Background and Aims: The estimation of standard spirometric measurements needs to measure a participant’s non-mutated standing height. Even so, as a direct consequence of physical impairment, traumatic amputation, as well as other structural deformities or neuromuscular disablement, a few patients referred for lung function assessment cannot stand. Materials and methods: The study involved 202 participants and consist of two elements that are data collection and data analysis. There were four types of data: standing height measurement, arm span measurement, sitting height measurement and predicted pulmonary function, including forced vital capacity (FVC) and forced expiratory volume (FEV1), which was studied based on correlational analysis. Results: The study shows a positive, linear solid correlation between arm span and standing height measure in centimetre with an R-value of 0.919. There is a positive moderate linear correlation between arm span and sitting height measure in centimetre with an R-value of 0.604. Sitting height and standing height has a positive, strong linear correlation with an R-value of 0.744. For the pulmonary function test, a positive, strong linear correlation between Forced Vital Capacity prediction using sitting height and Forced Vital Capacity prediction using standing height with an R-value of 0.710. There was a positive moderate linear correlation between Forced Expiratory Volume prediction using sitting height and Forced Expiratory Volume prediction using standing height with an R-value of 0.577. The relationship between forced vital capacity and forced expiratory volume predicted value of a pulmonary function using arm span and forced vital capacity with forced expiratory volume predicted value of a pulmonary function using standing height shows a positive, strong linear correlation with forced vital capacity R-value of pulmonary function 0.950 and forced expiratory volume R-value of 0.938. Conclusion: Overall, based on the obtained results of the study, it has been proven that the arm span measurement would be the most compatible alternative measure to be used instead of standing height in the case of a patient with permanent disability or incapacitated for clinical purposes and pulmonary function test compared to sitting height.
Addressing data anomalies (e.g., garbage data, outliers, redundant data, and missing data) plays a vital role in performing accurate analytics (billing, forecasting, load profiling, etc.) on smart homes' energy consumption data. From the literature, it has been identified that the data imputation with machine learning (ML)-based single-classifier approaches are used to address data quality issues. However, these approaches are not effective to address the hidden issues of smart home energy consumption data due to the presence of a variety of anomalies. Hence, this paper proposes ML-based ensemble classifiers using random forest (RF), support vector machine (SVM), decision tree (DT), naive Bayes, K-nearest neighbor, and neural networks to handle all the possible anomalies in smart home energy consumption data. The proposed approach initially identifies all anomalies and removes them, and then imputes this removed/missing information. The entire implementation consists of four parts. Part 1 presents anomaly detection and removal, part 2 presents data imputation, part 3 presents single-classifier approaches, and part 4 presents ensemble classifiers approaches. To assess the classifiers' performance, various metrics, namely, accuracy, precision, recall/sensitivity, specificity, and F1 score are computed. From these metrics, it is identified that the ensemble classifier "RF+SVM+DT" has shown superior performance over the conventional single classifiers as well the other ensemble classifiers for anomaly handling.