Search Results - francis+m%c3%a9ndez+mediavilla

4 Results

Sort By:

Uncertainty Estimation for Classification Algorithms through Confusion Matrix Analysis

Description: This technology improves upon traditional point estimates of model accuracy by implementing interval estimation techniques within Frequentist and Bayesian frameworks. Utilizing bootstrap and Monte Carlo sampling methods, it provides a robust measure of uncertainty for classification performance metrics, enhancing the reliability and interpretability...

Published: 12/16/2025 | Inventor(s): Amir Liron, Francis Méndez Mediavilla

Keywords(s): Machine Learning, Software, Statistical Analysis

Category(s): Data/AI, Software

Automated Time Studies using Computer Vision and Large Language Models

Description: This technology uses advanced machine learning algorithms and computer vision techniques to automatically analyze video recordings of work processes, segmenting frames to identify and classify human actions like general movement or tool usage. It employs predetermined time study methods such as Basic MOST to estimate task durations accurately,...

Published: 11/13/2025 | Inventor(s): Abhimanyu Sharotry, Jesus Jimenez, Francis Méndez Mediavilla, Aleah White, Noe Tavira, Lauren Cravy

Keywords(s): Computer Vision, Industrial Process Optimization, Machine Learning

Category(s): Data/AI, Engineering

Manual Punch Press Workstation for Visually Impaired Workforce

Description: This innovative system integrates a computer vision system with machine learning models to monitor and analyze the placement of operators' hands on machine switches in real-time. It ensures the machinery operates only when it confirms the correct hand placement and button pressing by the operator, enhancing safety and security. The...

Published: 11/11/2025 | Inventor(s): Abhimanyu Sharotry, Noe Tavira, Jesus Jimenez, Francis Méndez Mediavilla

Keywords(s): Safety Compliance, Visually Impaired operators

Category(s): Engineering

A Human Digital Twin for factory workers to predict fatigue using computer vision

Description: A cutting-edge solution that utilizes RGB camera feeds to identify human skeletons with models like MediaPipe and OpenPose, analyzing poses and movements to assess fatigue. It uniquely identifies individuals without facial recognition, using limb length and walking patterns, to create and update a digital twin for ongoing, personalized...

Published: 11/11/2025 | Inventor(s): Abhimanyu Sharotry, Francis Méndez Mediavilla, Jesus Jimenez

Keywords(s): Fatigue, Human Digital Twin, Real-time Hazard Prevention, Safety

Category(s): Data/AI, Engineering