1393 research outputs found
Sort by
Factors and Design Features Influencing the Continued Use of Wearable Devices
No full textThe initial healthy uptake of wearable devices is not necessarily accompanied by sustained or continued use. Accordingly, this study investigates the factors influencing the continuous use of wearable devices with a particular emphasis on design features. We complemented the expectation-confirmation model (ECM) theoretical foundation with various design features such as trust, readability, dialogue support, personalization, device battery, appeal, and social support. The study employs a simultaneous mixed method research design denoted as QUANT + qual. The quantitative analysis leverages partial least squares structural equation modeling (PLS-SEM) using survey data collected from wearable device users. The qualitative analysis complements the quantitative focus of the research by providing insights into the results obtained from the quantitative analysis. We found that subjects tend to use wearables daily (60%) or several times a week (33%), and 91% plan to use them even more. Subjects indicated multiple usages for wearables. Most subjects were using wearables for healthcare and wellness (61%) or sports and fitness (54%) and had smartwatches wearable type (74%). The model explains 24.1% (p \u3c 0.01) of the variance of continued intention to use. As a theoretical contribution, the findings support using the ECM as a theoretical foundation for explaining the continued use of wearables. Partial least squares (PLS) and qualitative data analysis highlight the relative importance that wearable users place on perceived usefulness. Most notable are tracking functions and design features such as device battery, integration with other apps/devices, dialogue support, and appeal
Exploring the Interoperability for Information Exchange Between Acute and Post-Acute Care Settings
Get PDFThe seamless transfer and assimilation of healthcare data is foundational to delivering holistic, timely, and effective patient care across the healthcare spectrum. In an era where medical histories are as intricate as they are critical, information exchange ensures clinicians and caregivers have a comprehensive view of patient journeys, irrespective of where care was previously rendered. However, disparities in Electronic Health Record (EHR) system adoption, especially in long-term and post-acute care (LTPAC) settings, have consistently obstructed unrestricted interoperability.
While much of the historical discourse around interoperability has been limited to hospital-to-hospital data exchanges, the complexities and barriers associated with consistent data transfer in LTPAC settings remain inadequately explored. This dissertation seeks to bridge this gap, delineating the factors that impede and facilitate health information exchange in LTPAC environments.
Grounded theory served as the overarching methodology for our qualitative case study research, guiding our exploration of interoperability within the complex healthcare environment encompassing acute and post-acute care settings. This approach facilitated a systematic examination of data, steering our data acquisition activities throughout the case study. Drawing on the insights from 35 stakeholder interviews, encompassing a spectrum from technical specialists to decision-makers, we navigated four predominant facets: technical, operational, organizational, and compliance. Expanding on these facets, key findings are captured by nine distinct categories along these four facets:
1. Technical Aspects: At the heart, “Data Management and Integrity” stood out as pivotal, underscoring the indispensable need for integrated, reliable data structures. This technical backbone was further strengthened by insights from “Infrastructure and Integration” and the call for globalized “Standardization and Best Practices.”
2. Operational Dynamics: Operational efficiency hinged on streamlined “Operational Processes and Workflows” that encapsulated patient transitions. The equilibrium between visionary tech adoptions and their financial implications was captured in “Resource and Financial Management.” The necessity for continuous upskilling and proficiency was captured in “Learning and Proficiency Enhancement.”
3. Organizational Framework: A transformative shift in “Organizational Management and Strategy” was evident, moving towards an integrative, patient-centric paradigm. The crucial interplay between healthcare entities and external partners was crystallized in “Stakeholder and Vendor Dynamics.”
4. Compliance Challenges: With a dynamic healthcare landscape, the evolving nature of “Compliance and Governance” was spotlighted, emphasizing the need for setups to be proactive, adaptive, and future-ready in their compliance efforts.
In conclusion, the findings distill a multifaceted exploration into actionable insights for health information exchange in LTPAC scenarios. As the healthcare landscape shifts towards more integrated, data-driven approaches, the findings capture the current challenges and potential pathways for a cohesive, interoperable future. At its core, it advocates for a harmonized approach, weaving together technology, operations, strategy, and compliance, all converging towards enhanced patient care. The insights provided are pivotal for policy-making, healthcare operations, and guiding further research in healthcare interoperability
MACHINE LEARNING APPLICATIONS IN MALWARE CLASSIFICATION: A METAANALYSIS LITERATURE REVIEW
Get PDFWith a text mining and bibliometrics approach, this study reviews the literature on the evolution of malware classification using machine learning. This work takes literature from 2008 to 2022 on the subject of using machine learning for malware classification to understand the impact of this technology on malware classification. Throughout this study, we seek to answer three main research questions: RQ1: Is the application of machine learning for malware classification growing? RQ2: What is the most common machine-learning application for malware classification? RQ3: What are the outcomes of the most common machine learning applications? The analysis of 2186 articles resulting from a data collection process from peerreviewed databases shows the trajectory of the application of this technology on malware classification as well as trends in both the machine learning and malware classification fields of study. This study performs quantitative and qualitative analysis using statistical and N-gram analysis techniques and a formal literature review to answer the proposed research questions. The research reveals methods such as support vector machines and random forests to be standard machine learning methods for malware classification in efforts to detect maliciousness or categorize malware by family. Machine learning is a highly researched technology with many applications, from malware classification and beyond
Bayesian Social Subgraph Generative Models: Social Network Twins using Belief Networks and Ego Behavior Models
Get PDFTowards Long-Term Impact of Deep Learning Systems in Medical Imaging
Get PDFDeep learning has driven AI\u27s rapid growth in recent years, especially in the medical domain, where deep CNNs are the state-of-the-art for image recognition and classification. However, training them from scratch is challenging due to the lack of data and high computational requirements. Transfer Learning (TL) is an effective approach for limited training data, and TL integrated with GANs has improved image analysis models. It was unclear how much impact big data-driven Deep Learning systems had on adoption and acceptance in real-world healthcare. Specifically, the effectiveness of recently developed DL systems as scalable and generalizable AI applications remained an open question.
Accordingly, the main objective of this research work is to assess the effectiveness of TL-GAN systems on broad adoption. This study explored the combination of transfer learning and generative adversarial networks (GANs) in medical imaging by conducting a systematic literature review. In addition, the scalability dimension of these systems was evaluated by examining the dynamics of GAN-augmented datasets and the accuracy achieved on target datasets. Finally, the generalization capabilities of the combination of transfer learning and GANs were evaluated.
The study added to the current literature on TL and GANs in medical imaging, specifically in image synthesis and computational efficiency. Two strategies for combining TL and GANs were identified and summarized. The study also examined the impact of artificially augmented training datasets on the Fine-Tuning layer, finding that larger datasets resulted in more parameters being trained for optimal performance. Additionally, the study investigated the effect of synthetic dataset size on classification accuracy in TL settings, concluding that target validation accuracy stabilized as the dataset size increased. Furthermore, the study explored the generalizability of the models trained on GAN-augmented datasets and found that pre-trained models exhibited good performance when applied to various target datasets, indicating a high degree of generalizability in the models
China’s Rise in the Global AI Sector
Get PDFThe Artificial Intelligence (AI) sector within China flourished rapidly, beginning primarily in the early 2000s, due to early investment by the Chinese Communist Government (CCP). Currently, China’s AI expertise continues to flourish, causing concern among other countries who hold the superior status of technological superpowers. Chinese advancement within AI appeared abrupt and unexpected to other countries. However, analysis of Chinese legislative policies – including its ‘New Generation Artificial Intelligence Development Plan\u27 (AIDP) and ‘Made in China 2025’ - indicate a clear and steady progression towards technological hegemony within the AI field. China’s unanticipated rise in AI calls for a scholarly analysis of Chinese technological history, as well as an examination of current factors influencing this rapid advancement. This paper aims to analyze the development of AI in China, showing that China’s public and private sectors are both actively pursuing rapid AI growth. Specifically, this paper focuses on factors aiding this growth, ongoing challenges, and China’s future potential as a global leader in AI
Alumni Perceptions of Cybersecurity Employment Preparation Using the NICE Framework
Get PDFThe cybersecurity workforce suffers from an ongoing talent shortage and a lack of information correlating cybersecurity education programs to alumni employment outcomes. This cross-sectional study evaluated the post-graduation employment outcomes of alumni who attended two-year colleges designated by the National Security Agency (NSA) as Centers of Academic Excellence in Cyber Defense (CAE-CD). Stakeholders of this project were identified as government agencies, the NSA, employers, faculty, students, and organizations that rely on cybersecurity talent to keep their systems secure from cyberattacks. This study used the explanatory sequential mixed methods approach to compare perceptions of the intended Program of Study work roles to alumni employment outcomes using the NICE Framework work roles.
This multi-phased, nested sample study included CAE-CD designated Points of Contact (POCs) at two-year colleges and their alumni. The first phase included a call for participation requesting POCs to provide academic program information via online survey and to contact their cybersecurity program alumni with a link to an online survey. The second phase of the study included an online survey requesting that the alumni provide data about their work experience, academic program information, industry-recognized certification achieved, and any co/extra-curricular participation.
Overall, the demographics of the alumni sample were more diverse than those of the U.S. cybersecurity workforce and the alumni noted that their two-year academic programs were important to the preparation for their current job. Of the alumni who reported they were currently employed, approximately 80% held technology-related positions. Recommendations are made for the use of the resulting knowledge by cybersecurity stakeholders to better understand the employment outcomes of two-year college alumni from CAE-CD cybersecurity programs
A Performance-Explainability-Fairness Framework For Benchmarking ML Models
Get PDFMachine learning (ML) models have achieved remarkable success in various applications; however, ensuring their robustness and fairness remains a critical challenge. In this research, we present a comprehensive framework designed to evaluate and benchmark ML models through the lenses of performance, explainability, and fairness. This framework addresses the increasing need for a holistic assessment of ML models, considering not only their predictive power but also their interpretability and equitable deployment.
The proposed framework leverages a multi-faceted evaluation approach, integrating performance metrics with explainability and fairness assessments. Performance evaluation incorporates standard measures such as accuracy, precision, and recall, but extends to overall balanced error rate, overall area under the receiver operating characteristic (ROC) curve (AUC), to capture model behavior across different performance aspects. Explainability assessment employs state-of-the-art techniques to quantify the interpretability of model decisions, ensuring that model behavior can be understood and trusted by stakeholders. The fairness evaluation
examines model predictions in terms of demographic parity, equalized odds, thereby addressing concerns of bias and discrimination in the deployment of ML systems.
To demonstrate the practical utility of the framework, we apply it to a diverse set of ML algorithms across various functional domains, including finance, criminology, education, and healthcare prediction. The results showcase the importance of a balanced evaluation approach, revealing trade-offs between performance, explainability, and fairness that can inform model selection and deployment decisions. Furthermore, we provide insights into the analysis of tradeoffs in selecting the appropriate model for use cases where performance, interpretability and fairness are important.
In summary, the Performance-Explainability-Fairness Framework offers a unified methodology for evaluating and benchmarking ML models, enabling practitioners and researchers to make informed decisions about model suitability and ensuring responsible and equitable AI deployment. We believe that this framework represents a crucial step towards building trustworthy and accountable ML systems in an era where AI plays an increasingly prominent role in decision-making processes
Functional analysis of differentially expressed genes in alfalfa (Medicago sativa) inoculated with Aphanomyces euteiches race 1 and race 2
Get PDFAphanomyces root rot caused by Aphanomyces eureiches ,s one of the most destructive diseases of alfalfa. Resistant cultivars have been developed that exhibit race-specific resistance. Transcript profiling was done to gain a better understanding of the compatible and incompatible interactions. Three-day-old Seed lings of the check cultivars WAPH-1 (resistant to race 1 strains) and WAPH-5 ( resistant to race 1 and race 2 strains) were inoculated with MF-1 (race 1) and IVIE R-4 (race 2) and RNA extracted 24 h post-inoculation, with three biological replicates. RNA.seq using an lllumina HiSeq 2500 to obtain 125 bp paired-end reacts was carried out with \u3e 10.5 million reads/sample. Differentially expressed genes (DEGs) were identified after sequence trimming and quality control. The incompatible interaction in WAPH-1 and WAPH-5 to MF-1 contained the most Unique up-regulated DEGs, 637 and 217, respectively. The incompatible response of WAPH-5 to MF-1 and MER-4 appears to be similar with 258 common up-regulated DEGs and only 59 unique DEGs in response to MER-4. Functional an notation of the DEGs was performed using the Blast2GO tool. The unique DEGs of the incompatible interactions were primarily placed into four categories in the Gene Ontology term Biological Processes: \u27defense response,\u27 \u27response to stress,\u27 \u27organic substance catabolic process,\u27 and \u27protein phosphorylation\u27. These results increase understanding of the A. euteiches and alfalfa molecular interaction for development of cultivars with increased resistant to Aphanomyces root rot.https://scholar.dsu.edu/erposters/1005/thumbnail.jp