted versus PE‐adjusted scores.ResultAmong returnees completing all 4 assessments, we found significant PEs for 11 tests at wave 2, 8 tests at wave 3, and 5 tests at wave 4. PEs were most apparent among episodic and visual memory tests. PE‐adjusted cognitive factor scores were significantly lower than unadjusted factor scores at all follow‐ups for all domains except fluency. MCI prevalence increased up to 20% after PE adjustment (from 14% to 18% at wave 4), indicating earlier detection.ConclusionPEs persist across multiple assessments and decades, even with long testing intervals. Importantly, even very small PEs can shift scores below the impairment threshold, resulting in earlier detection and diagnosis of MCI. Additionally, we previously showed that PE‐adjusted MCI diagnosis increases accuracy based on biomarker concordance and would dramatically reduce costs and length of clinical trials by reducing necessary sample size and increasing power. These results underscore the importance of accounting for PEs in longitudinal studies.

This article provides a methodological overview of research using the Carnegie Elective Classification for Community Engagement dataset. Established in 2006 to recognize institutionalized campus-community partnerships, 368 institutions currently hold the classification. In 2023, the Carnegie Elective Classifications Research Lab (CECRL) was formed as an international collaboration with eight co‑labs, structuring data use, expanding access, and fostering a networked community of research practice. In this article, we describe the dataset, showcase current CECRL research trajectories, and discuss emerging and future research possibilities. This article offers scholars a roadmap for leveraging the Carnegie Electives data to advance understanding and evidence‑based strategies for community engagement in higher education.

This innovative practice paper falls under the Innovative Teaching and Learning track and focuses on improving graduate student retention in an online software engineering master's program (MSCS-SE) designed for career changers through the use of a novel onboarding process. The MSCS-SE, launched in 2021, targets students without a computer science or mathematics undergraduate degree Traditionally, many such students have struggled with the program's fast-paced introductory programming course. We developed an onboarding scheme to support student success featuring a Master Skills Profiler (MSP) placement exam and a foundational programming course. The MSP helps students assess their overall initial skill levels in programming and mathematical foundations. Based on the results, students receive tailored course recommendations. Those identified as needing additional preparation are encouraged to take a Basic Programming and Discrete Mathematics course, which fills knowledge gaps but does not count toward degree credits. To further support students, a tuition waiver was introduced for those placed into this preparatory course. This approach encourages students to make an informed decision rather than self-assessing into an overly challenging course, ultimately improving retention and program success. Retention data from multiple cohorts indicate that the onboarding scheme improved student persistence. Initial findings show that students who followed the placement recommendations were more likely to successfully complete the first programming course and, ultimately, the program. The tuition waiver further increased enrollment in the preparatory course, ensuring students had the necessary foundation. Future work includes a deeper longitudinal analysis of student outcomes and expanding the approach to other graduate programs.