{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T13:59:08Z","timestamp":1769263148904,"version":"3.49.0"},"reference-count":75,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,4,23]],"date-time":"2021-04-23T00:00:00Z","timestamp":1619136000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Spanish Ministry for Science, Innovation and Universities","award":["RTI2018-098958-B-I00"],"award-info":[{"award-number":["RTI2018-098958-B-I00"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This work proposes a quantile regression neural network based on a novel constrained weighted quantile loss (CWQLoss) and its application to probabilistic short and medium-term electric-load forecasting of special interest for smart grids operations. The method allows any point forecast neural network based on a multivariate multi-output regression model to be expanded to become a quantile regression model. CWQLoss extends the pinball loss to more than one quantile by creating a weighted average for all predictions in the forecast window and across all quantiles. The pinball loss for each quantile is evaluated separately. The proposed method imposes additional constraints on the quantile values and their associated weights. It is shown that these restrictions are important to have a stable and efficient model. Quantile weights are learned end-to-end by gradient descent along with the network weights. The proposed model achieves two objectives: (a) produce probabilistic (quantile and interval) forecasts with an associated probability for the predicted target values. (b) generate point forecasts by adopting the forecast for the median (0.5 quantiles). We provide specific metrics for point and probabilistic forecasts to evaluate the results considering both objectives. A comprehensive comparison is performed between a selection of classic and advanced forecasting models with the proposed quantile forecasting model. We consider different scenarios for the duration of the forecast window (1 h, 1-day, 1-week, and 1-month), with the proposed model achieving the best results in almost all scenarios. Additionally, we show that the proposed method obtains the best results when an additive ensemble neural network is used as the base model. The experimental results are drawn from real loads of a medium-sized city in Spain.<\/jats:p>","DOI":"10.3390\/s21092979","type":"journal-article","created":{"date-parts":[[2021,4,25]],"date-time":"2021-04-25T02:12:57Z","timestamp":1619316777000},"page":"2979","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Additive Ensemble Neural Network with Constrained Weighted Quantile Loss for Probabilistic Electric-Load Forecasting"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3550-560X","authenticated-orcid":false,"given":"Manuel","family":"Lopez-Martin","sequence":"first","affiliation":[{"name":"Department of TSyCeIT, ETSIT, University of Valladolid, Paseo de Bel\u00e9n 15, 47011 Valladolid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Sanchez-Esguevillas","sequence":"additional","affiliation":[{"name":"Department of TSyCeIT, ETSIT, University of Valladolid, Paseo de Bel\u00e9n 15, 47011 Valladolid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8822-2948","authenticated-orcid":false,"given":"Luis","family":"Hernandez-Callejo","sequence":"additional","affiliation":[{"name":"Department of EiFAB, Campus Universitario Duques de Soria, University of Valladolid, 42004 Soria, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7486-6152","authenticated-orcid":false,"given":"Juan Ignacio","family":"Arribas","sequence":"additional","affiliation":[{"name":"Department of TSyCeIT, ETSIT, University of Valladolid, Paseo de Bel\u00e9n 15, 47011 Valladolid, Spain"},{"name":"Castilla-Leon Neuroscience Institute, University of Salamanca, 37007 Salamanca, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7051-8479","authenticated-orcid":false,"given":"Belen","family":"Carro","sequence":"additional","affiliation":[{"name":"Department of TSyCeIT, ETSIT, University of Valladolid, Paseo de Bel\u00e9n 15, 47011 Valladolid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,4,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"51","DOI":"10.2478\/jlst-2020-0004","article-title":"Methods and Models for Electric Load Forecasting: A Comprehensive Review","volume":"11","author":"Hammad","year":"2020","journal-title":"Logist. Sustain. Transp."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Mohammed, A.A., and Aung, Z. (2016). Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation. Energies, 9.","DOI":"10.3390\/en9121017"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Koenker, R. (2005). Quantile Regression, Cambridge University Press.","DOI":"10.1017\/CBO9780511754098"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Nguyen, H., and Hansen, C.K. (2017, January 19\u201321). Short-term electricity load forecasting with Time Series Analysis. Proceedings of the 2017 IEEE International Conference on Prognostics and Health Management (ICPHM), Dallas, TX, USA.","DOI":"10.1109\/ICPHM.2017.7998331"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.1109\/SURV.2014.032014.00094","article-title":"A Survey on Electric Power Demand Forecasting: Future Trends in Smart Grids, Microgrids and Smart Buildings","volume":"16","author":"Baladron","year":"2014","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_6","unstructured":"Benidis, K., Rangapuram, S.S., Flunkert, V., Wang, B., Maddix, D., Turkmen, C., Gasthaus, J., Bohlke-Schneider, M., Salinas, D., and Stella, L. (2020). Neural forecasting: Introduction and literature overview. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Lim, B., and Zohren, S. (2020). Time Series Forecasting With Deep Learning: A Survey. arXiv.","DOI":"10.1098\/rsta.2020.0209"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"111799","DOI":"10.1016\/j.enconman.2019.111799","article-title":"A review of deep learning for renewable energy forecasting","volume":"198","author":"Wang","year":"2019","journal-title":"Energy Convers. Manag."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1016\/j.future.2019.05.060","article-title":"Neural network architecture based on gradient boosting for IoT traffic prediction","volume":"100","author":"Carro","year":"2019","journal-title":"Futur. Gener. Comput. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"211","DOI":"10.3150\/10-BEJ267","article-title":"Estimating conditional quantiles with the help of the pinball loss","volume":"17","author":"Steinwart","year":"2011","journal-title":"Bernoulli"},{"key":"ref_11","unstructured":"Hatalis, K., Lamadrid, A.J., Scheinberg, K., and Kishore, S. (2017). Smooth Pinball Neural Network for Probabilistic Forecasting of Wind Power. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/s13042-011-0031-2","article-title":"Gradient descent algorithms for quantile regression with smooth approximation","volume":"2","author":"Zheng","year":"2011","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_13","unstructured":"Lang, C., Steinborn, F., Steffens, O., and Lang, E.W. (2019). Electricity Load Forecasting\u2014An Evaluation of Simple 1D-CNN Network Structures. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Singh, N., Vyjayanthi, C., and Modi, C. (2020, January 11\u201312). Multi-step Short-term Electric Load Forecasting using 2D Convolutional Neural Networks. Proceedings of the 2020 IEEE-HYDCON, Hyderabad, India.","DOI":"10.1109\/HYDCON48903.2020.9242917"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1109\/TSG.2017.2753802","article-title":"Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network","volume":"10","author":"Kong","year":"2019","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"113192","DOI":"10.1109\/ACCESS.2020.3003748","article-title":"Additive Ensemble Neural Networks","volume":"8","author":"Park","year":"2020","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez, L., Baladr\u00f3n, C., Aguiar, J.M., Carro, B., S\u00e1nchez-Esguevillas, A., and Lloret, J. (2014). Artificial neural networks for short-term load forecasting in microgrids environment. Energy.","DOI":"10.1016\/j.energy.2014.07.065"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Aufaure, M.-A., and Zim\u00e1nyi, E. (2012, January 15\u201321). Machine Learning Strategies for Time Series Forecasting BT\u2014Business Intelligence: Second European Summer School. Proceedings of the eBISS 2012, Brussels, Belgium. Tutorial Lectures.","DOI":"10.1007\/978-3-642-27358-2"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"101533","DOI":"10.1016\/j.scs.2019.101533","article-title":"Modeling and forecasting building energy consumption: A review of data-driven techniques","volume":"48","author":"Bourdeau","year":"2019","journal-title":"Sustain. Cities Soc."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Makridakis, S., Spiliotis, E., and Assimakopoulos, V. (2018). Statistical and Machine Learning forecasting methods: Concerns and ways forward. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0194889"},{"key":"ref_21","first-page":"125","article-title":"Review of Methods to Predict Connectivity of IoT Wireless Devices","volume":"38","author":"Martin","year":"2017","journal-title":"Ad. Hoc. Sens. Wirel. Netw."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1017\/S0022112010001217","article-title":"Dynamic mode decomposition of numerical and experimental data","volume":"656","author":"Schmid","year":"2010","journal-title":"J. Fluid Mech."},{"key":"ref_23","unstructured":"Tirunagari, S., Kouchaki, S., Poh, N., Bober, M., Windridge, D., and Dynamic, D.W. (2021, April 22). Dynamic Mode Decomposition for Univariate Time Series: Analysing Trends and Forecasting. Available online: https:\/\/hal.archives-ouvertes.fr\/hal-01463744\/."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/j.apenergy.2018.09.190","article-title":"A data-driven strategy for short-term electric load forecasting using dynamic mode decomposition model","volume":"232","author":"Mohan","year":"2018","journal-title":"Appl. Energy"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lopez-Martin, M., Carro, B., Sanchez-Esguevillas, A., and Lloret, J. (2017). Network Traffic Classifier with Convolutional and Recurrent Neural Networks for Internet of Things. IEEE Access, 5.","DOI":"10.1109\/ACCESS.2017.2747560"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lopez-Martin, M., Carro, B., Lloret, J., Egea, S., and Sanchez-Esguevillas, A. (2018). Deep Learning Model for Multimedia Quality of Experience Prediction Based on Network Flow Packets. IEEE Commun. Mag., 56.","DOI":"10.1109\/MCOM.2018.1701156"},{"key":"ref_27","unstructured":"Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural Machine Translation by Jointly Learning to Align and Translate. arXiv."},{"key":"ref_28","unstructured":"Sutskever, I., Vinyals, O., and Le, Q.V. (2014). Sequence to Sequence Learning with Neural Networks. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Luong, M.-T., Pham, H., and Manning, C.D. (2015). Effective Approaches to Attention-based Neural Machine Translation. arXiv.","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.future.2019.12.013","article-title":"IoT type-of-traffic forecasting method based on gradient boosting neural networks","volume":"105","author":"Carro","year":"2020","journal-title":"Futur. Gener. Comput. Syst."},{"key":"ref_31","unstructured":"Fort, S., Hu, H., and Lakshminarayanan, B. (2019). Deep Ensembles: A Loss Landscape Perspective. arXiv."},{"key":"ref_32","unstructured":"Frankle, J., and Carbin, M. (2018). The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks. arXiv."},{"key":"ref_33","unstructured":"Jain, S., Liu, G., Mueller, J., and Gifford, D. (February, January 27). Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensembles. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3207","DOI":"10.1007\/s00477-018-1573-6","article-title":"Non-crossing nonlinear regression quantiles by monotone composite quantile regression neural network, with application to rainfall extremes","volume":"32","author":"Cannon","year":"2018","journal-title":"Stoch. Environ. Res. Risk Assess."},{"key":"ref_35","unstructured":"Hatalis, K., Lamadrid, A.J., Scheinberg, K., and Kishore, S. (2019). A Novel Smoothed Loss and Penalty Function for Noncrossing Composite Quantile Estimation via Deep Neural Networks. arXiv."},{"key":"ref_36","first-page":"1479","article-title":"Oracle model selection for nonlinear models based on weighted composite quantile regression","volume":"22","author":"Jiang","year":"2012","journal-title":"Stat. Sin."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1016\/j.jspi.2013.01.002","article-title":"Weighted local linear composite quantile estimation for the case of general error distributions","volume":"143","author":"Sun","year":"2013","journal-title":"J. Stat. Plan. Inference"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.jspi.2018.09.003","article-title":"Composite versus model-averaged quantile regression","volume":"200","author":"Bloznelis","year":"2019","journal-title":"J. Stat. Plan. Inference"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.jmva.2016.02.015","article-title":"Weighted composite quantile regression for single-index models","volume":"148","author":"Jiang","year":"2016","journal-title":"J. Multivar. Anal."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"104669","DOI":"10.1016\/j.jmva.2020.104669","article-title":"Single-index composite quantile regression for massive data","volume":"180","author":"Jiang","year":"2020","journal-title":"J. Multivar. Anal."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1344","DOI":"10.1016\/j.comnet.2012.12.017","article-title":"Cyber security in the Smart Grid: Survey and challenges","volume":"57","author":"Wang","year":"2013","journal-title":"Comput. Netw."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Bogner, K., Pappenberger, F., and Zappa, M. (2019). Machine Learning Techniques for Predicting the Energy Consumption\/Production and Its Uncertainties Driven by Meteorological Observations and Forecasts. Sustainability, 11.","DOI":"10.3390\/su11123328"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"9147545","DOI":"10.1155\/2020\/9147545","article-title":"Unified Quantile Regression Deep Neural Network with Time-Cognition for Probabilistic Residential Load Forecasting","volume":"2020","author":"Deng","year":"2020","journal-title":"Complexity"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"5442","DOI":"10.1109\/TSG.2020.2995777","article-title":"Improving Probabilistic Load Forecasting Using Quantile Regression NN With Skip Connections","volume":"11","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.apenergy.2018.10.078","article-title":"Probabilistic individual load forecasting using pinball loss guided LSTM","volume":"235","author":"Wang","year":"2019","journal-title":"Appl. Energy"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"114368","DOI":"10.1016\/j.apenergy.2019.114368","article-title":"Short-term electrical load forecasting based on error correction using dynamic mode decomposition","volume":"261","author":"Kong","year":"2020","journal-title":"Appl. Energy"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.neucom.2020.01.031","article-title":"Empirical Mode Decomposition based Multi-objective Deep Belief Network for short-term power load forecasting","volume":"388","author":"Fan","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"177874","DOI":"10.1109\/ACCESS.2019.2958383","article-title":"Machine Learning Algorithms for Short-Term Load Forecast in Residential Buildings Using Smart Meters, Sensors and Big Data Solutions","volume":"7","author":"Oprea","year":"2019","journal-title":"IEEE Access"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Jacob, M., Neves, C., and Greetham, D.V. (2020). Short Term Load Forecasting BT\u2014Forecasting and Assessing Risk of Individual Electricity Peaks, Springer International Publishing.","DOI":"10.1007\/978-3-030-28669-9"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Pinto, T., Pra\u00e7a, I., Vale, Z., and Silva, J. (2020). Ensemble learning for electricity consumption forecasting in office buildings. Neurocomputing.","DOI":"10.1016\/j.neucom.2020.02.124"},{"key":"ref_51","unstructured":"Gasparin, A., Lukovic, S., and Alippi, C. (2019). Deep Learning for Time Series Forecasting: The Electric Load Case. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Gong, G., An, X., Mahato, N.K., Sun, S., Chen, S., and Wen, Y. (2019). Research on Short-Term Load Prediction Based on Seq2seq Model. Energies, 12.","DOI":"10.3390\/en12163199"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/j.neucom.2019.12.118","article-title":"Multivariate time series forecasting via attention-based encoder\u2013decoder framework","volume":"388","author":"Du","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_54","unstructured":"Huang, Y., Wang, N., Gao, W., Guo, X., Huang, C., Hao, T., and Zhan, J. (2019). LoadCNN: A Low Training Cost Deep Learning Model for Day-Ahead Individual Residential Load Forecasting. arXiv."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Karampelas, P., Vita, V., Pavlatos, C., Mladenov, V., and Ekonomou, L. (2010, January 13\u201325). Design of artificial neural network models for the prediction of the Hellenic energy consumption. Proceedings of the 10th Symposium on Neural Network Applications in Electrical Engineering, Osaka, Japan.","DOI":"10.1109\/NEUREL.2010.5644049"},{"key":"ref_56","first-page":"64","article-title":"A short-term load forecasting method using artificial neural networks and wavelet analysis","volume":"1","author":"Ekonomou","year":"2016","journal-title":"Int. J. Power Syst."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1016\/j.jesit.2018.01.001","article-title":"Smart grids security challenges: Classification by sources of threats","volume":"5","author":"Otuoze","year":"2018","journal-title":"J. Electr. Syst. Inf. Technol."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1049\/iet-stg.2019.0081","article-title":"Rule-based classification of energy theft and anomalies in consumers load demand profile","volume":"2","author":"Jain","year":"2019","journal-title":"IET Smart Grid"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Cody, C., Ford, V., and Siraj, A. (2015, January 9\u201311). Decision Tree Learning for Fraud Detection in Consumer Energy Consumption. Proceedings of the 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), Miami, FL, USA.","DOI":"10.1109\/ICMLA.2015.80"},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"169","DOI":"10.3390\/forecast1010012","article-title":"Quantile Regression and Clustering Models of Prediction Intervals for Weather Forecasts: A Comparative Study","volume":"1","author":"Zarnani","year":"2019","journal-title":"Forecasting"},{"key":"ref_61","unstructured":"Pinson, P., Kariniotakis, G., Nielsen, H.A., Nielsen, T.S., and Madsen, H. (March, January 27). Properties of quantile and interval forecasts of wind generation and their evaluation. Proceedings of the 2006 European Wind Energy Conference (EWEC 2006), Ath\u00e8nes, Greece."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/j.ejcon.2020.08.001","article-title":"Hybrid data-driven fuzzy active disturbance rejection control for tower crane systems","volume":"58","author":"Roman","year":"2021","journal-title":"Eur. J. Control"},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Pan, Y., Zhou, Q., and Lu, C. (2020). Event-Triggered Adaptive Fuzzy Control for Stochastic Nonlinear Systems with Unmeasured States and Unknown Backlash-Like Hysteresis. IEEE Trans. Fuzzy Syst., 1.","DOI":"10.1109\/TFUZZ.2020.2973950"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.1080\/14697688.2016.1170194","article-title":"Dynamic Mode Decomposition for Financial Trading Strategies","volume":"16","author":"Mann","year":"2016","journal-title":"Quant. Financ."},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Hartung, J., and Knapp, G. (2005). Multivariate Multiple Regression. Encyclopedia of Statistics in Behavioral Science, John Wiley & Sons, Ltd.","DOI":"10.1002\/0470013192.bsa432"},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Netw."},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_68","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv."},{"key":"ref_69","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_70","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_71","doi-asserted-by":"crossref","first-page":"1287","DOI":"10.1287\/opre.1080.0665","article-title":"Evaluating Quantile Assessments","volume":"57","author":"Jose","year":"2009","journal-title":"Oper. Res."},{"key":"ref_72","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1080\/01621459.1972.10481224","article-title":"A Decision-Theoretic Approach to Interval Estimation","volume":"67","author":"Winkler","year":"1972","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_73","unstructured":"Ruder, S. (2017). An Overview of Multi-Task Learning in Deep Neural Networks. arXiv."},{"key":"ref_74","unstructured":"Sener, O., and Koltun, V. (2018). Multi-Task Learning as Multi-Objective Optimization. arXiv."},{"key":"ref_75","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/j.crma.2012.03.014","article-title":"Multiple-gradient descent algorithm (MGDA) for multiobjective optimization","volume":"350","year":"2012","journal-title":"Comptes Rendus Math."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/9\/2979\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:52:10Z","timestamp":1760161930000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/9\/2979"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,23]]},"references-count":75,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["s21092979"],"URL":"https:\/\/doi.org\/10.3390\/s21092979","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,23]]}}}