Algorithm A1. Fall Prediction Algorithm (FPA): Pseudocode of the Proposed Model [20]

Input: Blood Pressure, Heart Rate and$O_2$in Blood—Datasets from public Repository. Output: Fall Prediction Outcome—Risk level classification 1.Apply data sets for data extraction to the input datasets. 2.Feed the retrieved features to the fuzzy prediction model to train it and formulate rules for categorizing risk levels. (a)Fuzzification: Transform crisp data into fuzzy data. (b)Membership function: Formulate the membership function based on the parameter values (Normal, Low, Moderate, High, and Emergency) Input function: ‘trapmf’. (c)Fuzzy Rule Generation: Formulate fuzzy rules from the fuzzy data. Fuzzy rule: Rule 1: For Normal BP,                    if PP is Normal                    and HR is Normal                    and ${\mathrm{O}}_2$ is Normal                    then Risk Level is Normal (No risk of fall detected)                 .Rule 83: For High BP, (126–130/80–90)                    if PP is High                    and HR is High (110–129 bpm)                    and ${\mathrm{O}}_2$ is Moderate (95–96%)                    then Risk Level is High (Will have a risk of falling in                     few days if this condition persists) (d)Defuzzification: Transform the fuzzy rules into crisp rules. 3.Employ cross-validation on the model using the testing dataset with MFS. Evaluate the model’s performance based on accuracy, specificity, and sensitivity metrics. 4.Perform evaluation results to validate the results.