Interaction from structure using machine learning: in and out of equilibrium

Prediction of pair potential given a typical configuration of an interacting classical system is a difficult inverse problem. There exists no exact result that can predict the potential given the structural information. We demonstrate that using machine learning (ML) one can get a quick but accurate answer to the question: "which pair potential lead to the given structure (represented by pair correlation function)?" We use artificial neural network (NN) to address this question and show that this ML technique is capable of providing very accurate prediction of pair potential irrespective of whether the system is in a crystalline, liquid or gas phase. We show that the trained network works well for sample system configurations taken from both equilibrium and out of equilibrium simulations (active matter systems) when the later is mapped to an effective equilibrium system with a modified potential. We show that the ML prediction about the effective interaction for the active system is not only useful to make prediction about the MIPS (motility induced phase separation) phase but also identifies the transition towards this state.

Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning

Accelerometer-based fitness trackers and smartwatches are proliferating with incessant attention towards health tracking. Despite their growing popularity, accurately measuring hallmark measures of physical activities has yet to be accomplished in adults of all ages. In this work, we evaluated the performance of four machine learning models: decision tree, random forest, extreme gradient boosting (XGBoost) and least absolute shrinkage and selection operator (LASSO), to estimate the hallmark measures of physical activities in young (20-50 years), middle-aged (50-70 years], and older adults (70-89 years]. Our models were built to recognize physical activity types, recognize physical activity intensities, estimate energy expenditure (EE) and recognize individual physical activities using wrist-worn tri-axial accelerometer data (33 activities per participant) from a large sample of participants (n = 253, 62% women, aged 20-89 years old). Results showed that the machine learning models were quite accurate at recognizing physical activity type and intensity and estimating energy expenditure. However, models performed less optimally when recognizing individual physical activities. F1-Scores derived from XGBoost's models were high for sedentary (0.955-0.973), locomotion (0.942-0.964) and lifestyle (0.913-0.949) activity types with no apparent difference across age groups. Low (0.919-0.947), light (0.813-0.828) and moderate (0.846-0.875) physical activity intensities were also recognized accurately. The root mean square error range for EE was approximately 1 equivalent of resting EE [0.835-1.009 METs]. Generally, random forest and XGBoost models outperformed other models. In conclusion, machine learning models to label physical activity types, activity intensity and energy expenditure are accurate and there are minimal differences in their performance across young, middle-aged and older adults.