Current workforce evaluation tools, such as interviews, cognitive assessments, and questionnaires, can be helpful in assessing job performance, but do not always accurately reflect how an individual is performing. In addition, these traditional tools can mean more paperwork, bias, and missing indicators of performance. Mobile sensors are already being successfully used to improve health and wellness. Can they also be used to monitor and improve our job performance?
The mPerf team includes some of the nation's leading researchers in work performance, interpersonal communications, stress, sensor design and signal processing, mobile sensing, mobile computing, machine learning, computational modeling, and mobile health.
Mobile Health
University of Memphis
Work Performance
University of Minnesota
Interpersonal Communications
University of Memphis
Stress
University of Minnesota
Medical School, Duluth Campus
Sensor Design, Signal Processing
The Ohio State University
Mobile Sensing
Cornell University
Mobile Computing
University of California, Los Angeles
Machine Learning
University of Massachusetts Amherst
Computational Modeling
University of Massachusetts Amherst
A prediction approach based on semantically meaningful, theoretically motivated, technically feasible intermediate markers ensures generalizability and interpretability.
Theoretically-grounded models and efficient software implementations will enable objective assessment of everyday job performance for employers worldwide.