These are recent publications by Quinnipiac University authors, either about AI or using AI in research.
References
Areias, A. C., Janela, D., Moulder, R. G., Molinos, M., Bento, V., Moreira, C., . . . Costa, F. (2024). Applying AI to safely and effectively scale care to address chronic MSK conditions. Journal of Clinical Medicine, 13(15) doi:10.3390/jcm13154366
Background/Objectives: The rising prevalence of musculoskeletal (MSK) conditions has not been balanced by a sufficient increase in healthcare providers. Scalability challenges are being addressed through the use of artificial intelligence (AI) in some healthcare sectors, with this showing potential to also improve MSK care. Digital care programs (DCP) generate automatically collected data, thus making them ideal candidates for AI implementation into workflows, with the potential to unlock care scalability. In this study, we aimed to assess the impact of scaling care through AI in patient outcomes, engagement, satisfaction, and adverse events. Methods: Post hoc analysis of a prospective, pre-post cohort study assessing the impact on outcomes after a 2.3-fold increase in PT-to-patient ratio, supported by the implementation of a machine learning-based tool to assist physical therapists (PTs) in patient care management. The intervention group (IG) consisted of a DCP supported by an AI tool, while the comparison group (CG) consisted of the DCP alone. The primary outcome concerned the pain response rate (reaching a minimal clinically important change of 30%). Other outcomes included mental health, program engagement, satisfaction, and the adverse event rate. Results: Similar improvements in pain response were observed, regardless of the group (response rate: 64% vs. 63%; p = 0.399). Equivalent recoveries were also reported in mental health outcomes, specifically in anxiety (p = 0.928) and depression (p = 0.187). Higher completion rates were observed in the IG (79.9% (N = 19,252) vs. CG 70.1% (N = 8489); p < 0.001). Patient engagement remained consistent in both groups, as well as high satisfaction (IG: 8.76/10, SD 1.75 vs. CG: 8.60/10, SD 1.76; p = 0.021). Intervention-related adverse events were rare and even across groups (IG: 0.58% and CG 0.69%; p = 0.231). Conclusions: The study underscores the potential of scaling MSK care that is supported by AI without compromising patient outcomes, despite the increase in PT-to-patient ratios. © 2024 by the authors.
Baker, B. J., Godde, K., & Ullinger, J. (2025). Exploring kinship within a late meroitic to medieval cemetery in sudan using k-modes clustering. American Journal of Biological Anthropology, 186(3) doi:10.1002/ajpa.70016
Objectives: Intracemetery patterns at the Qinifab School site, a late Meroitic to Christian period cemetery (c. 250–1400 CE) between the fourth and fifth cataracts of the Nile River in Sudan, are modeled to explore the role of kinship in cemetery organization during significant sociopolitical and religious shifts. Materials and Methods: Sixty-eight cranial and 36 dental nonmetric traits were examined among 67 adults. A machine-learning clustering method (k-modes clustering algorithm), new to biological anthropology, was used to detect patterning among biological, demographic, and temporal data and validated with inter-individual Mahalanobis distances and mixed data principal components analysis using only biological data. Results: When three validated clusters were examined, a pattern emerged that aligned with the archaeological context of the cemetery when time period is considered. One cluster concentrated at the oldest end of the site appeared to be a founding group, with the other two groups equally comprising later periods. Some mortuary patterning by sex was visually identified; a few late to Post-Meroitic males grouped together in one cluster. Discussion: Individuals from Clusters 1 and 3 were buried near each other infrequently, which suggests two different kin groups may have intermarried with the third, or one group held a status that allowed identification with the other clusters. Kinship was not a determinant for males with archery items or individuals with incisor avulsion, as they were found in all three clusters. The Qinifab School cemetery reflects temporal organization, a multilocal residence pattern, and a lack of sex stratification for the medieval period. © 2025 Wiley Periodicals LLC.
Brady, A. G. (2024). Uncovering patterns in process data to analyze interactions and learning outcomes within a computer-based learning environment. Research in Science Education, 54(1), 83–100. doi:10.1007/s11165-023-10109-6
Computer-based learning environments (CBLEs) are powerful tools to support student learning. Increasingly of interest is the data that is recorded as learners interact with a CBLE. This process data yields opportunities for researchers to examine learners’ engagement with a CBLE and explore whether specific interactions are associated with learner variables, with direct implications for improving learning outcomes and CBLE design. As CBLEs increase in number and complexity, researchers continue to seek more effective strategies to analyze process data. While a variety of strategies are in use, from visualizations to predictive modeling, none yet offer the capabilities to both uncover hidden, meaningful interactions and descriptively analyze those interactions rapidly across the complete data set. This paper details a method that addresses current challenges, and then applies the method to existing data from a prior study which investigated the effects of adding a visual scaffold to a chemistry-based CBLE. Using a biochemical coding approach through a cultural-historical activity theory (CHAT) framework, the method successfully identified 257 unique, meaningful patterns of interaction that were strategically grouped into nine categories of mediated actions. Though no differences in mediated actions were observed between learners in the experimental (visual scaffolds) and control conditions, three mediated actions were significantly and positively associated with higher learning outcomes in the visual scaffold condition. The results not only provide insight into why the addition of visual scaffolds led to higher learning outcomes among participants but have broader implications for filling a gap in the field of process data analytics for CBLEs in science education. © 2023, The Author(s), under exclusive licence to Springer Nature B.V.
Chataut, R., Gyawali, P. K., & Usman, Y. (2024). Can AI keep you safe? A study of large language models for phishing detection. Paper presented at the 548–554. Retrieved from https://www.scopus.com/inward/record.uri?eid=2-s2.0-85186746797&doi=10.1109%2fCCWC60891.2024.10427626&partnerID=40&md5=ee2f6a3cb36d46e2363cf0efaa233e11
Phishing attacks continue to be a pervasive challenge in cybersecurity, with threat actors constantly developing new strategies to penetrate email inboxes and compromise sensitive data. In this study, we investigate the effectiveness of Large Language Models (LLMs) in the crucial task of phishing email detection. With the growing sophistication of these attacks, we assess the performance of three distinct LLMs: GPT-3.5, GPT-4, and a customized ChatGPT, against a carefully curated dataset containing both phishing and legitimate emails. Our research reveals the proficiency of LLMs in identifying phishing emails, with each model showing varying levels of success. The paper outlines the strengths and limitations of GPT-3.5, GPT-4, and the custom ChatGPT, illuminating their respective suitability for practical applications in email security. These results underscore the potential of LLMs in effectively identifying phishing emails and their significant implications for enhancing cybersecurity measures and safeguarding users from the risks of online fraud. © 2024 IEEE.
Chataut, R., Nankya, M., & Akl, R. (2024). 6G networks and the AI Revolution—Exploring technologies, applications, and emerging challenges. Sensors, 24(6) doi:10.3390/s24061888
In the rapidly evolving landscape of wireless communication, each successive generation of networks has achieved significant technological leaps, profoundly transforming the way we connect and interact. From the analog simplicity of 1G to the digital prowess of 5G, the journey of mobile networks has been marked by constant innovation and escalating demands for faster, more reliable, and more efficient communication systems. As 5G becomes a global reality, laying the foundation for an interconnected world, the quest for even more advanced networks leads us to the threshold of the sixth-generation (6G) era. This paper presents a hierarchical exploration of 6G networks, poised at the forefront of the next revolution in wireless technology. This study delves into the technological advancements that underpin the need for 6G, examining its key features, benefits, and key enabling technologies. We dissect the intricacies of cutting-edge innovations like terahertz communication, ultra-massive MIMO, artificial intelligence (AI), machine learning (ML), quantum communication, and reconfigurable intelligent surfaces. Through a meticulous analysis, we evaluate the strengths, weaknesses, and state-of-the-art research in these areas, offering a wider view of the current progress and potential applications of 6G networks. Central to our discussion is the transformative role of AI in shaping the future of 6G networks. By integrating AI and ML, 6G networks are expected to offer unprecedented capabilities, from enhanced mobile broadband to groundbreaking applications in areas like smart cities and autonomous systems. This integration heralds a new era of intelligent, self-optimizing networks that promise to redefine the parameters of connectivity and digital interaction. We also address critical challenges in the deployment of 6G, from technological hurdles to regulatory concerns, providing a holistic assessment of potential barriers. By highlighting the interplay between 6G and AI technologies, this study maps out the current landscape and lights the path forward in this rapidly evolving domain. This paper aims to be a cornerstone resource, providing essential insights, addressing unresolved research questions, and stimulating further investigation into the multifaceted realm of 6G networks. By highlighting the synergy between 6G and AI technologies, we aim to illuminate the path forward in this rapidly evolving field. © 2024 by the authors.
Chataut, R., Upadhyay, A., Usman, Y., Nankya, M., & Gyawali, P. K. (2024). Spam no more: A cross-model analysis of machine learning techniques and large language model efficacies. Paper presented at the 116–122. Retrieved from https://www.scopus.com/inward/record.uri?eid=2-s2.0-85218343734&doi=10.1109%2fCSNet64211.2024.10851763&partnerID=40&md5=7d3c6e638e343a87b5aab18e02cb1dc2
With the increasing sophistication of phishing scams, financial fraud, and malicious cyber-attacks, the need for effective spam detection mechanisms to safeguard users is more critical than ever. In this paper, we present a comprehensive evaluation of traditional machine learning models and Large Language Models (LLMs) in the context of spam detection. By assessing a variety of traditional ML models such as Support Vector Machines (SVM), Logistic Regression, Random Forest, Naive Bayes, K-Nearest Neighbors (KNN), and XGBoost on several performance metrics, we establish a baseline of effectiveness for spam identification tasks. We extend our analysis to include LLMs, specifically ChatGPT 3.5, Perplexity AI, and our own customized fine-tuned GPT model, referred to as TextGPT. Our findings show that while traditional ML models are effective, LLMs demonstrate exceptional potential in enhancing spam detection. Through a rigorous comparative analysis, this study highlights the strengths of both traditional and advanced approaches, showcasing the promising application of LLMs in improving spam detection processes. © 2024 IEEE.
Chataut, R., Usman, Y., Rahman, C. M. A., Gyawali, S., & Gyawali, P. K. (2024). Enhancing phishing detection with AI: A novel dataset and comprehensive analysis using machine learning and large language models. Paper presented at the 226–232. Retrieved from https://www.scopus.com/inward/record.uri?eid=2-s2.0-85212705449&doi=10.1109%2fUEMCON62879.2024.10754710&partnerID=40&md5=742366f8ea2fbf9c8da0503f27ddab0d
Phishing emails are a significant threat to organizations, with over 90 % of cyber attacks starting from a malicious email. Despite built-in security measures, relying solely on these defenses can leave organizations vulnerable to cybercriminals who exploit human nature and the lack of tight security. Phishing emails, designed to deceive recipients into disclosing personal and financial information, represent a significant cybersecurity challenge. This paper introduces a comprehensive dataset curated explicitly for detecting phishing emails, featuring a collection of authentic and phishing emails. The dataset includes a broad spectrum of phishing techniques, such as sophisticated social engineering tactics, impersonation of reputable entities, and using urgent or threatening language to manipulate recipients. Phishing emails were collected to cover various scenarios, including financial fraud, account verification, and malware dissemination attempts. Our analysis involves a range of classical machine learning models alongside exploratory analysis with LLMs. The performance of these models was rigorously evaluated to furnish a comparative analysis of their detection capabilities. The dataset, one of the largest of its kind, offers a significant resource for researchers and cybersecurity professionals aiming to advance phishing detection methods. The dataset used in this research is publicly available, enabling further exploration and replication of the findings by the research community 1]. © 2024 IEEE.
Grünewald, A., Gürpinar, T., Culotta, C., & Guderian, A. (2024). Archetypes of blockchain-based business models in enterprise networks. Information Systems and E-Business Management, 22(4), 633–665. doi:10.1007/s10257-024-00673-3
Many enterprises are currently engaged in developing blockchain-based business models. Enterprise networks offer a variety of potential applications for blockchain solutions as they benefit from transparency and security as well as automation of handling data, material, and financial flows along their supply chains. Despite profound potentials, the indicated business models are still in their early stages and need further investigation. To provide an overview of existing blockchain-based business models in the context of enterprise networks, the underlying paper designs a multidimensional taxonomy and identifies several archetypes of blockchain-based businesses. For the taxonomy development, data from 101 blockchain start-ups serves as a basis for empirical validation. Using hierarchical clustering and the k-means method, seven archetypes that sharpen the understanding of how blockchain solutions affect business models in enterprise networks and enable new business models are derived. The proposed work results are intended to be applied in future research and practice to classify and assess the integration of blockchain solutions into existing business models and to support developing new ones that leverage emerging technological capabilities. © The Author(s) 2024.
Gürpinar, T. (2025). Towards web 4.0: Frameworks for autonomous AI agents and decentralized enterprise coordination. Frontiers in Blockchain, 8 doi:10.3389/fbloc.2025.1591907
The rise of Web 4.0 marks a shift toward decentralized, autonomous AI-driven ecosystems, where intelligent agents interact, transact, and self-govern across digital and physical environments. This paper presents a layered framework outlining the infrastructural, behavioral, and governance dimensions required for enabling autonomous AI agents in decentralized ecosystems. It also explores how enterprises can strategically adopt Web 4.0 applications while mitigating risks related to decentralization and AI coordination. A conceptual approach is adopted, synthesizing research on blockchain-enabled AI, decentralized governance, and autonomous agent interactions. The paper introduces a six-layer framework visualizing key dimensions for Web 4.0 adoption, alongside a framework focusing on enterprise integration guidelines. The study identifies six essential dimensions – spanning infrastructure, trust, and governance – that collectively enable Web 4.0. AI agents require decentralized coordination, transparent behavioral norms, and scalable governance structures to operate autonomously and ethically. Enterprises adopting Web 4.0 must address challenges in data privacy, AI training, multi-agent interaction, and governance. The findings highlight that successful enterprise adoption will depend on trust mechanisms, regulatory alignment, and scalable AI deployment models that balance autonomy with accountability. Copyright © 2025 Gürpinar.
Hanggodo, S., Koustov, T., Sharp, K., & Grant-Kels, J. (2025). Ethical implications of artificial intelligence–written personal statements in dermatology. Journal of the American Academy of Dermatology, doi:10.1016/j.jaad.2025.03.030
Hogrefe, J., Cruz, E., Jaiswal, C., & Riofrio, J. (2024). AITracker: A neural network designed for efficient and affordable eye tracking. Paper presented at the 100–107. Retrieved from https://www.scopus.com/inward/record.uri?eid=2-s2.0-85212669096&doi=10.1109%2fUEMCON62879.2024.10754664&partnerID=40&md5=8ee13ee7e20166d380176a56d7f9cf12
Eye-tracking technology has long been a cornerstone in both academic and research fields, offering insights into behavior, cognition, and visual perception. That being said, however, its accessibility is hindered by the high costs and proprietary nature of existing methodologies. To address these issues, we present AITracker, an open-source application that works using only a standard webcam, leveraging a deep-learning model in order to provide accurate eye-tracking capabilities. Our solution offers flexibility and adaptability, enabling users to customize individual parameters in the software to meet their specific needs. Through robust data collection and neural network training, AITracker achieves incredibly fast response times with a high degree of accuracy, enabling gaze-tracking in up to eight directions, as well as blink detection. In order to better understand the impact of this technology in the context of existing solutions, this paper compares AITracker's multi-layered neural network to various other prevalent eye-tracking methodologies. To that end, this paper also notes certain limitations that inhibit the software, including an undersized dataset and problematic distribution. Additionally, we explore various application scenarios, including hardware integration for assistive technology, hands-free gaming interfaces, advertising research, and attention monitoring in education. Moreover, feedback gathered from different users highlights the effectiveness and impact of AITracker across a diverse array of contexts. © 2024 IEEE.
Klufas, T., Hanggodo, S., Lee, C., Negrini, E., Zhou, A. E., & Grant-Kels, J. (2025). Implications of artificial intelligence scribe usage. Journal of the American Academy of Dermatology, doi:10.1016/j.jaad.2025.04.014
Kovbasiuk, A., Triantoro, T., Przegalińska, A., Sowa, K., Ciechanowski, L., & Gloor, P. (2025). The personality profile of early generative AI adopters: A big five perspective. Central European Management Journal, 33(2), 252–264. doi:10.1108/CEMJ-02-2024-0067
Purpose: This pilot study aimed to evaluate the impact of the big five personality traits on user engagement with chatbots at the early stages of artificial intelligence (AI) adoption. Design/methodology/approach: The pilot study involved 62 participants segmented into two groups to measure variables including engagement duration, task performance and future AI usage intentions. Findings: The findings advocate for the incorporation of psychological principles into technology design to facilitate more tailored and efficient human–AI collaboration. Originality/value: This pilot research study highlights the relationship between the big five personality traits and chatbot usage and provides valuable insights for customizing chatbot development to align with specific user characteristics. This will serve to enhance both user satisfaction and task productivity. © 2024, Anna Kovbasiuk, Tamilla Triantoro, Aleksandra Przegalińska, Konrad Sowa, Leon Ciechanowski and Peter Gloor.
Lang, G., Triantoro, T., & Sharp, J. H. (2024). Large language models as AI-powered educational assistants: Comparing GPT-4 and gemini for writing teaching cases. Journal of Information Systems Education, 35(3), 390–407. doi:10.62273/YCIJ6454
This study explores the potential of large language models (LLMs), specifically GPT-4 and Gemini, in generating teaching cases for information systems courses. A unique prompt for writing three different types of teaching cases such as a descriptive case, a normative case, and a project-based case on the same IS topic (i.e., the introduction of blockchain technology in an insurance company) was developed and submitted to each LLM. The generated teaching cases from each LLM were assessed using subjective content evaluation measures such as relevance and accuracy, complexity and depth, structure and coherence, and creativity as well as objective readability measures such as Automated Readability Index, Coleman-Liau Index, Flesch-Kincaid Grade Level, Gunning Fog Index, Linsear Write Index, and SMOG Index. The findings suggest that while both LLMs perform well on objective measures, GPT-4 outperforms Gemini on subjective measures, indicating a superior ability to create content that is more relevant, complex, structured, coherent, and creative. This research provides initial empirical evidence and highlights the promise of LLMs in enhancing IS education while also acknowledging the need for careful proofreading and further research to optimize their use. © Copyright ©2024 by the Information Systems & Computing Academic Professionals, Inc. (ISCAP). Permission to make digital or hard copies of all or part of this journal for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial use. All copies must bear this notice and full citation. Permission from the Editor is required to post to servers, redistribute to lists, or utilize in a for-profit or commercial use. Permission requests should be sent to the Editor-in-Chief, Journal of Information Systems Education, editor@jise.org.
Laskin, A. V., & D'Agostino, G. (2024). The delphi panel investigation of artificial intelligence in investor relations. Public Relations Review, 50(4) doi:10.1016/j.pubrev.2024.102489
In recent years, there has been a discernible upswing in the attention dedicated to artificial intelligence (AI) within the domains of public relations, advertising, and marketing. Notably, the subdomain of investor relations has maintained a significant historical engagement with AI, actively employing AI and AI-enabled tools for several decades, a practice traceable back to the 1980s. This protracted involvement presents a reservoir of invaluable insights germane to comprehending the broader integration of AI within the purview of public relations. This scholarly inquiry embarks on a Delphi panel examination to scrutinize the deployment of AI in investor relations, proffers a systematic classification of AI-enabled tools within this realm, and prognosticates the trajectory of AI's influence on investor relations and financial communications. The panel of Delphi participants comprises seasoned authorities in the field, boasting a cumulative professional experience spanning 161 years. Leveraging the depth of expertise inherent in investor relations, the study not only illuminates the current landscape but also posits conceivable trajectories for the evolution of AI across other subfields within the domain of public relations. © 2024 Elsevier Inc.
Laskin, A. V., & Freberg, K. (2024). PUBLIC RELATIONS AND STRATEGIC COMMUNICATION IN 2050: Trends shaping the future of the profession Retrieved from https://www.scopus.com/inward/record.uri?eid=2-s2.0-85210685608&doi=10.4324%2f9781003426653&partnerID=40&md5=bcdae94ab6874fd13fa502701b57bacc
Taking stock of the technological, political, economic, and social trends that exist today, this book extends the discussion to analyze and predict how these trends will affect the public relations and strategic communication industry of the future. This book is divided into two sections, the first addressing such key topics as artificial intelligence (AI), big data, political polarization, and misinformation, the second looking at key facets of the profession, such as media relations, crisis communication, and measurement and evaluation. Leading researchers in the discipline share their analysis of these topics while also providing theoretically based and practically relevant insights on how the industry must evolve to keep up with, and perhaps anticipate, changes in culture, society, and technology. This book will be of interest to scholars, industry professionals, and advanced undergraduate and graduate students in public relations and strategic communication. © 2025 selection and editorial matter, Alexander V. Laskin and Karen Freberg; individual chapters, the contributors.
Maoujoud, A., Asserraji, M., Laboudi, F., Ahid, S., & Parks, R. (2024). With the generalization of AI and algorithms, will we still need a nephrologist in the dialysis room? Blood Purification, 53(4), 301–305. doi:10.1159/000536074
Mattanah, J., Holt, L., Feinn, R., Bowley, O., Marszalek, K., Albert, E., . . . Katzenberg, C. (2024). Faculty-student rapport, student engagement, and approaches to collegiate learning: Exploring a mediational model. Current Psychology, 43(28), 23505–23516. doi:10.1007/s12144-024-06096-0
Students value a close, supportive relationship with their professors, which has been shown to enhance their learning in higher education. However, more needs to be known about how quality faculty-student relationships shape students’ engagement and approaches to learning in higher education. In a diverse sample of 966 undergraduates from two different institutions of higher education, the current study explored the relationship between faculty-student rapport, student engagement, and deep and surface approaches to learning. Faculty-student rapport was positively correlated with student engagement (r =.50) and deep learning (r =.30), and negatively correlated with surface learning (r = -.21). Student engagement was positively correlated with deep learning (r =.70) and negatively with surface learning (r = -.32). Using multilevel modelling with students nested within classrooms, engagement was shown to mediate the effects of rapport on greater levels of deep learning (β =.31) and lower levels of surface learning (β = -.12). Although results held up across a range of demographic characteristics, some differences were noted for rapport-building among Asian American students and engagement across men versus women. These results have important implications for how faculty can engage students in the learning process by developing close, supportive relationships with their students and by extending their relationship with their students outside the classroom. © The Author(s) 2024.
Nankya, M., Mugisa, A., Usman, Y., Upadhyay, A., & Chataut, R. (2024). Security and privacy in E-health systems: A review of AI and machine learning techniques. IEEE Access, doi:10.1109/ACCESS.2024.3469215
The adoption of electronic health (e-health) systems has transformed healthcare delivery by harnessing digital technologies to enhance patient care, optimize operations, and improve health outcomes. This paper provides a comprehensive overview of the current state of e-health systems, tracing their evolution from traditional paper-based records to advanced Electronic Health Record Systems(EHRs) and examining the diverse components and applications that support healthcare providers and patients. A key focus is on the emerging trends in AI-driven cybersecurity for e-health, which are essential for protecting sensitive health data. AI's capabilities in continuous monitoring, advanced pattern recognition, real-time threat response, predictive analytics, and scalability fundamentally change the security landscape of e-health systems. The paper discusses how AI strengthens data security through techniques like anomaly detection, automated countermeasures, and adaptive learning algorithms, enhancing the efficiency and accuracy of threat detection and response. Furthermore, the paper delves into future directions and research opportunities in AI-driven cybersecurity for e-health. These include the development of advanced threat detection systems that adapt through continuous learning, quantum-resistant encryption to safeguard against future threats, and privacy-preserving AI techniques that protect patient confidentiality while ensuring data remains useful for analysis. The importance of automating regulatory compliance, securing data interoperability via blockchain, and prioritizing ethical AI development are also highlighted as critical research areas. By emphasizing innovative security solutions, collaborative efforts, ongoing research, and ethical practices, the e-health sector can build resilient and secure healthcare infrastructures, ultimately enhancing patient care and health outcomes. © 2013 IEEE.
Nichols, T., Zemlanicky, J., Luo, Z., Li, Q., & Zheng, J. (2024). Image-based PDF malware detection using pre-trained deep neural networks. Paper presented at the Retrieved from https://www.scopus.com/inward/record.uri?eid=2-s2.0-85194066547&doi=10.1109%2fISDFS60797.2024.10527343&partnerID=40&md5=ad96ad418e7d04755b26f9aa44d692fb
PDF is a popular document file format with a flexible file structure that can embed diverse types of content, including images and JavaScript code. However, these features make it a favored vehicle for malware attackers. In this paper, we propose an image-based PDF malware detection method that utilizes pre-trained deep neural networks (DNNs). Specifically, we convert PDF files into fixed-size grayscale images using an image visualization technique. These images are then fed into pre-trained DNN models to classify them as benign or malicious. We investigated four classical pre-trained DNN models in our study. We evaluated the performance of the proposed method using the publicly available Contagio PDF malware dataset. Our results demonstrate that MobileNetv3 achieves the best detection performance with an accuracy of 0.9969 and exhibits low computational complexity, making it a promising solution for image-based PDF malware detection. © 2024 IEEE.
Norberg, P. A., & Horne, D. R. (2024). When the bridge is not human: Algorithmic interference in forming social relationships through the manipulation of weak ties. Journal of Consumer Affairs, 58(2), 606–629. doi:10.1111/joca.12586
In recent years, social media applications have grown in number and in user bases. Recommendation algorithms on these platforms refer social others and related content to users. Using Granovetter's tie strength theory and the literature on relationship formation as conceptual foundations, we argue that these social media algorithms can damage a user's ability to establish diverse relationships and the benefits therein, thereby reducing personal, and, when aggregated, societal advantages. We argue that this occurs because the algorithms take on social actor roles and operate as “weak tie imposters” that serve as bridges to like others and content. This work provides a new conceptualization of the role recommendation algorithms play in social relationships, argues how they impact social relationship development and user privacy, and offers potential solutions to the issues related to algorithmic interference. © 2024 American Council on Consumer Interests.
Obuchi, S. P., Kojima, M., Suzuki, H., Garbalosa, J. C., Imamura, K., Ihara, K., . . . Kawai, H. (2024). Artificial intelligence detection of cognitive impairment in older adults during walking. Alzheimer's and Dementia: Diagnosis, Assessment and Disease Monitoring, 16(3) doi:10.1002/dad2.70012
INTRODUCTION: To detect early cognitive impairment in community-dwelling older adults, this study explored the viability of artificial intelligence (AI)-assisted linear acceleration and angular velocity analysis during walking. METHODS: This cross-sectional study included 879 participants without dementia (female, 60.6%; mean age, 73.5 years) from the 2011 Comprehensive Gerontology Survey. Sensors attached to the pelvis and left ankle recorded the triaxial linear acceleration and angular velocity while the participants walked at a comfortable speed. Cognitive impairment was determined using Mini-Mental State Examination scores. Deep learning models were used to discern the linear acceleration and angular velocity data of 12,302 walking strides. RESULTS: The models’ average sensitivity, specificity, and area under the curve were 0.961, 0.643, and 0.833, respectively, across 30 testing datasets. DISCUSSION: AI-enabled gait analysis can be used to detect signs of cognitive impairment. Integrating this AI model into smartphones may help detect dementia early, facilitating better prevention. Highlights: Artificial intelligence (AI)-enabled gait analysis can be used to detect the early signs of cognitive decline. This AI model was constructed using data from a community-dwelling cohort. AI-assisted linear acceleration and angular velocity analysis during gait was used. The model may help in early detection of dementia. © 2024 The Author(s). Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring published by Wiley Periodicals LLC on behalf of Alzheimer's Association.
Pennekamp, J., Matzutt, R., Klinkmüller, C., Bader, L., Serror, M., Wagner, E., . . . Wehrle, K. (2024). An interdisciplinary survey on information flows in supply chains. ACM Computing Surveys, 56(2) doi:10.1145/3606693
Supply chains form the backbone of modern economies and therefore require reliable information flows. In practice, however, supply chains face severe technical challenges, especially regarding security and privacy. In this work, we consolidate studies from supply chain management, information systems, and computer science from 2010-2021 in an interdisciplinary meta-survey to make this topic holistically accessible to interdisciplinary research. In particular, we identify a significant potential for computer scientists to remedy technical challenges and improve the robustness of information flows. We subsequently present a concise information flow-focused taxonomy for supply chains before discussing future research directions to provide possible entry points. © 2023 Copyright held by the owner/author(s).
Przegalinska, A., & Triantoro, T. (2024). Converging minds: The creative potential of collaborative AI Retrieved from https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195743463&doi=10.1201%2f9781032656618&partnerID=40&md5=5dc2ac21bb905afefce724640a19ff9b
This groundbreaking book explores the power of collaborative AI in amplifying human creativity and expertise. Written by two seasoned experts in data analytics, AI, and machine learning, the book offers a comprehensive overview of the creative process behind AI-powered content generation. It takes the reader through a unique collaborative process between human authors and various AI-based topic experts, created, prompted, and fine-tuned by the authors. This book features a comprehensive list of prompts that readers can use to create their own ChatGPT-powered topic experts. By following these expertly crafted prompts, individuals and businesses alike can harness the power of AI, tailoring it to their specific needs and fostering a fruitful collaboration between humans and machines. With real-world use cases and deep insights into the foundations of generative AI, the book showcases how humans and machines can work together to achieve better business outcomes and tackle complex challenges. Social and ethical implications of collaborative AI are covered and how it may impact the future of work and employment. Through reading the book, readers will gain a deep understanding of the latest advancements in AI and how they can shape our world. Converging Minds: The Creative Potential of Collaborative AI is essential reading for anyone interested in the transformative potential of AI-powered content generation and human-AI collaboration. It will appeal to data scientists, machine learning architects, prompt engineers, general computer scientists, and engineers in the fields of generative AI and deep learning. Chapter 1 of this book is freely available as a downloadable Open Access PDF at https://www.taylorfrancis.com under a Creative Commons Attribution- No Derivatives (CC-BY -ND)] 4.0 license. © 2024 Aleksandra Przegalinska and Tamilla Triantoro.
Przegalinska, A., Triantoro, T., Kovbasiuk, A., Ciechanowski, L., Freeman, R. B., & Sowa, K. (2025). Collaborative AI in the workplace: Enhancing organizational performance through resource-based and task-technology fit perspectives. International Journal of Information Management, 81 doi:10.1016/j.ijinfomgt.2024.102853
This research examines how artificial intelligence, human capabilities, and task types influence organizational outcomes. By leveraging the frameworks of the Resource-Based View and Task Technology Fit theories, we executed two distinct studies to assess the effectiveness of a generative AI tool in aiding task performance across a spectrum of task complexities and creative demands. The initial study tested the utility of generative AI across diverse tasks and the significance of AI-related skills enhancement. The subsequent study explored interactions between humans and AI, analyzing emotional tone, sentence structure, and word choice. Our results indicate that incorporating AI can significantly improve organizational task performance in areas such as automation, support, creative endeavors, and innovation processes. We also observed that generative AI generally presents more positive sentiment, utilizes simpler language, and has a narrower vocabulary than human counterparts. These insights contribute to a broader understanding of AI's strengths and weaknesses in organizational settings and guide the strategic implementation of AI systems. © 2024 The Authors
Ruocco, M., Duggan, J., Jaiswal, C., O'Neill, B., & Majeski, K. (2024). Leveraging AI face-tracking and gesture recognition for hands-free computing: Bridging the gap for users with physical disabilities. Paper presented at the 232–239. Retrieved from https://www.scopus.com/inward/record.uri?eid=2-s2.0-85215126699&doi=10.1109%2fGHTC62424.2024.10771580&partnerID=40&md5=2e5793a4b960d4ecfa4384725896d620
This paper introduces AccessiMove, an innovative software solution designed to empower users with limited hand mobility by providing hands-free interaction with a computer system. Through the combined use of AI-based facial tracking and gesture recognition technologies, AccessiMove enables precise and intuitive mouse control through the analysis of facial positioning and eye events (blinks). Users can manipulate the on-screen cursor, facilitating a natural and responsive computing experience without reliance on traditional input devices. Moreover, the incorporation of gesture recognition technology allows users to execute actions and key presses by performing specific gestures, further enhancing the range of hands-free interactions. The software boasts a user-friendly interface with customizable settings, catering to individual preferences and varying degrees of motor abilities. AccessiMove's adaptability extends to diverse applications, encompassing general computing tasks, multimedia consumption, and even entertainment. To validate the efficacy of AccessiMove, this paper presents results from a pilot usability study with a prototype version of the software, highlighting the software's positive impact on enhancing computer accessibility. The findings underscore AccessiMove's potential to empower individuals with physical impairments, promoting greater independence and engagement in the digital realm. © 2024 IEEE.
Usman, Y., Gyawali, P. K., Gyawali, S., & Chataut, R. (2024). The dark side of AI: Large language models as tools for cyber attacks on vehicle systems. Paper presented at the 169–175. Retrieved from https://www.scopus.com/inward/record.uri?eid=2-s2.0-85212685216&doi=10.1109%2fUEMCON62879.2024.10754676&partnerID=40&md5=f2f233145efc5caeaa7c701f11aa53c3
The rapid evolution of autonomous vehicles (AVs) presents significant opportunities for enhancing transportation safety and efficiency. However, with increasing connectivity and complex electronic systems, AVs also become vulnerable to cyberattacks. This paper investigates cybersecurity challenges in the realm of AVs, highlighting the role of artificial intelligence (AI), specifically Large Language Models (LLMs), in exploiting vulnerabilities. We analyze various attack vectors, including Controller Area Network (CAN) manipulation, Bluetooth vulnerabilities, and Key Fob hacking, emphasizing the need for proactive cybersecurity measures. Recent incidents, such as the remote compromise of various vehicle models, underscore the urgent need for robust security solutions in the automotive industry. By leveraging LLMs, attackers can craft sophisticated cyber threats targeting AVs, posing risks to both safety and privacy. We introduce HackerGPT, a customized LLM tailored for cyber attack generation, and demonstrate attacks on virtual CAN networks, Bluetooth systems, and Key Fobs. At the same time, our experiments reveal successful compromises in certain vehicle models; limitations exist, particularly in vehicles with advanced encryption and robust signal transmission protocols. However, this research underscores the broader need for increased awareness and proactive security measures in the automotive sector. Our findings aim to contribute significantly to the ongoing discourse on automotive cybersecurity, offering actionable insights for manufacturers and cybersecurity professionals to safeguard the future of mobility. © 2024 IEEE.
Yanamadala, V., Bento, V., & Cohen, S. P. (2024). The rise of AI in health care: Transforming the future. Journal of the International Society of Physical and Rehabilitation Medicine, 7(4), 115–116. doi:10.1097/ph9.0000000000000049
Yawson, R. M. (2025). Perspectives on the promise and perils of generative AI in academia. Human Resource Development International, 28(3), 476–487. doi:10.1080/13678868.2024.2334983
Recent advances in generative artificial intelligence (AI), spearheaded by models such as GPT-3, DALL-E 2, and ChatGPT, have demonstrated capabilities to produce remarkably human-like text, images, and speech. This has fuelled growing interest in applying these technologies in academic contexts to augment teaching, research, and knowledge creation. However, the integration of emerging technologies into education requires a thoughtful evaluation to ensure responsible and ethical adoption. This essay provides a balanced perspective on both the potential promise and the possible perils of deploying generative AI in academia. It examines key technical factors that require evaluation, discusses risks and limitations, and proposes an informed framework for assessing when and how these technologies could appropriately enhance academic pursuits. © 2024 Informa UK Limited, trading as Taylor & Francis Group.
Yawson, R. M., & Goryunova, E. (2025). Nested complexity: A conceptual framework for leveraging AI for sustainable organizations and human resource development. Advances in Developing Human Resources, 27(2-3), 91–123. doi:10.1177/15234223251335908
Problem: Organizations face increasing complexity in implementing artificial intelligence (AI) while maintaining a focus on human resource development. Human Resource Development (HRD) professionals struggle to balance technological advancement with human capital development amidst volatile, uncertain, complex, and ambiguous (VUCA) environments. Solution: We propose a “nested complexity” framework that conceptualizes AI implementation challenges as multi-layered complexities spanning technological, ethical, and regulatory dimensions, nested within broader environmental complexity. Through a narrative literature review and conceptual integration, we develop practical guidelines for assessing organizational readiness, developing learning strategies, and managing change during AI implementation. Stakeholders: This framework provides HRD professionals with structured approaches for leading AI initiatives while prioritizing human development. It enables organizations to develop implementation strategies that balance technological advancement with human capabilities, offering practical tools for building organizational capacity that supports successful AI integration while maintaining focus on human capital development. © The Author(s) 2025.
