{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T19:01:52Z","timestamp":1785438112050,"version":"3.56.0"},"reference-count":45,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-RS-2023-00259995"],"award-info":[{"award-number":["NRF-RS-2023-00259995"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"award":["NRF-RS-2023-00259995"],"award-info":[{"award-number":["NRF-RS-2023-00259995"]}],"id":[{"id":"https:\/\/ror.org\/013aysd81","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Sensor-based environmental monitoring systems are often affected by missing, noisy, and unreliable measurements caused by sensor faults, sparse deployment, calibration drift, and communication interruptions. To address these challenges, this study proposes an intelligent virtual sensor generation framework that integrates physical-constraint-based preprocessing, statistical virtual sensor modeling, KL-divergence-based fusion, deep generative augmentation, and temporal prediction. The raw weather-station data are first refined using threshold-based filtering, physical validity constraints, and Isolation Forest-based outlier detection. To handle the circular nature of wind direction, the angle is encoded using sine and cosine components during modeling and reconstructed using the atan2 function for evaluation. Multiple statistical methods, including Inverse Distance Weighting, Kernel Density Estimation, Ridge Regression, and Copula-based modeling, are employed to generate complementary virtual sensor data. These outputs are adaptively fused using KL divergence according to their distributional similarity with real sensor data. The fused datasets are further augmented using Variational Autoencoders and Conditional Tabular Generative Adversarial Networks, and then evaluated using BiLSTM and BiGRU models with MAE, MSE, and RMSE metrics. The experimental results demonstrate that the proposed framework generates physically valid and distributionally consistent virtual sensor data. Fusion-based methods outperform standalone approaches, while VAE-based augmentation generally provides better statistical fidelity and lower prediction errors than CTGAN. Additional validation using a public NOAA weather-station dataset further supports the transferability of the proposed fusion-based virtual sensing workflow. Comparisons with TimeGAN and diffusion-based temporal generative baselines, supported by Wilcoxon signed-rank testing, confirm the statistical significance and competitive performance of the proposed framework. A quantitative computational analysis also demonstrates the practical feasibility of the framework in terms of training time, inference time, memory consumption, and scalability. Overall, the proposed framework offers a reliable and scalable solution for virtual sensing in sensor-sparse and fault-prone environmental monitoring systems.<\/jats:p>","DOI":"10.3390\/s26134123","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:50:37Z","timestamp":1782867037000},"page":"4123","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Intelligent Virtual Sensor Generation Using KL-Divergence- Based Fusion and Deep Generative Learning for Smart Environmental Monitoring"],"prefix":"10.3390","volume":"26","author":[{"given":"Murad Ali","family":"Khan","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Jeju National University, Jeju 63243, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qazi Waqas","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Jeju National University, Jeju 63243, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9159-5279","authenticated-orcid":false,"given":"Muhammad","family":"Faizan","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Jeju National University, Jeju 63243, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0180-4209","authenticated-orcid":false,"given":"Ji-Eun","family":"Kim","sequence":"additional","affiliation":[{"name":"Autonomous IoT Research Center, Korea Electronics Technology Institute, Seongnam 13509, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Il-yeop","family":"Ahn","sequence":"additional","affiliation":[{"name":"Autonomous IoT Research Center, Korea Electronics Technology Institute, Seongnam 13509, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Do-Hyeun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Jeju National University, Jeju 63243, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"ref_1","first-page":"21","article-title":"Sensor Fusion and Virtual Sensor Design for Enhanced Multi-Sensor Data Accuracy in Autonomous Systems","volume":"1","author":"Sahoo","year":"2024","journal-title":"Int. J. Smart Sustain. Intell. Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1036","DOI":"10.32996\/jcsts.2025.7.4.117","article-title":"Technical Review: The Rise of Machine Learning for Sensor Design","volume":"7","author":"Jain","year":"2025","journal-title":"J. Comput. Sci. Technol. Stud."},{"key":"ref_3","unstructured":"Russo, S.A. (2025). Robust Anomaly Detection for Time Series Data in Sensor-Based Critical Systems. [Ph.D. Thesis, Universit\u00e0 degli Studi di Trieste]. Available online: https:\/\/hdl.handle.net\/11368\/3107341."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bala, B., and Behal, S. (2024). A brief survey of data preprocessing in machine learning and deep learning techniques. Proceedings of the 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), IEEE.","DOI":"10.1109\/I-SMAC61858.2024.10714767"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"100802","DOI":"10.1016\/j.spasta.2023.100802","article-title":"Copula-based data-driven multiple-point simulation method","volume":"59","author":"Sohrabian","year":"2024","journal-title":"Spat. Stat."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e40044","DOI":"10.1016\/j.heliyon.2024.e40044","article-title":"Sensitivity analysis of parameters for carbon sequestration: Symbolic regression models based on open porous media reservoir simulators predictions","volume":"10","author":"Praks","year":"2024","journal-title":"Heliyon"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"106206","DOI":"10.1016\/j.oregeorev.2024.106206","article-title":"Inverse radius weighting and its python package \u201cIRWPy\u201d: A new topography-informed interpolation to enhance geological interpretations","volume":"172","author":"Sadeghi","year":"2024","journal-title":"Ore Geol. Rev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1007\/s12145-024-01594-y","article-title":"Evaluating the efficiency and accuracy of the copula-based rainfall-runoff model","volume":"18","author":"Mirabbasi","year":"2025","journal-title":"Earth Sci. Inform."},{"key":"ref_9","unstructured":"Mechqrane, Y., and Elabbassi, I. (2025). From Prediction to Action: A Constraint-Based Approach to Predictive Policing. Proceedings of the 31st International Conference on Principles and Practice of Constraint Programming (CP 2025), Schloss Dagstuhl\u2013Leibniz-Zentrum f\u00fcr Informatik."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"102136","DOI":"10.1016\/j.inffus.2023.102136","article-title":"A systematic review of data fusion techniques for optimized structural health monitoring","volume":"103","author":"Hassani","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref_11","first-page":"32536","article-title":"Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence","volume":"37","author":"Korba","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"65445","DOI":"10.52202\/079017-2090","article-title":"Wasserstein distance rivals kullback-leibler divergence for knowledge distillation","volume":"37","author":"Lv","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Vishnu Shankar, S., Naffees Gowsar, S., and Manjubala, M. (2025). Variational autoencoders (vaes). Revolution with Generative AI: Trends and Techniques, Springer.","DOI":"10.1007\/978-3-031-91660-1_3"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Randhawa, P., Jasthi, V.N., Piyush, K., Kaushik, G.K., Batamulay, M., Prasad, S., Rawat, M., Veernapu, K., and Naik, N. (2026). Conditional Tabular Generative Adversarial Network Based Clinical Data Augmentation for Enhanced Predictive Modeling in Chronic Kidney Disease Diagnosis. BioMedInformatics, 6.","DOI":"10.3390\/biomedinformatics6010006"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Bhat, K.A., and Sofi, S.A. (2024). A synergistic fusion of shallow and deep generative model to enhance machine learning efficacy and classification performance in data-scarce environments. Int. J. Inf. Technol., 1\u201321.","DOI":"10.1007\/s41870-024-02120-5"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"128360","DOI":"10.1016\/j.neucom.2024.128360","article-title":"Discriminative Hamiltonian variational autoencoder for accurate tumor segmentation in data-scarce regimes","volume":"606","author":"Kebaili","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"12354","DOI":"10.1109\/ACCESS.2026.3655481","article-title":"Deep Recurrent Architectures for EEG-Based Classification of Major Psychiatric Disorders: A Comparative Study of LSTM, BiLSTM, GRU, BiGRU, and Their Hybrids","volume":"14","year":"2026","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Dumre, P., Bhattarai, S., and Shashikala, H. (2024). Optimizing linear regression models: A comparative study of error metrics. Proceedings of the 2024 4th International Conference on Technological Advancements in Computational Sciences (ICTACS), IEEE.","DOI":"10.1109\/ICTACS62700.2024.10840719"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Jaradat, Y.M., Alia, M.A., Masoud, M.Z., Manasrah, A.A., Jannoud, I.A., and Alheyasat, O. (2025). Beyond One-Size-Fits-All: Comparing and Selecting Regression Metrics for Robust Model Assessment. Proceedings of the 2025 12th International Conference on Information Technology (ICIT), IEEE.","DOI":"10.1109\/ICIT64950.2025.11049268"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"40607","DOI":"10.1109\/ACCESS.2025.3547160","article-title":"A virtual infrastructure model based on data reuse to support intelligent transportation system applications","volume":"13","author":"Miranda","year":"2025","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"15167","DOI":"10.1109\/JSEN.2025.3549652","article-title":"Model complexity reduction in bayesian sensor calibration and its relation to principal component analysis","volume":"25","author":"Winter","year":"2025","journal-title":"IEEE Sens. J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"53","DOI":"10.4236\/jcc.2024.1211004","article-title":"Missing data imputation: A comprehensive review","volume":"12","author":"Alwateer","year":"2024","journal-title":"J. Comput. Commun."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7574","DOI":"10.1109\/ACCESS.2024.3519390","article-title":"Transformer-Driven Inverse Learning for AI-Powered Ceramic Material Innovation With Advanced Data Preprocessing","volume":"13","author":"Khan","year":"2024","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1049\/cit2.70000","article-title":"Enhancing patient rehabilitation predictions with a hybrid anomaly detection model: Density-based clustering and interquartile range methods","volume":"10","author":"Khan","year":"2025","journal-title":"Caai Trans. Intell. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s11831-023-09972-3","article-title":"A review of stochastic analysis of the seepage through earth dams with a focus on the application of monte carlo simulation","volume":"31","author":"Kalateh","year":"2024","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"043047","DOI":"10.1103\/9jdd-6ct8","article-title":"Modeling non-Gaussianities in pulsar timing array data analysis using Gaussian mixture models","volume":"113","author":"Falxa","year":"2026","journal-title":"Phys. Rev. D"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"104830","DOI":"10.1016\/j.trc.2024.104830","article-title":"Copula-based transferable models for synthetic population generation","volume":"169","author":"Yang","year":"2024","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"134569","DOI":"10.1016\/j.jhydrol.2025.134569","article-title":"A combined spatial interpolation method of co-Kriging with inverse distance weighting and random forest for soil water and salt in arid oasis","volume":"664","author":"Liu","year":"2025","journal-title":"J. Hydrol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6921","DOI":"10.1038\/s41598-026-36740-7","article-title":"Kernel mean matching enhances risk estimation under spatial distribution shifts","volume":"16","author":"Serov","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1007\/s42488-024-00119-y","article-title":"Detecting drifts in data streams using Kullback-Leibler (KL) divergence measure for data engineering applications","volume":"6","author":"Kurian","year":"2024","journal-title":"J. Data Inf. Manag."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e70051","DOI":"10.1111\/tgis.70051","article-title":"Exploration-Based Statistical Learning for Selecting Kernel Density Estimates of Spatial Point Patterns","volume":"29","author":"Govorov","year":"2025","journal-title":"Trans. Gis"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1007\/s10044-025-01507-9","article-title":"Elastic matching through the lens of probability and divergence in time series prediction","volume":"28","author":"Forouzan","year":"2025","journal-title":"Pattern Anal. Appl."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Islam, M.M., Belal, T., Anik, M.A.H.C., and Sharif, A. (2026). Predicting Materials Using Variational Autoencoders: A Systematic Literature Review. Arch. Comput. Methods Eng., 1\u201352.","DOI":"10.1007\/s11831-025-10485-4"},{"key":"ref_34","unstructured":"Lee, K. (2024). ProctGAN: Progressive Conditional Tabular GAN for Imbalanced Data. [Ph.D. Thesis, Graduate School, Seoul National University]."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Khan, M.A., Waqas Khan, Q., Kim, J.E., Jeong, S., Ahn, I.y., and Kim, D.H. (2026). From Physical to Virtual Sensors: VSG-SGL for Reliable and Cost-Efficient Environmental Monitoring. Automation, 7.","DOI":"10.3390\/automation7010027"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"180093","DOI":"10.1109\/ACCESS.2024.3508271","article-title":"A comprehensive review on deep learning-based data fusion","volume":"12","author":"Hussain","year":"2024","journal-title":"IEEE Access"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.1039\/D5LC00020C","article-title":"Machine learning-assisted flexible dual modal sensor for multi-sensing detection and target object recognition in the grasping process","volume":"25","author":"Dong","year":"2025","journal-title":"Lab. A Chip."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","volume":"37","author":"Lim","year":"2021","journal-title":"Int. J. Forecast."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"5388","DOI":"10.1109\/TKDE.2023.3333824","article-title":"Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey","volume":"36","author":"Jin","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_40","unstructured":"Sahili, Z.A., and Awad, M. (2023). Spatio-Temporal Graph Neural Networks: A Survey. arXiv."},{"key":"ref_41","unstructured":"Yoon, J., Jarrett, D., and van der Schaar, M. (2019). Time-series Generative Adversarial Networks. Adv. Neural Inf. Process. Syst., 32."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1631\/FITEE.2300310","article-title":"Diffusion Models for Time-Series Applications: A Survey","volume":"25","author":"Lin","year":"2024","journal-title":"Front. Inf. Technol. Electron. Eng."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"5739","DOI":"10.1007\/s41060-025-00816-w","article-title":"Synthetic data generation for healthcare: Exploring generative adversarial networks variants for medical tabular data","volume":"20","author":"Ahmed","year":"2025","journal-title":"Int. J. Data Sci. Anal."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., and Zhang, W. (2021, January 11\u201315). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence, Atlanta, GA, USA.","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref_45","unstructured":"Kantor, D., Casey, N.W., Menne, M.J., and Buddenberg, A. (2026, June 24). Local Climatological Data (LCD), Version 2, 2023, Available online: https:\/\/www.ncei.noaa.gov\/metadata\/geoportal\/rest\/metadata\/item\/gov.noaa.ncdc:C01688\/html."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4123\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:58:02Z","timestamp":1782867482000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4123"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":45,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26134123"],"URL":"https:\/\/doi.org\/10.3390\/s26134123","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}