Engineering/Computer Science

Gabriel Cooper, Gabrcoop@ttu.edu
Texas Tech University, with Dr. Xiaolong Liu

Electromagnetic System Design for Soft Robotics Manipulation
As soft robotics and electromagnetic control system technology advances, surgical assistance by robotics is now more prominent than ever before, calling for new capabilities of precision and minimal invasive surgical assistance to be developed. Soft robotics have been a particular interest for bioengineering researchers due to the responsiveness to human tissue preventing damage. This research aims to develop a dynamic versatility of biological cilia, a new innovative approach to actuation mechanisms for artificial cilia. Researchers hypothesized that with such a design, the control system will be able to manipulate individual cilia on both the power and recovery stroke demonstrating omnidirectional manipulation of the cilium. Utilization and design for the artificial cilia along with the electromagnetism produced is simulated and experimentally developed to analyze the capabilities of the system. Further exploration of the system shows promises to improve the responsiveness of the cilium demonstrating biomimicry in the technology.
 

Valeria Pena, vpena23fl@ollusa.edu
Our Lady of the Lake University, with Dr. Samantha Galvan

Harnessing AI for Marketing Insights: A Mixed-Methods Approach to Predictive  Accuracy and Language Analysis
Artificial intelligence (AI) is rapidly altering the marketing landscape, empowering organizations to predict consumer trends, personalize content, and optimize campaigns on an unprecedented scale. Despite these advances, questions remain about how reliably AI- driven models can forecast rapidly evolving market behaviors and create culturally resonant communications. This study poses the research question: How does the integration of machine learning (ML) and natural language processing (NLP) influence the predictive accuracy and communicative effectiveness of contemporary marketing strategies? The significance of this research lies in the growing reliance on AI among organizations seeking both operational agility and competitive distinction while navigating issues of data quality, cultural nuance, and ethical responsibility. To address these complexities, this project employs a mixed-methods approach: quantitative analysis of AI-driven web personalization performance metrics including adaptation rates and user engagement, will be paired with a qualitative assessment of AI-generated language through thematic and discourse analysis. This methodology is designed to capture both the measurable impact of AI on marketing outcomes and the nuanced shifts in brand communication as AI-generated content becomes more prevalent. By critically evaluating the capabilities and challenges of AI-driven marketing, this research aims to illuminate best practices and identify areas where ongoing human oversight remains essential.
 

Alison Sanchez, asanchez02185@gmail.com
Texas Tech University, with Dr. Uma Chinta Maheswari

Systematic Review of AI-Enhanced Social Robotics for Autism Therapy: The Case of NAO
Robot-assisted therapy (RAT) using social robots, particularly the NAO humanoid robot, has garnered significant interest as a complementary tool for autism spectrum disorder (ASD) intervention due to its potential to enhance socio-cognitive skills. Given the increasing prevalence of ASD and a shortage of medical personnel, early and effective interventions are crucial. This research systematically reviews the existing literature to identify current capabilities and critical gaps in the application of social robots, specifically NAO robots augmented with AI-driven, external add-on models, for autism intervention. Current literature reveals that children with ASD generally respond positively to social robots, demonstrating increased engagement, eye contact, and confidence. Our review highlights key technological enhancements (including gesture detection, AI-based action monitoring, emotion recognition, gaze tracking, and cloud-based speech processing) that significantly improve the robot's responsiveness, personalization, and therapeutic relevance. However, notable challenges persist, such as the robot's need for technical expertise, limited generalizability of acquired skills to human interactions, and insufficient long-term evidence of effectiveness. Despite these issues, the findings support the use of social robots as assistive, not replacement, tools for therapists, and call for the future development of more autonomous, multimodal, and ethically sound systems.

This may include closed-loop AI architectures with sophisticated, individualized prompting and reward mechanisms (e.g., improved long-term memory algorithms) that integrate interactive environmental factors. Overall, large-scale clinical studies and deeper collaboration between engineers and clinicians are essential to ensure these technologies are practical, effective, and aligned with the complex needs of children with ASD.