Explore

Applying unsupervised machine learning to NFL Combine data to evaluate the validity of the 225-lb bench press repetition test — examining whether performance on this test predicts draft outcomes and whether variance within positions undermines its predictive utility.

Analyzing neuromuscular performance characteristics and fatigue patterns in competitive four-wall handball players — providing sport-specific data to inform training design and injury prevention strategies.

Integrating AI-powered motion analysis and machine learning tools into the research-to-education pipeline — developing scalable assessment protocols that bridge laboratory precision with real-world coaching and training applications.

Developing individualized load-velocity profiles for the lat pulldown movement in upper-body dominant athletes — establishing velocity-based training thresholds to optimize strength programming and reduce fatigue-related performance decrements.

Validating a gold-standard protocol for assessing posterior shoulder strength and stability in overhead and throwing athletes — comparing standing and posterior testing positions to establish normative data and clinical cutoffs.

Examining whether a custom-fitted mouthguard affects isometric cervical muscle strength and activation patterns — with implications for athletic performance and injury prevention protocols.

Classifying how individuals respond differently to overhead shoulder loading — identifying distinct fatigue phenotypes using EMG, force plates, and AI-assisted pattern recognition to improve athletic screening and training prescription.