Disclosed is a computer-implemented method for inputting sensing information to an ensemble model to obtain a final result value. The computer-implemented method includes obtaining pieces of sensing information associated with a biometric state, inputting the pieces of sensing information to an ensemble model which includes a plurality of models and combines result values output from the plurality of models to output the final result value, inputting first sensing information of the pieces of sensing information to a first model of the plurality of models, obtaining a first uncertainty of the first model by using at least one of an input value and an output value of the first model, and determining a first weight value of a first result value of the first model by using the first uncertainty, inputting second sensing information of the pieces of sensing information to a second model of the plurality of models, obtaining a second uncertainty of the second model by using at least one of an input value and an output value of the second model, and determining a second weight value of a second result value of the second model by using the second uncertainty, combining, by using the ensemble model, the first result value to which the first weight value is applied and a second result value to which the second weight value is applied to obtain the final result value, and performing an operation corresponding to the biometric state, based on the final result value.