David Hua

Dr. David Hua

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
Hesham M AllamHesham M Allam
Hesham M Allam
CDChris Davison
Chris Davison
FKFaisal Kalota
Faisal Kalota
ELEdward Lazaros
Edward Lazaros
DHDavid Hua
David Hua
As suicide rates increase globally, there is a growing need for effective, data-driven methods in mental health monitoring. This study leverages advanced artificial intelligence (AI), particularly natural language processing (NLP) and machine learning (ML), to identify suicidal ideation from Twitter data. A predictive model was developed to process social media posts in real time, using NLP and sentiment analysis to detect textual and emotional cues associated with distress. The model aims to identify potential suicide risks accurately, while minimizing false positives, offering a practical tool for targeted mental health interventions. The study achieved notable predictive performance, with an accuracy of 85%, precision of 88%, and recall of 83% in detecting potential suicide posts. Advanced preprocessing techniques, including tokenization, stemming, and feature extraction with term frequency–inverse document frequency (TF-IDF) and count vectorization, ensured high-quality data transformation. A random forest classifier was selected for its ability to handle high-dimensional data and effectively capture linguistic and emotional patterns linked to suicidal ideation. The model’s reliability was supported by a precision–recall AUC score of 0.93, demonstrating its potential for real-time mental health monitoring and intervention. By identifying behavioral patterns and triggers, such as social isolation and bullying, this framework provides a scalable and efficient solution for mental health support, contributing significantly to suicide prevention strategies worldwide.

10 December 2019 in Analytical Chemistry
Verified
Journal Article
Open access
HDHeather Desaire
Heather Desaire
DHDavid Hua
David Hua
MALDI-TOF MS has shown great utility for rapidly identifying microbial species. It can be used to successfully type bacteria and fungi from a variety of sources more rapidly and cost-effectively than traditional methods. One area where improvements are necessary is in the typing of highly similar samples, such as those samples from the same genus but different species or samples from within a single species but from different strains. One promising way to address this current limitation is by using advanced machine learning techniques. In this work, we adapt a newly developed machine learning tool, the Aristotle Classifier, to bacterial classification of MALDI-TOF MS data. This tool was originally developed for classifying glycomics and glycoproteomics data, so we modified it to be well-suited for assigning mass spectral data from bacterial proteins. The classifier exceeds existing benchmarks in classifying bacteria, and it shows particularly strong performance when the samples to be identified are highly similar. The combination of mass spectrometry data and tools like the Aristotle Classifier could ameliorate the ambiguities associated with challenging bacterial classification problems.

28 September 2016 in TechTrends
Verified
Journal Article
Closed access
PDF file
ASAlexander R. Schrameyer
Alexander R. Schrameyer
TGTracy M. Graves
Tracy M. Graves
DHDavid Hua
David Hua
NBNile C. Brandt
Nile C. Brandt

15 July 2024
Verified
Book Chapter
Closed access
PDF file
FKFaisal Kalota
Faisal Kalota
DHDavid Hua
David Hua
ABAfsaneh Behforouz
Afsaneh Behforouz
The world is witnessing the Fourth Industrial Revolution (FIR), also known as Industry 4.0 (I4.0). This chapter introduces the Fourth Industrial Revolution and also discusses some of the socio-economic implications associated with it. After highlighting the first three industrial revolutions, the section on I4.0 provides a brief overview of various I4.0 technologies, followed by the socio-economic implications of I4.0. The socio-economic implications include but are not limited to organizational impact, workforce development, potential legal issues, security, and ethical concerns. The chapter concludes with recommendations for businesses, government agencies, and academic institutions. <!----> <!----> <!----> <!---->

1 January 2024 in SSRN Electronic Journal
Verified
Preprint
Open access
AHAllam Hesham
Allam Hesham
JDJuan Dempere
Juan Dempere
FKFaisal Kalota
Faisal Kalota
DHDavid Hua
David Hua
In recent years, educational institutions worldwide have increasingly embraced technology as a means of enhancing the learning experience and adapting to the demands of the modern era. This trend toward digital transformation has become even more pronounced in the wake of the COVID-19 pandemic, which necessitated a rapid shift to remote learning modalities. Learning Management Systems (LMS) have emerged as crucial tools for educational continuity, enabling institutions to deliver course materials, facilitate communication, and manage student progress in virtual environments. However, the success of LMS implementation varied among educational institutions, with some achieving seamless transitions while others encountered challenges stemming from students' reluctance to fully embrace the technology. This paper contributes to the understanding of LMS adoption in higher education institutions in Dubai, UAE, by proposing a comprehensive model based on the Technology Acceptance Model (TAM) and enhanced with modern factors that fit the nature of virtual learning. Methods: Employing a quantitative research approach, the study utilized the main structure of the Technology Acceptance Model (TAM) to propose an enhanced version of factors that might influence students' acceptance of online learning management systems. To collect the necessary data, a self-administered survey questionnaire was distributed to 500 students, ensuring a comprehensive dataset for analysis. The analysis was conducted using Partial Least Square Structural Equation Modeling (PLS-SEM), a robust statistical technique suitable for complex models with latent variables. This method allowed the researchers to empirically validate the proposed model, assessing the impact of various modern factors tailored to the nature of virtual learning environments. Results: The study's empirical findings revealed several significant factors influencing students' intentions to use LMS, including personal innovation, perceived utility, system quality, service quality, and information quality. While system quality encompasses the technical aspects and functionalities of the LMS, information quality focuses on the relevance, accuracy, completeness, and timeliness of the system's content. Discussion: These insights provide valuable guidance for educational institutions in Dubai and beyond, offering actionable recommendations for optimizing LMS implementation strategies to enhance student engagement and educational outcomes in the digital learning landscape.

16 December 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
Hesham M AllamHesham M Allam
Hesham M Allam
ELEdward Lazeros
Edward Lazeros
DHDavid Hua
David Hua
FKFaisal Kalota
Faisal Kalota
CDChris Davison
Chris Davison
As global suicide rates continue to rise, the demand for innovative, data-driven solutions in mental health surveillance has never been more urgent. This study harnesses the power of advanced artificial intelligence (AI) and machine learning techniques to detect suicidal ideation from Twitter data, presenting a groundbreaking approach to suicide prevention. A robust, real-time predictive model was developed to process vast volumes of social media posts, integrating natural language processing (NLP) and sentiment analysis to identify textual and emotional cues indicative of distress. This approach enables precise detection of potential suicide risks while significantly minimizing false positives, paving the way for more accurate and effective mental health interventions. The study's findings highlight the transformative potential of machine learning in suicide prevention. By uncovering behavioral patterns and context-specific triggers such as social isolation and bullying, it establishes a benchmark for the application of AI in sensitive, real-time mental health contexts. The proposed framework offers a scalable, high-performance tool for timely, data-driven responses, contributing substantially to global suicide prevention strategies. The model demonstrated exceptional predictive performance, achieving an overall accuracy of 85%, a precision of 88%, and a recall of 83% in detecting "Potential Suicide Posts." High-quality data transformation was ensured through advanced preprocessing techniques, including tokenization, stemming, and feature extraction using Term Frequency-Inverse Document Frequency (TF-IDF) and Count Vectorization. A Random Forest Classifier, chosen for its robustness in handling high-dimensional data, effectively captured linguistic and emotional patterns associated with suicidal ideation. The model’s reliability was further validated with an impressive Precision-Recall AUC score of 0.93, solidifying its efficacy as a powerful tool for real-time mental health surveillance and intervention.