Abstract: A non-transitory computer-readable storage medium contains instructions that configure at least one processor that is in communication with at least one storage device, to balance energy expenditure by a user with food intake by the user by storing, at the at least one storage device, at least one stored recipe for the production of at least one meal component and an energy amount corresponding to the at least one meal component, each stored recipe having at least one ingredient; optimizing at least one stored recipe by multiplying, at the at least one processor, a recipe scaling factor by the energy amount of the at least one stored recipe to obtain an optimized recipe having an optimized energy amount, wherein the optimized recipe minimizes an energy difference between the total recommended energy intake and the optimized energy amount of the recipe; where the optimizing is subject to at least one constraint.

Abstract: An energy balancing system scales portion sizes of user-selected meal recipes to control a digital scale to prompt the user to measure scaled quantities of meal ingredients to prepare scaled meals. Physical activity tracking devices provide data to generate physical activity energy expenditures for energy burned by physical activity. The physical activity energy is added to a basal metabolic rate of energy expenditure that is a function of sex, weight, height, and age. The total energy expended are scaled down for a weight-loss goal to obtain the total recommended energy. A recipe portion-size optimizer adjusts scaling factors for each recipe so that the total recommended energy is met by the scaled meals. Amounts of nutrients for the recipes can also be scaled by the scaling factors to match recommended nutrient amounts when the meal recipe optimizer generates the scaling factors using an over-determined linear system optimizer.

Abstract: A computer-implemented method for machine learning and prediction relating to exercise by a user during a bout of exercise may include providing a physical activity measurement device that includes at least one input and at least one output; providing a machine learning model; via the at least one input, collecting physiological data from the user; adding the physiological data acquired by the collecting to the user's physiological data set; training the machine learning model on the user's said physiological data set; making at least one prediction for the user based on the application of the machine learning model to at least one input during the bout of exercise, and communicating at least one prediction to the user via at least one output.

Abstract: An energy balancing system scales portion sizes of user-selected meal recipes to control a digital scale to prompt the user to measure scaled quantities of meal ingredients to prepare scaled meals. Physical activity tracking devices provide data to generate physical activity energy expenditures for energy burned by physical activity. The physical activity energy is added to a basal metabolic rate of energy expenditure that is a function of sex, weight, height, and age. The total energy expended are scaled down for a weight-loss goal to obtain the total recommended energy. A recipe portion-size optimizer adjusts scaling factors for each recipe so that the total recommended energy is met by the scaled meals. Amounts of nutrients for the recipes can also be scaled by the scaling factors to match recommended nutrient amounts when the meal recipe optimizer generates the scaling factors using an over-determined linear system optimizer.