@article{scholars16106,
       publisher = {MDPI},
          volume = {22},
          number = {23},
         journal = {Sensors},
            year = {2022},
            note = {cited By 6},
           title = {Machine Learning-Based Ensemble Classifiers for Anomaly Handling in Smart Home Energy Consumption Data},
             doi = {10.3390/s22239323},
            issn = {14248220},
        abstract = {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{\^a}?? 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{\^a}?? performance, various metrics, namely, accuracy, precision, recall/sensitivity, specificity, and F1 score are computed. From these metrics, it is identified that the ensemble classifier {\^a}??RF+SVM+DT{\^a}?? has shown superior performance over the conventional single classifiers as well the other ensemble classifiers for anomaly handling. {\^A}{\copyright} 2022 by the authors.},
        keywords = {Anomaly detection; Automation; Decision trees; Electric loads; Energy utilization; Intelligent buildings; Learning systems; Nearest neighbor search; Smart meters; Support vector machines, Anomaly-handling; Data anomalies; Data imputation; Energy consumption datum; Ensemble-classifier; Machine-learning; Smart home data; Smart homes; Smart meter data; Tracebase dataset, Classification (of information), Bayes theorem; cluster analysis; machine learning; support vector machine, Bayes Theorem; Cluster Analysis; Machine Learning; Neural Networks, Computer; Support Vector Machine},
          author = {Kasaraneni, P. P. and Venkata Pavan Kumar, Y. and Moganti, G. L. K. and Kannan, R.},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85143847225&doi=10.3390\%2fs22239323&partnerID=40&md5=d5ddaea488606fc2c5cf16c497ffac7d}
}