{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:19:40Z","timestamp":1760145580468,"version":"build-2065373602"},"reference-count":42,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T00:00:00Z","timestamp":1722384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Copel Distribui\u00e7\u00e3o S.A.","award":["ANEEL-PD-02866-0508\/2019"],"award-info":[{"award-number":["ANEEL-PD-02866-0508\/2019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Load recognition remains not comprehensively explored in Home Energy Management Systems (HEMSs). There are gaps in current approaches to load recognition, such as enhancing appliance identification and increasing the overall performance of the load-recognition system through more robust models. To address this issue, we propose a novel approach based on the Analysis of Variance (ANOVA) F-test combined with SelectKBest and gradient-boosting machines (GBMs) for load recognition. The proposed approach improves the feature selection and consequently aids inter-class separability. Further, we optimized GBM models, such as the histogram-based gradient-boosting machine (HistGBM), light gradient-boosting machine (LightGBM), and XGBoost (extreme gradient boosting), to create a more reliable load-recognition system. Our findings reveal that the ANOVA\u2013GBM approach achieves greater efficiency in training time, even when compared to Principal Component Analysis (PCA) and a higher number of features. ANOVA\u2013XGBoost is approximately 4.31 times faster than PCA\u2013XGBoost, ANOVA\u2013LightGBM is about 5.15 times faster than PCA\u2013LightGBM, and ANOVA\u2013HistGBM is 2.27 times faster than PCA\u2013HistGBM. The general performance results expose the impact on the overall performance of the load-recognition system. Some of the key results show that the ANOVA\u2013LightGBM pair reached 96.42% accuracy, 96.27% F1, and a Kappa index of 0.9404; the ANOVA\u2013HistGBM combination achieved 96.64% accuracy, 96.48% F1, and a Kappa index of 0.9434; and the ANOVA\u2013XGBoost pair attained 96.75% accuracy, 96.64% F1, and a Kappa index of 0.9452; such findings overcome rival methods from the literature. In addition, the accuracy gain of the proposed approach is prominent when compared straight to its competitors. The higher accuracy gains were 13.09, 13.31, and 13.42 percentage points (pp) for the pairs ANOVA\u2013LightGBM, ANOVA\u2013HistGBM, and ANOVA\u2013XGBoost, respectively. These significant improvements highlight the effectiveness and refinement of the proposed approach.<\/jats:p>","DOI":"10.3390\/s24154965","type":"journal-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T17:16:49Z","timestamp":1722446209000},"page":"4965","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Analysis of Variance Combined with Optimized Gradient Boosting Machines for Enhanced Load Recognition in Home Energy Management Systems"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5922-6440","authenticated-orcid":false,"given":"Thales W.","family":"Cabral","sequence":"first","affiliation":[{"name":"Department of Communications, School of Electrical and Computer Engineering, University of Campinas, Campinas 13083-852, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fernando B.","family":"Neto","sequence":"additional","affiliation":[{"name":"Copel Distribui\u00e7\u00e3o S.A., Curitiba 81200240, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo R.","family":"de Lima","sequence":"additional","affiliation":[{"name":"Department of Hardware Design, Instituto de Pesquisa Eldorado, Campinas 13083-898, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0517-1496","authenticated-orcid":false,"given":"Gustavo","family":"Fraidenraich","sequence":"additional","affiliation":[{"name":"Department of Communications, School of Electrical and Computer Engineering, University of Campinas, Campinas 13083-852, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5782-9608","authenticated-orcid":false,"given":"Lu\u00eds G. P.","family":"Meloni","sequence":"additional","affiliation":[{"name":"Department of Communications, School of Electrical and Computer Engineering, University of Campinas, Campinas 13083-852, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"108130","DOI":"10.1016\/j.est.2023.108130","article-title":"A tri-layer stochastic framework to manage electricity market within a smart community in the presence of energy storage systems","volume":"71","author":"Mansouri","year":"2023","journal-title":"J. Energy Storage"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"109917","DOI":"10.1016\/j.ijepes.2024.109917","article-title":"A two-stage optimal mechanism for managing energy and ancillary services markets in renewable-based transmission and distribution networks by participating electric vehicle and demand response aggregators","volume":"158","author":"Nie","year":"2024","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Mansouri, S.A., Nematbakhsh, E., Ramos, A., \u00c1vila, J.P.C., Garc\u00eda-Gonz\u00e1lez, J., and Jordehi, A.R. (2023, January 3\u20136). Bi-level mechanism for decentralized coordination of internet data centers and energy communities in local congestion management markets. Proceedings of the 2023 IEEE International Conference on Energy Technologies for Future Grids (ETFG), Wollongong, NSW, Australia.","DOI":"10.1109\/ETFG55873.2023.10407758"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"123067","DOI":"10.1016\/j.apenergy.2024.123067","article-title":"An ADMM-enabled robust optimization framework for self-healing scheduling of smart grids integrated with smart prosumers","volume":"363","author":"Zhang","year":"2024","journal-title":"Appl. Energy"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"104946","DOI":"10.1016\/j.scs.2023.104946","article-title":"A three-stage mechanism for flexibility-oriented energy management of renewable-based community microgrids with high penetration of smart homes and electric vehicles","volume":"99","author":"Zhou","year":"2023","journal-title":"Sustain. Cities Soc."},{"key":"ref_6","unstructured":"Cary, R., and Benton, D. (2012). Creating a Market for Electricity Savings: Paying for Energy Efficiency through the Energy Bill, Green Alliance."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.enbuild.2018.11.006","article-title":"Novel real-time model-based fault detection method for automatic identification of abnormal energy performance in building ventilation units","volume":"183","author":"Bang","year":"2019","journal-title":"Energy Build."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Rashid, H., and Singh, P. (2018, January 18\u201320). Monitor: An abnormality detection approach in buildings energy consumption. Proceedings of the 2018 IEEE 4th International Conference on Collaboration and Internet Computing (CIC), Philadelphia, PA, USA.","DOI":"10.1109\/CIC.2018.00-44"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1007\/s12667-019-00364-w","article-title":"Home energy management system (HEMS): Concept, architecture, infrastructure, challenges and energy management schemes","volume":"13","author":"Mahapatra","year":"2022","journal-title":"Energy Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Motta, L.L., Ferreira, L.C., Cabral, T.W., Lemes, D.A., Cardoso, G.d.S., Borchardt, A., Cardieri, P., Fraidenraich, G., de Lima, E.R., and Neto, F.B. (2023). General Overview and Proof of Concept of a Smart Home Energy Management System Architecture. Electronics, 12.","DOI":"10.3390\/electronics12214453"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Jo, H.C., Park, H.A., Kwon, S.Y., and Cho, K.H. (2024). Home Energy Management Systems (HEMSs) with Optimal Energy Management of Home Appliances Using IoT. Energies, 17.","DOI":"10.3390\/en17123009"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"70746","DOI":"10.1109\/ACCESS.2021.3078340","article-title":"Load disaggregation based on time window for HEMS application","volume":"9","author":"Lemes","year":"2021","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Tsai, C.W., Chiang, K.C., Hsieh, H.Y., Yang, C.W., Lin, J., and Chang, Y.C. (2022). Feature Extraction of Anomaly Electricity Usage Behavior in Residence Using Autoencoder. Electronics, 11.","DOI":"10.3390\/electronics11091450"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"650","DOI":"10.4218\/etrij.2022-0135","article-title":"Anomaly detection of smart metering system for power management with battery storage system\/electric vehicle","volume":"45","author":"Lee","year":"2023","journal-title":"ETRI J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"31244","DOI":"10.1109\/ACCESS.2023.3262128","article-title":"High-Reliability Load Recognition in Home Energy Management Systems","volume":"11","author":"Cabral","year":"2023","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Faustine, A., and Pereira, L. (2020). Multi-label learning for appliance recognition in NILM using Fryze-current decomposition and convolutional neural network. Energies, 13.","DOI":"10.3390\/en13164154"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2035","DOI":"10.1049\/el.2015.2385","article-title":"Approach for home appliance recognition using vector projection length and Stockwell transform","volume":"51","author":"Borin","year":"2015","journal-title":"Electron. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.procs.2020.02.267","article-title":"Event-Driven System For Proficient Load Recognition by Interpreting the Smart Meter Data","volume":"168","author":"Qaisar","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Soe, W.T., and Belleudy, C. (2019, January 11\u201313). Load recognition from smart plug sensor for energy management in a smart home. Proceedings of the 2019 IEEE Sensors Applications Symposium (SAS), Sophia Antipolis, France.","DOI":"10.1109\/SAS.2019.8706089"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.enbuild.2017.09.087","article-title":"Appliance classification using VI trajectories and convolutional neural networks","volume":"158","author":"Ruyssinck","year":"2018","journal-title":"Energy Build."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhiren, R., Bo, T., Longfeng, W., Hui, L., Yanfei, L., and Haiping, W. (2019, January 5\u20137). Non-intrusive load identification method based on integrated intelligence strategy. Proceedings of the 2019 25th International Conference on Automation and Computing (ICAC), Lancaster, UK.","DOI":"10.23919\/IConAC.2019.8895194"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1016\/j.egyr.2021.01.040","article-title":"Non-invasive load identification based on LSTM-BP neural network","volume":"7","author":"Huang","year":"2021","journal-title":"Energy Rep."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1007\/s40747-020-00254-0","article-title":"Image-based mains signal disaggregation and load recognition","volume":"7","author":"Matindife","year":"2021","journal-title":"Complex Intell. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3252","DOI":"10.1109\/TSG.2021.3066570","article-title":"Toward load identification based on the Hilbert transform and sequence to sequence long short-term memory","volume":"12","author":"Heo","year":"2021","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2279","DOI":"10.1007\/s42835-020-00465-y","article-title":"Signal piloted processing of the smart meter data for effective appliances recognition","volume":"15","author":"Alsharif","year":"2020","journal-title":"J. Electr. Eng. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/0169-7439(89)80095-4","article-title":"Analysis of variance (ANOVA)","volume":"6","author":"Sthle","year":"1989","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_27","unstructured":"Prasad, G., Munasinghe, T., and Seneviratne, O. (2020, January 19\u201323). A two-step framework for Parkinson\u2019s disease classification: Using multiple one-way ANOVA on speech features and decision trees. Proceedings of the CEUR Workshop, Galway, Ireland."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"853","DOI":"10.3390\/biomedinformatics4010048","article-title":"Comparing ANOVA and PowerShap Feature Selection Methods via Shapley Additive Explanations of Models of Mental Workload Built with the Theta and Alpha EEG Band Ratios","volume":"4","author":"Raufi","year":"2024","journal-title":"BioMedInformatics"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6215","DOI":"10.1007\/s11276-020-02428-7","article-title":"Construction of an indoor radio environment map using gradient boosting decision tree","volume":"26","author":"Rufaida","year":"2020","journal-title":"Wirel. Netw."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"104767","DOI":"10.1016\/j.autcon.2023.104767","article-title":"Comparison of histogram-based gradient boosting classification machine, random Forest, and deep convolutional neural network for pavement raveling severity classification","volume":"148","year":"2023","journal-title":"Autom. Constr."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"119030","DOI":"10.1016\/j.eswa.2022.119030","article-title":"Dual-IDS: A bagging-based gradient boosting decision tree model for network anomaly intrusion detection system","volume":"213","author":"Louk","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_32","unstructured":"Ong, Y.J., Zhou, Y., Baracaldo, N., and Ludwig, H. (2020). Adaptive histogram-based gradient boosted trees for federated learning. arXiv."},{"key":"ref_33","first-page":"3146","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_35","unstructured":"Kolter, J.Z., and Jaakkola, T. (2012, January 21\u201323). Approximate inference in additive factorial hmms with application to energy disaggregation. Proceedings of the Artificial Intelligence and Statistics, PMLR, La Palma, Spain."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"4447","DOI":"10.1109\/TCE.2023.3328147","article-title":"Low Runtime Approach for Fault Detection for Refrigeration Systems in Smart Homes Using Wavelet Transform","volume":"70","author":"Lemes","year":"2023","journal-title":"IEEE Trans. Consum. Electron."},{"key":"ref_37","unstructured":"G\u00e9ron, A. (2019). Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, O\u2019Reilly Media, Inc."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Kuhn, M., and Johnson, K. (2013). Applied Predictive Modeling, Springer.","DOI":"10.1007\/978-1-4614-6849-3"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Labur\u00fa, F., Cabral, T., Gomes, F., Lima, E., Filho, J., and Meloni, L. (2024). New Insights into Gas-in-Oil-Based Fault Diagnosis of Power Transformers. Energies, 17.","DOI":"10.3390\/en17122889"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"SELLAMI, E.M., and Rhinane, H. (2024). Google Earth Engine and Machine Learning for Flash Flood Exposure Mapping\u2014Case Study: Tetouan, Morocco. Geosciences, 14.","DOI":"10.3390\/geosciences14060152"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"e258","DOI":"10.1016\/j.acra.2020.06.010","article-title":"Histological subtypes classification of lung cancers on CT images using 3D deep learning and radiomics","volume":"28","author":"Guo","year":"2021","journal-title":"Acad. Radiol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"37843","DOI":"10.1109\/ACCESS.2020.2975906","article-title":"Hybrid feature model for emotion recognition in Arabic text","volume":"8","author":"Alswaidan","year":"2020","journal-title":"IEEE Access"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/15\/4965\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:27:17Z","timestamp":1760110037000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/15\/4965"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,31]]},"references-count":42,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["s24154965"],"URL":"https:\/\/doi.org\/10.3390\/s24154965","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2024,7,31]]}}}