{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:24:58Z","timestamp":1760059498411,"version":"build-2065373602"},"reference-count":21,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Major Project in Humanities and Social Sciences of Tianjin Municipal Education Commission: Research on Big Data Activating the Cultural New Momentum of Tianjin\u2019s \u2018Grand Canal+\u2019 Initiative","award":["2021JWZD11"],"award-info":[{"award-number":["2021JWZD11"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Informatics"],"abstract":"<jats:p>Non-Intrusive Load Monitoring (NILM) technology, enabled by high-precision electrical data acquisition sensors at household entry points, facilitates real-time monitoring of electricity consumption, enhancing user interaction with smart home systems and reducing electrical safety risks. However, the growing diversity of household appliances and limitations in NILM accuracy and robustness necessitate innovative solutions. Additionally, outdated public datasets fail to capture the rapid evolution of modern appliances. To address these challenges, we constructed a high-sampling-rate voltage\u2013current dataset, measuring 15 common household appliances across diverse scenarios in a controlled laboratory environment tailored to regional grid standards (220 V\/50 Hz). We propose an AI-driven NILM method that integrates power-mapped, color-coded voltage\u2013current (V\u2013I) trajectories with frequency-domain features to significantly improve load recognition accuracy and robustness. By leveraging deep learning frameworks, this approach enriches temporal feature representation through chromatic mapping of instantaneous power and incorporates frequency-domain spectrograms to capture dynamic load behaviors. A novel channel-wise attention mechanism optimizes multi-dimensional feature fusion, dynamically prioritizing critical information while suppressing noise. Comparative experiments on the custom dataset demonstrate superior performance, particularly in distinguishing appliances with similar load profiles, underscoring the method\u2019s potential for advancing smart home energy management, user-centric energy feedback, and social informatics applications in complex electrical environments.<\/jats:p>","DOI":"10.3390\/informatics12020055","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:45:26Z","timestamp":1750157126000},"page":"55","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-Enhanced Non-Intrusive Load Monitoring for Smart Home Energy Optimization and User-Centric Interaction"],"prefix":"10.3390","volume":"12","author":[{"given":"Xiang","family":"Li","sequence":"first","affiliation":[{"name":"College of Politics and Public Administration, Tianjin Normal University, Tianjin 300387, China"}]},{"given":"Yunhe","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China"}]},{"given":"Xinyu","family":"Jia","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China"}]},{"given":"Fan","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China"}]},{"given":"Bowen","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China"}]},{"given":"Shuqing","family":"He","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Linyi University, Linyi 276000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5205-6167","authenticated-orcid":false,"given":"Jia","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Zeng, W., Han, Z., Xie, Y., Liang, R., and Bao, Y. (2023). Non-intrusive load monitoring through coupling sequence matrix reconstruction and cross stage partial network. Measurement, 220.","DOI":"10.1016\/j.measurement.2023.113358"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zheng, G., Hu, Y., Xiao, Z., and Ding, X. (2023, January 13\u201315). Graph-Based Dependency-Aware Non-Intrusive Load Monitoring. Proceedings of the Chinese Conference on Pattern Recognition and Computer Vision (PRCV), Xiamen, China.","DOI":"10.1007\/978-981-99-8549-4_8"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"9497","DOI":"10.1109\/TII.2024.3383521","article-title":"Non-intrusive load monitoring based on an efficient deep learning model with local feature extraction","volume":"20","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yan, Z., Hao, P., Nardello, M., Brunelli, D., and Wen, H. (2025). A Generalizable Load Recognition Method in NILM Based on Transferable Random Forest. IEEE Trans. Instrum. Meas., 74.","DOI":"10.1109\/TIM.2025.3570355"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"de Diego-Ot\u00f3n, L., Hern\u00e1ndez, \u00c1., Fuentes, D., Nieto, R., and Navarro, V.M. (2025). Architectural strategies for enhanced NILM classification and anomaly detection: Addressing limited data scenarios. Expert Syst. Appl., 282.","DOI":"10.1016\/j.eswa.2025.127756"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Hao, P., Yan, Z., and Wen, H. (2025). Privacy-Preserving NILM: A Self-Alignment Source-Aware Domain Adaptation Approach. IEEE Trans. Instrum. Meas., 74.","DOI":"10.1109\/TIM.2025.3542871"},{"key":"ref_7","unstructured":"Shi, D. (2025, June 12). NILM Datasets for Research: IAWE, REDD, and UKDALE. IEEE Dataport. Available online: https:\/\/ieee-dataport.org\/documents\/nilm-datasets-research-iawe-redd-and-ukdale."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Guo, X., Wang, C., Wu, T., Li, R., Zhu, H., and Zhang, H. (2023). Detecting the novel appliance in non-intrusive load monitoring. Appl. Energy, 343.","DOI":"10.1016\/j.apenergy.2023.121193"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1016\/j.comcom.2021.06.023","article-title":"A deep learning based non-intrusive household load identification for smart grid in China","volume":"177","author":"Chen","year":"2021","journal-title":"Comput. Commun."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Lu, J., Zhao, R., Liu, B., Yu, Z., Zhang, J., and Xu, Z. (2023). An overview of non-intrusive load monitoring based on VI trajectory signature. Energies, 16.","DOI":"10.3390\/en16020939"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Shi, J., Zhi, D., and Fu, R. (2023). Research on a non-intrusive load recognition algorithm based on high-frequency signal decomposition with improved VI trajectory and background color coding. Mathematics, 12.","DOI":"10.20944\/preprints202311.1088.v1"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"19147","DOI":"10.1007\/s00521-022-07508-7","article-title":"Non-intrusive load monitoring based on semi-supervised smooth teacher graph learning with voltage\u2013current trajectory","volume":"34","author":"Han","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chen, T., Qin, H., Li, X., Wan, W., and Yan, W. (2023). A non-intrusive load monitoring method based on feature fusion and SE-ResNet. Electronics, 12.","DOI":"10.3390\/electronics12081909"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Grover, H., Panwar, L., Verma, A., Panigrahi, B.K., and Bhatti, T. (2022). A multi-head Convolutional Neural Network based non-intrusive load monitoring algorithm under dynamic grid voltage conditions. Sustain. Energy Grids Netw., 32.","DOI":"10.1016\/j.segan.2022.100938"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yao, L., Wang, J., and Zhao, C. (2024). Non-Intrusive Load Monitoring Based on Multiscale Attention Mechanisms. Energies, 17.","DOI":"10.3390\/en17081944"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Ding, Y., Luo, Q., Wang, P., Li, Q., Liu, H., Fang, K., and Cheng, H. (2022). Non-invasive load identification algorithm based on color coding and feature fusion of power and current. Front. Energy Res., 10.","DOI":"10.3389\/fenrg.2022.899669"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"He, J., Liu, J., Zhang, Z., Chen, Y., Liu, Y., Khoussainov, B., and Zhu, L. (2023, January 7\u201314). MSDC: Exploiting multi-state power consumption in non-intrusive load monitoring based on a dual-CNN model. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i4.25636"},{"key":"ref_18","unstructured":"Liu, H., Sun, Y., and Wang, Y. (2025). A Non-Invasive Load Monitoring Method for Edge Computing Based on MobileNetV3 and Dynamic Time Regulation. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1434","DOI":"10.1109\/TGCN.2023.3244278","article-title":"Performance-aware NILM model optimization for edge deployment","volume":"7","author":"Sykiotis","year":"2023","journal-title":"IEEE Trans. Green Commun. Netw."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"77441","DOI":"10.1109\/ACCESS.2023.3292911","article-title":"Non-intrusive load monitoring based on residual u-net and conditional generation adversarial networks","volume":"11","author":"Wang","year":"2023","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Azad, M.I., Rajabi, R., and Estebsari, A. (2023, January 6\u20139). Non-intrusive load monitoring (nilm) using deep neural networks: A review. Proceedings of the 2023 IEEE International Conference on Environment and Electrical Engineering and 2023 IEEE Industrial and Commercial Power Systems Europe (EEEIC\/I&CPS Europe), Madrid, Spain.","DOI":"10.1109\/EEEIC\/ICPSEurope57605.2023.10194770"}],"container-title":["Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-9709\/12\/2\/55\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:53:45Z","timestamp":1760032425000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-9709\/12\/2\/55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":21,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["informatics12020055"],"URL":"https:\/\/doi.org\/10.3390\/informatics12020055","relation":{},"ISSN":["2227-9709"],"issn-type":[{"type":"electronic","value":"2227-9709"}],"subject":[],"published":{"date-parts":[[2025,6,17]]}}}