"Unknown unknowns" and the inherent difficulty of achieving accurate self-assessments

Abstract Background Recently, machine learning techniques have been applied to data collected from inertial measurement units to automatically assess balance, but rely on hand-engineered features. We explore the utility of machine learning to automatically extract important features from inertial measurement unit data for balance assessment. Findings Ten participants with balance concerns performed multiple balance exercises in a laboratory setting while wearing an inertial measurement unit on their lower back. Physical therapists watched video recordings of participants performing the exercises and rated balance on a 5-point scale. We trained machine learning models using different representations of the unprocessed inertial measurement unit data to estimate physical therapist ratings. On a held-out test set, we compared these learned models to one another, to participants’ self-assessments of balance, and to models trained using hand-engineered features. Utilizing the unprocessed kinematic data from the inertial measurement unit provided significant improvements over both self-assessments and models using hand-engineered features (AUROC of 0.806 vs. 0.768, 0.665). Conclusions Unprocessed data from an inertial measurement unit used as input to a machine learning model produced accurate estimates of balance performance. The ability to learn from unprocessed data presents a potentially generalizable approach for assessing balance without the need for labor-intensive feature engineering, while maintaining comparable model performance.

Download Full-text

Temporal and social comparative self-assessments of physical health in young, middle-aged, and young-old adults in the MIDUS study

Journal of Behavioral Medicine ◽

10.1007/s10865-021-00204-2 ◽

2021 ◽

Author(s):

Jerry Suls ◽

Rebecca A. Ferrer ◽

William M. P. Klein

Keyword(s):

Physical Health ◽

Middle Aged ◽

Old Adults ◽

Self Assessments ◽

Young Old

Download Full-text

Gender Differences in Academic Efficacy across STEM Fields

Sociological Perspectives ◽

10.1177/07311214211028617 ◽

2021 ◽

pp. 073112142110286

Author(s):

Jennifer Ashlock ◽

Miodrag Stojnic ◽

Zeynep Tufekci

Keyword(s):

Gender Differences ◽

Gender Gap ◽

Meaning Making ◽

Stem Fields ◽

Data Set ◽

Science Technology ◽

Middle Schoolers ◽

Self Assessments ◽

Math Grades ◽

And Mathematics

Cultural processes can reduce self-selection into math and science fields, but it remains unclear how confidence in computer science develops, where women are currently the least represented in STEM (science, technology, engineering, and mathematics). Few studies evaluate both computer skills and self-assessments of skill. In this paper, we evaluate gender differences in efficacy across three STEM fields using a data set of middle schoolers, a particularly consequential period for academic pathways. Even though girls and boys do not significantly differ in terms of math grades and have similar levels of computer skill, the gender gap in computer efficacy is twice as large as the gap for math. We offer support for disaggregation of STEM fields, so the unique meaning making around computing can be addressed.

Download Full-text

Switched Capacitor DC-DC Converters: A Survey on the Main Topologies, Design Characteristics, and Applications

Energies ◽

10.3390/en14082231 ◽

2021 ◽

Vol 14 (8) ◽

pp. 2231

Author(s):

Alencar Franco de Souza ◽

Fernando Lessa Tofoli ◽

Enio Roberto Ribeiro

Keyword(s):

Voltage Regulation ◽

Inherent Difficulty ◽

Practical Applications ◽

Dc Power ◽

Higher Power ◽

Voltage Doubler ◽

Converter Design ◽

Design Characteristics ◽

And Performance ◽

Full Charge

This work presents a review of the main topologies of switched capacitors (SCs) used in DC-DC power conversion. Initially, the basic configurations are analyzed, that is, voltage doubler, series-parallel, Dickson, Fibonacci, and ladder. Some aspects regarding the choice of semiconductors and capacitors used in the circuits are addressed, as well their impact on the converter behavior. The operation of the structures in terms of full charge, partial charge, and no charge conditions is investigated. It is worth mentioning that these aspects directly influence the converter design and performance in terms of efficiency. Since voltage regulation is an inherent difficulty with SC converters, some control methods are presented for this purpose. Finally, some practical applications and the possibility of designing DC-DC converters for higher power levels are analyzed.

Download Full-text